-- Training jobs (BACKLOG F4): a LoRA adapter trained on a node, from a base
-- model's weights and question/answer pairs, and what it made. The pairs
-- and the adapter are kept here, in the store every control plane reads:
-- they are megabytes, and a job's record is worth little without them.
CREATE TABLE train_jobs (
  id             TEXT PRIMARY KEY,
  -- name is the adapter's: what clients will ask for it by.
  name           TEXT NOT NULL,
  -- model is the catalog model the adapter is for; base_repo and
  -- base_revision the weights it is trained on.
  model          TEXT NOT NULL,
  base_repo      TEXT NOT NULL,
  base_revision  TEXT NOT NULL DEFAULT '',
  node           TEXT NOT NULL,
  gpu_memory_mib INTEGER NOT NULL,
  params         TEXT NOT NULL DEFAULT '',
  gguf           INTEGER NOT NULL DEFAULT 0,
  data           BLOB NOT NULL,
  pairs          INTEGER NOT NULL,
  -- state is queued, starting, preparing, running, done, failed or
  -- cancelled.
  state          TEXT NOT NULL,
  step           INTEGER NOT NULL DEFAULT 0,
  steps          INTEGER NOT NULL DEFAULT 0,
  loss           REAL NOT NULL DEFAULT 0,
  message        TEXT NOT NULL DEFAULT '',
  peak_mib       INTEGER NOT NULL DEFAULT 0,
  created_at     INTEGER NOT NULL,
  started_at     INTEGER NOT NULL DEFAULT 0,
  finished_at    INTEGER NOT NULL DEFAULT 0,
  created_by     TEXT NOT NULL DEFAULT ''
);
CREATE INDEX train_jobs_by_state ON train_jobs (state);

-- What a job made: the PEFT adapter as a gzipped tar, and for llama.cpp the
-- adapter as GGUF.
CREATE TABLE train_artifacts (
  job_id TEXT NOT NULL REFERENCES train_jobs(id) ON DELETE CASCADE,
  kind   TEXT NOT NULL,
  data   BLOB NOT NULL,
  PRIMARY KEY (job_id, kind)
);