fix(data-process): 发布精确三路数据切分

This commit is contained in:
caoxiaozhu
2026-07-24 20:43:47 +08:00
parent e6a5a36bc0
commit 9cb77c251a
8 changed files with 405 additions and 181 deletions

View File

@@ -11,7 +11,7 @@ from urllib.parse import urlsplit, urlunsplit
import httpx
from app.modules.data_process.algorithms import normalize_text, stable_split
from app.modules.data_process.algorithms import normalize_text, stable_split_assignments
class ModelGenerationError(ValueError):
@@ -203,7 +203,7 @@ def generate_model_records(
"original_output": "",
"status": "invalid",
"error": error_message,
"split": stable_split(result_id, split, seed=task_id),
"split": "train",
}
)
if on_progress:
@@ -236,7 +236,7 @@ def generate_model_records(
"original_output": output,
"status": "valid" if valid else "invalid",
"error": None if valid else "model result is missing instruction or output",
"split": stable_split(result_id, split, seed=task_id),
"split": "train",
}
)
if on_progress:
@@ -244,6 +244,13 @@ def generate_model_records(
finally:
if owns_client:
http_client.close()
assignments = stable_split_assignments(
[str(result["id"]) for result in results],
split,
seed=task_id,
)
for result, assignment in zip(results, assignments, strict=True):
result["split"] = assignment
return results