UCT HPC cluster

JOB DETAILS FOR JOB 1238975

captured Sun Aug 16 10:06:02 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8260 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=PENDING Reason=Resources Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:00 TimeLimit=02:00:00 TimeMin=N/A
   SubmitTime=2026-08-16T09:56:13 EligibleTime=2026-08-16T09:56:13
   AccrueTime=2026-08-16T09:56:13
   StartTime=2026-08-17T03:20:32 EndTime=2026-08-17T05:20:32 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-16T10:05:46 Scheduler=Backfill:*
   Partition=a100 AllocNode:Sid=srvrochpc001:1104935
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList= SchedNodeList=srvrocgpu010
   NumNodes=1-1 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=(null)
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm_snapshots/pure-gdn-hpo-poscache-20260816-34a3f7d5/scripts/run_pos_runtime_equivalence_gate.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/scratch/lmbanr001/masters/sallm/logs/jobs/pos-cache-gate-ampere-1238975.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/pos-cache-gate-ampere-1238975.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8

UCT HPC clusterJOB DETAILS FOR JOB 1238975

captured Sun Aug 16 10:06:41 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8260 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=CANCELLED Reason=Resources Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:00 TimeLimit=02:00:00 TimeMin=N/A
   SubmitTime=2026-08-16T09:56:13 EligibleTime=2026-08-16T09:56:13
   AccrueTime=2026-08-16T09:56:13
   StartTime=2026-08-16T10:06:18 EndTime=2026-08-16T10:06:18 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-16T10:06:16 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc001:1104935
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList= SchedNodeList=srvrocgpu010
   NumNodes=1 NumCPUs=8 NumTasks=N/A 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=(null)
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm_snapshots/pure-gdn-hpo-poscache-20260816-34a3f7d5/scripts/run_pos_runtime_equivalence_gate.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/scratch/lmbanr001/masters/sallm/logs/jobs/pos-cache-gate-ampere-1238975.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/pos-cache-gate-ampere-1238975.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8

UCT HPC clusterJOB DETAILS FOR JOB 1238975

captured Sun Aug 16 10:07:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8260 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=CANCELLED Reason=Resources Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:00 TimeLimit=02:00:00 TimeMin=N/A
   SubmitTime=2026-08-16T09:56:13 EligibleTime=2026-08-16T09:56:13
   AccrueTime=2026-08-16T09:56:13
   StartTime=2026-08-16T10:06:18 EndTime=2026-08-16T10:06:18 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-16T10:06:16 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc001:1104935
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList= SchedNodeList=srvrocgpu010
   NumNodes=1 NumCPUs=8 NumTasks=N/A 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=(null)
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm_snapshots/pure-gdn-hpo-poscache-20260816-34a3f7d5/scripts/run_pos_runtime_equivalence_gate.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/scratch/lmbanr001/masters/sallm/logs/jobs/pos-cache-gate-ampere-1238975.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/pos-cache-gate-ampere-1238975.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8

UCT HPC clusterJOB DETAILS FOR JOB 1238975

captured Sun Aug 16 10:07:36 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8260 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=CANCELLED Reason=Resources Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:00 TimeLimit=02:00:00 TimeMin=N/A
   SubmitTime=2026-08-16T09:56:13 EligibleTime=2026-08-16T09:56:13
   AccrueTime=2026-08-16T09:56:13
   StartTime=2026-08-16T10:06:18 EndTime=2026-08-16T10:06:18 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-16T10:06:16 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc001:1104935
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList= SchedNodeList=srvrocgpu010
   NumNodes=1 NumCPUs=8 NumTasks=N/A 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=(null)
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm_snapshots/pure-gdn-hpo-poscache-20260816-34a3f7d5/scripts/run_pos_runtime_equivalence_gate.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/scratch/lmbanr001/masters/sallm/logs/jobs/pos-cache-gate-ampere-1238975.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/pos-cache-gate-ampere-1238975.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8

UCT HPC clusterJOB DETAILS FOR JOB 1238975

captured Sun Aug 16 10:08:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8260 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=CANCELLED Reason=Resources Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:00 TimeLimit=02:00:00 TimeMin=N/A
   SubmitTime=2026-08-16T09:56:13 EligibleTime=2026-08-16T09:56:13
   AccrueTime=2026-08-16T09:56:13
   StartTime=2026-08-16T10:06:18 EndTime=2026-08-16T10:06:18 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-16T10:06:16 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc001:1104935
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList= SchedNodeList=srvrocgpu010
   NumNodes=1 NumCPUs=8 NumTasks=N/A 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=(null)
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm_snapshots/pure-gdn-hpo-poscache-20260816-34a3f7d5/scripts/run_pos_runtime_equivalence_gate.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/scratch/lmbanr001/masters/sallm/logs/jobs/pos-cache-gate-ampere-1238975.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/pos-cache-gate-ampere-1238975.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8