MaxRAM=1G |
JobId=190297 JobName=sallm-ft UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A Priority=7663 Nice=0 Account=nlpgroup QOS=nlpgroup JobState=RUNNING Reason=None Dependency=(null) Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0 DerivedExitCode=0:0 RunTime=00:00:23 TimeLimit=2-00:00:00 TimeMin=N/A SubmitTime=2025-07-29T06:03:38 EligibleTime=2025-07-29T06:03:38 AccrueTime=2025-07-29T06:03:38 StartTime=2025-07-29T06:03:38 EndTime=2025-07-31T06:03:38 Deadline=N/A SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-07-29T06:03:38 Scheduler=Main Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:3949706 ReqNodeList=(null) ExcNodeList=(null) NodeList=srvrocgpu010 BatchHost=srvrocgpu010 NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:* ReqTRES=cpu=1,mem=9142M,node=1,billing=3,gres/gpu=2 AllocTRES=cpu=4,mem=36568M,node=1,billing=9,gres/gpu=2,gres/gpu:ampere=2 Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=* JOB_GRES=gpu:ampere:2 Nodes=srvrocgpu010 CPU_IDs=0-1,28-29 Mem=36568 GRES=gpu:ampere:2(IDX:0,2) MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0 Features=(null) DelayBoot=00:00:00 OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null) Command=/home/lmbanr001/masters/sallm/scripts/launch_finetune.sh WorkDir=/home/lmbanr001/masters/sallm StdErr=/home/lmbanr001/masters/sallm/slurm-190297.out StdIn=/dev/null StdOut=/home/lmbanr001/masters/sallm/slurm-190297.out Power= CpusPerTres=gres/gpu:2 TresPerNode=gres/gpu:2 MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL |
JobId=190297 JobName=sallm-ft UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A Priority=7663 Nice=0 Account=nlpgroup QOS=nlpgroup JobState=FAILED Reason=NonZeroExitCode Dependency=(null) Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0 DerivedExitCode=0:0 RunTime=00:00:52 TimeLimit=2-00:00:00 TimeMin=N/A SubmitTime=2025-07-29T06:03:38 EligibleTime=2025-07-29T06:03:38 AccrueTime=2025-07-29T06:03:38 StartTime=2025-07-29T06:03:38 EndTime=2025-07-29T06:04:30 Deadline=N/A SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-07-29T06:03:38 Scheduler=Main Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:3949706 ReqNodeList=(null) ExcNodeList=(null) NodeList=srvrocgpu010 BatchHost=srvrocgpu010 NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:* ReqTRES=cpu=1,mem=9142M,node=1,billing=3,gres/gpu=2 AllocTRES=cpu=4,mem=36568M,node=1,billing=9,gres/gpu=2,gres/gpu:ampere=2 Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=* JOB_GRES=gpu:ampere:2 Nodes=srvrocgpu010 CPU_IDs=0-1,28-29 Mem=36568 GRES= MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0 Features=(null) DelayBoot=00:00:00 OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null) Command=/home/lmbanr001/masters/sallm/scripts/launch_finetune.sh WorkDir=/home/lmbanr001/masters/sallm StdErr=/home/lmbanr001/masters/sallm/slurm-190297.out StdIn=/dev/null StdOut=/home/lmbanr001/masters/sallm/slurm-190297.out Power= CpusPerTres=gres/gpu:2 TresPerNode=gres/gpu:2 MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL |
JobId=190297 JobName=sallm-ft UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A Priority=7663 Nice=0 Account=nlpgroup QOS=nlpgroup JobState=FAILED Reason=NonZeroExitCode Dependency=(null) Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0 DerivedExitCode=0:0 RunTime=00:00:52 TimeLimit=2-00:00:00 TimeMin=N/A SubmitTime=2025-07-29T06:03:38 EligibleTime=2025-07-29T06:03:38 AccrueTime=2025-07-29T06:03:38 StartTime=2025-07-29T06:03:38 EndTime=2025-07-29T06:04:30 Deadline=N/A SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-07-29T06:03:38 Scheduler=Main Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:3949706 ReqNodeList=(null) ExcNodeList=(null) NodeList=srvrocgpu010 BatchHost=srvrocgpu010 NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:* ReqTRES=cpu=1,mem=9142M,node=1,billing=3,gres/gpu=2 AllocTRES=cpu=4,mem=36568M,node=1,billing=9,gres/gpu=2,gres/gpu:ampere=2 Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=* JOB_GRES=gpu:ampere:2 Nodes=srvrocgpu010 CPU_IDs=0-1,28-29 Mem=36568 GRES= MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0 Features=(null) DelayBoot=00:00:00 OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null) Command=/home/lmbanr001/masters/sallm/scripts/launch_finetune.sh WorkDir=/home/lmbanr001/masters/sallm StdErr=/home/lmbanr001/masters/sallm/slurm-190297.out StdIn=/dev/null StdOut=/home/lmbanr001/masters/sallm/slurm-190297.out Power= CpusPerTres=gres/gpu:2 TresPerNode=gres/gpu:2 MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL |
JobId=190297 JobName=sallm-ft UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A Priority=7663 Nice=0 Account=nlpgroup QOS=nlpgroup JobState=FAILED Reason=NonZeroExitCode Dependency=(null) Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0 DerivedExitCode=0:0 RunTime=00:00:52 TimeLimit=2-00:00:00 TimeMin=N/A SubmitTime=2025-07-29T06:03:38 EligibleTime=2025-07-29T06:03:38 AccrueTime=2025-07-29T06:03:38 StartTime=2025-07-29T06:03:38 EndTime=2025-07-29T06:04:30 Deadline=N/A SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-07-29T06:03:38 Scheduler=Main Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:3949706 ReqNodeList=(null) ExcNodeList=(null) NodeList=srvrocgpu010 BatchHost=srvrocgpu010 NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:* ReqTRES=cpu=1,mem=9142M,node=1,billing=3,gres/gpu=2 AllocTRES=cpu=4,mem=36568M,node=1,billing=9,gres/gpu=2,gres/gpu:ampere=2 Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=* JOB_GRES=gpu:ampere:2 Nodes=srvrocgpu010 CPU_IDs=0-1,28-29 Mem=36568 GRES= MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0 Features=(null) DelayBoot=00:00:00 OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null) Command=/home/lmbanr001/masters/sallm/scripts/launch_finetune.sh WorkDir=/home/lmbanr001/masters/sallm StdErr=/home/lmbanr001/masters/sallm/slurm-190297.out StdIn=/dev/null StdOut=/home/lmbanr001/masters/sallm/slurm-190297.out Power= CpusPerTres=gres/gpu:2 TresPerNode=gres/gpu:2 MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL |
JobId=190297 JobName=sallm-ft UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A Priority=7663 Nice=0 Account=nlpgroup QOS=nlpgroup JobState=FAILED Reason=NonZeroExitCode Dependency=(null) Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0 DerivedExitCode=0:0 RunTime=00:00:52 TimeLimit=2-00:00:00 TimeMin=N/A SubmitTime=2025-07-29T06:03:38 EligibleTime=2025-07-29T06:03:38 AccrueTime=2025-07-29T06:03:38 StartTime=2025-07-29T06:03:38 EndTime=2025-07-29T06:04:30 Deadline=N/A SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-07-29T06:03:38 Scheduler=Main Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:3949706 ReqNodeList=(null) ExcNodeList=(null) NodeList=srvrocgpu010 BatchHost=srvrocgpu010 NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:* ReqTRES=cpu=1,mem=9142M,node=1,billing=3,gres/gpu=2 AllocTRES=cpu=4,mem=36568M,node=1,billing=9,gres/gpu=2,gres/gpu:ampere=2 Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=* JOB_GRES=gpu:ampere:2 Nodes=srvrocgpu010 CPU_IDs=0-1,28-29 Mem=36568 GRES= MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0 Features=(null) DelayBoot=00:00:00 OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null) Command=/home/lmbanr001/masters/sallm/scripts/launch_finetune.sh WorkDir=/home/lmbanr001/masters/sallm StdErr=/home/lmbanr001/masters/sallm/slurm-190297.out StdIn=/dev/null StdOut=/home/lmbanr001/masters/sallm/slurm-190297.out Power= CpusPerTres=gres/gpu:2 TresPerNode=gres/gpu:2 MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL |