mirror of
https://github.com/mcloh/decision-models-benchmark.git
synced 2026-11-05 22:04:12 +00:00
59 lines
1.3 KiB
JSON
59 lines
1.3 KiB
JSON
{
|
|
"candidate": {
|
|
"name": "laya",
|
|
"model_id": "laya@1720e3e3357c",
|
|
"revision": "1720e3e3357cfe1e281542e223f8273b0890ca34",
|
|
"adapter_version": "0.1.0",
|
|
"device": "cuda",
|
|
"context_limit": 1024,
|
|
"probabilities_source": "native"
|
|
},
|
|
"precision": "float32",
|
|
"device": "cuda",
|
|
"split": "dev",
|
|
"examples": 50,
|
|
"seed": 20261007,
|
|
"warmup": 5,
|
|
"batch_size": 1,
|
|
"state_budget_tokens": 512,
|
|
"process_guard": "ok",
|
|
"load_seconds": 8.46,
|
|
"warmup_latency_ms": [
|
|
260.7,
|
|
22.5,
|
|
27.4,
|
|
21.5,
|
|
21.8
|
|
],
|
|
"latency_ms": {
|
|
"n": 45,
|
|
"p50": 21.237645000013572,
|
|
"p95": 23.064290799999295,
|
|
"p99": 25.273738600021716,
|
|
"mean": 21.341669533332052
|
|
},
|
|
"errors": {},
|
|
"truncated": 0,
|
|
"state_tokens_max": 88,
|
|
"rss_peak_mib": 2779.8515625,
|
|
"gpu_mem_peak_mib": 1811.0,
|
|
"gpu_util_mean_pct": 6.785714285714286,
|
|
"quality": {
|
|
"n": 50,
|
|
"errors": 0,
|
|
"accuracy": 0.66,
|
|
"macro_f1": 0.6346938775510205,
|
|
"macro_precision": 0.6244047619047619,
|
|
"macro_recall": 0.7142857142857142
|
|
},
|
|
"calibration_raw": {
|
|
"brier": 0.5653510164045072,
|
|
"nll": 2.310904764203164,
|
|
"ece": 0.2660502261031441
|
|
},
|
|
"oci": {
|
|
"region": "sa-saopaulo-1",
|
|
"run_id": "20261007T174356Z-laya-evaluate"
|
|
}
|
|
}
|