MaxRAM=3.2G |
lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
Priority=7231 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=00:00:30 TimeLimit=2-00:00:00 TimeMin=N/A
SubmitTime=2026-01-11T18:01:59 EligibleTime=2026-01-11T18:01:59
AccrueTime=2026-01-11T18:01:59
StartTime=2026-01-12T01:57:04 EndTime=2026-01-14T01:57:04 Deadline=N/A
SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-01-12T01:57:04 Scheduler=Backfill
Partition=l40s AllocNode:Sid=srvrochpc001:2133531
ReqNodeList=(null) ExcNodeList=(null)
NodeList=srvrocgpu015
BatchHost=srvrocgpu015
NumNodes=1 NumCPUs=4 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=4,mem=40000M,node=1,billing=7,gres/gpu=2,gres/gpu:l40s=2
Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
JOB_GRES=gpu:l40s:2
Nodes=srvrocgpu015 CPU_IDs=6-7,30-31 Mem=40000 GRES=gpu:l40s:2(IDX:2-3)
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/train_final_rwkv.sh
WorkDir=/home/lmbanr001/masters/sallm
StdErr=/home/lmbanr001/masters/sallm/slurm-418784.out
StdIn=/dev/null
StdOut=/home/lmbanr001/masters/sallm/slurm-418784.out
Power=
CpusPerTres=gres/gpu:2
TresPerNode=gres/gpu:2
MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL
|
lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
Priority=7231 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=00:00:48 TimeLimit=2-00:00:00 TimeMin=N/A
SubmitTime=2026-01-11T18:01:59 EligibleTime=2026-01-11T18:01:59
AccrueTime=2026-01-11T18:01:59
StartTime=2026-01-12T01:57:04 EndTime=2026-01-12T01:57:52 Deadline=N/A
SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-01-12T01:57:04 Scheduler=Backfill
Partition=l40s AllocNode:Sid=srvrochpc001:2133531
ReqNodeList=(null) ExcNodeList=(null)
NodeList=srvrocgpu015
BatchHost=srvrocgpu015
NumNodes=1 NumCPUs=4 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=4,mem=40000M,node=1,billing=7,gres/gpu=2,gres/gpu:l40s=2
Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
JOB_GRES=gpu:l40s:2
Nodes=srvrocgpu015 CPU_IDs=6-7,30-31 Mem=40000 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/train_final_rwkv.sh
WorkDir=/home/lmbanr001/masters/sallm
StdErr=/home/lmbanr001/masters/sallm/slurm-418784.out
StdIn=/dev/null
StdOut=/home/lmbanr001/masters/sallm/slurm-418784.out
Power=
CpusPerTres=gres/gpu:2
TresPerNode=gres/gpu:2
MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL
|
lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
Priority=7231 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=00:00:48 TimeLimit=2-00:00:00 TimeMin=N/A
SubmitTime=2026-01-11T18:01:59 EligibleTime=2026-01-11T18:01:59
AccrueTime=2026-01-11T18:01:59
StartTime=2026-01-12T01:57:04 EndTime=2026-01-12T01:57:52 Deadline=N/A
SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-01-12T01:57:04 Scheduler=Backfill
Partition=l40s AllocNode:Sid=srvrochpc001:2133531
ReqNodeList=(null) ExcNodeList=(null)
NodeList=srvrocgpu015
BatchHost=srvrocgpu015
NumNodes=1 NumCPUs=4 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=4,mem=40000M,node=1,billing=7,gres/gpu=2,gres/gpu:l40s=2
Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
JOB_GRES=gpu:l40s:2
Nodes=srvrocgpu015 CPU_IDs=6-7,30-31 Mem=40000 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/train_final_rwkv.sh
WorkDir=/home/lmbanr001/masters/sallm
StdErr=/home/lmbanr001/masters/sallm/slurm-418784.out
StdIn=/dev/null
StdOut=/home/lmbanr001/masters/sallm/slurm-418784.out
Power=
CpusPerTres=gres/gpu:2
TresPerNode=gres/gpu:2
MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL
|
lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
Priority=7231 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=00:00:48 TimeLimit=2-00:00:00 TimeMin=N/A
SubmitTime=2026-01-11T18:01:59 EligibleTime=2026-01-11T18:01:59
AccrueTime=2026-01-11T18:01:59
StartTime=2026-01-12T01:57:04 EndTime=2026-01-12T01:57:52 Deadline=N/A
SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-01-12T01:57:04 Scheduler=Backfill
Partition=l40s AllocNode:Sid=srvrochpc001:2133531
ReqNodeList=(null) ExcNodeList=(null)
NodeList=srvrocgpu015
BatchHost=srvrocgpu015
NumNodes=1 NumCPUs=4 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=4,mem=40000M,node=1,billing=7,gres/gpu=2,gres/gpu:l40s=2
Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
JOB_GRES=gpu:l40s:2
Nodes=srvrocgpu015 CPU_IDs=6-7,30-31 Mem=40000 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/train_final_rwkv.sh
WorkDir=/home/lmbanr001/masters/sallm
StdErr=/home/lmbanr001/masters/sallm/slurm-418784.out
StdIn=/dev/null
StdOut=/home/lmbanr001/masters/sallm/slurm-418784.out
Power=
CpusPerTres=gres/gpu:2
TresPerNode=gres/gpu:2
MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL
|
lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
Priority=7231 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=00:00:48 TimeLimit=2-00:00:00 TimeMin=N/A
SubmitTime=2026-01-11T18:01:59 EligibleTime=2026-01-11T18:01:59
AccrueTime=2026-01-11T18:01:59
StartTime=2026-01-12T01:57:04 EndTime=2026-01-12T01:57:52 Deadline=N/A
SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-01-12T01:57:04 Scheduler=Backfill
Partition=l40s AllocNode:Sid=srvrochpc001:2133531
ReqNodeList=(null) ExcNodeList=(null)
NodeList=srvrocgpu015
BatchHost=srvrocgpu015
NumNodes=1 NumCPUs=4 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=4,mem=40000M,node=1,billing=7,gres/gpu=2,gres/gpu:l40s=2
Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
JOB_GRES=gpu:l40s:2
Nodes=srvrocgpu015 CPU_IDs=6-7,30-31 Mem=40000 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/train_final_rwkv.sh
WorkDir=/home/lmbanr001/masters/sallm
StdErr=/home/lmbanr001/masters/sallm/slurm-418784.out
StdIn=/dev/null
StdOut=/home/lmbanr001/masters/sallm/slurm-418784.out
Power=
CpusPerTres=gres/gpu:2
TresPerNode=gres/gpu:2
MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL
|