JOB DETAILS FOR JOB 1331858

captured Thu Sep 10 16:15:40 SAST 2026

MaxRAM=2.5G
MaxVMSize=0G
AveCPUFreq=2.90M
AveDiskRead=2834340102
AveDiskWrite=1183425080

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7870 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=00:05:41 TimeLimit=00:30:00 TimeMin=N/A
   SubmitTime=2026-09-10T14:54:58 EligibleTime=2026-09-10T14:54:58
   AccrueTime=2026-09-10T14:54:58
   StartTime=2026-09-10T16:09:59 EndTime=2026-09-10T16:39:59 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-10T16:09:59 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:878899
   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=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,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=2-3,5-10 Mem=73136 GRES=gpu:ampere:1(IDX:1)
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=(null)
   WorkDir=/home/lmbanr001/masters/sallm_snapshots/pure-gdn-general-recovery-20260909-v3
   StdErr=/scratch/lmbanr001/masters/sallm/logs/jobs/gdn-general-pos-batch-gate-runtime-v2-20260910.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/gdn-general-pos-batch-gate-runtime-v2-20260910.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
UCT HPC clusterJOB DETAILS FOR JOB 1331858

captured Thu Sep 10 16:16:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7870 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:06:01 TimeLimit=00:30:00 TimeMin=N/A
   SubmitTime=2026-09-10T14:54:58 EligibleTime=2026-09-10T14:54:58
   AccrueTime=2026-09-10T14:54:58
   StartTime=2026-09-10T16:09:59 EndTime=2026-09-10T16:16:00 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-10T16:09:59 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:878899
   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=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,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=2-3,5-10 Mem=73136 GRES=
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=(null)
   WorkDir=/home/lmbanr001/masters/sallm_snapshots/pure-gdn-general-recovery-20260909-v3
   StdErr=/scratch/lmbanr001/masters/sallm/logs/jobs/gdn-general-pos-batch-gate-runtime-v2-20260910.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/gdn-general-pos-batch-gate-runtime-v2-20260910.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
UCT HPC clusterJOB DETAILS FOR JOB 1331858

captured Thu Sep 10 16:16:38 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7870 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:06:01 TimeLimit=00:30:00 TimeMin=N/A
   SubmitTime=2026-09-10T14:54:58 EligibleTime=2026-09-10T14:54:58
   AccrueTime=2026-09-10T14:54:58
   StartTime=2026-09-10T16:09:59 EndTime=2026-09-10T16:16:00 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-10T16:09:59 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:878899
   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=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,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=2-3,5-10 Mem=73136 GRES=
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=(null)
   WorkDir=/home/lmbanr001/masters/sallm_snapshots/pure-gdn-general-recovery-20260909-v3
   StdErr=/scratch/lmbanr001/masters/sallm/logs/jobs/gdn-general-pos-batch-gate-runtime-v2-20260910.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/gdn-general-pos-batch-gate-runtime-v2-20260910.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
UCT HPC clusterJOB DETAILS FOR JOB 1331858

captured Thu Sep 10 16:17:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7870 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:06:01 TimeLimit=00:30:00 TimeMin=N/A
   SubmitTime=2026-09-10T14:54:58 EligibleTime=2026-09-10T14:54:58
   AccrueTime=2026-09-10T14:54:58
   StartTime=2026-09-10T16:09:59 EndTime=2026-09-10T16:16:00 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-10T16:09:59 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:878899
   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=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,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=2-3,5-10 Mem=73136 GRES=
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=(null)
   WorkDir=/home/lmbanr001/masters/sallm_snapshots/pure-gdn-general-recovery-20260909-v3
   StdErr=/scratch/lmbanr001/masters/sallm/logs/jobs/gdn-general-pos-batch-gate-runtime-v2-20260910.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/gdn-general-pos-batch-gate-runtime-v2-20260910.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
UCT HPC clusterJOB DETAILS FOR JOB 1331858

captured Thu Sep 10 16:17:38 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7870 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:06:01 TimeLimit=00:30:00 TimeMin=N/A
   SubmitTime=2026-09-10T14:54:58 EligibleTime=2026-09-10T14:54:58
   AccrueTime=2026-09-10T14:54:58
   StartTime=2026-09-10T16:09:59 EndTime=2026-09-10T16:16:00 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-10T16:09:59 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:878899
   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=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,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=2-3,5-10 Mem=73136 GRES=
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=(null)
   WorkDir=/home/lmbanr001/masters/sallm_snapshots/pure-gdn-general-recovery-20260909-v3
   StdErr=/scratch/lmbanr001/masters/sallm/logs/jobs/gdn-general-pos-batch-gate-runtime-v2-20260910.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/gdn-general-pos-batch-gate-runtime-v2-20260910.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8