MaxRAM=12.9G |
JobId=111230 JobName=sallm_transformer_best_final UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A Priority=8774 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=20:53:20 TimeLimit=2-00:00:00 TimeMin=N/A SubmitTime=2025-04-15T06:13:41 EligibleTime=2025-04-15T06:13:41 AccrueTime=2025-04-15T06:13:41 StartTime=2025-04-15T06:13:41 EndTime=2025-04-17T06:13:41 Deadline=N/A SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-04-15T06:13:41 Scheduler=Backfill Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:4054692 ReqNodeList=(null) ExcNodeList=(null) NodeList=srvrocgpu010 BatchHost=srvrocgpu010 NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:* ReqTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere=4 AllocTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere=4 Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=* JOB_GRES=gpu:ampere:4 Nodes=srvrocgpu010 CPU_IDs=0-3,28-31 Mem=73136 GRES=gpu:ampere:4(IDX:0-3) 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/transformer_training/final/run_final_training.sh WorkDir=/home/lmbanr001/masters/sallm/transformer_training/final StdErr=/home/lmbanr001/masters/sallm/transformer_training/final/slurm-111230.out StdIn=/dev/null StdOut=/home/lmbanr001/masters/sallm/transformer_training/final/slurm-111230.out Power= TresPerNode=gres/gpu:ampere:4 MailUser=lmbanr001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT |
JobId=111230 JobName=sallm_transformer_best_final UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A Priority=8774 Nice=0 Account=nlpgroup QOS=nlpgroup JobState=COMPLETED Reason=None Dependency=(null) Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0 DerivedExitCode=0:0 RunTime=20:53:44 TimeLimit=2-00:00:00 TimeMin=N/A SubmitTime=2025-04-15T06:13:41 EligibleTime=2025-04-15T06:13:41 AccrueTime=2025-04-15T06:13:41 StartTime=2025-04-15T06:13:41 EndTime=2025-04-16T03:07:25 Deadline=N/A SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-04-15T06:13:41 Scheduler=Backfill Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:4054692 ReqNodeList=(null) ExcNodeList=(null) NodeList=srvrocgpu010 BatchHost=srvrocgpu010 NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:* ReqTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere=4 AllocTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere=4 Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=* JOB_GRES=gpu:ampere:4 Nodes=srvrocgpu010 CPU_IDs=0-3,28-31 Mem=73136 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/transformer_training/final/run_final_training.sh WorkDir=/home/lmbanr001/masters/sallm/transformer_training/final StdErr=/home/lmbanr001/masters/sallm/transformer_training/final/slurm-111230.out StdIn=/dev/null StdOut=/home/lmbanr001/masters/sallm/transformer_training/final/slurm-111230.out Power= TresPerNode=gres/gpu:ampere:4 MailUser=lmbanr001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT |
JobId=111230 JobName=sallm_transformer_best_final UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A Priority=8774 Nice=0 Account=nlpgroup QOS=nlpgroup JobState=COMPLETED Reason=None Dependency=(null) Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0 DerivedExitCode=0:0 RunTime=20:53:44 TimeLimit=2-00:00:00 TimeMin=N/A SubmitTime=2025-04-15T06:13:41 EligibleTime=2025-04-15T06:13:41 AccrueTime=2025-04-15T06:13:41 StartTime=2025-04-15T06:13:41 EndTime=2025-04-16T03:07:25 Deadline=N/A SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-04-15T06:13:41 Scheduler=Backfill Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:4054692 ReqNodeList=(null) ExcNodeList=(null) NodeList=srvrocgpu010 BatchHost=srvrocgpu010 NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:* ReqTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere=4 AllocTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere=4 Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=* JOB_GRES=gpu:ampere:4 Nodes=srvrocgpu010 CPU_IDs=0-3,28-31 Mem=73136 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/transformer_training/final/run_final_training.sh WorkDir=/home/lmbanr001/masters/sallm/transformer_training/final StdErr=/home/lmbanr001/masters/sallm/transformer_training/final/slurm-111230.out StdIn=/dev/null StdOut=/home/lmbanr001/masters/sallm/transformer_training/final/slurm-111230.out Power= TresPerNode=gres/gpu:ampere:4 MailUser=lmbanr001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT |
JobId=111230 JobName=sallm_transformer_best_final UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A Priority=8774 Nice=0 Account=nlpgroup QOS=nlpgroup JobState=COMPLETED Reason=None Dependency=(null) Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0 DerivedExitCode=0:0 RunTime=20:53:44 TimeLimit=2-00:00:00 TimeMin=N/A SubmitTime=2025-04-15T06:13:41 EligibleTime=2025-04-15T06:13:41 AccrueTime=2025-04-15T06:13:41 StartTime=2025-04-15T06:13:41 EndTime=2025-04-16T03:07:25 Deadline=N/A SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-04-15T06:13:41 Scheduler=Backfill Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:4054692 ReqNodeList=(null) ExcNodeList=(null) NodeList=srvrocgpu010 BatchHost=srvrocgpu010 NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:* ReqTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere=4 AllocTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere=4 Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=* JOB_GRES=gpu:ampere:4 Nodes=srvrocgpu010 CPU_IDs=0-3,28-31 Mem=73136 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/transformer_training/final/run_final_training.sh WorkDir=/home/lmbanr001/masters/sallm/transformer_training/final StdErr=/home/lmbanr001/masters/sallm/transformer_training/final/slurm-111230.out StdIn=/dev/null StdOut=/home/lmbanr001/masters/sallm/transformer_training/final/slurm-111230.out Power= TresPerNode=gres/gpu:ampere:4 MailUser=lmbanr001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT |
JobId=111230 JobName=sallm_transformer_best_final UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A Priority=8774 Nice=0 Account=nlpgroup QOS=nlpgroup JobState=COMPLETED Reason=None Dependency=(null) Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0 DerivedExitCode=0:0 RunTime=20:53:44 TimeLimit=2-00:00:00 TimeMin=N/A SubmitTime=2025-04-15T06:13:41 EligibleTime=2025-04-15T06:13:41 AccrueTime=2025-04-15T06:13:41 StartTime=2025-04-15T06:13:41 EndTime=2025-04-16T03:07:25 Deadline=N/A SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-04-15T06:13:41 Scheduler=Backfill Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:4054692 ReqNodeList=(null) ExcNodeList=(null) NodeList=srvrocgpu010 BatchHost=srvrocgpu010 NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:* ReqTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere=4 AllocTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere=4 Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=* JOB_GRES=gpu:ampere:4 Nodes=srvrocgpu010 CPU_IDs=0-3,28-31 Mem=73136 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/transformer_training/final/run_final_training.sh WorkDir=/home/lmbanr001/masters/sallm/transformer_training/final StdErr=/home/lmbanr001/masters/sallm/transformer_training/final/slurm-111230.out StdIn=/dev/null StdOut=/home/lmbanr001/masters/sallm/transformer_training/final/slurm-111230.out Power= TresPerNode=gres/gpu:ampere:4 MailUser=lmbanr001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT |
JobId=111230 JobName=sallm_transformer_best_final UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A Priority=8774 Nice=0 Account=nlpgroup QOS=nlpgroup JobState=COMPLETED Reason=None Dependency=(null) Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0 DerivedExitCode=0:0 RunTime=20:53:44 TimeLimit=2-00:00:00 TimeMin=N/A SubmitTime=2025-04-15T06:13:41 EligibleTime=2025-04-15T06:13:41 AccrueTime=2025-04-15T06:13:41 StartTime=2025-04-15T06:13:41 EndTime=2025-04-16T03:07:25 Deadline=N/A SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-04-15T06:13:41 Scheduler=Backfill Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:4054692 ReqNodeList=(null) ExcNodeList=(null) NodeList=srvrocgpu010 BatchHost=srvrocgpu010 NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:* ReqTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere=4 AllocTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere=4 Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=* JOB_GRES=gpu:ampere:4 Nodes=srvrocgpu010 CPU_IDs=0-3,28-31 Mem=73136 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/transformer_training/final/run_final_training.sh WorkDir=/home/lmbanr001/masters/sallm/transformer_training/final StdErr=/home/lmbanr001/masters/sallm/transformer_training/final/slurm-111230.out StdIn=/dev/null StdOut=/home/lmbanr001/masters/sallm/transformer_training/final/slurm-111230.out Power= TresPerNode=gres/gpu:ampere:4 MailUser=lmbanr001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT |