Skip to content

try-best-params-from-first-pass-tpe-study #178

@david-thrower

Description

@david-thrower

{
'embedding_n': 12,
'activation': 'gelu',
'predecessor_level_connection_affinity_factor_first': 38.7,
'predecessor_level_connection_affinity_factor_main': 4.6,
'max_consecutive_lateral_connections': 32,
'p_lateral_connection': 17.1,
'num_lateral_connection_tries_per_unit': 1,
'learning_rate': 0.046500145665525995,
'epochs': 7,
'batch_size': 22,
'dropout': 0.6500000000000001,
'maximum_units_per_level': 7,
'maximum_neurons_per_unit': 7,
'temperature': 36912 # iRoPE theta
}

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions