lxxcat004(1221969272 Catherine Li) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A Priority=7763 Nice=0 Account=l40sugrd QOS=l40sugrd JobState=PENDING Reason=QOSMaxGRESPerUser Dependency=(null) Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0 DerivedExitCode=0:0 RunTime=00:00:00 TimeLimit=1-00:00:00 TimeMin=N/A SubmitTime=2026-08-24T12:10:12 EligibleTime=2026-08-24T12:10:12 AccrueTime=Unknown StartTime=2026-08-25T03:39:29 EndTime=2026-08-26T03:39:29 Deadline=N/A SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-25T03:39:00 Scheduler=Backfill:* Partition=l40s AllocNode:Sid=srvrochpc100:1392778 ReqNodeList=(null) ExcNodeList=(null) NodeList= NumNodes=1-1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:* ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1 AllocTRES=(null) Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=* MinCPUsNode=8 MinMemoryCPU=10000M MinTmpDiskNode=0 Features=(null) DelayBoot=00:00:00 OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null) Command=/scratch/lxxcat004/InstaRoadPrototype/scripts/hpc/tm/train_peft.sbatch WorkDir=/scratch/lxxcat004/InstaRoadPrototype StdErr=/home/lxxcat004/InstaRoad/InstaRoadPrototype/logs/slurm-1263403.out StdIn=/dev/null StdOut=/home/lxxcat004/InstaRoad/InstaRoadPrototype/logs/slurm-1263403.out Power= TresPerNode=gres/gpu:1 TresPerTask=cpu:8 MailUser=lxxcat004@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT |
lxxcat004(1221969272 Catherine Li) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
Priority=7763 Nice=0 Account=l40sugrd QOS=l40sugrd
JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=2:0
DerivedExitCode=0:0
RunTime=00:00:18 TimeLimit=1-00:00:00 TimeMin=N/A
SubmitTime=2026-08-24T12:10:12 EligibleTime=2026-08-24T12:10:12
AccrueTime=Unknown
StartTime=2026-08-25T03:39:30 EndTime=2026-08-25T03:39:48 Deadline=N/A
SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-25T03:39:30 Scheduler=Backfill
Partition=l40s AllocNode:Sid=srvrochpc100:1392778
ReqNodeList=(null) ExcNodeList=(null)
NodeList=srvrocgpu014
BatchHost=srvrocgpu014
NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1
AllocTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1,gres/gpu:l40s=1
Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
JOB_GRES=gpu:l40s:1
Nodes=srvrocgpu014 CPU_IDs=0,9-11,25-28 Mem=80000 GRES=
MinCPUsNode=8 MinMemoryCPU=10000M MinTmpDiskNode=0
Features=(null) DelayBoot=00:00:00
OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
Command=/scratch/lxxcat004/InstaRoadPrototype/scripts/hpc/tm/train_peft.sbatch
WorkDir=/scratch/lxxcat004/InstaRoadPrototype
StdErr=/home/lxxcat004/InstaRoad/InstaRoadPrototype/logs/slurm-1263403.out
StdIn=/dev/null
StdOut=/home/lxxcat004/InstaRoad/InstaRoadPrototype/logs/slurm-1263403.out
Power=
TresPerNode=gres/gpu:1
TresPerTask=cpu:8
MailUser=lxxcat004@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
|
lxxcat004(1221969272 Catherine Li) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
Priority=7763 Nice=0 Account=l40sugrd QOS=l40sugrd
JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=2:0
DerivedExitCode=0:0
RunTime=00:00:18 TimeLimit=1-00:00:00 TimeMin=N/A
SubmitTime=2026-08-24T12:10:12 EligibleTime=2026-08-24T12:10:12
AccrueTime=Unknown
StartTime=2026-08-25T03:39:30 EndTime=2026-08-25T03:39:48 Deadline=N/A
SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-25T03:39:30 Scheduler=Backfill
Partition=l40s AllocNode:Sid=srvrochpc100:1392778
ReqNodeList=(null) ExcNodeList=(null)
NodeList=srvrocgpu014
BatchHost=srvrocgpu014
NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1
AllocTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1,gres/gpu:l40s=1
Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
JOB_GRES=gpu:l40s:1
Nodes=srvrocgpu014 CPU_IDs=0,9-11,25-28 Mem=80000 GRES=
MinCPUsNode=8 MinMemoryCPU=10000M MinTmpDiskNode=0
Features=(null) DelayBoot=00:00:00
OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
Command=/scratch/lxxcat004/InstaRoadPrototype/scripts/hpc/tm/train_peft.sbatch
WorkDir=/scratch/lxxcat004/InstaRoadPrototype
StdErr=/home/lxxcat004/InstaRoad/InstaRoadPrototype/logs/slurm-1263403.out
StdIn=/dev/null
StdOut=/home/lxxcat004/InstaRoad/InstaRoadPrototype/logs/slurm-1263403.out
Power=
TresPerNode=gres/gpu:1
TresPerTask=cpu:8
MailUser=lxxcat004@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
|
lxxcat004(1221969272 Catherine Li) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
Priority=7763 Nice=0 Account=l40sugrd QOS=l40sugrd
JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=2:0
DerivedExitCode=0:0
RunTime=00:00:18 TimeLimit=1-00:00:00 TimeMin=N/A
SubmitTime=2026-08-24T12:10:12 EligibleTime=2026-08-24T12:10:12
AccrueTime=Unknown
StartTime=2026-08-25T03:39:30 EndTime=2026-08-25T03:39:48 Deadline=N/A
SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-25T03:39:30 Scheduler=Backfill
Partition=l40s AllocNode:Sid=srvrochpc100:1392778
ReqNodeList=(null) ExcNodeList=(null)
NodeList=srvrocgpu014
BatchHost=srvrocgpu014
NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1
AllocTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1,gres/gpu:l40s=1
Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
JOB_GRES=gpu:l40s:1
Nodes=srvrocgpu014 CPU_IDs=0,9-11,25-28 Mem=80000 GRES=
MinCPUsNode=8 MinMemoryCPU=10000M MinTmpDiskNode=0
Features=(null) DelayBoot=00:00:00
OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
Command=/scratch/lxxcat004/InstaRoadPrototype/scripts/hpc/tm/train_peft.sbatch
WorkDir=/scratch/lxxcat004/InstaRoadPrototype
StdErr=/home/lxxcat004/InstaRoad/InstaRoadPrototype/logs/slurm-1263403.out
StdIn=/dev/null
StdOut=/home/lxxcat004/InstaRoad/InstaRoadPrototype/logs/slurm-1263403.out
Power=
TresPerNode=gres/gpu:1
TresPerTask=cpu:8
MailUser=lxxcat004@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
|