UCT HPC cluster

JOB DETAILS FOR JOB 1370116

captured Fri Sep 25 04:10:01 SAST 2026

MaxRAM=1.8G
MaxVMSize=0G
AveCPUFreq=92K
AveDiskRead=6126734449
AveDiskWrite=61888106

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7467 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=02:35:28 TimeLimit=12:00:00 TimeMin=N/A
   SubmitTime=2026-09-25T01:34:32 EligibleTime=2026-09-25T01:34:32
   AccrueTime=2026-09-25T01:34:32
   StartTime=2026-09-25T01:34:33 EndTime=2026-09-25T13:34:33 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-25T01:34:33 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1322127
   ReqNodeList=(null) ExcNodeList=srvrocgpu009
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=48G,node=1,billing=9,gres/gpu=1
   AllocTRES=cpu=4,mem=48G,node=1,billing=9,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=17-18,37-38 Mem=49152 GRES=gpu:ampere:1(IDX:3)
   MinCPUsNode=6 MinMemoryNode=48G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_snapshots/generation-protocol-v4-xlstm-bs1-20260925/run_xlstm_bs1.sbatch
   WorkDir=/scratch/lmbanr001/masters/sallm_snapshots/generation-protocol-v4-xlstm-bs1-20260925
   StdErr=/scratch/lmbanr001/masters/sallm/results/generation_protocol_v4_xlstm_bs1_20260925/slurm/gen-xlstm-bs1-1370116.err
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/results/generation_protocol_v4_xlstm_bs1_20260925/slurm/gen-xlstm-bs1-1370116.out
   Power=
   TresPerNode=gres/gpu:1
   TresPerTask=cpu:4

UCT HPC clusterJOB DETAILS FOR JOB 1370116

captured Fri Sep 25 04:10:37 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7467 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:15
   RunTime=02:35:40 TimeLimit=12:00:00 TimeMin=N/A
   SubmitTime=2026-09-25T01:34:32 EligibleTime=2026-09-25T01:34:32
   AccrueTime=2026-09-25T01:34:32
   StartTime=2026-09-25T01:34:33 EndTime=2026-09-25T04:10:13 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-25T01:34:33 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1322127
   ReqNodeList=(null) ExcNodeList=srvrocgpu009
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=48G,node=1,billing=9,gres/gpu=1
   AllocTRES=cpu=4,mem=48G,node=1,billing=9,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=17-18,37-38 Mem=49152 GRES=
   MinCPUsNode=6 MinMemoryNode=48G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_snapshots/generation-protocol-v4-xlstm-bs1-20260925/run_xlstm_bs1.sbatch
   WorkDir=/scratch/lmbanr001/masters/sallm_snapshots/generation-protocol-v4-xlstm-bs1-20260925
   StdErr=/scratch/lmbanr001/masters/sallm/results/generation_protocol_v4_xlstm_bs1_20260925/slurm/gen-xlstm-bs1-1370116.err
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/results/generation_protocol_v4_xlstm_bs1_20260925/slurm/gen-xlstm-bs1-1370116.out
   Power=
   TresPerNode=gres/gpu:1
   TresPerTask=cpu:4

UCT HPC clusterJOB DETAILS FOR JOB 1370116

captured Fri Sep 25 04:11:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7467 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:15
   RunTime=02:35:40 TimeLimit=12:00:00 TimeMin=N/A
   SubmitTime=2026-09-25T01:34:32 EligibleTime=2026-09-25T01:34:32
   AccrueTime=2026-09-25T01:34:32
   StartTime=2026-09-25T01:34:33 EndTime=2026-09-25T04:10:13 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-25T01:34:33 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1322127
   ReqNodeList=(null) ExcNodeList=srvrocgpu009
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=48G,node=1,billing=9,gres/gpu=1
   AllocTRES=cpu=4,mem=48G,node=1,billing=9,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=17-18,37-38 Mem=49152 GRES=
   MinCPUsNode=6 MinMemoryNode=48G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_snapshots/generation-protocol-v4-xlstm-bs1-20260925/run_xlstm_bs1.sbatch
   WorkDir=/scratch/lmbanr001/masters/sallm_snapshots/generation-protocol-v4-xlstm-bs1-20260925
   StdErr=/scratch/lmbanr001/masters/sallm/results/generation_protocol_v4_xlstm_bs1_20260925/slurm/gen-xlstm-bs1-1370116.err
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/results/generation_protocol_v4_xlstm_bs1_20260925/slurm/gen-xlstm-bs1-1370116.out
   Power=
   TresPerNode=gres/gpu:1
   TresPerTask=cpu:4

UCT HPC clusterJOB DETAILS FOR JOB 1370116

captured Fri Sep 25 04:11:36 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7467 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:15
   RunTime=02:35:40 TimeLimit=12:00:00 TimeMin=N/A
   SubmitTime=2026-09-25T01:34:32 EligibleTime=2026-09-25T01:34:32
   AccrueTime=2026-09-25T01:34:32
   StartTime=2026-09-25T01:34:33 EndTime=2026-09-25T04:10:13 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-25T01:34:33 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1322127
   ReqNodeList=(null) ExcNodeList=srvrocgpu009
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=48G,node=1,billing=9,gres/gpu=1
   AllocTRES=cpu=4,mem=48G,node=1,billing=9,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=17-18,37-38 Mem=49152 GRES=
   MinCPUsNode=6 MinMemoryNode=48G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_snapshots/generation-protocol-v4-xlstm-bs1-20260925/run_xlstm_bs1.sbatch
   WorkDir=/scratch/lmbanr001/masters/sallm_snapshots/generation-protocol-v4-xlstm-bs1-20260925
   StdErr=/scratch/lmbanr001/masters/sallm/results/generation_protocol_v4_xlstm_bs1_20260925/slurm/gen-xlstm-bs1-1370116.err
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/results/generation_protocol_v4_xlstm_bs1_20260925/slurm/gen-xlstm-bs1-1370116.out
   Power=
   TresPerNode=gres/gpu:1
   TresPerTask=cpu:4

UCT HPC clusterJOB DETAILS FOR JOB 1370116

captured Fri Sep 25 04:12:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7467 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:15
   RunTime=02:35:40 TimeLimit=12:00:00 TimeMin=N/A
   SubmitTime=2026-09-25T01:34:32 EligibleTime=2026-09-25T01:34:32
   AccrueTime=2026-09-25T01:34:32
   StartTime=2026-09-25T01:34:33 EndTime=2026-09-25T04:10:13 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-25T01:34:33 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1322127
   ReqNodeList=(null) ExcNodeList=srvrocgpu009
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=48G,node=1,billing=9,gres/gpu=1
   AllocTRES=cpu=4,mem=48G,node=1,billing=9,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=17-18,37-38 Mem=49152 GRES=
   MinCPUsNode=6 MinMemoryNode=48G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_snapshots/generation-protocol-v4-xlstm-bs1-20260925/run_xlstm_bs1.sbatch
   WorkDir=/scratch/lmbanr001/masters/sallm_snapshots/generation-protocol-v4-xlstm-bs1-20260925
   StdErr=/scratch/lmbanr001/masters/sallm/results/generation_protocol_v4_xlstm_bs1_20260925/slurm/gen-xlstm-bs1-1370116.err
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/results/generation_protocol_v4_xlstm_bs1_20260925/slurm/gen-xlstm-bs1-1370116.out
   Power=
   TresPerNode=gres/gpu:1
   TresPerTask=cpu:4

UCT HPC clusterJOB DETAILS FOR JOB 1370116

captured Fri Sep 25 04:12:36 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7467 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:15
   RunTime=02:35:40 TimeLimit=12:00:00 TimeMin=N/A
   SubmitTime=2026-09-25T01:34:32 EligibleTime=2026-09-25T01:34:32
   AccrueTime=2026-09-25T01:34:32
   StartTime=2026-09-25T01:34:33 EndTime=2026-09-25T04:10:13 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-25T01:34:33 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1322127
   ReqNodeList=(null) ExcNodeList=srvrocgpu009
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=48G,node=1,billing=9,gres/gpu=1
   AllocTRES=cpu=4,mem=48G,node=1,billing=9,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=17-18,37-38 Mem=49152 GRES=
   MinCPUsNode=6 MinMemoryNode=48G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_snapshots/generation-protocol-v4-xlstm-bs1-20260925/run_xlstm_bs1.sbatch
   WorkDir=/scratch/lmbanr001/masters/sallm_snapshots/generation-protocol-v4-xlstm-bs1-20260925
   StdErr=/scratch/lmbanr001/masters/sallm/results/generation_protocol_v4_xlstm_bs1_20260925/slurm/gen-xlstm-bs1-1370116.err
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/results/generation_protocol_v4_xlstm_bs1_20260925/slurm/gen-xlstm-bs1-1370116.out
   Power=
   TresPerNode=gres/gpu:1
   TresPerTask=cpu:4