{
  "checkpoint_policy": {
    "acceptance_artifact": false,
    "distributed_with_book": false,
    "reason": "Training adapters are intentionally local and are not distributed to readers.",
    "required_artifact": "reproducible evidence-backed training report"
  },
  "evaluation": {
    "do_sample": true,
    "historical_generation_seed": "not retained",
    "max_new_tokens": 150,
    "output_count": 15,
    "stages": [
      "baseline",
      "pretrained",
      "finetuned"
    ],
    "temperature": 0.3,
    "test_count": 5
  },
  "experiment": "7-5",
  "historical_environment_from_report": {
    "cuda_compute_capability": "8.9",
    "cuda_toolkit": "12.8",
    "gpu": "NVIDIA GeForce RTX 4090",
    "gpu_memory_gb": 23.647,
    "platform": "Linux",
    "torch": "2.8.0+cu128",
    "transformers": "4.56.2",
    "triton": "3.4.0",
    "unsloth": "2025.10.4",
    "xformers": "0.0.32.post2"
  },
  "historical_evidence_boundary": {
    "claim": "The retained terminal report proves a three-stage evaluation ran on the reported RTX 4090 software stack. It does not prove the byte identity of the historical adapters or upstream data.",
    "historical_checkpoint_hashes_retained": false,
    "historical_training_executed": true,
    "historical_upstream_revisions_retained": false,
    "raw_three_stage_evaluation_retained": true
  },
  "schema_version": "exp7-5-reproduction-contract-v1",
  "training": {
    "continued_pretraining": {
      "batch_size": 2,
      "dataset_fraction": 0.05,
      "dataset_split_seed": "not explicitly recorded by the historical script",
      "embedding_learning_rate": 1e-05,
      "epochs": 1,
      "gradient_accumulation_steps": 8,
      "learning_rate": 5e-05,
      "max_steps": -1,
      "optimizer": "adamw_8bit",
      "scheduler": "linear",
      "trainer_seed": 42,
      "warmup_ratio": 0.1,
      "warmup_steps": 10,
      "weight_decay": 0.01
    },
    "instruction_sft": {
      "batch_size": 2,
      "embedding_learning_rate": 1e-05,
      "epochs": 2,
      "gradient_accumulation_steps": 8,
      "learning_rate": 5e-05,
      "max_steps": -1,
      "optimizer": "adamw_8bit",
      "scheduler": "linear",
      "trainer_seed": 42,
      "warmup_ratio": 0.1,
      "warmup_steps": 10,
      "weight_decay": 0.0
    },
    "lora": {
      "alpha": 32,
      "bias": "none",
      "dropout": 0,
      "gradient_checkpointing": "unsloth",
      "random_state": 3407,
      "rank": 128,
      "target_modules": [
        "q_proj",
        "k_proj",
        "v_proj",
        "o_proj",
        "gate_proj",
        "up_proj",
        "down_proj",
        "embed_tokens",
        "lm_head"
      ],
      "use_rslora": true
    },
    "model_loading": {
      "load_in_4bit": true,
      "max_sequence_length": 2048
    }
  },
  "upstream_revisions": {
    "base_model": {
      "note": "This immutable revision is the frozen reproduction contract selected on 2026-07-31. The historical run did not retain its resolved upstream commit, so this is not claimed to be the exact historical revision.",
      "repository": "unsloth/mistral-7b-v0.3",
      "revision": "9ea1b83f5ced5663c5fa89c300fe59f9bdcd2b10"
    },
    "continued_pretraining_dataset": {
      "configuration": "20231101.ko",
      "note": "This immutable revision is the frozen reproduction contract selected on 2026-07-31. The historical run did not retain its resolved upstream commit, so this is not claimed to be the exact historical revision.",
      "repository": "wikimedia/wikipedia",
      "revision": "b04c8d1ceb2f5cd4588862100d08de323dccfbaa"
    },
    "instruction_dataset": {
      "note": "This immutable revision is the frozen reproduction contract selected on 2026-07-31. The historical run did not retain its resolved upstream commit, so this is not claimed to be the exact historical revision.",
      "repository": "FreedomIntelligence/alpaca-gpt4-korean",
      "revision": "f38ae19cf673363d74fab6217de46c1b9c3150d4"
    }
  }
}