mirror of
https://github.com/mcloh/decision-models-benchmark.git
synced 2026-11-05 22:04:12 +00:00
62 lines
1.3 KiB
JSON
62 lines
1.3 KiB
JSON
{
|
|
"candidate": {
|
|
"name": "laya",
|
|
"model_id": "laya@1720e3e3357c",
|
|
"revision": "1720e3e3357cfe1e281542e223f8273b0890ca34",
|
|
"adapter_version": "0.2.0",
|
|
"device": "cuda",
|
|
"context_limit": 1024,
|
|
"probabilities_source": "native"
|
|
},
|
|
"precision": "float32",
|
|
"device": "cuda",
|
|
"split": "test",
|
|
"examples": 1744,
|
|
"seed": 20261007,
|
|
"warmup": 5,
|
|
"batch_size": 1,
|
|
"state_budget_tokens": 512,
|
|
"process_guard": "ok",
|
|
"repetition": 1,
|
|
"load_seconds": 9.41,
|
|
"warmup_latency_ms": [
|
|
259.6,
|
|
22.3,
|
|
21.2,
|
|
27.7,
|
|
21.0
|
|
],
|
|
"latency_ms": {
|
|
"n": 1739,
|
|
"p50": 21.537158999990424,
|
|
"p95": 22.871617600003447,
|
|
"p99": 25.027770079997236,
|
|
"mean": 21.6004349787235
|
|
},
|
|
"errors": {},
|
|
"truncated": 0,
|
|
"with_diagnostics": 0,
|
|
"operational_env": {},
|
|
"state_tokens_max": 104,
|
|
"rss_peak_mib": 2794.40625,
|
|
"gpu_mem_peak_mib": 1811.0,
|
|
"gpu_util_mean_pct": 24.77173913043478,
|
|
"quality": {
|
|
"n": 1744,
|
|
"errors": 0,
|
|
"accuracy": 0.5676605504587156,
|
|
"macro_f1": 0.5902077449915867,
|
|
"macro_precision": 0.5865531568955725,
|
|
"macro_recall": 0.6342550712930707
|
|
},
|
|
"calibration_raw": {
|
|
"brier": 0.6835072642580573,
|
|
"nll": 2.224622951476565,
|
|
"ece": 0.27112323442274655
|
|
},
|
|
"oci": {
|
|
"region": "sa-saopaulo-1",
|
|
"run_id": "20261007T222231Z-laya-evaluate"
|
|
}
|
|
}
|