docs(autotrain): joint seed x steps smoke sweep, real new evidence - #1132
Merged
Conversation
Sixth slice of the DSH5-10 replay-preference scope: extraction of all 7 named patterns finished in the prior slice, so this takes the smallest next step of the still-unattempted training scope -- converting an already extracted OperatorReplayPreferenceRowV1 into this repo's existing PreferencePair shape (the same schema slm preference build-pairs/train already reads/writes), so a later slice can feed rows into that harness without inventing a second corpus shape. prompt is the row's real, pack-authorized input-state OpenUI source (traces carry no user utterances to recover instead); chosen/rejected are the row's own legal-set action tokens verbatim, not replayed alternate programs; composite_reward is never called on those tokens since scoring "undo" as OpenUI source would manufacture a meaningless number. A row whose input state is foreign to its trace (e.g. MERGE_SUCCESS, grounded on a branch-edit tip) is skipped with a reason, never fabricated. Claim class: wiring, same tier as every prior slice. No training, checkpointing, or composite-reward scoring is attempted; the DSH3 policy heads, four-baseline comparison, and held-out measurement remain fully unattempted. Verified (fresh Python 3.12 venv, NODE_OPTIONS= npm ci in src/apps/openui_bridge): 69 passed (61 baseline + 8 new) across tests/test_dsl/test_replay_preference.py plus the sibling merge/ conversation/disposition suites; ruff check clean; verify_version_stamps --check ok (dsl.operators.replay_preference v6->v7); repo_policy ok; verify_decode_invariants clean. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01BUwBZ5X9HJzzvVjXcd2RZ9
Follow-up to the ledger's diminishing-returns note after batch #4: instead of another single-variable check, this batch varies --seed (1, 2, 3) and --steps (4, 16) jointly against main HEAD f3adde1 (PR #1131, already merged), same wf_smoke_v2 fixture/model/recipe as every prior batch. 6 more independently-run rows, combined with the prior single-variable batches into a full seed x steps grid: seed-to-seed spread is real but bounded and shrinks as steps increase, and seed introduces variance without a directional bias (seed 0 is neither systematically highest nor lowest). Genuinely new joint evidence, not a repeat of either single-variable batch. Still fixture_or_scratch: n=1 per (seed, steps) cell, 101-record fixture, context-backend scratch. No convergence/generalization/ship claim. Per the ledger's own next-steps note, the smoke-loop's role as a harness liveness check is now thoroughly covered at this fixture size; the next scheduled iteration should move off this fixture entirely. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01BUwBZ5X9HJzzvVjXcd2RZ9
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
|
Important Review skippedAuto reviews are disabled on base/target branches other than the default branch. Please check the settings in the CodeRabbit UI or the ⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Plus Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Tyler-R-Kendrick
pushed a commit
that referenced
this pull request
Jul 27, 2026
…e row Addresses review on #1123 (Tyler-R-Kendrick): this batch's ledger section was based on a stale main tip and clobbered the already-merged batch #4 (#1120, steps 4/16/32) and joint seed x steps sweep (#1132) sections. Rebases onto main HEAD e0eaeec, appending the 64/128-step extended-range check after both instead of overwriting them -- complementary, not superseded, as those two already conclude the fixture's step/seed variance is otherwise thoroughly covered. Also fixes the missing wall_s cell on the 8-step reference row in the step-scaling comparison table (was breaking the table's column count). Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01VDeTk7RxBAbWX5fKjBqb4r
This was referenced Jul 27, 2026
Closed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Stacked on #1131. Follow-up to the smoke ledger's own diminishing-returns note after batch #4 (
docs/design/autotrain-loop-ledger-20260725.md): instead of another single-variable rerun, this batch varies--seed(1, 2, 3) and--steps(4, 16) jointly againstmainHEADf3adde1b(PR #1131), samewf_smoke_v2fixture/model/recipe as every prior batch in this ledger.python -m scripts.train_modelinvocations, fresh Python 3.12 venv this session).autotrain-wf-smoke-20260727-joint-seedvar-measured-results.md).``fixture_or_scratch, not a ship claim — n=1 per (seed, steps) cell, 101-record fixture,context-backend scratch. No convergence/generalization/ship claim made.verify_version_stamps --check: 0 components touched), no checkpoint promoted.Honest scope note carried into the doc: per the ledger's own next-steps note, the smoke-loop's role as a harness liveness + variance check is now thoroughly covered at this fixture size. The doc explicitly flags that the next iteration should move off this fixture — and, specifically for the DSH5-10 thread PR #1131 advanced, that the real next step there is wiring
TypedOperatorPolicyScorer(the issue's own named consumer), since #1131 found the genericPreferencePaircomposite-reward shape is a structural mismatch for exact-state action-token rows.Verification
Test plan
repo_policy— okverify_version_stamps --check— oklast_loss/wall_svalue cross-checked against the realoutputs/runs/<run_id>/train_summary.jsonproduced this sessionGenerated by Claude Code