Topaz train errors while running

Welcome to the forum Salima @S_12_Daou . Please can you

  1. post the outputs of these commands on the worker node where Topaz training failed:
    uname -a
    free -h
    
  2. let us know whether the node also runs significant workloads outside CryoSPARC
  3. post the outputs of these commands on the CryoSPARC master host. Please replace /path/to with the actual path of the directory that contains the cryosparc_master/ directory.
    cd /path/to/cryosparc_master/ # replace with actual path
    csprojectid='P19'
    csjobid='J220'
    ./bin/cryosparcm cli "get_job('$csprojectid', '$csjobid', 'job_type', 'version', 'instance_information', 'status',  'params_spec', 'errors_run', 'input_slot_groups', 'started_at')" 
    ./bin/cryosparcm eventlog $csprojectid $csjobid | tail -n 40
    ./bin/cryosparcm joblog $csprojectid $csjobid | tail -n 20
    cd - # back to previous directory
    

[edited 2025-11-24 with corrected instructions]