{
  "note": "bash-sft-04",
  "date_published": "2026-09-02",
  "status": "research note, not a paper",
  "ship": false,
  "kept_checkpoint": {
    "label": "last40-wd01",
    "locked_pass": 92,
    "locked_n": 98,
    "non_newest_pass": 88,
    "non_newest_n": 94,
    "newest_pass": 4,
    "newest_n": 4,
    "unpublished_weights_sha256": "b3558c0f140a659f0c661bf9795ed59049cdfed5db42c1e3e8e8480e8ad901b2"
  },
  "rejected_continuation": {
    "label": "shlex-v2-continue",
    "init": "last40-wd01",
    "train_rows": 2240,
    "val_rows": 117,
    "epochs": 1.0,
    "learning_rate": 1e-5,
    "lr_scheduler_type": "cosine",
    "weight_decay": 0.1,
    "max_length": 1024,
    "seed": 42,
    "train_loss": 0.7068098528044564,
    "eval_loss": 0.4751433730125427,
    "wall_clock_seconds": 58.97115007899998,
    "peak_gpu_memory_gib": 16.60340404510498,
    "gpu": "NVIDIA RTX 6000 Ada Generation",
    "droplet_id": "597095105",
    "droplet_deleted_after_pull": true,
    "unpublished_weights_sha256": "303275de21da76fa08a9f602ba033e9e34ce44253031080ec1283caabdd80cf9",
    "weights_bytes": 3087467144
  },
  "scores": {
    "arm0_v1_original_pass": 92,
    "arm0_v1_envelope_pass": 86,
    "continue_v1_original_pass": 82,
    "continue_v1_envelope_pass": 84,
    "arm0_locked_hard_pass": 2,
    "continue_locked_hard_pass": 2,
    "locked_hard_n": 27,
    "continue_non_newest_pass": 81,
    "continue_newest_pass": 1
  }
}