MaxRAM=1.4G |
symdyl001(465022116 Dylan Saayman) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
Priority=7537 Nice=0 Account=l40sugrd QOS=l40sugrd
JobState=RUNNING Reason=None Dependency=(null)
Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
DerivedExitCode=0:0
RunTime=00:00:15 TimeLimit=00:30:00 TimeMin=N/A
SubmitTime=2026-06-28T00:09:01 EligibleTime=2026-06-28T00:09:01
AccrueTime=Unknown
StartTime=2026-06-28T00:09:24 EndTime=2026-06-28T00:39:24 Deadline=N/A
SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-06-28T00:09:24 Scheduler=Backfill
Partition=l40s AllocNode:Sid=srvrochpc001:1413248
ReqNodeList=(null) ExcNodeList=(null)
NodeList=srvrocgpu015
BatchHost=srvrocgpu015
NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
ReqTRES=cpu=8,mem=100G,node=1,billing=18,gres/gpu=1,gres/gpu:l40s=1
AllocTRES=cpu=8,mem=100G,node=1,billing=18,gres/gpu=1,gres/gpu:l40s=1
Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
JOB_GRES=gpu:l40s:1
Nodes=srvrocgpu015 CPU_IDs=4,8,14-15,28,32,38-39 Mem=102400 GRES=gpu:l40s:1(IDX:1)
MinCPUsNode=11 MinMemoryNode=100G MinTmpDiskNode=0
Features=(null) DelayBoot=00:00:00
OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
Command=/home/symdyl001/afriquellm_llama/cpt_scripts/llama3.1_cpt/run_train_smoke.sh
WorkDir=/scratch/symdyl001/afriquellm/logs
StdErr=/scratch/symdyl001/afriquellm/logs/llama_cpt_smoke_963667.err
StdIn=/dev/null
StdOut=/scratch/symdyl001/afriquellm/logs/llama_cpt_smoke_963667.out
Power=
TresPerNode=gres/gpu:l40s:1
TresPerTask=cpu:8
MailUser=symdyl001@myuct.ac.za MailType=BEGIN,END,FAIL
|
symdyl001(465022116 Dylan Saayman) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
Priority=7537 Nice=0 Account=l40sugrd QOS=l40sugrd
JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
DerivedExitCode=0:0
RunTime=00:00:24 TimeLimit=00:30:00 TimeMin=N/A
SubmitTime=2026-06-28T00:09:01 EligibleTime=2026-06-28T00:09:01
AccrueTime=Unknown
StartTime=2026-06-28T00:09:24 EndTime=2026-06-28T00:09:48 Deadline=N/A
SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-06-28T00:09:24 Scheduler=Backfill
Partition=l40s AllocNode:Sid=srvrochpc001:1413248
ReqNodeList=(null) ExcNodeList=(null)
NodeList=srvrocgpu015
BatchHost=srvrocgpu015
NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
ReqTRES=cpu=8,mem=100G,node=1,billing=18,gres/gpu=1,gres/gpu:l40s=1
AllocTRES=cpu=8,mem=100G,node=1,billing=18,gres/gpu=1,gres/gpu:l40s=1
Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
JOB_GRES=gpu:l40s:1
Nodes=srvrocgpu015 CPU_IDs=4,8,14-15,28,32,38-39 Mem=102400 GRES=
MinCPUsNode=11 MinMemoryNode=100G MinTmpDiskNode=0
Features=(null) DelayBoot=00:00:00
OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
Command=/home/symdyl001/afriquellm_llama/cpt_scripts/llama3.1_cpt/run_train_smoke.sh
WorkDir=/scratch/symdyl001/afriquellm/logs
StdErr=/scratch/symdyl001/afriquellm/logs/llama_cpt_smoke_963667.err
StdIn=/dev/null
StdOut=/scratch/symdyl001/afriquellm/logs/llama_cpt_smoke_963667.out
Power=
TresPerNode=gres/gpu:l40s:1
TresPerTask=cpu:8
MailUser=symdyl001@myuct.ac.za MailType=BEGIN,END,FAIL
|
symdyl001(465022116 Dylan Saayman) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
Priority=7537 Nice=0 Account=l40sugrd QOS=l40sugrd
JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
DerivedExitCode=0:0
RunTime=00:00:24 TimeLimit=00:30:00 TimeMin=N/A
SubmitTime=2026-06-28T00:09:01 EligibleTime=2026-06-28T00:09:01
AccrueTime=Unknown
StartTime=2026-06-28T00:09:24 EndTime=2026-06-28T00:09:48 Deadline=N/A
SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-06-28T00:09:24 Scheduler=Backfill
Partition=l40s AllocNode:Sid=srvrochpc001:1413248
ReqNodeList=(null) ExcNodeList=(null)
NodeList=srvrocgpu015
BatchHost=srvrocgpu015
NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
ReqTRES=cpu=8,mem=100G,node=1,billing=18,gres/gpu=1,gres/gpu:l40s=1
AllocTRES=cpu=8,mem=100G,node=1,billing=18,gres/gpu=1,gres/gpu:l40s=1
Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
JOB_GRES=gpu:l40s:1
Nodes=srvrocgpu015 CPU_IDs=4,8,14-15,28,32,38-39 Mem=102400 GRES=
MinCPUsNode=11 MinMemoryNode=100G MinTmpDiskNode=0
Features=(null) DelayBoot=00:00:00
OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
Command=/home/symdyl001/afriquellm_llama/cpt_scripts/llama3.1_cpt/run_train_smoke.sh
WorkDir=/scratch/symdyl001/afriquellm/logs
StdErr=/scratch/symdyl001/afriquellm/logs/llama_cpt_smoke_963667.err
StdIn=/dev/null
StdOut=/scratch/symdyl001/afriquellm/logs/llama_cpt_smoke_963667.out
Power=
TresPerNode=gres/gpu:l40s:1
TresPerTask=cpu:8
MailUser=symdyl001@myuct.ac.za MailType=BEGIN,END,FAIL
|
symdyl001(465022116 Dylan Saayman) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
Priority=7537 Nice=0 Account=l40sugrd QOS=l40sugrd
JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
DerivedExitCode=0:0
RunTime=00:00:24 TimeLimit=00:30:00 TimeMin=N/A
SubmitTime=2026-06-28T00:09:01 EligibleTime=2026-06-28T00:09:01
AccrueTime=Unknown
StartTime=2026-06-28T00:09:24 EndTime=2026-06-28T00:09:48 Deadline=N/A
SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-06-28T00:09:24 Scheduler=Backfill
Partition=l40s AllocNode:Sid=srvrochpc001:1413248
ReqNodeList=(null) ExcNodeList=(null)
NodeList=srvrocgpu015
BatchHost=srvrocgpu015
NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
ReqTRES=cpu=8,mem=100G,node=1,billing=18,gres/gpu=1,gres/gpu:l40s=1
AllocTRES=cpu=8,mem=100G,node=1,billing=18,gres/gpu=1,gres/gpu:l40s=1
Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
JOB_GRES=gpu:l40s:1
Nodes=srvrocgpu015 CPU_IDs=4,8,14-15,28,32,38-39 Mem=102400 GRES=
MinCPUsNode=11 MinMemoryNode=100G MinTmpDiskNode=0
Features=(null) DelayBoot=00:00:00
OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
Command=/home/symdyl001/afriquellm_llama/cpt_scripts/llama3.1_cpt/run_train_smoke.sh
WorkDir=/scratch/symdyl001/afriquellm/logs
StdErr=/scratch/symdyl001/afriquellm/logs/llama_cpt_smoke_963667.err
StdIn=/dev/null
StdOut=/scratch/symdyl001/afriquellm/logs/llama_cpt_smoke_963667.out
Power=
TresPerNode=gres/gpu:l40s:1
TresPerTask=cpu:8
MailUser=symdyl001@myuct.ac.za MailType=BEGIN,END,FAIL
|
symdyl001(465022116 Dylan Saayman) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
Priority=7537 Nice=0 Account=l40sugrd QOS=l40sugrd
JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
DerivedExitCode=0:0
RunTime=00:00:24 TimeLimit=00:30:00 TimeMin=N/A
SubmitTime=2026-06-28T00:09:01 EligibleTime=2026-06-28T00:09:01
AccrueTime=Unknown
StartTime=2026-06-28T00:09:24 EndTime=2026-06-28T00:09:48 Deadline=N/A
SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-06-28T00:09:24 Scheduler=Backfill
Partition=l40s AllocNode:Sid=srvrochpc001:1413248
ReqNodeList=(null) ExcNodeList=(null)
NodeList=srvrocgpu015
BatchHost=srvrocgpu015
NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
ReqTRES=cpu=8,mem=100G,node=1,billing=18,gres/gpu=1,gres/gpu:l40s=1
AllocTRES=cpu=8,mem=100G,node=1,billing=18,gres/gpu=1,gres/gpu:l40s=1
Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
JOB_GRES=gpu:l40s:1
Nodes=srvrocgpu015 CPU_IDs=4,8,14-15,28,32,38-39 Mem=102400 GRES=
MinCPUsNode=11 MinMemoryNode=100G MinTmpDiskNode=0
Features=(null) DelayBoot=00:00:00
OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
Command=/home/symdyl001/afriquellm_llama/cpt_scripts/llama3.1_cpt/run_train_smoke.sh
WorkDir=/scratch/symdyl001/afriquellm/logs
StdErr=/scratch/symdyl001/afriquellm/logs/llama_cpt_smoke_963667.err
StdIn=/dev/null
StdOut=/scratch/symdyl001/afriquellm/logs/llama_cpt_smoke_963667.out
Power=
TresPerNode=gres/gpu:l40s:1
TresPerTask=cpu:8
MailUser=symdyl001@myuct.ac.za MailType=BEGIN,END,FAIL
|