mirror of
https://github.com/mcloh/decision-models-benchmark.git
synced 2026-11-05 22:04:12 +00:00
57 lines
1.2 KiB
JSON
57 lines
1.2 KiB
JSON
{
|
|
"candidate": {
|
|
"name": "rizzo_flow",
|
|
"model_id": "rizzo_flow@55633c8cbd2b",
|
|
"revision": "55633c8cbd2b826bd3eefdeb05310450996649df",
|
|
"adapter_version": "0.1.0",
|
|
"device": "cpu",
|
|
"context_limit": 2048,
|
|
"probabilities_source": "native"
|
|
},
|
|
"precision": "gguf-q8_0",
|
|
"device": "cpu",
|
|
"split": "dev",
|
|
"examples": 50,
|
|
"seed": 20261007,
|
|
"warmup": 5,
|
|
"batch_size": 1,
|
|
"state_budget_tokens": 512,
|
|
"process_guard": "ok",
|
|
"load_seconds": 4.05,
|
|
"warmup_latency_ms": [
|
|
12644.8,
|
|
12270.7,
|
|
10005.1,
|
|
8619.5,
|
|
12360.3
|
|
],
|
|
"latency_ms": {
|
|
"n": 45,
|
|
"p50": 12734.375058000069,
|
|
"p95": 18693.618147000027,
|
|
"p99": 19293.5656688,
|
|
"mean": 13519.72670173334
|
|
},
|
|
"errors": {},
|
|
"truncated": 0,
|
|
"state_tokens_max": 118,
|
|
"rss_peak_mib": 4936.19140625,
|
|
"quality": {
|
|
"n": 50,
|
|
"errors": 0,
|
|
"accuracy": 0.86,
|
|
"macro_f1": 0.875,
|
|
"macro_precision": 0.8586309523809523,
|
|
"macro_recall": 0.9136904761904762
|
|
},
|
|
"calibration_raw": {
|
|
"brier": 0.2316420465506699,
|
|
"nll": 0.4476962898724017,
|
|
"ece": 0.09500269948893228
|
|
},
|
|
"oci": {
|
|
"region": "us-chicago-1",
|
|
"run_id": "20261007T174254Z-rizzo_flow-evaluate"
|
|
}
|
|
}
|