← Back to Architecture

parallel residuals

Architecture
Used in
58 PRs
Best BPB
0.9457
Avg BPB
1.1244

Submissions

PR #1204by msisovicRECORD
1.1063
PR #1274by MatoTeziTanka
1.0876
PR #1326by aryanbhosale
1.0896
PR #1333by aryanbhosale
1.0766
PR #1334by aryanbhosaleRECORD
1.0897
PR #1338by bigbag
1.0955
PR #1339by bigbag
1.0955
PR #1381by X-Abhishek-X
1.1604
PR #1396by erichroepke
1.1067
PR #1412by Robby955RECORD
1.0835
PR #1420by abaybektursun
1.0801
PR #1425by dentity007
1.4479
PR #1435by AbhayAnandUCSD
1.0980
PR #1437by dexhunter
1.0780
PR #1450by andrewbaggio1
1.0848
PR #1477by aryanbhosaleRECORD
1.0822
PR #1485by ndokutovich
1.0679
PR #1489by joshkmartinez
1.0736
PR #1492by bigbag
1.0810
PR #1493by bigbagRECORD
1.0810
PR #1499by dippatel1994
1.6323
PR #1515by dexhunter
1.0872
PR #1521by aryanbhosale
1.0802
PR #1532by nogakeren
1.0803
PR #1534by someone114514
1.0846
PR #1541by bigbag
1.0778
PR #1570by yufang67
1.0970
PR #1578by mikeapedia
1.0668
PR #1614by seekerPrice
1.5096
PR #1620by shiawyonglim
1.6644
PR #1635by PapaFranku4647
1.1063
PR #1647by powerpratik
1.0616
PR #1661by anderamondarainh-stack
1.1444
PR #1667by MarioPaerleRECORD
1.0714
PR #1720by kiyoaki
1.0818
PR #1725by teslaeco
1.0813
PR #1731by Victory963
1.0785
PR #1733by G3sparky
1.3262
PR #1737by sakthivarshans
1.0723
PR #1750by teslaeco
1.0809
PR #1755by OE-GOD
1.0746
PR #1760by BrandtChristian
1.1863
PR #1776by anmarhindi
1.0808
PR #1780by wisebreadloaf
1.0806
PR #1812by EthanNing
1.0729
PR #1814by suryavanshi
1.0742
PR #1832by sricursion
1.0992
PR #1893by Hieuabssy
1.0901
PR #1913by Jeffrey-Le
1.0847
PR #1919by dev-pratap-singh
1.0587
PR #1929by davie2009kh
0.9457
PR #1932by PrzemyslaV88
1.0796
PR #1934by liujshi
1.0599
PR #1936by hilbertmeng
1.0769
PR #1943by LoBreeze
1.0818
PR #1974by harborglowvintage-oss
1.2193
PR #1985by yigengjiang
1.1093
PR #2028by Arnie016
1.0898

Hyperparameters Across PRs

pr_numberparameters
1204{"start_layer":7}
1274{"start_layer":7}
1326{"start_layer":7}
1333{"start_layer":7}
1334{"start_layer":7}
1338{"start_layer":7}
1339{"start_layer":7}
1381{"start_layer":7}
1396{"start_layer":7}
1412{"start_layer":7}
1420{"start_layer":7,"end_layer":10}
1425{"start_layer":6}
1435{"layers":"7+"}
1437{"start_layer":7,"end_layer":10}
1450{"layers":[7,8,9,10]}
1477{"start_layer":7}
1485{"start_layer":7}
1489{"start_layer":7}
1492{"layers":"7+"}
1493{"layers":"7+"}
1499{"start_layer":7}
1515{"start_layer":7}
1521
1532{"layers":"7+"}
1534
1541{"start_layer":7,"new_scalar_params":66}
1570{"start_layer":7}
1578
1614{"start_layer":7}
1620
1635{"start_layer":7}
1647
1661{"start_layer":7}
1667{"start_layer":7}
1720{"start_layer":7}
1725
1731{"start_layer":7}
1733
1737{"start_layer":7}
1750
1755{"start_layer":7}
1760{"start_layer":7}
1776{"start_layer":7}
1780{"start_layer":7}
1812{"start_layer":7}
1814
1832
1893{"parallel_start_layer":7}
1913{"start_layer":7}
1919{"blocks":"every block"}
1929
1932{"start_layer":7}
1934{"start_layer":8}
1936{"start_layer":7}
1943{"start_layer":7}
1974{"layers_start":7}
1985{"start_layer":7}
2028{"layer":7}