Files
zagreus-0.4b-italic-kl/evaluation/provenance.json
ModelHub XC 30e7dd7c9b 初始化项目,由ModelHub XC社区提供模型
Model: GitMarco27/zagreus-0.4b-italic-kl
Source: Original Platform
2026-07-25 11:26:09 +08:00

44 lines
1.5 KiB
JSON

{
"schema": 1,
"model": "zagreus-0.4b-italic-kl",
"model_weights_sha256": "5e0284467f727f22000b897a3c40f3e5c24b519de463f71a4212149fe1913c6e",
"base_model": "mii-llm/zagreus-0.4B-ita",
"base_revision": "f463a5beabf054809ee3cc702c711215a5fde690",
"evaluator": "Crisp-Unimib/ITALIC",
"evaluator_revision": "92df420ff686babeea54e217b9f90f8471374916",
"evaluator_sha256": "ed4e4c63109245146040b234018ffb720ed088e6d55aef074cd9755dc3ed94f1",
"italic_data_sha256": "ca877846f19a6d781ba151382e4f43b10efad1a7e375b5e0c50b047a3917e0af",
"original_official_results_sha256": "eb5d61796c868d583c8b37794589ce1ac24984a08ccae896ee96d3996889c0b0",
"public_official_results_sha256": "a8cecd85d6577725611a6ce7cef873fabe41028a66a12276e99238646892f383",
"public_result_transformations": [
"Changed only the local served-model alias to zagreus-0.4b-italic-kl."
],
"evaluation": {
"questions": 10000,
"zero_shot": true,
"fast": true,
"temperature": 0.0,
"metrics": {
"accuracy": 0.3381,
"accuracy:std": 0.4730627759610768
},
"prediction_counts": {
"A": 3780,
"B": 2611,
"C": 2400,
"D": 1209
},
"empty_parses": 0,
"started_at": "2026-07-15T07:38:58Z",
"ended_at": "2026-07-15T07:46:32Z",
"wall_seconds": 454
},
"final_run": {
"hardware": "NVIDIA A100 80GB PCIe",
"resource_wall_hours": 0.7531477777777777,
"h100_equivalent_hours": 0.3622406266820453,
"estimated_provider_cost_usd": 1.046875411111111,
"within_10_h100_equivalent_hours": true
}
}