{ "items": 1319, "correct": 931, "accuracy": 0.7058377558756633, "evaluator_id": "5ce61cac464d6d7739964d336937b9a4de9d9b6a48b9905f59a0d978824a1d70", "checkpoint": "tinker://337d1e6ad746cc57412bd1332d4d628b/weights/rx-gs1-init-run_bf5c66cfd2", "metric": "accuracy", "arm": "base", "seed": 0, "predictions_ref": "base/eval.jsonl", "timings": { "setup_seconds": 22.131285839999975, "scoring_seconds": 192.77965556 } }