Make default checkpoint out_dir name reflect only non-default hyperparams
CI / Format (ruff format) (push) Successful in 27s
CI / Lint (ruff check) (push) Successful in 28s
CI / Sync project version with tag (push) Has been skipped
CI / Type check (ty) (push) Successful in 23s
CI / Tests (push) Successful in 53s
CI / Format (ruff format) (pull_request) Successful in 28s
CI / Lint (ruff check) (pull_request) Successful in 28s
CI / Sync project version with tag (pull_request) Has been skipped
CI / Type check (ty) (pull_request) Successful in 22s
CI / Tests (pull_request) Successful in 52s
CI / Format (ruff format) (push) Successful in 27s
CI / Lint (ruff check) (push) Successful in 28s
CI / Sync project version with tag (push) Has been skipped
CI / Type check (ty) (push) Successful in 23s
CI / Tests (push) Successful in 53s
CI / Format (ruff format) (pull_request) Successful in 28s
CI / Lint (ruff check) (pull_request) Successful in 28s
CI / Sync project version with tag (pull_request) Has been skipped
CI / Type check (ty) (pull_request) Successful in 22s
CI / Tests (pull_request) Successful in 52s
Previously the same fixed 7 fields (mode/hidden_dim/n_blocks/emb_dim/ conditioning/lr/batch_size) were always baked into the name, even for a vanilla run, and router config wasn't represented at all. Now default_out_dir_name only includes fields that differ from DEFAULT_CONFIG, adds router/seed/epochs as candidates, and caps at 6 shown fields with a hashed overflow suffix for heavily-swept configs.
This commit is contained in:
+100
-1
@@ -1,3 +1,5 @@
|
||||
from datetime import datetime
|
||||
|
||||
from giant import config as gconfig
|
||||
|
||||
|
||||
@@ -144,4 +146,101 @@ def test_resolve_expert_dims_explicit_override_wins():
|
||||
def test_resolve_expert_dims_partial_override_mixes_explicit_and_inherited():
|
||||
router_cfg = {"expert_hidden_dim": 128, "expert_n_blocks": 0}
|
||||
hidden_dim, n_blocks = gconfig.resolve_expert_dims(router_cfg, 512, 6)
|
||||
assert (hidden_dim, n_blocks) == (128, 6) # n_blocks inherited, hidden_dim not
|
||||
assert (hidden_dim, n_blocks) == (128, 6)
|
||||
|
||||
|
||||
def _default_cfg(**overrides):
|
||||
train_overrides = {
|
||||
k: v for k, v in overrides.items() if k in gconfig.DEFAULT_CONFIG["train"]
|
||||
}
|
||||
model_overrides = {
|
||||
k: v for k, v in overrides.items() if k in gconfig.DEFAULT_CONFIG["model"]
|
||||
}
|
||||
router_overrides = overrides.get("router")
|
||||
if router_overrides:
|
||||
model_overrides["router"] = router_overrides
|
||||
return gconfig.merge_cli_overrides(
|
||||
gconfig.DEFAULT_CONFIG, None, train_overrides, model_overrides
|
||||
)
|
||||
|
||||
|
||||
_NOW = datetime(2026, 7, 29, 14, 30)
|
||||
|
||||
|
||||
def test_default_out_dir_name_all_defaults_is_just_the_timestamp():
|
||||
cfg = _default_cfg()
|
||||
assert gconfig.default_out_dir_name(cfg, now=_NOW) == "20260729_1430"
|
||||
|
||||
|
||||
def test_default_out_dir_name_single_non_default_field():
|
||||
cfg = _default_cfg(hidden_dim=512)
|
||||
assert gconfig.default_out_dir_name(cfg, now=_NOW) == "20260729_1430_h512"
|
||||
|
||||
|
||||
def test_default_out_dir_name_conditioning_embedding_shown_abbreviated():
|
||||
cfg = _default_cfg(conditioning="embedding")
|
||||
assert gconfig.default_out_dir_name(cfg, now=_NOW) == "20260729_1430_cemb"
|
||||
|
||||
|
||||
def test_default_out_dir_name_conditioning_default_omitted():
|
||||
cfg = _default_cfg(conditioning="physical")
|
||||
assert gconfig.default_out_dir_name(cfg, now=_NOW) == "20260729_1430"
|
||||
|
||||
|
||||
def test_default_out_dir_name_router_enabled_shown_as_unit():
|
||||
cfg = _default_cfg(router={"enabled": True, "type": "energy", "n_experts": 8})
|
||||
assert gconfig.default_out_dir_name(cfg, now=_NOW) == "20260729_1430_r-energy8"
|
||||
|
||||
|
||||
def test_default_out_dir_name_router_disabled_omitted_even_if_subfields_nondefault():
|
||||
cfg = _default_cfg(router={"enabled": False, "type": "pdg", "n_experts": 8})
|
||||
assert gconfig.default_out_dir_name(cfg, now=_NOW) == "20260729_1430"
|
||||
|
||||
|
||||
def test_default_out_dir_name_mode_shown_bare_no_prefix():
|
||||
cfg = _default_cfg(mode="wgan")
|
||||
assert gconfig.default_out_dir_name(cfg, now=_NOW) == "20260729_1430_wgan"
|
||||
|
||||
|
||||
def test_default_out_dir_name_overflow_caps_and_hashes_remainder():
|
||||
cfg = _default_cfg(
|
||||
mode="wgan",
|
||||
router={"enabled": True, "type": "energy", "n_experts": 8},
|
||||
conditioning="embedding",
|
||||
hidden_dim=512,
|
||||
n_blocks=8,
|
||||
emb_dim=32,
|
||||
lr=1e-3,
|
||||
batch_size=2048,
|
||||
seed=3,
|
||||
epochs=200,
|
||||
)
|
||||
name = gconfig.default_out_dir_name(cfg, now=_NOW)
|
||||
# First 6 by priority: mode, router, conditioning, hidden_dim, n_blocks, emb_dim.
|
||||
assert name.startswith("20260729_1430_wgan_r-energy8_cemb_h512_b8_e32_+4more-")
|
||||
digest = name.split("-")[-1]
|
||||
assert len(digest) == 6
|
||||
|
||||
|
||||
def test_default_out_dir_name_overflow_hash_is_deterministic_and_value_sensitive():
|
||||
base = dict(
|
||||
mode="wgan",
|
||||
router={"enabled": True, "type": "energy", "n_experts": 8},
|
||||
conditioning="embedding",
|
||||
hidden_dim=512,
|
||||
n_blocks=8,
|
||||
emb_dim=32,
|
||||
lr=1e-3,
|
||||
batch_size=2048,
|
||||
seed=3,
|
||||
epochs=200,
|
||||
)
|
||||
name_a = gconfig.default_out_dir_name(_default_cfg(**base), now=_NOW)
|
||||
name_b = gconfig.default_out_dir_name(_default_cfg(**base), now=_NOW)
|
||||
assert name_a == name_b # stable across calls with the same overflow set
|
||||
|
||||
changed = dict(base, epochs=999)
|
||||
name_c = gconfig.default_out_dir_name(_default_cfg(**changed), now=_NOW)
|
||||
assert (
|
||||
name_c != name_a
|
||||
) # differs when an overflowed value changes # n_blocks inherited, hidden_dim not
|
||||
|
||||
Reference in New Issue
Block a user