{ "arm": { "cards": [ "GPU-46890836-d8f7-e868-1977-c1ce28db0d7a", "GPU-7aa0be10-974f-6430-52fe-09018a0e2e08" ], "host": "http://127.0.0.1:8000", "mode": "generate", "model": "openjev-fp8", "name": "openjev-fp8-generate-32k", "note": "ARM 9: the same model and flags as arm 2 with --max-model-len 32768, run ONLY on the 17 items arm 2 refused as overlong", "num_ctx": 32768, "quant": "FP8 e4m3, 128x128 weight blocks, dynamic activations", "runtime": "vllm", "seed": 20260921, "top_logprobs": 20 }, "census": null, "ended": "2026-09-21T21:38:56Z", "energy": { "cards": [ "GPU-46890836-d8f7-e868-1977-c1ce28db0d7a", "GPU-7aa0be10-974f-6430-52fe-09018a0e2e08" ], "decisions": 6, "joules": 293334.30866440415, "joules_per_decision": 48889.05144406736, "mean_watts": 487.95364348551163, "net_joules_per_decision": 20931.851291584357, "peak_watts": 250.92, "per_card": { "GPU-46890836-d8f7-e868-1977-c1ce28db0d7a": { "joules": 145680.33983535052, "mean_watts": 242.33528266955477, "min_watts": 115.06, "peak_watts": 250.92, "samples": 602, "seconds": 601.1519999504089 }, "GPU-7aa0be10-974f-6430-52fe-09018a0e2e08": { "joules": 147653.96882905363, "mean_watts": 245.62040367960375, "min_watts": 140.07, "peak_watts": 249.77, "samples": 602, "seconds": 601.1470000743866 } }, "samples": 1204, "seconds": 601.1519999504089 }, "idle": { "cards": [ "GPU-46890836-d8f7-e868-1977-c1ce28db0d7a", "GPU-7aa0be10-974f-6430-52fe-09018a0e2e08" ], "joules": 2515.2328245210647, "mean_watts": 279.0362519441601, "peak_watts": 189.1, "per_card": { "GPU-46890836-d8f7-e868-1977-c1ce28db0d7a": { "joules": 1145.5298080801963, "mean_watts": 127.08340198998307, "min_watts": 115.49, "peak_watts": 164.67, "samples": 10, "seconds": 9.014000177383423 }, "GPU-7aa0be10-974f-6430-52fe-09018a0e2e08": { "joules": 1369.7030164408684, "mean_watts": 152.03718579989643, "min_watts": 140.15, "peak_watts": 189.1, "samples": 10, "seconds": 9.009000062942505 } }, "samples": 20, "seconds": 9.014000177383423, "what": "the draw of these cards immediately before the arm, with the model resident and no work in flight" }, "kit": { "a_labels": { "no": 21, "yes": 42 }, "b_labelled": 1, "bank_sha256": "35d58866da02e3ac731814e63ef0ceac97a25ee8b224c1c32c29df6ddbcc3d1c", "built": null, "c_per_guest": 18, "c_roster": [ { "id": "darwin", "name": "Charles Darwin" }, { "id": "einstein", "name": "Albert Einstein" }, { "id": "hypatia", "name": "Hypatia of Alexandria" }, { "id": "ibn_sina", "name": "Ibn Sina" }, { "id": "sagan", "name": "Carl Sagan" }, { "id": "socrates", "name": "Socrates of Athens" } ], "counts": { "a": 63, "articles": 42, "b": 42, "c": 108 }, "docroot": "/workshop/s2s-research-hub/site", "seed": 20260921, "wall_sha256": "80484f8379a5977cf56033f335c27c8f54fac683c7adf3e800def5fa419e698c", "wall_url": "https://longtable.strata2signal.com/api/wall" }, "overlong": {}, "pin": { "card": "GPU-46890836-d8f7-e868-1977-c1ce28db0d7a", "cards": [ "GPU-46890836-d8f7-e868-1977-c1ce28db0d7a", "GPU-7aa0be10-974f-6430-52fe-09018a0e2e08" ], "floor_mib": 200.0, "growth_mib": { "GPU-46890836-d8f7-e868-1977-c1ce28db0d7a": 0.0, "GPU-7aa0be10-974f-6430-52fe-09018a0e2e08": 0.0 }, "memory_after_mib": { "GPU-46890836-d8f7-e868-1977-c1ce28db0d7a": 21246.0, "GPU-7aa0be10-974f-6430-52fe-09018a0e2e08": 21246.0 }, "memory_after_named_mib": 21246.0, "memory_after_per_card_mib": { "GPU-46890836-d8f7-e868-1977-c1ce28db0d7a": 21246.0, "GPU-7aa0be10-974f-6430-52fe-09018a0e2e08": 21246.0 }, "named_grew": false, "ok": false, "others_quiet": true, "per_card_grew": { "GPU-46890836-d8f7-e868-1977-c1ce28db0d7a": false, "GPU-7aa0be10-974f-6430-52fe-09018a0e2e08": false }, "resident": true }, "readout": { "NOUL_BIAS": 0.0, "NOUL_T": 1.829074, "T": 0.85, "floor": -30.0, "instructions": { "a": "Does the article in the state answer this reader's question? Question: %s", "b": "Which section of the article in the state contains the answer to this reader's question? Question: %s", "c": "Six people are at a dinner table. Which of them said the line below?\nLine: %s" }, "protocol": "openjev old (untargeted) path" }, "refusal_policy": "README §A2.5: an item whose prompt exceeds the served context is refused with its measured token count and excluded from every rate; it is never truncated", "started": "2026-09-21T21:28:44Z", "summary": { "accuracy": 1.0, "brier": 8.349285404259891e-05, "correct": 6, "errors": 0, "eval_tokens_total": 12, "floored_rows": 0, "letters_floored_total": 0, "median_seconds": 32.51558686950193, "n": 10, "n_labelled": 6, "n_reached": 6, "p95_seconds": 36.24430934400152, "prompt_tokens_total": 153461, "refused": 4, "refused_by_reason": { "overlong": 4 }, "reliability": [ { "accuracy": null, "correct": 0, "gap": null, "hi": 0.1, "lo": 0.0, "mean_p": null, "n": 0, "sum_p": 0.0 }, { "accuracy": null, "correct": 0, "gap": null, "hi": 0.2, "lo": 0.1, "mean_p": null, "n": 0, "sum_p": 0.0 }, { "accuracy": null, "correct": 0, "gap": null, "hi": 0.3, "lo": 0.2, "mean_p": null, "n": 0, "sum_p": 0.0 }, { "accuracy": null, "correct": 0, "gap": null, "hi": 0.4, "lo": 0.3, "mean_p": null, "n": 0, "sum_p": 0.0 }, { "accuracy": null, "correct": 0, "gap": null, "hi": 0.5, "lo": 0.4, "mean_p": null, "n": 0, "sum_p": 0.0 }, { "accuracy": null, "correct": 0, "gap": null, "hi": 0.6, "lo": 0.5, "mean_p": null, "n": 0, "sum_p": 0.0 }, { "accuracy": null, "correct": 0, "gap": null, "hi": 0.7, "lo": 0.6, "mean_p": null, "n": 0, "sum_p": 0.0 }, { "accuracy": null, "correct": 0, "gap": null, "hi": 0.8, "lo": 0.7, "mean_p": null, "n": 0, "sum_p": 0.0 }, { "accuracy": null, "correct": 0, "gap": null, "hi": 0.9, "lo": 0.8, "mean_p": null, "n": 0, "sum_p": 0.0 }, { "accuracy": 1.0, "correct": 6, "gap": -0.006461147500351649, "hi": 1.0, "lo": 0.9, "mean_p": 0.9935388524996484, "n": 6, "sum_p": 5.96123311499789 } ], "unparsed": 0 }, "task": "along", "wall_seconds": 601.1383872250008 }