{
"apiVersion": "tuneplane/v1",
"kind": "TrainingJob",
"metadata": {
"name": "my-grpo",
"project": "my-lab",
"owner": "",
"display_name": "",
"labels": {}
},
"spec": {
"recipe": {
"name": "nemo-rl/grpo",
"version": "0.7.0",
"digest": "sha256:…",
"plugins": []
},
"source": { "exp": "experiments/my-grpo", "entrypoint": "" },
"framework": {
"kind": "nemo-rl",
"version": "0.7.0",
"runtime_id": "nemo-rl-0.7.0",
"image": "",
"observability_url": ""
},
"resources": {
"pools": [{ "name": "train", "series": "h200", "nodes": 1, "gpus_per_node": 8 }],
"roles": { "actor": "train", "rollout": "train" }
},
"model": {
"base": "Qwen/Qwen2.5-1.5B",
"peft": null,
"init_from": { "run_id": "run-4f2a91", "kind": "checkpoint", "step": 500 }
},
"data": {
"train": { "dataset": "alice/gsm8k-zh@v2", "split": "", "path": "train.parquet" },
"validation": null,
"volumes": ["acme/support-transcripts"],
"output_dataset": "",
"environment": "",
"quality": { "max_duplicate_ratio": null, "overlap_with": "", "max_overlap_ratio": null }
},
"hyperparams": { "policy.optimizer.kwargs.lr": 1e-6 },
"lifecycle": { "on_success": ["export"] },
"evaluation": {
"suites": ["gsm8k"],
"runner": "",
"baseline": "",
"limit": null,
"gates": [{ "metric": "exact_match", "min": 0.4, "max": null, "max_regression": 0.02 }]
},
"plugins": [{ "id": "alice/opsd-patch", "version": "1.2.0", "digest": "sha256:…" }]
},
"provenance": {
"core_version": "0.3.2",
"git_commit": "…",
"git_dirty": false,
"config_sha": "…",
"model_name": "Qwen/Qwen2.5-1.5B"
}
}