List your company

Character-level language modeling on Shakespeare (test)

50.2AccuracyAdam
25.55231.95138.3544.749Jun 6, 2025

Evaluation results

MethodLinks
AdamArchitecture=4 x 128 + Skip2025.0650.215,80075.14.75
AdamArchitecture=1 x 2562025.0649.97,400202.7
AdamArchitecture=4 x 1282025.0649.828,600118.44.14
SGDArchitecture=4 x 128 + Skip2025.0638.9129,600619.74.78
SGDArchitecture=1 x 2562025.0635.7179,000480.92.69
SGDArchitecture=4 x 1282025.0635.163,000255.34.05
DRArchitecture=1 x 2562025.0632.416,60084951.14
DRArchitecture=4 x 128 + Skip2025.0632.232,8001,210.836.91
APArchitecture=4 x 128 + Skip2025.0630.2205,2002,964.414.44
APArchitecture=1 x 2562025.0629.698,8001,64616.66
DRArchitecture=4 x 1282025.0626.710,400234.122.51
APArchitecture=4 x 1282025.0626.5182,4001,688.69.26