Files
giant/configs/router_energy_n10_embedding.toml
T

24 lines
453 B
TOML

[train]
mode = "flow"
epochs = 30
lr = 3e-4
warmup_epochs = 3
val_fraction = 0.1
num_workers = 4
[model]
conditioning = "embedding"
dropout = 0.0
expert_hidden_dim = 128
expert_n_blocks = 4
[model.router]
enabled = true
type = "energy"
n_experts = 10
expert_hidden_dim = 128
expert_n_blocks = 4
temperature = 0.05
lambda_balance = 0.035
learn_centers = true