JOB DETAILS FOR JOB 1302264

captured Sat Sep 5 15:40:54 SAST 2026

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

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7560 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=00:01:19 TimeLimit=00:15:00 TimeMin=N/A
   SubmitTime=2026-09-05T15:39:35 EligibleTime=2026-09-05T15:39:35
   AccrueTime=Unknown
   StartTime=2026-09-05T15:39:35 EndTime=2026-09-05T15:54:35 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-05T15:39:35 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc103:3399041
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu009
   BatchHost=srvrocgpu009
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=32G,node=1,billing=8,gres/gpu=1
   AllocTRES=cpu=4,mem=32G,node=1,billing=8,gres/gpu=1,gres/gpu:amperemk=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:amperemk:1
     Nodes=srvrocgpu009 CPU_IDs=0-2,4 Mem=32768 GRES=gpu:amperemk:1(IDX:0)
   MinCPUsNode=4 MinMemoryNode=32G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/ORION/baicai/l3_tahoe_cellstate_bridge_retention_20260905T125609Z/scripts/production_a1.sbatch
   WorkDir=/home/bxxjin001
   StdErr=/scratch/bxxjin001/ORION/baicai/l3_tahoe_cellstate_bridge_retention_20260905T125609Z/logs/a1_film_train_1302262_0.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/ORION/baicai/l3_tahoe_cellstate_bridge_retention_20260905T125609Z/logs/a1_film_train_1302262_0.out
   Power=
   TresPerNode=gres/gpu:1
   TresPerTask=cpu:4
UCT HPC clusterJOB DETAILS FOR JOB 1302264

captured Sat Sep 5 15:41:31 SAST 2026

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7560 Nice=0 Account=a100free QOS=a100free
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:01:30 TimeLimit=00:15:00 TimeMin=N/A
   SubmitTime=2026-09-05T15:39:35 EligibleTime=2026-09-05T15:39:35
   AccrueTime=Unknown
   StartTime=2026-09-05T15:39:35 EndTime=2026-09-05T15:41:05 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-05T15:39:35 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc103:3399041
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu009
   BatchHost=srvrocgpu009
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=32G,node=1,billing=8,gres/gpu=1
   AllocTRES=cpu=4,mem=32G,node=1,billing=8,gres/gpu=1,gres/gpu:amperemk=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:amperemk:1
     Nodes=srvrocgpu009 CPU_IDs=0-2,4 Mem=32768 GRES=
   MinCPUsNode=4 MinMemoryNode=32G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/ORION/baicai/l3_tahoe_cellstate_bridge_retention_20260905T125609Z/scripts/production_a1.sbatch
   WorkDir=/home/bxxjin001
   StdErr=/scratch/bxxjin001/ORION/baicai/l3_tahoe_cellstate_bridge_retention_20260905T125609Z/logs/a1_film_train_1302262_0.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/ORION/baicai/l3_tahoe_cellstate_bridge_retention_20260905T125609Z/logs/a1_film_train_1302262_0.out
   Power=
   TresPerNode=gres/gpu:1
   TresPerTask=cpu:4
UCT HPC clusterJOB DETAILS FOR JOB 1302264

captured Sat Sep 5 15:42:01 SAST 2026

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7560 Nice=0 Account=a100free QOS=a100free
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:01:30 TimeLimit=00:15:00 TimeMin=N/A
   SubmitTime=2026-09-05T15:39:35 EligibleTime=2026-09-05T15:39:35
   AccrueTime=Unknown
   StartTime=2026-09-05T15:39:35 EndTime=2026-09-05T15:41:05 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-05T15:39:35 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc103:3399041
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu009
   BatchHost=srvrocgpu009
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=32G,node=1,billing=8,gres/gpu=1
   AllocTRES=cpu=4,mem=32G,node=1,billing=8,gres/gpu=1,gres/gpu:amperemk=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:amperemk:1
     Nodes=srvrocgpu009 CPU_IDs=0-2,4 Mem=32768 GRES=
   MinCPUsNode=4 MinMemoryNode=32G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/ORION/baicai/l3_tahoe_cellstate_bridge_retention_20260905T125609Z/scripts/production_a1.sbatch
   WorkDir=/home/bxxjin001
   StdErr=/scratch/bxxjin001/ORION/baicai/l3_tahoe_cellstate_bridge_retention_20260905T125609Z/logs/a1_film_train_1302262_0.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/ORION/baicai/l3_tahoe_cellstate_bridge_retention_20260905T125609Z/logs/a1_film_train_1302262_0.out
   Power=
   TresPerNode=gres/gpu:1
   TresPerTask=cpu:4
UCT HPC clusterJOB DETAILS FOR JOB 1302264

captured Sat Sep 5 15:42:52 SAST 2026

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7560 Nice=0 Account=a100free QOS=a100free
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:01:30 TimeLimit=00:15:00 TimeMin=N/A
   SubmitTime=2026-09-05T15:39:35 EligibleTime=2026-09-05T15:39:35
   AccrueTime=Unknown
   StartTime=2026-09-05T15:39:35 EndTime=2026-09-05T15:41:05 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-05T15:39:35 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc103:3399041
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu009
   BatchHost=srvrocgpu009
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=32G,node=1,billing=8,gres/gpu=1
   AllocTRES=cpu=4,mem=32G,node=1,billing=8,gres/gpu=1,gres/gpu:amperemk=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:amperemk:1
     Nodes=srvrocgpu009 CPU_IDs=0-2,4 Mem=32768 GRES=
   MinCPUsNode=4 MinMemoryNode=32G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/ORION/baicai/l3_tahoe_cellstate_bridge_retention_20260905T125609Z/scripts/production_a1.sbatch
   WorkDir=/home/bxxjin001
   StdErr=/scratch/bxxjin001/ORION/baicai/l3_tahoe_cellstate_bridge_retention_20260905T125609Z/logs/a1_film_train_1302262_0.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/ORION/baicai/l3_tahoe_cellstate_bridge_retention_20260905T125609Z/logs/a1_film_train_1302262_0.out
   Power=
   TresPerNode=gres/gpu:1
   TresPerTask=cpu:4