mirror of
https://github.com/mcloh/decision-models-benchmark.git
synced 2026-11-05 22:04:12 +00:00
61 lines
1.3 KiB
JSON
61 lines
1.3 KiB
JSON
{
|
|
"candidate": {
|
|
"name": "semif",
|
|
"model_id": "semif@851bf6e806ef",
|
|
"revision": "851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a",
|
|
"adapter_version": "0.2.0",
|
|
"device": "cuda",
|
|
"context_limit": 8192,
|
|
"probabilities_source": "native"
|
|
},
|
|
"precision": "bfloat16",
|
|
"device": "cuda",
|
|
"split": "dev",
|
|
"examples": 1183,
|
|
"seed": 20261007,
|
|
"warmup": 5,
|
|
"batch_size": 1,
|
|
"state_budget_tokens": 512,
|
|
"process_guard": "ok",
|
|
"load_seconds": 7.8,
|
|
"warmup_latency_ms": [
|
|
475.5,
|
|
178.9,
|
|
76.9,
|
|
141.7,
|
|
184.3
|
|
],
|
|
"latency_ms": {
|
|
"n": 1178,
|
|
"p50": 117.1211939999921,
|
|
"p95": 186.51699405000102,
|
|
"p99": 190.08992016000263,
|
|
"mean": 125.81136090662143
|
|
},
|
|
"errors": {},
|
|
"truncated": 0,
|
|
"with_diagnostics": 0,
|
|
"operational_env": {},
|
|
"state_tokens_max": 92,
|
|
"rss_peak_mib": 9027.6640625,
|
|
"gpu_mem_peak_mib": 8513.0,
|
|
"gpu_util_mean_pct": 87.24183006535948,
|
|
"quality": {
|
|
"n": 1183,
|
|
"errors": 0,
|
|
"accuracy": 0.8841927303465765,
|
|
"macro_f1": 0.900963005076605,
|
|
"macro_precision": 0.9043141854943706,
|
|
"macro_recall": 0.9103958961439549
|
|
},
|
|
"calibration_raw": {
|
|
"brier": 0.18796590703757624,
|
|
"nll": 0.4037357594473513,
|
|
"ece": 0.04242615879670591
|
|
},
|
|
"oci": {
|
|
"region": "sa-saopaulo-1",
|
|
"run_id": "20261007T212022Z-semif-evaluate"
|
|
}
|
|
}
|