lars
af2ee7c7ce
CI / Format (ruff format) (push) Successful in 28s
CI / Lint (ruff check) (push) Successful in 28s
CI / Sync project version with tag (push) Has been skipped
CI / Lint (ruff check) (pull_request) Successful in 26s
CI / Type check (ty) (push) Successful in 29s
CI / Format (ruff format) (pull_request) Successful in 31s
CI / Sync project version with tag (pull_request) Has been skipped
CI / Type check (ty) (pull_request) Successful in 31s
CI / Tests (push) Successful in 1m39s
CI / Tests (pull_request) Successful in 1m37s
Extends the 10-expert EnergyRouter + physical-conditioning benchmark config with the new opt-in gumbel combine weights, isolating the learn_centers/learn_temperature axis: none, centers only, and centers+temperature. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
23 lines
422 B
TOML
23 lines
422 B
TOML
[train]
|
|
mode = "flow"
|
|
epochs = 30
|
|
lr = 3e-4
|
|
warmup_epochs = 3
|
|
val_fraction = 0.1
|
|
num_workers = 4
|
|
|
|
[model]
|
|
conditioning = "physical"
|
|
dropout = 0.0
|
|
|
|
[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 = false
|
|
gumbel = true
|