Hyperparameter Power Impact in Transformer Language Model Training.
Lucas Hyberg Puvis de Chavannes, Mads Guldborg Kjeldgaard Kongsbak, Timmie Rantzau, Leon Derczynski
Browse the full EMNLP paper archive.
Lucas Hyberg Puvis de Chavannes, Mads Guldborg Kjeldgaard Kongsbak, Timmie Rantzau, Leon Derczynski
Browse the full EMNLP paper archive.