JOB DETAILS FOR JOB 1151333

captured Sat Aug 1 08:43:01 SAST 2026

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8352 Nice=0 Account=a100free QOS=a100free
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:00:06 TimeLimit=00:30:00 TimeMin=N/A
   SubmitTime=2026-08-01T08:42:47 EligibleTime=2026-08-01T08:42:47
   AccrueTime=2026-08-01T08:42:47
   StartTime=2026-08-01T08:42:47 EndTime=2026-08-01T08:42:53 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-01T08:42:47 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc101:1451405
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=64G,node=1,billing=15,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=64G,node=1,billing=15,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=0-3,28-31 Mem=65536 GRES=
   MinCPUsNode=8 MinMemoryNode=64G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/ORION/cucumber/experiments/gene_centric_dgrp/scripts/slurm/generated/run_a100_full978_xgb_c307_final_replication_v1_cuda_inference_probe.sbatch
   WorkDir=/scratch/bxxjin001/ORION/cucumber
   StdErr=/scratch/bxxjin001/ORION/cucumber/experiments/gene_centric_dgrp/slurm_logs/cuc_c307_reco_probe_1151333.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/ORION/cucumber/experiments/gene_centric_dgrp/slurm_logs/cuc_c307_reco_probe_1151333.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   

UCT HPC clusterJOB DETAILS FOR JOB 1151333

captured Sat Aug 1 08:43:38 SAST 2026

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8352 Nice=0 Account=a100free QOS=a100free
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:00:06 TimeLimit=00:30:00 TimeMin=N/A
   SubmitTime=2026-08-01T08:42:47 EligibleTime=2026-08-01T08:42:47
   AccrueTime=2026-08-01T08:42:47
   StartTime=2026-08-01T08:42:47 EndTime=2026-08-01T08:42:53 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-01T08:42:47 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc101:1451405
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=64G,node=1,billing=15,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=64G,node=1,billing=15,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=0-3,28-31 Mem=65536 GRES=
   MinCPUsNode=8 MinMemoryNode=64G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/ORION/cucumber/experiments/gene_centric_dgrp/scripts/slurm/generated/run_a100_full978_xgb_c307_final_replication_v1_cuda_inference_probe.sbatch
   WorkDir=/scratch/bxxjin001/ORION/cucumber
   StdErr=/scratch/bxxjin001/ORION/cucumber/experiments/gene_centric_dgrp/slurm_logs/cuc_c307_reco_probe_1151333.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/ORION/cucumber/experiments/gene_centric_dgrp/slurm_logs/cuc_c307_reco_probe_1151333.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   

UCT HPC clusterJOB DETAILS FOR JOB 1151333

captured Sat Aug 1 08:44:01 SAST 2026

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8352 Nice=0 Account=a100free QOS=a100free
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:00:06 TimeLimit=00:30:00 TimeMin=N/A
   SubmitTime=2026-08-01T08:42:47 EligibleTime=2026-08-01T08:42:47
   AccrueTime=2026-08-01T08:42:47
   StartTime=2026-08-01T08:42:47 EndTime=2026-08-01T08:42:53 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-01T08:42:47 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc101:1451405
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=64G,node=1,billing=15,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=64G,node=1,billing=15,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=0-3,28-31 Mem=65536 GRES=
   MinCPUsNode=8 MinMemoryNode=64G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/ORION/cucumber/experiments/gene_centric_dgrp/scripts/slurm/generated/run_a100_full978_xgb_c307_final_replication_v1_cuda_inference_probe.sbatch
   WorkDir=/scratch/bxxjin001/ORION/cucumber
   StdErr=/scratch/bxxjin001/ORION/cucumber/experiments/gene_centric_dgrp/slurm_logs/cuc_c307_reco_probe_1151333.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/ORION/cucumber/experiments/gene_centric_dgrp/slurm_logs/cuc_c307_reco_probe_1151333.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   

UCT HPC clusterJOB DETAILS FOR JOB 1151333

captured Sat Aug 1 08:44:38 SAST 2026

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8352 Nice=0 Account=a100free QOS=a100free
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:00:06 TimeLimit=00:30:00 TimeMin=N/A
   SubmitTime=2026-08-01T08:42:47 EligibleTime=2026-08-01T08:42:47
   AccrueTime=2026-08-01T08:42:47
   StartTime=2026-08-01T08:42:47 EndTime=2026-08-01T08:42:53 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-01T08:42:47 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc101:1451405
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=64G,node=1,billing=15,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=64G,node=1,billing=15,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=0-3,28-31 Mem=65536 GRES=
   MinCPUsNode=8 MinMemoryNode=64G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/ORION/cucumber/experiments/gene_centric_dgrp/scripts/slurm/generated/run_a100_full978_xgb_c307_final_replication_v1_cuda_inference_probe.sbatch
   WorkDir=/scratch/bxxjin001/ORION/cucumber
   StdErr=/scratch/bxxjin001/ORION/cucumber/experiments/gene_centric_dgrp/slurm_logs/cuc_c307_reco_probe_1151333.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/ORION/cucumber/experiments/gene_centric_dgrp/slurm_logs/cuc_c307_reco_probe_1151333.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   

UCT HPC clusterJOB DETAILS FOR JOB 1151333

captured Sat Aug 1 08:45:02 SAST 2026

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8352 Nice=0 Account=a100free QOS=a100free
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:00:06 TimeLimit=00:30:00 TimeMin=N/A
   SubmitTime=2026-08-01T08:42:47 EligibleTime=2026-08-01T08:42:47
   AccrueTime=2026-08-01T08:42:47
   StartTime=2026-08-01T08:42:47 EndTime=2026-08-01T08:42:53 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-01T08:42:47 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc101:1451405
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=64G,node=1,billing=15,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=64G,node=1,billing=15,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=0-3,28-31 Mem=65536 GRES=
   MinCPUsNode=8 MinMemoryNode=64G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/ORION/cucumber/experiments/gene_centric_dgrp/scripts/slurm/generated/run_a100_full978_xgb_c307_final_replication_v1_cuda_inference_probe.sbatch
   WorkDir=/scratch/bxxjin001/ORION/cucumber
   StdErr=/scratch/bxxjin001/ORION/cucumber/experiments/gene_centric_dgrp/slurm_logs/cuc_c307_reco_probe_1151333.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/ORION/cucumber/experiments/gene_centric_dgrp/slurm_logs/cuc_c307_reco_probe_1151333.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8