{
  "id": "foundation-20261029",
  "title": "Six-month foundation: a four-hour training budget",
  "date": "2026-10-29",
  "kind": "training",
  "status": "completed",
  "hypothesis": "Can a broader Lichess corpus improve next-move imitation within a fixed four-hour budget?",
  "baseline": "Fresh random initialization; expanded-validation NLL 5.029582. This run was trained from scratch, not continued from the September checkpoint.",
  "data": "April–September 2026 Lichess: 4,222,117 unique retained games. Train 4,137,488 games / 943,591,445 targets; validation 42,223 / 9,615,601; test 42,406 / 9,644,506 (not model-evaluated). Both recorded ratings >=2000; base+40×increment >=480 seconds; completed standard-start legal games; no BOT label; exact game-ID/full-sequence deduplication. No left crop.",
  "config": {
    "dataset_manifest_sha256": "0c5097b4793fd54ad31dd2b2c4220741371aa59c8be1cbe1dfc6d480fc451c94",
    "integrity_receipt_sha256": "620cd6a23a9e05379b70fcf541a0f7c18699b0e1e7576ec16ed7cc492e9ab894",
    "heldout_audit_sha256": "d8905b66852bdd9c09748439091f388bf29124466666cbe20ffd2485cfffa4e3",
    "runtime_sha256": {
      "loader_codec_smoke.py": "e009bb8303f9a0740bc77f6096386b8956ed1bc92eedd94a11ab1def0a95688e",
      "prepare_scaleup_plan.py": "74c6980429c4598980d5acd797d54b40780f6ef6132f57910810938630eb7280",
      "scaleup_cpu_tests.py": "43392c3b5dad91e9e3d15390aa1dca4cfc063950a8246ac2bab9fbd6cf0ac133",
      "scaleup_job.py": "2b71cbf6332aeb4ff0e7eb1b61e2d4fe314f9de8998e4ca6c33493c2acccc889",
      "scaleup_job_tests.py": "a819edefd535e660aec9fdf971944bde2b40dd66975270a25578d8361fc20ba8",
      "scaleup_plan.py": "0b8bd4d8174ba56ffb8780fbb77ee33ed519b19779ad2fc5f892dc70d95c2012",
      "scaleup_plan_tests.py": "33fdc882e4960fe33796afe9f8d1f25b1bde64168ccafb069e3b7a79594d79cc",
      "training_adapter.py": "1a0271cad107870345ef839378692d0d4036de44910e3e187c52c4e4d8244637",
      "training_collective_tests.py": "0ba6dd9a8bc2aa190c0f150ff85800c65271253eddf918671d5b57fec92975ed",
      "training_core.py": "140022ab400e6ef5f56fe4c3a1df28834afdc7f90e39b011968418a93795b856",
      "training_deadline.py": "11685a7e1078ac7e5f2fab07daad20316efb20f9cef56373e9cc5400e8b7c4ca",
      "training_deadline_failure_tests.py": "8daff953ef7d4ed4b3407b3aea28e2fef76baa7fad18f1c259254b425015b673",
      "training_deadline_tests.py": "f5ffd9b5cc0f74deff8b368602718ea8e44c8a4fa242171521814025996cccd3",
      "training_owned_launcher_tests.py": "5533574138545b45a224a84fa9577e463661c204864dc4956e768d29892c47ba",
      "training_terminal_tests.py": "5135821307b0b24e082f5767dc16779008beb5ec71910d18f000ecfd5bcd73a2",
      "training_tests.py": "ebc212cd288f63e88ed5f8986d80652584bc796de3606130322041b341b6ee54",
      "train_chess.py": "d1ead13673f9b4e613415ca7d0904d68bda0248bbdbf06d3736c2c8138257799",
      "verified_training_data.py": "fa00eb60a7c4c2061706ef94016f52bdef6cc04cbb2492ce8178dc02568fc71b",
      "chessdata/convert.py": "12dd6ae517a0f857684e4f9273f4a27168d9080b5f20e9260c0355053ff391c1",
      "chessdata/limits.py": "4d5cbc5d171068aff56104eae6c952848ea9c04751159b75942d1b99c9507311",
      "chessdata/pgn.py": "6f81cc6318220626b7f2d23ea623013360fab13afb7f663455ef4b0d043e4951",
      "chessdata/reader.py": "b825cdbe517a4b65ac2891787740c970009535127623a728929e18e5d226cea5",
      "chessdata/rust_backend.py": "8edd2d2d887c6da24fcc951ac77090e13f6bcc0bb6f89bcf47a02c5e1fc3c7cb",
      "chessdata/tokenizer.py": "0db7085edec22885bd8c51aac4d6867afc04203ba913ef561be97213df019029",
      "chessdata/__init__.py": "f0156ddfe522b44c33d849bbbbbc07a44f52f39c762822a512e5e8c1e710cf40",
      "run-training.sh": "aaca0c9c2d2be452343cdeb9b91daa8af335ca7576f298b6c08969638975d6f0"
    },
    "micro": 4,
    "accum": 4,
    "bucket": 2048,
    "seed": 2026,
    "lr": 0.0003,
    "collective_timeout_seconds": 900,
    "legality_eval_games": 128,
    "minimum_device_free_bytes": 4294967296,
    "non_optimizer_reserve_seconds": 1200,
    "throughput_discount": 0.85,
    "planned_validation_checks": 6,
    "epoch_optimizer_updates": 129297,
    "train_prediction_targets": 943591445,
    "train_games": 4137488,
    "initialization": "from_scratch",
    "maximum_epochs": 1,
    "test_model_evaluation": false,
    "model": {
      "vocab_size": 128,
      "n_positions": 1024,
      "n_ctx": 1024,
      "n_embd": 768,
      "n_layer": 12,
      "n_head": 12,
      "resid_pdrop": 0,
      "embd_pdrop": 0,
      "attn_pdrop": 0,
      "use_cache": false,
      "bos_token_id": 69,
      "eos_token_id": 70,
      "pad_token_id": 71,
      "attn_implementation": "sdpa"
    },
    "parameter_count": 85940736
  },
  "compute": "Two RTX 4090 GPUs. Whole job 3h 58m 04.401s; soft deadline stop. 75,558 updates, 2,417,856 unique games and 551,410,959 targets consumed: a partial first pass. Best checkpoint is earlier: step 72,198, 526,834,590 target exposures.",
  "results": [
    {
      "label": "Best expanded-validation NLL",
      "value": 0.5739030495971976
    },
    {
      "label": "Final unique games consumed",
      "value": 2417856
    },
    {
      "label": "Final prediction targets consumed",
      "value": 551410959
    }
  ],
  "limitations": [
    "Best validation belongs to step 72,198, not the final step 75,558 weights.",
    "Expanded-validation NLL is not directly comparable to the original smaller validation set; use the matched 7,000-game comparison.",
    "No held-out test model evaluation, reasoning traces, Elo estimate or completed Elite continuation.",
    "Foundation model-only weights and source are downloadable via the foundation guide. Six-month bulk data are not included; the older dataset download remains the historical September package."
  ],
  "checkpoint": "857bc93bfffb287dc67e2845a14c214a4691bc1a008dae1fa4d044e5fccc87d2",
  "sourceSnapshot": "foundation-20261029",
  "history": [
    {
      "step": 8022,
      "nll": 0.8020281492112645
    },
    {
      "step": 16044,
      "nll": 0.7062413286860573
    },
    {
      "step": 24066,
      "nll": 0.6585811909788196
    },
    {
      "step": 32088,
      "nll": 0.6230701939552107
    },
    {
      "step": 40110,
      "nll": 0.5984513133298186
    },
    {
      "step": 48132,
      "nll": 0.5853722610531451
    },
    {
      "step": 56154,
      "nll": 0.5806068211344487
    },
    {
      "step": 64176,
      "nll": 0.5771529146043254
    },
    {
      "step": 72198,
      "nll": 0.5739030495971976
    }
  ],
  "evidence": [
    {
      "label": "Terminal verification",
      "sha256": "7c1bfbf19d2e0ed7f14e59e8aaa892b1e064ab66610257802b30d1bf53023e4d",
      "selectedFields": {
        "stopping_reason": "total_deadline_soft_stop",
        "step": 75558,
        "unique_games": 2417856,
        "prediction_target_exposures": 551410959,
        "checkpoints": {
          "best": {
            "sha256": "857bc93bfffb287dc67e2845a14c214a4691bc1a008dae1fa4d044e5fccc87d2",
            "step": 72198,
            "bytes": 1031498263,
            "targets_at_checkpoint": 526834590
          },
          "last": {
            "sha256": "d000224f697a891687a74a8cce871d60024af3c3e536ec220fd21567eb350dc9",
            "step": 75558,
            "bytes": 1031498263,
            "targets_at_checkpoint": 551410959
          }
        }
      }
    }
  ]
}