{
  "base_model": {
    "repository": "Qwen/Qwen3-0.6B",
    "revision": "c1899de289a04d12100db370d81485cdf75e47ca",
    "parameter_count": 596049920
  },
  "selected_checkpoint": "A1",
  "parent_checkpoint_step": 14833,
  "parent_training": {
    "seed": 42,
    "effective_batch": 32,
    "rank": 32,
    "alpha": 64,
    "dropout": 0.05,
    "target_modules": [
      "q_proj",
      "k_proj",
      "v_proj",
      "o_proj",
      "gate_proj",
      "up_proj",
      "down_proj"
    ],
    "rows": 474635,
    "peak_learning_rate": 0.0002,
    "updates": 14833,
    "warmup_updates": 742,
    "optimizer": "AdamW",
    "betas": [
      0.9,
      0.999
    ],
    "epsilon": 1e-08,
    "weight_decay": 0.0,
    "schedule": "linear warmup then cosine decay",
    "base_dtype": "bfloat16",
    "trainable_adapter_dtype": "float32",
    "max_sequence_tokens": 2048,
    "assistant_only_loss": true,
    "length_bucketed": true,
    "prompt_file": "training-system-prompt.txt",
    "prompt_sha256": "80e46c8e196e108ea50420d1c7b0b28d9aa07a2df1ccbf49ebd63d466c4a37f5",
    "epochs": 1,
    "example_order": "shuffled length buckets; one complete weighted epoch"
  },
  "continuation": {
    "seed": 23042,
    "effective_batch": 32,
    "rank": 32,
    "alpha": 64,
    "dropout": 0.05,
    "target_modules": [
      "q_proj",
      "k_proj",
      "v_proj",
      "o_proj",
      "gate_proj",
      "up_proj",
      "down_proj"
    ],
    "rows": 2564,
    "peak_learning_rate": 5e-06,
    "updates": 200,
    "warmup_updates": 10,
    "optimizer": "AdamW",
    "betas": [
      0.9,
      0.999
    ],
    "epsilon": 1e-08,
    "weight_decay": 0.0,
    "schedule": "linear warmup then cosine decay",
    "base_dtype": "bfloat16",
    "trainable_adapter_dtype": "float32",
    "max_sequence_tokens": 2048,
    "assistant_only_loss": true,
    "length_bucketed": false,
    "prompt_file": "system-prompt.txt",
    "prompt_sha256": "3a9028d5aebb73c3ed7363e63eb3e751689218775ea5572ab0dc6807e522238b",
    "repair_mix_fraction": 0.5,
    "example_order": "seeded family-aware shuffle; repair/replay cohorts without replacement within cycles"
  },
  "training_data_release": "dirac-run/ec-training-data",
  "data_release_is_deduplicated_union_not_exact_weighted_epoch": true,
  "training_examples_from_other_repairs_also_in_data_release": true,
  "full_fidelity_artifacts_in_this_repository": true,
  "merged_dtype": "bfloat16",
  "adapter_dtype": "float32",
  "adapter_subfolder": "adapter",
  "optimizer_and_rng_state_included": false,
  "merge": "FP32(original BF16 base) + (alpha/r) * FP32(B @ A), then BF16 rounding",
  "gguf_repository": "dirac-run/ec-0.6b-gguf",
  "source_adapter_sha256": "b437a3915987229f36143672073321209f9ee466eb18b654dcb61c5839d42683",
  "source_fp32_merge_sha256": "b90ae1f9db878f339f7f6b669c3f7f61bb042e33af1b1792c33e2dd5eb9867f9"
}