Datasets:
File size: 2,701 Bytes
8ee5d29 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 | {
"schema": "albedo-gen-dpo-summary-v1",
"counts": {
"pairing_rejected:fewer_than_four_turns": 78,
"pairing_rejected:first_group_mismatch": 2433,
"pairs:dev": 1188,
"pairs:king_version:122": 927,
"pairs:king_version:123": 1706,
"pairs:king_version:124": 1693,
"pairs:king_version:125": 2679,
"pairs:king_version:126": 2609,
"pairs:king_version:127": 2636,
"pairs:preference:challenger": 5769,
"pairs:preference:king": 6236,
"pairs:preference:tie": 245,
"pairs:question_mode:None": 49,
"pairs:question_mode:milestone_ladder": 8868,
"pairs:question_mode:sota_anchored": 3333,
"pairs:train": 11062,
"rollout_unusable:challenger": 524,
"rollout_unusable:king": 525,
"sample_dropped:context_seen_in_newer_run": 21,
"sample_dropped:no_eligible_pairing": 421,
"sample_dropped:no_usable_rollout": 285,
"sample_dropped:rollout_contexts_differ": 213,
"sample_dropped:task_in_eval_batch": 453,
"samples:dev": 7083,
"samples:dropped_no_supervised_turn": 156,
"samples:k1": 12250,
"samples:k2": 12250,
"samples:k3": 12250,
"samples:k4": 12246,
"samples:k5": 12191,
"samples:k6": 11935,
"samples:train": 66039,
"samples_seen": 15476,
"skipped_truncated_artifact_line": 1
},
"pairs": 12250,
"samples": 73122,
"tie_share_of_pairs": 0.02,
"runs_used": 155,
"finished_at_range": [
"2026-09-04T13:35:54.633426+00:00",
"2026-09-23T02:22:12.392116+00:00"
],
"selection": {
"run_order": "newest first; one pair per exact context (the newest run wins)",
"pairing": "best score gap among the 4 King x challenger rollout pairings that pass the filters; one side is always King, the other challenger",
"filters": [
"both rollouts scored",
">= 4 assistant turns per side",
"4-6 equal behaviour groups",
"first behaviour group matches",
"winner not flagged amputated_thinking",
"task not in local eval batch"
],
"tie_share": 0.02,
"label": "production three-vote score of each rollout on the run's checklist"
},
"loss_contract": {
"assistant_tokens_of_the_final_group_only": true,
"earlier_groups_are_unsupervised_context": true,
"observations_are_context": true,
"harness_text_and_empty_turns": "loss false"
},
"think_contract": {
"content": "exact generation after '<|im_start|>assistant\\n<think>\\n'",
"render": "'<|im_start|>assistant\\n<think>\\n' + content + '<|im_end|>' verbatim; never through the chat template",
"think_closed": "false for turns that never closed the think block"
}
}
|