ライフサイクルコールバック

createTrainer({
  name: "support-bot-v1",
  model: "unsloth/gemma-4-E4B-it",
  dataset: { type: "huggingface", name: "arkorlab/triage-demo" },
  callbacks: {
    onStarted, onLog, onCheckpoint, onCompleted, onFailed,
  },
});

.start()                 ── ジョブ投入、{ jobId } を返す。コールバックはまだ。
   │
   ▼
.wait()                  ── SSE イベントストリームを開く。コールバックはここから発火。
   │
   ▼
onStarted ─── 1 回。ストリームが `training.started` を報告したとき
   │
   ▼
onLog     ─── 多数回。学習ステップのメトリックスバッチごとに 1 回
   │
   ▼
onCheckpoint ── 数回。アダプタチェックポイントが保存されたとき
   │
   ▼
onCompleted  ── 1 回。正常終了時
or
onFailed     ── 1 回。バックエンドが失敗を報告したとき

onStarted: ({ job }) => {
  console.log(`Run ${job.id} accepted`);
},

onLog: ({ step, loss, evalLoss }) => {
  if (loss !== null) {
    console.log(`step=${step} loss=${loss.toFixed(4)} evalLoss=${evalLoss ?? "-"}`);
  }
},

onCheckpoint: async ({ step, infer }) => {
  const res = await infer({
    messages: [{ role: "user", content: "Can't log in" }],
  });
  console.log(`step=${step} sample=`, await res.text());
},

onCompleted: ({ job, artifacts }) => {
  console.log(`Run ${job.id} done, ${artifacts.length} artifacts`);
},

onFailed: ({ job, error }) => {
  console.error(`Run ${job.id} failed: ${error}`);
},

import { createTrainer } from "arkor";

export const trainer = createTrainer({
  name: "support-bot-v1",
  model: "unsloth/gemma-4-E4B-it",
  dataset: { type: "huggingface", name: "arkorlab/triage-demo" },
  lora: { r: 16, alpha: 16 },
  maxSteps: 100,
  callbacks: {
    onStarted: ({ job }) => console.log(`started ${job.id}`),
    onLog: ({ step, loss }) => {
      if (loss !== null) console.log(`step=${step} loss=${loss.toFixed(4)}`);
    },
    onCheckpoint: async ({ step, infer }) => {
      const res = await infer({
        messages: [{ role: "user", content: "Hello!" }],
      });
      console.log(`ckpt @ ${step}:`, await res.text());
    },
    onCompleted: ({ job }) => console.log(`done ${job.id}`),
    onFailed: ({ error }) => console.error(`failed: ${error}`),
  },
});