lars
48faaee79d
CI / Lint (ruff check) (push) Successful in 27s
CI / Format (ruff format) (push) Successful in 30s
CI / Sync project version with tag (push) Has been skipped
CI / Type check (ty) (push) Successful in 31s
CI / Tests (push) Successful in 2m26s
CI / Lint (ruff check) (pull_request) Successful in 27s
CI / Format (ruff format) (pull_request) Successful in 27s
CI / Sync project version with tag (pull_request) Has been skipped
CI / Type check (ty) (pull_request) Successful in 27s
CI / Tests (pull_request) Successful in 2m23s
Stage 2 was trained on ground-truth stage-1 outcomes but deployed on
sampled ones, and in a rollout that gap compounds over every step of
every track — the same train/inference gap teacher_forcing="scheduled"
already closes within stage 2, just never applied at the stage
boundary. "sampled" was declared in the schema but rejected loudly by
validate_config as unimplemented; this lands the real implementation.
Mirrors the existing scheduled-sampling precedent rather than a hard
switch: new stage2_model.ctx_p_start/ctx_p_end (defaults 1.0 -> 0.0)
linearly ramp P(condition on ground truth) from epoch 0 to the final
epoch, so stage 2 doesn't chase a wildly moving stage-1 target early in
training. Per the plan discussed with the user: the sample is drawn
from stage 1's sampling_model() (EMA weights when present, matching
what inference actually deploys), mixed per example via a Bernoulli
draw (never blended within a row), and validation always uses the
ground truth regardless of the schedule. Fixes a latent bug the same
pattern would otherwise have hit: every sampler in giant/sample.py
flips its model to .eval() with no restore, so sampling from the raw
(non-EMA) stage-1 model mid-step now explicitly restores its .training
flag afterward to avoid silently corrupting stage 1's own training mode
for the rest of the epoch.
validate_config now enforces stage1_context in {"truth", "sampled"},
requires both stages active for "sampled" (nothing to sample from
otherwise), range-checks ctx_p_start/ctx_p_end, and rejects the
ctx_p_start = ctx_p_end = 1.0 configuration as an unadvertised no-op
identical to "truth".
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>