eaea4308fc
The head-vs-centroid eval (#1130) existed to prove the 'frozen embedding + trained head' spine; the operator accepted the tagging system and dropped the harness. Removed per rule 22: TagEvalCard + store, /api/tag_eval blueprint, tag_eval_run ml task, recover-stalled-tag-eval-runs sweep + beat entry, TagEvalRun model + table (migration 0073), and its tests. The eval's data loaders + metric helpers were NOT eval-specific — the nightly heads trainer runs on them — so they moved verbatim to services/ml/training_data.py (heads.py import updated; behavior unchanged). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01CDgx8bQS5YrGRK76v8HUnM
45 lines
1.8 KiB
Python
45 lines
1.8 KiB
Python
"""HeadTrainingRun — persisted lifecycle of a head-training batch (#114).
|
|
|
|
A persisted run row (not transient frontend state) so the run SURVIVES
|
|
navigation and the admin card can show live + historical status.
|
|
Training is idempotent (it upserts tag_head rows), so a SIGKILL'd run is harmless
|
|
— a maintenance recovery sweep flips a stalled `running` row to `error`, and the
|
|
next run re-trains. State machine: running → ready / error.
|
|
"""
|
|
|
|
from datetime import datetime
|
|
from typing import Any
|
|
|
|
from sqlalchemy import DateTime, Integer, String, Text, func
|
|
from sqlalchemy.dialects.postgresql import JSONB
|
|
from sqlalchemy.orm import Mapped, mapped_column
|
|
|
|
from .base import Base
|
|
|
|
|
|
class HeadTrainingRun(Base):
|
|
__tablename__ = "head_training_run"
|
|
|
|
id: Mapped[int] = mapped_column(Integer, primary_key=True)
|
|
# Training parameters: {min_positives, neg_ratio, precision_target, ...}.
|
|
params: Mapped[dict[str, Any]] = mapped_column(JSONB, nullable=False)
|
|
status: Mapped[str] = mapped_column(
|
|
String(16), nullable=False, default="running", index=True
|
|
)
|
|
# running | ready | error
|
|
started_at: Mapped[datetime] = mapped_column(
|
|
DateTime(timezone=True), nullable=False, server_default=func.now()
|
|
)
|
|
finished_at: Mapped[datetime | None] = mapped_column(
|
|
DateTime(timezone=True), nullable=True
|
|
)
|
|
# How many concepts got a (re)trained head vs were skipped (too few labels).
|
|
n_trained: Mapped[int | None] = mapped_column(Integer, nullable=True)
|
|
n_skipped: Mapped[int | None] = mapped_column(Integer, nullable=True)
|
|
error: Mapped[str | None] = mapped_column(Text, nullable=True)
|
|
# Last time the task made progress — the recovery sweep tells a live run
|
|
# from a SIGKILL'd one by this.
|
|
last_progress_at: Mapped[datetime | None] = mapped_column(
|
|
DateTime(timezone=True), nullable=True
|
|
)
|