UCT HPC cluster

JOB DETAILS FOR JOB 300128

captured Mon Oct 6 19:31:42 SAST 2025

MaxRAM=2.3G
MaxVMSize=0G
AveCPUFreq=1.53M
AveDiskRead=1130301481
AveDiskWrite=35795576

JobId=300128 JobName=sallm-eval
   UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7077 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=RUNNING Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:45:24 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-06T18:46:18 EligibleTime=2025-10-06T18:46:18
   AccrueTime=2025-10-06T18:46:18
   StartTime=2025-10-06T18:46:19 EndTime=2025-10-08T18:46:19 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-06T18:46:19 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:4120173
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu014
   BatchHost=srvrocgpu014
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=10000M,node=1,billing=1,gres/gpu=2
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=2,gres/gpu:l40s=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:2
     Nodes=srvrocgpu014 CPU_IDs=0-1,3-4,24-27 Mem=80000 GRES=gpu:l40s:2(IDX:0,2)
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm/scripts/launch_evaluation.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-300128.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-300128.out
   Power=
   CpusPerTres=gres/gpu:4
   TresPerNode=gres/gpu:2
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 300128

captured Mon Oct 6 19:32:02 SAST 2025

JobId=300128 JobName=sallm-eval
   UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7077 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=00:45:41 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-06T18:46:18 EligibleTime=2025-10-06T18:46:18
   AccrueTime=2025-10-06T18:46:18
   StartTime=2025-10-06T18:46:19 EndTime=2025-10-06T19:32:00 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-06T18:46:19 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:4120173
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu014
   BatchHost=srvrocgpu014
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=10000M,node=1,billing=1,gres/gpu=2
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=2,gres/gpu:l40s=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:2
     Nodes=srvrocgpu014 CPU_IDs=0-1,3-4,24-27 Mem=80000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm/scripts/launch_evaluation.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-300128.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-300128.out
   Power=
   CpusPerTres=gres/gpu:4
   TresPerNode=gres/gpu:2
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 300128

captured Mon Oct 6 19:32:42 SAST 2025

JobId=300128 JobName=sallm-eval
   UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7077 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=00:45:41 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-06T18:46:18 EligibleTime=2025-10-06T18:46:18
   AccrueTime=2025-10-06T18:46:18
   StartTime=2025-10-06T18:46:19 EndTime=2025-10-06T19:32:00 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-06T18:46:19 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:4120173
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu014
   BatchHost=srvrocgpu014
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=10000M,node=1,billing=1,gres/gpu=2
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=2,gres/gpu:l40s=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:2
     Nodes=srvrocgpu014 CPU_IDs=0-1,3-4,24-27 Mem=80000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm/scripts/launch_evaluation.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-300128.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-300128.out
   Power=
   CpusPerTres=gres/gpu:4
   TresPerNode=gres/gpu:2
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 300128

captured Mon Oct 6 19:33:01 SAST 2025

JobId=300128 JobName=sallm-eval
   UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7077 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=00:45:41 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-06T18:46:18 EligibleTime=2025-10-06T18:46:18
   AccrueTime=2025-10-06T18:46:18
   StartTime=2025-10-06T18:46:19 EndTime=2025-10-06T19:32:00 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-06T18:46:19 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:4120173
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu014
   BatchHost=srvrocgpu014
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=10000M,node=1,billing=1,gres/gpu=2
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=2,gres/gpu:l40s=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:2
     Nodes=srvrocgpu014 CPU_IDs=0-1,3-4,24-27 Mem=80000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm/scripts/launch_evaluation.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-300128.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-300128.out
   Power=
   CpusPerTres=gres/gpu:4
   TresPerNode=gres/gpu:2
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 300128

captured Mon Oct 6 19:33:42 SAST 2025

JobId=300128 JobName=sallm-eval
   UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7077 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=00:45:41 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-06T18:46:18 EligibleTime=2025-10-06T18:46:18
   AccrueTime=2025-10-06T18:46:18
   StartTime=2025-10-06T18:46:19 EndTime=2025-10-06T19:32:00 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-06T18:46:19 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:4120173
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu014
   BatchHost=srvrocgpu014
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=10000M,node=1,billing=1,gres/gpu=2
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=2,gres/gpu:l40s=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:2
     Nodes=srvrocgpu014 CPU_IDs=0-1,3-4,24-27 Mem=80000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm/scripts/launch_evaluation.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-300128.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-300128.out
   Power=
   CpusPerTres=gres/gpu:4
   TresPerNode=gres/gpu:2
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 300128

captured Mon Oct 6 19:34:01 SAST 2025

JobId=300128 JobName=sallm-eval
   UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7077 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=00:45:41 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-06T18:46:18 EligibleTime=2025-10-06T18:46:18
   AccrueTime=2025-10-06T18:46:18
   StartTime=2025-10-06T18:46:19 EndTime=2025-10-06T19:32:00 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-06T18:46:19 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:4120173
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu014
   BatchHost=srvrocgpu014
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=10000M,node=1,billing=1,gres/gpu=2
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=2,gres/gpu:l40s=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:2
     Nodes=srvrocgpu014 CPU_IDs=0-1,3-4,24-27 Mem=80000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm/scripts/launch_evaluation.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-300128.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-300128.out
   Power=
   CpusPerTres=gres/gpu:4
   TresPerNode=gres/gpu:2
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL