Get Job Status

Get detailed execution status for a customization job, including step-by-step progress and real-time training metrics.

Tip

This endpoint provides granular execution details including:

• Step-level status: model-and-dataset-download → customization-training-job → model-upload → model-entity-creation

• Training metrics: step, epoch, loss, learning_rate, grad_norm, val_loss

• Progress tracking: downloaded_files, uploaded_bytes, progress_pct

To list jobs or get job definitions (model entity, hyperparameters, spec), use List Active Jobs instead.

Prerequisites

Before you can get the status of a customization job, make sure that you have:

• Obtained the base URL of your NeMo Platform.

• Set the NMP_BASE_URL environment variable to your NeMo Platform endpoint

export NMP_BASE_URL="https://your-nmp-base-url"

---

To Get the Status of a Customization Job

Use the SDK to get detailed job status:

import os
from nemo_platform import NeMoPlatform

# Initialize the client
client = NeMoPlatform(
    base_url=os.environ.get("NMP_BASE_URL", "http://localhost:8080"),
    workspace="default",
)

# Get job status
job_name = "my-sft-job"
status = client.customization.jobs.get_status(
    name=job_name,
    workspace="default"
)

print(f"Job: {status.name}")
print(f"Status: {status.status}")

# Check step-level status and training progress
for step in status.steps or []:
    print(f"  Step '{step.name}': {step.status}")
    if step.name == "customization-training-job":
        for task in step.tasks or []:
            task_details = task.status_details or {}
            current_step = task_details.get("step")
            max_steps = task_details.get("max_steps")
            if current_step and max_steps:
                print(f"    Progress: {current_step}/{max_steps}")

Example Response

Active Job (Training in Progress)

{
  "id": "platform-job-2k8i3i1HqJHHPVB5M6Bk9Z",
  "error_details": null,
  "name": "my-sft-job",
  "status": "active",
  "status_details": {},
  "steps": [
    {
      "id": "platform-job-step-4RJTW5wSy4gHJ539EfTUif",
      "error_details": {},
      "name": "model-and-dataset-download",
      "status": "completed",
      "status_details": {
        "message": "Job completed successfully with exit code 0"
      },
      "tasks": [
        {
          "id": "platform-job-task-MBC2vcDEyv6Jw7RtFs5JDd",
          "error_details": {},
          "error_stack": "",
          "name": "task-5969b01a4b5a4bb181ba530ff51dafa6",
          "status": "completed",
          "status_details": {
            "message": "Job completed successfully with exit code 0",
            "phase": "completed",
            "total_filesets": 2,
            "completed_filesets": 1,
            "current_fileset": "default/sft-dataset",
            "fileset": "default/sft-dataset",
            "total_files": 2,
            "total_size": 2984632,
            "downloaded_files": 2,
            "downloaded_bytes": 2984632,
            "current_file": "validation.jsonl",
            "progress_pct": 100
          }
        }
      ]
    },
    {
      "id": "platform-job-step-9kme8ibxDGES4t9TZvLp4X",
      "error_details": {},
      "name": "customization-training-job",
      "status": "active",
      "status_details": {
        "message": "Job is running"
      },
      "tasks": [
        {
          "id": "platform-job-task-SawMB6ssVZd7NCiruFVJn8",
          "error_details": {},
          "error_stack": "",
          "name": "task-2249da790a574388ba02fcabd06cd338",
          "status": "active",
          "status_details": {
            "message": "Job is running",
            "phase": "training",
            "backend": "automodel",
            "max_steps": 94,
            "num_epochs": 2,
            "step": 8,
            "epoch": 1,
            "loss": 2.8918895721435547,
            "lr": 0.000049101714686276044,
            "grad_norm": 26.0
          }
        }
      ]
    }
  ]
}

Completed Job (All Steps Finished)

{
  "id": "platform-job-2k8i3i1HqJHHPVB5M6Bk9Z",
  "error_details": null,
  "name": "my-sft-job",
  "status": "completed",
  "status_details": {},
  "steps": [
    {
      "id": "platform-job-step-4RJTW5wSy4gHJ539EfTUif",
      "error_details": {},
      "name": "model-and-dataset-download",
      "status": "completed",
      "status_details": {
        "message": "Job completed successfully with exit code 0"
      },
      "tasks": [
        {
          "id": "platform-job-task-MBC2vcDEyv6Jw7RtFs5JDd",
          "error_details": {},
          "error_stack": "",
          "name": "task-5969b01a4b5a4bb181ba530ff51dafa6",
          "status": "completed",
          "status_details": {
            "message": "Job completed successfully with exit code 0",
            "phase": "completed",
            "total_filesets": 2,
            "completed_filesets": 1,
            "current_fileset": "default/sft-dataset",
            "fileset": "default/sft-dataset",
            "total_files": 2,
            "total_size": 2984632,
            "downloaded_files": 2,
            "downloaded_bytes": 2984632,
            "current_file": "validation.jsonl",
            "progress_pct": 100
          }
        }
      ]
    },
    {
      "id": "platform-job-step-9kme8ibxDGES4t9TZvLp4X",
      "error_details": {},
      "name": "customization-training-job",
      "status": "completed",
      "status_details": {
        "message": "Job completed successfully with exit code 0"
      },
      "tasks": [
        {
          "id": "platform-job-task-SawMB6ssVZd7NCiruFVJn8",
          "error_details": {},
          "error_stack": "",
          "name": "task-2249da790a574388ba02fcabd06cd338",
          "status": "completed",
          "status_details": {
            "message": "Job completed successfully with exit code 0",
            "phase": "processing_checkpoint",
            "backend": "automodel",
            "max_steps": 94,
            "num_epochs": 2,
            "step": 94,
            "epoch": 2,
            "loss": 0.3437718152999878,
            "lr": 5.000000000000001e-7,
            "grad_norm": 20.125,
            "val_loss": 0.5527229905128479,
            "checkpoint_path": "/var/run/scratch/job/training/checkpoints"
          }
        }
      ]
    },
    {
      "id": "platform-job-step-6gkKgfT5AwyamBWNtQFA9t",
      "error_details": {},
      "name": "model-upload",
      "status": "completed",
      "status_details": {
        "message": "Job completed successfully with exit code 0"
      },
      "tasks": [
        {
          "id": "platform-job-task-J2wt8G8X3vkUHZJCEhzYTP",
          "error_details": {},
          "error_stack": "",
          "name": "task-9647899028aa44c493ce1d65a4ec8f7b",
          "status": "completed",
          "status_details": {
            "message": "Job completed successfully with exit code 0",
            "phase": "completed",
            "total_filesets": 1,
            "completed_filesets": 0,
            "current_fileset": "default/customization-b5b20520fe4f",
            "fileset": "default/customization-b5b20520fe4f",
            "total_files": 7,
            "total_size": 2488928480,
            "uploaded_files": 7,
            "uploaded_bytes": 2488928480,
            "current_file": "model-00001-of-00001.safetensors",
            "progress_pct": 100
          }
        }
      ]
    },
    {
      "id": "platform-job-step-9NmC8mrS3VtthjUSo52EiB",
      "error_details": {},
      "name": "model-entity-creation",
      "status": "completed",
      "status_details": {
        "message": "Job completed successfully with exit code 0"
      },
      "tasks": [
        {
          "id": "platform-job-task-8Mbbz6AnZP5fQLu61aVRb",
          "error_details": {},
          "error_stack": "",
          "name": "task-ab80f766085f4203b72a612f38a2c1b0",
          "status": "completed",
          "status_details": {
            "message": "Job completed successfully with exit code 0"
          }
        }
      ]
    }
  ]
}