| { | |
| "schema": "stateplay-formal-model-publication-v1", | |
| "repo": "lupele/rl_model", | |
| "created_at": "2026-10-22T01:22:28.504083+00:00", | |
| "kind": "formal_stage_A", | |
| "run_id": "study_v1", | |
| "conditions": 2280, | |
| "candidates": 9120, | |
| "optimizer_step": 652, | |
| "mode": "B-only", | |
| "smoke": false, | |
| "source_sha256": "0de4a219b2e81424a909734648e55da602106586eb9638aa58e4522ed51b57bd", | |
| "published_sha256": "56328f45f3ee19237b63add2eb666dfcaa8aaebf505d29aa400a78519aea28ac", | |
| "metadata_only_changes": [ | |
| "/config/reward/endpoint", | |
| "/config/reward_model/inference_url", | |
| "/config/config_hash" | |
| ], | |
| "preserved_exactly": [ | |
| "schema", | |
| "live", | |
| "policies", | |
| "optimizer", | |
| "scheduler", | |
| "scaler", | |
| "state", | |
| "rank_rng", | |
| "sft_sha256", | |
| "tokenizer_sha256" | |
| ], | |
| "all_parameters_optimizer_rng_exactly_equal": true | |
| } | |