JOB DETAILS FOR JOB 1150356

captured Fri Jul 31 19:44:01 SAST 2026

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

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8352 Nice=0 Account=a100free QOS=a100free
   JobState=RUNNING Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=01:12:42 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2026-07-31T18:31:18 EligibleTime=2026-07-31T18:31:18
   AccrueTime=2026-07-31T18:31:19
   StartTime=2026-07-31T18:31:19 EndTime=2026-08-01T02:31:19 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-07-31T18:31:19 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc115:536867
   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=gpu:ampere:1(IDX:0)
   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_cuda_stage3_small_v1_p1_stage3b.sbatch
   WorkDir=/scratch/bxxjin001/ORION/cucumber
   StdErr=/scratch/bxxjin001/ORION/cucumber/experiments/gene_centric_dgrp/slurm_logs/cucumber_f978_xgb_s3sm_p1_b0_1150356.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/ORION/cucumber/experiments/gene_centric_dgrp/slurm_logs/cucumber_f978_xgb_s3sm_p1_b0_1150356.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   

UCT HPC clusterJOB DETAILS FOR JOB 1150356

captured Fri Jul 31 19:44:59 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=01:12:48 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2026-07-31T18:31:18 EligibleTime=2026-07-31T18:31:18
   AccrueTime=2026-07-31T18:31:19
   StartTime=2026-07-31T18:31:19 EndTime=2026-07-31T19:44:07 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-07-31T18:31:19 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc115:536867
   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_cuda_stage3_small_v1_p1_stage3b.sbatch
   WorkDir=/scratch/bxxjin001/ORION/cucumber
   StdErr=/scratch/bxxjin001/ORION/cucumber/experiments/gene_centric_dgrp/slurm_logs/cucumber_f978_xgb_s3sm_p1_b0_1150356.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/ORION/cucumber/experiments/gene_centric_dgrp/slurm_logs/cucumber_f978_xgb_s3sm_p1_b0_1150356.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   

UCT HPC clusterJOB DETAILS FOR JOB 1150356

captured Fri Jul 31 19:45:31 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=01:12:48 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2026-07-31T18:31:18 EligibleTime=2026-07-31T18:31:18
   AccrueTime=2026-07-31T18:31:19
   StartTime=2026-07-31T18:31:19 EndTime=2026-07-31T19:44:07 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-07-31T18:31:19 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc115:536867
   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_cuda_stage3_small_v1_p1_stage3b.sbatch
   WorkDir=/scratch/bxxjin001/ORION/cucumber
   StdErr=/scratch/bxxjin001/ORION/cucumber/experiments/gene_centric_dgrp/slurm_logs/cucumber_f978_xgb_s3sm_p1_b0_1150356.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/ORION/cucumber/experiments/gene_centric_dgrp/slurm_logs/cucumber_f978_xgb_s3sm_p1_b0_1150356.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8