lars
471a81b5e7
CI / Format (ruff format) (push) Successful in 26s
CI / Lint (ruff check) (push) Successful in 27s
CI / Sync project version with tag (push) Has been skipped
CI / Type check (ty) (push) Successful in 37s
CI / Lint (ruff check) (pull_request) Successful in 36s
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 33s
CI / Tests (push) Successful in 1m43s
CI / Tests (pull_request) Successful in 1m39s
Lets the vocab maps, event-id split index, and normalizer stats be warmed once for a dataset (right after `dwarf convert`, or before a `dwarf hparam-scan` sweep) without needing to also start training. Extracts the setup-stage logic out of giant/pipeline.py:run_train_job into a standalone run_setup_stage() (returning a SetupStageResult), reused by both run_train_job and the new dwarf command's scripts/warm_setup_cache.py — a behavior-preserving refactor, covered by the existing test_pipeline.py suite. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
53 lines
1.7 KiB
Python
53 lines
1.7 KiB
Python
"""dwarf warm-cache — precompute `giant train`'s setup-stage sidecar ahead of time.
|
|
|
|
Thin wrapper around `giant.pipeline.run_setup_stage` so a dataset's vocab
|
|
maps, event-id split index, and normalizer stats can be warmed once — e.g.
|
|
right after `dwarf convert`, or before kicking off a `dwarf hparam-scan`
|
|
sweep — without needing to also start training. See giant/data/setup_cache.py
|
|
for the sidecar itself.
|
|
"""
|
|
|
|
from pathlib import Path
|
|
|
|
from giant.pipeline import run_setup_stage
|
|
|
|
|
|
def run_warm_setup_cache(
|
|
data: str,
|
|
val_fraction: float = 0.1,
|
|
seed: int = 0,
|
|
conditioning: str = "physical",
|
|
router_enabled: bool = False,
|
|
router_type: str = "energy",
|
|
n_experts: int = 4,
|
|
rebuild: bool = False,
|
|
echo=print,
|
|
) -> None:
|
|
"""Populate (or refresh) the setup cache sidecar for `data`.
|
|
|
|
`val_fraction`/`seed`/`conditioning` select the normalizer cache entry
|
|
(`giant.data.setup_cache.normalizer_key`) — pass the same values a later
|
|
`giant train` invocation will use so it hits this warmed entry.
|
|
`router_enabled`/`router_type`/`n_experts` only matter for
|
|
`router_type == "process"` (warms that `n_experts`'s process map); the
|
|
energy-router reservoir sample is always collected regardless, so a
|
|
later `--router-type energy` run never needs to rescan just to seed
|
|
centers.
|
|
"""
|
|
router_cfg = {
|
|
"enabled": router_enabled,
|
|
"type": router_type,
|
|
"n_experts": n_experts,
|
|
}
|
|
run_setup_stage(
|
|
Path(data),
|
|
val_fraction=val_fraction,
|
|
seed=seed,
|
|
conditioning=conditioning,
|
|
router_cfg=router_cfg,
|
|
cache_setup=True,
|
|
rebuild_setup_cache=rebuild,
|
|
echo=echo,
|
|
)
|
|
echo("setup cache warmed.")
|