Model card: BIRD dev EX re-scored with --meta_time_out 3600 (SQLite 3.45.3), Spider test EX, checkpoint provenance

README.md

@@ -10,8 +10,14 @@ FINER-SQL 1.5B SQL-Writer continually trained with GRPO (format + execution rewa
 counterexample-enriched database environment of *Small Language Models for Text-to-SQL against Spurious Correctness*.
 Checkpoint step 6750 (dev-selected). Code: the `core-db-sql` GitHub repository.
 
-| BIRD dev EX | Spider dev EX | Spider dev TS |
-|---:|---:|---:|
-| 63.75 | 79.98 | 72.44 |
+| BIRD dev EX | Spider dev EX | Spider dev TS | Spider test EX |
+|---:|---:|---:|---:|
+| 63.82 (979/1534) | 79.98 (827/1034) | 72.44 (749/1034) | 81.79 (1756/2147) |
 
-k = 30 samples, T = 1.0, vote-after-verify selection, official evaluators. Prompts: `thanhdath/core-db-evaluation-prompts`.
+k = 30 samples, T = 1.0, seed 42, at most 2048 new tokens, vote-after-verify selection, official evaluators (BIRD:
+evaluation_bird_ex.py with SQLite 3.45.3 and `--meta_time_out 3600`; Spider: taoyds/test-suite-sql-eval @e97acc54,
+default flags; TS on the distilled Spider dev test suites). Prompts: `thanhdath/core-db-evaluation-prompts`
+(`bird_dev`, `spider_dev`; Spider test: `spider_test_full_schema`).
+
+Provenance: these weights are byte-identical to `thanhdath/15b-core-noam-1ep-pod` @ `d251e7068d4fb22bf2eae7e97039d1ba3c8e5269`, sub-folder `checkpoint-6750` (training step 6750).
+The saved predictions and the re-scoring script are in `scripts/rq2/` of the code repository.