| {"ntoken": 50000, "ninp": 300, "context_size": 700, "nhid": 1024, "nhidlast": 650, "nlayers": 3, "dropout": 0.4, "dropouth": 0.2, "dropouti": 0.55, "dropoute": 0.1, "wdrop": 0.5, "tie_weights": false, "ldropout": 0.29, "n_experts": 5} |
| {"ntoken": 50000, "ninp": 300, "context_size": 700, "nhid": 1024, "nhidlast": 650, "nlayers": 3, "dropout": 0.4, "dropouth": 0.2, "dropouti": 0.55, "dropoute": 0.1, "wdrop": 0.5, "tie_weights": false, "ldropout": 0.29, "n_experts": 5} |