Checking Your Customization Job Metrics

1
import os
2
from nemo_platform import NeMoPlatform
3
4
client = NeMoPlatform(
5
    base_url=os.environ.get("NMP_BASE_URL", "http://localhost:8080"),
6
    workspace="default",
7
)
8
9
# Get job status with metrics
10
job_name = "my-sft-job"
11
status = client.jobs.get_status(name=job_name, workspace="default")
12
13
print(f"Job: {status.name}")
14
print(f"Status: {status.status}")
15
16
# Check training step progress
17
for step in status.steps or []:
18
    if step.name == "training":
19
        for task in step.tasks or []:
20
            details = task.status_details or {}
21
            print(f"Training Phase: {details.get('phase')}")
22
            print(f"Step: {details.get('step')}/{details.get('max_steps')}")
23
            print(f"Epoch: {details.get('epoch')}/{details.get('num_epochs')}")
24
            print(f"Training Loss: {details.get('train_loss')}")
25
            print(f"Validation Loss: {details.get('val_loss')}")
26
            print(f"Learning Rate: {details.get('lr')}")
27
            print(f"Gradient Norm: {details.get('grad_norm')}")

1
from nemo_automodel_plugin.schema import AutomodelJobInput
2
3
# Create an Automodel job with W&B integration
4
spec = AutomodelJobInput(
5
    model="default/llama-3-2-1b",
6
    dataset={"training": "default/my-dataset"},
7
    training={"training_type": "sft", "finetuning_type": "lora"},
8
    schedule={"epochs": 3},
9
    batch={"global_batch_size": 16, "micro_batch_size": 1},
10
    optimizer={"learning_rate": 1e-4},
11
    integrations={
12
        "wandb": {
13
            "project": "my-finetuning-project",
14
            "entity": "my-team",
15
            "tags": ["fine-tuning", "llama"],
16
            "api_key_secret": "my-wandb-key",
17
        }
18
    },
19
)
20
21
job = client.customization.automodel.jobs.create(
22
    name="my-wandb-job",
23
    workspace="default",
24
    spec=spec,
25
)
26
27
print(f"Submitted job: {job.job.name}")