List your company

Character-level language modeling on Shakespeare (train)

59.8AccuracyAdam
25.79234.62143.4552.279Jun 6, 2025

Evaluation results

MethodLinks
AdamArchitecture=1 x 2562025.0659.87.4202.7
AdamArchitecture=4 x 128 + Skip2025.065915.875.14.75
AdamArchitecture=4 x 1282025.0657.928.6118.44.14
SGDArchitecture=4 x 128 + Skip2025.0642.6129.6619.74.78
SGDArchitecture=1 x 2562025.0638.8179480.92.69
SGDArchitecture=4 x 1282025.0637.163255.34.05
DRArchitecture=1 x 2562025.063416.684951.14
DRArchitecture=4 x 128 + Skip2025.0633.932.81,210.836.91
APArchitecture=4 x 128 + Skip2025.0631.1205.22,964.414.44
APArchitecture=1 x 2562025.0630.498.81,64616.66
DRArchitecture=4 x 1282025.0627.410.4234.122.51
APArchitecture=4 x 1282025.0627.1182.41,688.69.26