{
  "deliverable": "sophia.pt",
  "sha256": "e49ddc2cbbd311330f21fe52ada853e3ed745cf5f2e47de83da3898234592268",
  "equals": "runs/dpo_e3",
  "chain": [
    {
      "stage": "pretrain",
      "run": "runs/pretrain_e3bc2d5_bf16_qkclip",
      "ckpt": "checkpoints/ckpt_step15259.pt",
      "steps": 15259,
      "tokens": "20B",
      "seed": 42
    },
    {
      "stage": "sft",
      "run": "runs/sft",
      "ckpt": "ckpt_final.pt",
      "steps": 7176,
      "data": "release/corpus (88,267 rows x 3ep)",
      "val_loss": 2.6183438087448114,
      "selected": "epoch3 via haiku rank (mean rank 1.88, repeat 9.7%)"
    },
    {
      "stage": "rft_experiment",
      "run": "runs/rft_e3.pt",
      "steps": 104,
      "verdict": "null result on powered probe; not shipped"
    },
    {
      "stage": "dpo",
      "run": "runs/dpo_e3",
      "steps": 500,
      "pairs": 1953,
      "beta": 0.1,
      "lr": 1e-06,
      "verdict": "WINNER: probe paired +2.10 (t=+3.71), pass70 z=+3.62, pack +1.16, all flags down, no diversity loss"
    }
  ],
  "eval": {
    "judge": "claude-haiku-4-5 via frostfox",
    "probe_n16_t04": {
      "e3": 49.16,
      "dpo": 51.37,
      "paired_diff": 2.1,
      "t": 3.71
    },
    "pack_30x6_t07": {
      "e3": 27.93,
      "dpo": 29.08,
      "paired_diff": 1.16,
      "t": 0.94
    }
  },
  "external_upload": false,
  "release_name": "sophia",
  "release_dir": "release/sophia",
  "version": "1.0.0"
}
