View results and checkpoints¶

Inspect metrics after training and find checkpoints you can deploy later.

Prerequisites¶

A finished or running experiment in a project you can access.

1. Open the project¶

From Experiments in the sidebar, open the project that contains your run.

Project page with Experiments tab selected — The project **Experiments** tab.¶

2. Results tab¶

Click the Results tab for charts and run metadata. Scroll metric charts for reward, loss, or task-specific series, and use the metric picker (if available) to inspect and compare specific chart series.

Results tab selected — The **Results** tab.¶

Visible Experiment Metrics — Visible selected **Experiment Metrics**.¶

3. Checkpoints¶

Switch back to the Experiments tab and expand the experiment row. The expanded area shows a run summary chart and a Checkpoints table listing saved steps.

Checkpoints table after expanding an experiment row — Checkpoints listed in the expanded experiment row.¶

4. Deploy checkpoint¶

In the Checkpoints table, select the checkpoint row you want to use, then click the deploy (satellite) icon (Deploy checkpoint tooltip). In the deploy modal, review checkpoint details, enter deployment fields, and confirm to deploy that selected checkpoint.

Deploy checkpoint modal for selected checkpoint — Deploy checkpoint confirmation modal.¶

From the terminal¶

List experiments and checkpoints.

Install the CLI and sign in (Authentication):

pip install "agilerl[arena]"
arena login
# or: export ARENA_API_KEY=arena_pat_…

curl -sS "$ARENA_URL/api/cli/v1/experiments/list?project=llm-work" \
  -H "Authorization: Bearer $ARENA_API_KEY"

curl -sS -G "$ARENA_URL/api/cli/v1/experiments/jobs/checkpoints" \
  -H "Authorization: Bearer $ARENA_API_KEY" \
  --data-urlencode "experimentName=sft-run"

steps on each checkpoint row is the handle for deploy and resume. Scores are often null.

Python¶

from agilerl.arena import ArenaClient

with ArenaClient() as client:
    print(client.list_experiments(project="llm-work"))
    print(client.list_checkpoints("sft-run"))