JOB DETAILS FOR JOB 1356171

captured Mon Sep 21 07:48:01 SAST 2026

MaxRAM=2.4G
MaxVMSize=0G
AveCPUFreq=3.25M
AveDiskRead=903279173
AveDiskWrite=207131

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7717 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=RUNNING Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:03 TimeLimit=00:30:00 TimeMin=N/A
   SubmitTime=2026-09-21T07:47:57 EligibleTime=2026-09-21T07:47:57
   AccrueTime=2026-09-21T07:47:57
   StartTime=2026-09-21T07:47:58 EndTime=2026-09-21T08:17:58 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-21T07:47:58 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001:2525089
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=32G,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=32G,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu012 CPU_IDs=0-1,24-25 Mem=32768 GRES=gpu:l40s:1(IDX:0)
   MinCPUsNode=4 MinMemoryNode=32G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_snapshots/full-matrix-mamba-generation-cache-repair-20260921-v2/canary.sbatch
   WorkDir=/home/lmbanr001
   StdErr=/scratch/lmbanr001/masters/sallm/results/full_matrix_execution_20260916_v1/slurm/fm-mamba-gen-cache-canary-1356171.err
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/results/full_matrix_execution_20260916_v1/slurm/fm-mamba-gen-cache-canary-1356171.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   TresPerTask=cpu:4
   

UCT HPC clusterJOB DETAILS FOR JOB 1356171

captured Mon Sep 21 07:48:55 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7717 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:00:28 TimeLimit=00:30:00 TimeMin=N/A
   SubmitTime=2026-09-21T07:47:57 EligibleTime=2026-09-21T07:47:57
   AccrueTime=2026-09-21T07:47:57
   StartTime=2026-09-21T07:47:58 EndTime=2026-09-21T07:48:26 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-21T07:47:58 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001:2525089
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=32G,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=32G,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu012 CPU_IDs=0-1,24-25 Mem=32768 GRES=
   MinCPUsNode=4 MinMemoryNode=32G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_snapshots/full-matrix-mamba-generation-cache-repair-20260921-v2/canary.sbatch
   WorkDir=/home/lmbanr001
   StdErr=/scratch/lmbanr001/masters/sallm/results/full_matrix_execution_20260916_v1/slurm/fm-mamba-gen-cache-canary-1356171.err
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/results/full_matrix_execution_20260916_v1/slurm/fm-mamba-gen-cache-canary-1356171.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   TresPerTask=cpu:4
   

UCT HPC clusterJOB DETAILS FOR JOB 1356171

captured Mon Sep 21 07:49:31 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7717 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:00:28 TimeLimit=00:30:00 TimeMin=N/A
   SubmitTime=2026-09-21T07:47:57 EligibleTime=2026-09-21T07:47:57
   AccrueTime=2026-09-21T07:47:57
   StartTime=2026-09-21T07:47:58 EndTime=2026-09-21T07:48:26 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-21T07:47:58 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001:2525089
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=32G,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=32G,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu012 CPU_IDs=0-1,24-25 Mem=32768 GRES=
   MinCPUsNode=4 MinMemoryNode=32G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_snapshots/full-matrix-mamba-generation-cache-repair-20260921-v2/canary.sbatch
   WorkDir=/home/lmbanr001
   StdErr=/scratch/lmbanr001/masters/sallm/results/full_matrix_execution_20260916_v1/slurm/fm-mamba-gen-cache-canary-1356171.err
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/results/full_matrix_execution_20260916_v1/slurm/fm-mamba-gen-cache-canary-1356171.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   TresPerTask=cpu:4
   

UCT HPC clusterJOB DETAILS FOR JOB 1356171

captured Mon Sep 21 07:50:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7717 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:00:28 TimeLimit=00:30:00 TimeMin=N/A
   SubmitTime=2026-09-21T07:47:57 EligibleTime=2026-09-21T07:47:57
   AccrueTime=2026-09-21T07:47:57
   StartTime=2026-09-21T07:47:58 EndTime=2026-09-21T07:48:26 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-21T07:47:58 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001:2525089
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=32G,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=32G,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu012 CPU_IDs=0-1,24-25 Mem=32768 GRES=
   MinCPUsNode=4 MinMemoryNode=32G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_snapshots/full-matrix-mamba-generation-cache-repair-20260921-v2/canary.sbatch
   WorkDir=/home/lmbanr001
   StdErr=/scratch/lmbanr001/masters/sallm/results/full_matrix_execution_20260916_v1/slurm/fm-mamba-gen-cache-canary-1356171.err
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/results/full_matrix_execution_20260916_v1/slurm/fm-mamba-gen-cache-canary-1356171.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   TresPerTask=cpu:4