MaxRAM=0G |
lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
Priority=7716 Nice=45 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=1-08:34:51 TimeLimit=2-00:00:00 TimeMin=N/A
SubmitTime=2026-10-15T04:37:29 EligibleTime=2026-10-15T04:37:29
AccrueTime=Unknown
StartTime=2026-10-15T10:00:10 EndTime=2026-10-17T10:00:10 Deadline=N/A
SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-10-15T10:00:10 Scheduler=Main
Partition=l40s AllocNode:Sid=srvrocgpu016.uct.ac.za:1471344
ReqNodeList=(null) ExcNodeList=(null)
NodeList=srvrocgpu012
BatchHost=srvrocgpu012
NumNodes=1 NumCPUs=6 NumTasks=1 CPUs/Task=6 ReqB:S:C:T=0:0:*:*
ReqTRES=cpu=6,mem=64G,node=1,billing=12,gres/gpu=1,gres/gpu:l40s=1
AllocTRES=cpu=6,mem=64G,node=1,billing=12,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=1,3,5,25,30-31 Mem=65536 GRES=gpu:l40s:1(IDX:2)
MinCPUsNode=7 MinMemoryNode=64G MinTmpDiskNode=0
Features=(null) DelayBoot=00:00:00
OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
Command=/scratch/lmbanr001/masters/sallm/results/fft_rollout_20260926/code/fft_rollout/lane.sbatch
WorkDir=/scratch/lmbanr001/masters/sallm/results/fft_rollout_20260926/code/fft_rollout
StdErr=/scratch/lmbanr001/masters/sallm/results/fft_rollout_20260926/logs/fft-xlstm_e2_full-0-1486065.out
StdIn=/dev/null
StdOut=/scratch/lmbanr001/masters/sallm/results/fft_rollout_20260926/logs/fft-xlstm_e2_full-0-1486065.out
Power=
TresPerNode=gres/gpu:l40s:1
TresPerTask=cpu:6
|
lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
Priority=7716 Nice=45 Account=l40sfree QOS=l40sfree
JobState=NODE_FAIL Reason=NodeDown FailedNode=srvrocgpu012 Dependency=(null)
Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
DerivedExitCode=0:0
RunTime=1-08:35:05 TimeLimit=2-00:00:00 TimeMin=N/A
SubmitTime=2026-10-15T04:37:29 EligibleTime=2026-10-15T04:37:29
AccrueTime=Unknown
StartTime=2026-10-15T10:00:10 EndTime=2026-10-16T18:35:15 Deadline=N/A
SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-10-15T10:00:10 Scheduler=Main
Partition=l40s AllocNode:Sid=srvrocgpu016.uct.ac.za:1471344
ReqNodeList=(null) ExcNodeList=(null)
NodeList=srvrocgpu012
BatchHost=srvrocgpu012
NumNodes=1 NumCPUs=6 NumTasks=1 CPUs/Task=6 ReqB:S:C:T=0:0:*:*
ReqTRES=cpu=6,mem=64G,node=1,billing=12,gres/gpu=1,gres/gpu:l40s=1
AllocTRES=cpu=6,mem=64G,node=1,billing=12,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=1,3,5,25,30-31 Mem=65536 GRES=
MinCPUsNode=7 MinMemoryNode=64G MinTmpDiskNode=0
Features=(null) DelayBoot=00:00:00
OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
Command=/scratch/lmbanr001/masters/sallm/results/fft_rollout_20260926/code/fft_rollout/lane.sbatch
WorkDir=/scratch/lmbanr001/masters/sallm/results/fft_rollout_20260926/code/fft_rollout
StdErr=/scratch/lmbanr001/masters/sallm/results/fft_rollout_20260926/logs/fft-xlstm_e2_full-0-1486065.out
StdIn=/dev/null
StdOut=/scratch/lmbanr001/masters/sallm/results/fft_rollout_20260926/logs/fft-xlstm_e2_full-0-1486065.out
Power=
TresPerNode=gres/gpu:l40s:1
TresPerTask=cpu:6
|
lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
Priority=7716 Nice=45 Account=l40sfree QOS=l40sfree
JobState=NODE_FAIL Reason=NodeDown FailedNode=srvrocgpu012 Dependency=(null)
Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
DerivedExitCode=0:0
RunTime=1-08:35:05 TimeLimit=2-00:00:00 TimeMin=N/A
SubmitTime=2026-10-15T04:37:29 EligibleTime=2026-10-15T04:37:29
AccrueTime=Unknown
StartTime=2026-10-15T10:00:10 EndTime=2026-10-16T18:35:15 Deadline=N/A
SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-10-15T10:00:10 Scheduler=Main
Partition=l40s AllocNode:Sid=srvrocgpu016.uct.ac.za:1471344
ReqNodeList=(null) ExcNodeList=(null)
NodeList=srvrocgpu012
BatchHost=srvrocgpu012
NumNodes=1 NumCPUs=6 NumTasks=1 CPUs/Task=6 ReqB:S:C:T=0:0:*:*
ReqTRES=cpu=6,mem=64G,node=1,billing=12,gres/gpu=1,gres/gpu:l40s=1
AllocTRES=cpu=6,mem=64G,node=1,billing=12,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=1,3,5,25,30-31 Mem=65536 GRES=
MinCPUsNode=7 MinMemoryNode=64G MinTmpDiskNode=0
Features=(null) DelayBoot=00:00:00
OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
Command=/scratch/lmbanr001/masters/sallm/results/fft_rollout_20260926/code/fft_rollout/lane.sbatch
WorkDir=/scratch/lmbanr001/masters/sallm/results/fft_rollout_20260926/code/fft_rollout
StdErr=/scratch/lmbanr001/masters/sallm/results/fft_rollout_20260926/logs/fft-xlstm_e2_full-0-1486065.out
StdIn=/dev/null
StdOut=/scratch/lmbanr001/masters/sallm/results/fft_rollout_20260926/logs/fft-xlstm_e2_full-0-1486065.out
Power=
TresPerNode=gres/gpu:l40s:1
TresPerTask=cpu:6
|