Stochastic Optimization On Penn Treebank
Metriken
Bit per Character (BPC)
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | Bit per Character (BPC) | Paper Title | Repository |
---|---|---|---|
AdaShift | 1.274 | Domain-independent Dominance of Adaptive Methods | |
AdaBound | 2.863 | Domain-independent Dominance of Adaptive Methods | |
AvaGrad | 1.175 | Domain-independent Dominance of Adaptive Methods | |
AdamW | 1.23 | Domain-independent Dominance of Adaptive Methods |
0 of 4 row(s) selected.