gahow/aituner
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
157bf3668d11ea6daea90066a8c0ff1fd24ab14b
aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-expansion-lo/fixed-po-comparison.stdout.json
Gahow Wang 39766141fb Decompose good/bad selection split across frozen surfaces 
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-20 12:05:20 +08:00

2 lines
2.3 KiB
JSON
Raw Blame History

{"e2e_ms:mean": {"agreement": 1.0, "concordant_pairs": 48, "discordant_pairs": 0, "informative_pairs": 48, "real_ranking": ["tp4_mns8", "tp4_mns32", "tp4_mns64", "tp4_mns16", "tp2_mns64", "tp2_mns8", "tp2_mns32", "tp2_mns16", "tp1_mns32", "tp1_mns16", "tp1_mns8", "tp1_mns64"], "real_winner": "tp4_mns8", "selected_config_real_regret": 0.014895639803871355, "sim_ranking": ["tp4_mns16", "tp4_mns32", "tp4_mns64", "tp4_mns8", "tp2_mns16", "tp2_mns32", "tp2_mns64", "tp2_mns8", "tp1_mns16", "tp1_mns32", "tp1_mns64", "tp1_mns8"], "sim_winner": "tp4_mns16", "tied_pairs": 18, "winner_match": false}, "e2e_ms:p90": {"agreement": 1.0, "concordant_pairs": 48, "discordant_pairs": 0, "informative_pairs": 48, "real_ranking": ["tp4_mns8", "tp4_mns64", "tp4_mns32", "tp4_mns16", "tp2_mns64", "tp2_mns8", "tp2_mns32", "tp2_mns16", "tp1_mns16", "tp1_mns32", "tp1_mns8", "tp1_mns64"], "real_winner": "tp4_mns8", "selected_config_real_regret": 0.03590282591969048, "sim_ranking": ["tp4_mns16", "tp4_mns32", "tp4_mns64", "tp4_mns8", "tp2_mns16", "tp2_mns32", "tp2_mns64", "tp2_mns8", "tp1_mns16", "tp1_mns32", "tp1_mns64", "tp1_mns8"], "sim_winner": "tp4_mns16", "tied_pairs": 18, "winner_match": false}, "ttft_ms:mean": {"agreement": 1.0, "concordant_pairs": 48, "discordant_pairs": 0, "informative_pairs": 48, "real_ranking": ["tp4_mns8", "tp4_mns32", "tp4_mns64", "tp4_mns16", "tp2_mns64", "tp2_mns8", "tp2_mns32", "tp2_mns16", "tp1_mns32", "tp1_mns16", "tp1_mns8", "tp1_mns64"], "real_winner": "tp4_mns8", "selected_config_real_regret": 0.014940997472395743, "sim_ranking": ["tp4_mns16", "tp4_mns32", "tp4_mns64", "tp4_mns8", "tp2_mns16", "tp2_mns32", "tp2_mns64", "tp2_mns8", "tp1_mns16", "tp1_mns32", "tp1_mns64", "tp1_mns8"], "sim_winner": "tp4_mns16", "tied_pairs": 18, "winner_match": false}, "ttft_ms:p90": {"agreement": 1.0, "concordant_pairs": 48, "discordant_pairs": 0, "informative_pairs": 48, "real_ranking": ["tp4_mns8", "tp4_mns64", "tp4_mns32", "tp4_mns16", "tp2_mns64", "tp2_mns8", "tp2_mns32", "tp2_mns16", "tp1_mns16", "tp1_mns32", "tp1_mns8", "tp1_mns64"], "real_winner": "tp4_mns8", "selected_config_real_regret": 0.035908453871728634, "sim_ranking": ["tp4_mns16", "tp4_mns32", "tp4_mns64", "tp4_mns8", "tp2_mns16", "tp2_mns32", "tp2_mns64", "tp2_mns8", "tp1_mns16", "tp1_mns32", "tp1_mns64", "tp1_mns8"], "sim_winner": "tp4_mns16", "tied_pairs": 18, "winner_match": false}}
Reference in New Issue View Git Blame Copy Permalink