JOB DETAILS FOR JOB 243141

captured Mon Aug 25 15:45:45 SAST 2025

JobId=243141 JobName=test_set_eval
   UserId=wbbcor001(1221869528 Corey Webb) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7075 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=00:00:15 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T15:45:03 EligibleTime=2025-08-25T15:45:03
   AccrueTime=2025-08-25T15:45:03
   StartTime=2025-08-25T15:45:03 EndTime=2025-08-25T15:45:18 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T15:45:03 Scheduler=Backfill
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:2761155
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu014
   BatchHost=srvrocgpu014
   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=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu014 CPU_IDs=0,7,31-32 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/test_set_eval.sh
   WorkDir=/home/wbbcor001/finetuning-qwen
   StdErr=/home/wbbcor001/finetuning-qwen/test-set-eval-243141.out
   StdIn=/dev/null
   StdOut=/home/wbbcor001/finetuning-qwen/test-set-eval-243141.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   TresPerTask=cpu:4
   MailUser=wbbcor001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
   

UCT HPC clusterJOB DETAILS FOR JOB 243141

captured Mon Aug 25 15:46:01 SAST 2025

JobId=243141 JobName=test_set_eval
   UserId=wbbcor001(1221869528 Corey Webb) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7075 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=00:00:15 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T15:45:03 EligibleTime=2025-08-25T15:45:03
   AccrueTime=2025-08-25T15:45:03
   StartTime=2025-08-25T15:45:03 EndTime=2025-08-25T15:45:18 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T15:45:03 Scheduler=Backfill
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:2761155
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu014
   BatchHost=srvrocgpu014
   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=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu014 CPU_IDs=0,7,31-32 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/test_set_eval.sh
   WorkDir=/home/wbbcor001/finetuning-qwen
   StdErr=/home/wbbcor001/finetuning-qwen/test-set-eval-243141.out
   StdIn=/dev/null
   StdOut=/home/wbbcor001/finetuning-qwen/test-set-eval-243141.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   TresPerTask=cpu:4
   MailUser=wbbcor001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
   

UCT HPC clusterJOB DETAILS FOR JOB 243141

captured Mon Aug 25 15:46:43 SAST 2025

JobId=243141 JobName=test_set_eval
   UserId=wbbcor001(1221869528 Corey Webb) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7075 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=00:00:15 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T15:45:03 EligibleTime=2025-08-25T15:45:03
   AccrueTime=2025-08-25T15:45:03
   StartTime=2025-08-25T15:45:03 EndTime=2025-08-25T15:45:18 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T15:45:03 Scheduler=Backfill
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:2761155
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu014
   BatchHost=srvrocgpu014
   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=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu014 CPU_IDs=0,7,31-32 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/test_set_eval.sh
   WorkDir=/home/wbbcor001/finetuning-qwen
   StdErr=/home/wbbcor001/finetuning-qwen/test-set-eval-243141.out
   StdIn=/dev/null
   StdOut=/home/wbbcor001/finetuning-qwen/test-set-eval-243141.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   TresPerTask=cpu:4
   MailUser=wbbcor001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
   

UCT HPC clusterJOB DETAILS FOR JOB 243141

captured Mon Aug 25 15:47:01 SAST 2025

JobId=243141 JobName=test_set_eval
   UserId=wbbcor001(1221869528 Corey Webb) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7075 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=00:00:15 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T15:45:03 EligibleTime=2025-08-25T15:45:03
   AccrueTime=2025-08-25T15:45:03
   StartTime=2025-08-25T15:45:03 EndTime=2025-08-25T15:45:18 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T15:45:03 Scheduler=Backfill
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:2761155
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu014
   BatchHost=srvrocgpu014
   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=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu014 CPU_IDs=0,7,31-32 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/test_set_eval.sh
   WorkDir=/home/wbbcor001/finetuning-qwen
   StdErr=/home/wbbcor001/finetuning-qwen/test-set-eval-243141.out
   StdIn=/dev/null
   StdOut=/home/wbbcor001/finetuning-qwen/test-set-eval-243141.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   TresPerTask=cpu:4
   MailUser=wbbcor001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT