url/SkillOpt
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(spreadsheetbench)+optimizer: fix verify-feedback bloat, drop optimizer-side truncation, soft-disable gate

Browse Source 
A. SpreadsheetBench verification-feedback bloat
   - rollout.py _auto_verify_output: use official _compare_cell_value (was
     repr() equality, which falsely flagged 5 vs 5.0 / None vs ""); collapse
     correct-and-empty cells into a count so large sparse answer ranges no
     longer flood feedback with MBs of None=None noise.
   - codegen_agent.py _build_eval_feedback: only list WRONG cells, collapse
     correct ones into a count.
   Scoring is unaffected (evaluate() is independent); this only fixes the
   target model's multi-turn solving feedback.

B. Remove optimizer-side truncation (bloat source now fixed)
   - reflect.py: drop _MAX_TRAJ_CHARS cap and all per-field clips.
   - update_modes.py / clip.py / lr_autonomous.py: describe_item /
     short_item_summary no longer truncate; raise ranking/lr token budget.
   - trainer.py _format_step_buffer: full task_ids / target.
   - slow_update.py: full comparison samples.

C. Soft-disable gate
   - config.py / trainer.py: use_gate=false no longer raises; validation still
     runs but candidates are force-accepted (new force_accept branch + log).

Misc: aggregate.py merge token budget 4096 -> 16384.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
Cuzyoung
2026-06-01 11:23:08 +00:00
parent f64a41397c
commit 372fd56c1e
10 changed files with 138 additions and 94 deletions
Download Patch File Download Diff File Expand all files Collapse all files
skillopt/gradient/aggregate.py
+2 -2
View File
@@ -46,7 +46,7 @@ def _merge_batch(
response, _ = chat_optimizer(
system=system_prompt,
user=user,
max_completion_tokens=64000 if is_full_rewrite_minibatch_mode(update_mode) else 4096,
max_completion_tokens=64000 if is_full_rewrite_minibatch_mode(update_mode) else 16384,
retries=3,
stage="merge",
)
@@ -231,7 +231,7 @@ def merge_patches(
response, _ = chat_optimizer(
system=merge_final_prompt,
user=user,
max_completion_tokens=64000 if is_full_rewrite_minibatch_mode(update_mode) else 4096,
max_completion_tokens=64000 if is_full_rewrite_minibatch_mode(update_mode) else 16384,
retries=3,
stage="merge",
)