JOB DETAILS FOR JOB 243179

captured Mon Aug 25 16:21:01 SAST 2025

MaxRAM=0G
MaxVMSize=0G
AveCPUFreq=
AveDiskRead=
AveDiskWrite=

JobId=243179 JobName=grpo-fin
   UserId=wbbcor001(1221869528 Corey Webb) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7175 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=RUNNING Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:02:09 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T16:18:52 EligibleTime=2025-08-25T16:18:52
   AccrueTime=2025-08-25T16:18:52
   StartTime=2025-08-25T16:18:52 EndTime=2025-08-27T16:18:52 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:18:52 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:2965128
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu016
   BatchHost=srvrocgpu016
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=2,gres/gpu:l40s=2
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=2,gres/gpu:l40s=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:2
     Nodes=srvrocgpu016 CPU_IDs=0-1,24-25 Mem=40000 GRES=gpu:l40s:2(IDX:0-1)
   MinCPUsNode=4 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/wbbcor001/finetuning-qwen/batch_rl.sh
   WorkDir=/home/wbbcor001/finetuning-qwen
   StdErr=/home/wbbcor001/finetuning-qwen/GRPO-finetune-243179.out
   StdIn=/dev/null
   StdOut=/home/wbbcor001/finetuning-qwen/GRPO-finetune-243179.out
   Power=
   TresPerNode=gres/gpu:l40s:2
   TresPerTask=cpu:4
   MailUser=wbbcor001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
UCT HPC clusterJOB DETAILS FOR JOB 243179

captured Mon Aug 25 16:21:43 SAST 2025

JobId=243179 JobName=grpo-fin
   UserId=wbbcor001(1221869528 Corey Webb) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7175 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=1:0
   RunTime=00:02:18 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T16:18:52 EligibleTime=2025-08-25T16:18:52
   AccrueTime=2025-08-25T16:18:52
   StartTime=2025-08-25T16:18:52 EndTime=2025-08-25T16:21:10 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:18:52 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:2965128
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu016
   BatchHost=srvrocgpu016
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=2,gres/gpu:l40s=2
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=2,gres/gpu:l40s=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:2
     Nodes=srvrocgpu016 CPU_IDs=0-1,24-25 Mem=40000 GRES=
   MinCPUsNode=4 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/wbbcor001/finetuning-qwen/batch_rl.sh
   WorkDir=/home/wbbcor001/finetuning-qwen
   StdErr=/home/wbbcor001/finetuning-qwen/GRPO-finetune-243179.out
   StdIn=/dev/null
   StdOut=/home/wbbcor001/finetuning-qwen/GRPO-finetune-243179.out
   Power=
   TresPerNode=gres/gpu:l40s:2
   TresPerTask=cpu:4
   MailUser=wbbcor001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
UCT HPC clusterJOB DETAILS FOR JOB 243179

captured Mon Aug 25 16:22:01 SAST 2025

JobId=243179 JobName=grpo-fin
   UserId=wbbcor001(1221869528 Corey Webb) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7175 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=1:0
   RunTime=00:02:18 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T16:18:52 EligibleTime=2025-08-25T16:18:52
   AccrueTime=2025-08-25T16:18:52
   StartTime=2025-08-25T16:18:52 EndTime=2025-08-25T16:21:10 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:18:52 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:2965128
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu016
   BatchHost=srvrocgpu016
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=2,gres/gpu:l40s=2
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=2,gres/gpu:l40s=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:2
     Nodes=srvrocgpu016 CPU_IDs=0-1,24-25 Mem=40000 GRES=
   MinCPUsNode=4 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/wbbcor001/finetuning-qwen/batch_rl.sh
   WorkDir=/home/wbbcor001/finetuning-qwen
   StdErr=/home/wbbcor001/finetuning-qwen/GRPO-finetune-243179.out
   StdIn=/dev/null
   StdOut=/home/wbbcor001/finetuning-qwen/GRPO-finetune-243179.out
   Power=
   TresPerNode=gres/gpu:l40s:2
   TresPerTask=cpu:4
   MailUser=wbbcor001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
UCT HPC clusterJOB DETAILS FOR JOB 243179

captured Mon Aug 25 16:22:43 SAST 2025

JobId=243179 JobName=grpo-fin
   UserId=wbbcor001(1221869528 Corey Webb) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7175 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=1:0
   RunTime=00:02:18 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T16:18:52 EligibleTime=2025-08-25T16:18:52
   AccrueTime=2025-08-25T16:18:52
   StartTime=2025-08-25T16:18:52 EndTime=2025-08-25T16:21:10 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:18:52 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:2965128
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu016
   BatchHost=srvrocgpu016
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=2,gres/gpu:l40s=2
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=2,gres/gpu:l40s=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:2
     Nodes=srvrocgpu016 CPU_IDs=0-1,24-25 Mem=40000 GRES=
   MinCPUsNode=4 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/wbbcor001/finetuning-qwen/batch_rl.sh
   WorkDir=/home/wbbcor001/finetuning-qwen
   StdErr=/home/wbbcor001/finetuning-qwen/GRPO-finetune-243179.out
   StdIn=/dev/null
   StdOut=/home/wbbcor001/finetuning-qwen/GRPO-finetune-243179.out
   Power=
   TresPerNode=gres/gpu:l40s:2
   TresPerTask=cpu:4
   MailUser=wbbcor001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
UCT HPC clusterJOB DETAILS FOR JOB 243179

captured Mon Aug 25 16:23:01 SAST 2025

JobId=243179 JobName=grpo-fin
   UserId=wbbcor001(1221869528 Corey Webb) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7175 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=1:0
   RunTime=00:02:18 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T16:18:52 EligibleTime=2025-08-25T16:18:52
   AccrueTime=2025-08-25T16:18:52
   StartTime=2025-08-25T16:18:52 EndTime=2025-08-25T16:21:10 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:18:52 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:2965128
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu016
   BatchHost=srvrocgpu016
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=2,gres/gpu:l40s=2
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=2,gres/gpu:l40s=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:2
     Nodes=srvrocgpu016 CPU_IDs=0-1,24-25 Mem=40000 GRES=
   MinCPUsNode=4 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/wbbcor001/finetuning-qwen/batch_rl.sh
   WorkDir=/home/wbbcor001/finetuning-qwen
   StdErr=/home/wbbcor001/finetuning-qwen/GRPO-finetune-243179.out
   StdIn=/dev/null
   StdOut=/home/wbbcor001/finetuning-qwen/GRPO-finetune-243179.out
   Power=
   TresPerNode=gres/gpu:l40s:2
   TresPerTask=cpu:4
   MailUser=wbbcor001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT