JobId=303429 JobName=ssmt-train
UserId=yhxjin001(1221971307 Jing Yeh) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
Priority=7109 Nice=0 Account=l40sfree QOS=l40sfree
JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=2:0
DerivedExitCode=0:0
RunTime=00:00:13 TimeLimit=04:00:00 TimeMin=N/A
SubmitTime=2025-10-09T11:14:05 EligibleTime=2025-10-09T11:14:05
AccrueTime=2025-10-09T11:14:06
StartTime=2025-10-09T11:14:06 EndTime=2025-10-09T11:14:19 Deadline=N/A
SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-09T11:14:06 Scheduler=Main
Partition=l40s AllocNode:Sid=srvrochpc100:1000502
ReqNodeList=(null) ExcNodeList=(null)
NodeList=srvrocgpu014
BatchHost=srvrocgpu014
NumNodes=1 NumCPUs=2 NumTasks=2 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
ReqTRES=cpu=2,mem=16G,node=1,billing=3,gres/gpu=2
AllocTRES=cpu=2,mem=16G,node=1,billing=3,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=2,26 Mem=16384 GRES=
MinCPUsNode=1 MinMemoryCPU=8G MinTmpDiskNode=0
Features=(null) DelayBoot=00:00:00
OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
Command=/home/yhxjin001/Eng-Amis SSMT/ssmt/train_baseline_container.sh
WorkDir=/home/yhxjin001/Eng-Amis SSMT/ssmt
StdErr=/home/yhxjin001/Eng-Amis SSMT/ssmt/slurm-303429.out
StdIn=/dev/null
StdOut=/home/yhxjin001/Eng-Amis SSMT/ssmt/slurm-303429.out
Power=
TresPerNode=gres/gpu:2
MailUser=yhxjin001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
|
JobId=303429 JobName=ssmt-train
UserId=yhxjin001(1221971307 Jing Yeh) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
Priority=7109 Nice=0 Account=l40sfree QOS=l40sfree
JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=2:0
DerivedExitCode=0:0
RunTime=00:00:13 TimeLimit=04:00:00 TimeMin=N/A
SubmitTime=2025-10-09T11:14:05 EligibleTime=2025-10-09T11:14:05
AccrueTime=2025-10-09T11:14:06
StartTime=2025-10-09T11:14:06 EndTime=2025-10-09T11:14:19 Deadline=N/A
SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-09T11:14:06 Scheduler=Main
Partition=l40s AllocNode:Sid=srvrochpc100:1000502
ReqNodeList=(null) ExcNodeList=(null)
NodeList=srvrocgpu014
BatchHost=srvrocgpu014
NumNodes=1 NumCPUs=2 NumTasks=2 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
ReqTRES=cpu=2,mem=16G,node=1,billing=3,gres/gpu=2
AllocTRES=cpu=2,mem=16G,node=1,billing=3,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=2,26 Mem=16384 GRES=
MinCPUsNode=1 MinMemoryCPU=8G MinTmpDiskNode=0
Features=(null) DelayBoot=00:00:00
OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
Command=/home/yhxjin001/Eng-Amis SSMT/ssmt/train_baseline_container.sh
WorkDir=/home/yhxjin001/Eng-Amis SSMT/ssmt
StdErr=/home/yhxjin001/Eng-Amis SSMT/ssmt/slurm-303429.out
StdIn=/dev/null
StdOut=/home/yhxjin001/Eng-Amis SSMT/ssmt/slurm-303429.out
Power=
TresPerNode=gres/gpu:2
MailUser=yhxjin001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
|
JobId=303429 JobName=ssmt-train
UserId=yhxjin001(1221971307 Jing Yeh) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
Priority=7109 Nice=0 Account=l40sfree QOS=l40sfree
JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=2:0
DerivedExitCode=0:0
RunTime=00:00:13 TimeLimit=04:00:00 TimeMin=N/A
SubmitTime=2025-10-09T11:14:05 EligibleTime=2025-10-09T11:14:05
AccrueTime=2025-10-09T11:14:06
StartTime=2025-10-09T11:14:06 EndTime=2025-10-09T11:14:19 Deadline=N/A
SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-09T11:14:06 Scheduler=Main
Partition=l40s AllocNode:Sid=srvrochpc100:1000502
ReqNodeList=(null) ExcNodeList=(null)
NodeList=srvrocgpu014
BatchHost=srvrocgpu014
NumNodes=1 NumCPUs=2 NumTasks=2 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
ReqTRES=cpu=2,mem=16G,node=1,billing=3,gres/gpu=2
AllocTRES=cpu=2,mem=16G,node=1,billing=3,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=2,26 Mem=16384 GRES=
MinCPUsNode=1 MinMemoryCPU=8G MinTmpDiskNode=0
Features=(null) DelayBoot=00:00:00
OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
Command=/home/yhxjin001/Eng-Amis SSMT/ssmt/train_baseline_container.sh
WorkDir=/home/yhxjin001/Eng-Amis SSMT/ssmt
StdErr=/home/yhxjin001/Eng-Amis SSMT/ssmt/slurm-303429.out
StdIn=/dev/null
StdOut=/home/yhxjin001/Eng-Amis SSMT/ssmt/slurm-303429.out
Power=
TresPerNode=gres/gpu:2
MailUser=yhxjin001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
|
JobId=303429 JobName=ssmt-train
UserId=yhxjin001(1221971307 Jing Yeh) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
Priority=7109 Nice=0 Account=l40sfree QOS=l40sfree
JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=2:0
DerivedExitCode=0:0
RunTime=00:00:13 TimeLimit=04:00:00 TimeMin=N/A
SubmitTime=2025-10-09T11:14:05 EligibleTime=2025-10-09T11:14:05
AccrueTime=2025-10-09T11:14:06
StartTime=2025-10-09T11:14:06 EndTime=2025-10-09T11:14:19 Deadline=N/A
SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-09T11:14:06 Scheduler=Main
Partition=l40s AllocNode:Sid=srvrochpc100:1000502
ReqNodeList=(null) ExcNodeList=(null)
NodeList=srvrocgpu014
BatchHost=srvrocgpu014
NumNodes=1 NumCPUs=2 NumTasks=2 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
ReqTRES=cpu=2,mem=16G,node=1,billing=3,gres/gpu=2
AllocTRES=cpu=2,mem=16G,node=1,billing=3,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=2,26 Mem=16384 GRES=
MinCPUsNode=1 MinMemoryCPU=8G MinTmpDiskNode=0
Features=(null) DelayBoot=00:00:00
OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
Command=/home/yhxjin001/Eng-Amis SSMT/ssmt/train_baseline_container.sh
WorkDir=/home/yhxjin001/Eng-Amis SSMT/ssmt
StdErr=/home/yhxjin001/Eng-Amis SSMT/ssmt/slurm-303429.out
StdIn=/dev/null
StdOut=/home/yhxjin001/Eng-Amis SSMT/ssmt/slurm-303429.out
Power=
TresPerNode=gres/gpu:2
MailUser=yhxjin001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
|