{
  "training_run_id": "9f27c001-b92c-55a7-9e12-1a8bd858e16d",
  "experiment": "w1_qwen3-8b-base",
  "tag": "w1_qwen3-8b-base",
  "model": "Qwen/Qwen3-8B-Base",
  "model_short": null,
  "task": null,
  "seed": 42,
  "rank": null,
  "lr": 1e-05,
  "group_size": 8,
  "steps": 30,
  "platform": "tinker",
  "campaign": "bitter_lesson_v2",
  "wave": "1-frontier",
  "status": "completed",
  "last10_avg": 0.9875,
  "first5_avg": 0.875,
  "peak_reward": 1.0,
  "peak_accuracy": null,
  "last10_accuracy": null,
  "heldout_accuracy": null,
  "heldout_n": null,
  "timestamp": "2026-04-19T11:31:34.068282",
  "experiment_family": null,
  "notes": null,
  "source_json": "experiments/tinker-runs/results/campaign_v2_20260419_111623.json",
  "weight_checkpoints": [],
  "sampler_weight_checkpoints": [
    {
      "kind": "sampler_weights",
      "step": "final",
      "uri": "tinker://9f27c001-b92c-55a7-9e12-1a8bd858e16d:train:0/sampler_weights/final"
    }
  ],
  "hf_repo_id": "arvindcr4/tinker-rl-w1_qwen3-8b-base-qwen3-8b-base-s42-run2",
  "run_variant": "run2"
}