{
  "model": "Qwen2.5-0.5B-Instruct",
  "train_pairs": 259,
  "dev_eligible": 71,
  "test_eligible": 85,
  "test_pool": 100,
  "selected_epoch": 2,
  "selection": "best observed passing count on dev; earliest epoch if unknowns tie",
  "status_note": "error means execution unresolved after RemoteProtocolError and one retry; it is not counted as pass or fail and root cause was not established",
  "per_task": [
    {
      "id": 13,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 18,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "pass",
      "lora-no-feedback": "pass",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 21,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "pass",
      "lora-no-feedback": "pass",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 25,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "pass",
      "lora-no-feedback": "pass",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 30,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 32,
      "base-feedback": "pass",
      "base-no-feedback": "pass",
      "lora-feedback": "pass",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 37,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 42,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 48,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 72,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 73,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 77,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 83,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 85,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "pass"
    },
    {
      "id": 86,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 88,
      "base-feedback": "fail",
      "base-no-feedback": "pass",
      "lora-feedback": "pass",
      "lora-no-feedback": "pass",
      "nofb-trained-feedback": "pass",
      "nofb-trained-no-feedback": "pass"
    },
    {
      "id": 100,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "pass",
      "nofb-trained-no-feedback": "error"
    },
    {
      "id": 106,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 126,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "pass",
      "lora-no-feedback": "pass",
      "nofb-trained-feedback": "pass",
      "nofb-trained-no-feedback": "pass"
    },
    {
      "id": 131,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "pass",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 134,
      "base-feedback": "fail",
      "base-no-feedback": "pass",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 138,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 144,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "pass",
      "nofb-trained-no-feedback": "pass"
    },
    {
      "id": 152,
      "base-feedback": "fail",
      "base-no-feedback": "error",
      "lora-feedback": "pass",
      "lora-no-feedback": "pass",
      "nofb-trained-feedback": "pass",
      "nofb-trained-no-feedback": "pass"
    },
    {
      "id": 155,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 156,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 165,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 166,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 169,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 171,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "pass",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 178,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 188,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 195,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "pass",
      "lora-no-feedback": "pass",
      "nofb-trained-feedback": "pass",
      "nofb-trained-no-feedback": "pass"
    },
    {
      "id": 199,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "pass",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 203,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 207,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 211,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "error",
      "lora-no-feedback": "pass",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 219,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 223,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "pass",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 235,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 256,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 259,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 264,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 272,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "pass"
    },
    {
      "id": 275,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 276,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 277,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 280,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "pass",
      "lora-no-feedback": "pass",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 300,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 302,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "pass",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 305,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 324,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 326,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 328,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 331,
      "base-feedback": "pass",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "pass",
      "nofb-trained-no-feedback": "pass"
    },
    {
      "id": 348,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 351,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "pass",
      "lora-no-feedback": "pass",
      "nofb-trained-feedback": "pass",
      "nofb-trained-no-feedback": "pass"
    },
    {
      "id": 352,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "pass",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 353,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 365,
      "base-feedback": "pass",
      "base-no-feedback": "pass",
      "lora-feedback": "fail",
      "lora-no-feedback": "pass",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 381,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "pass",
      "nofb-trained-no-feedback": "pass"
    },
    {
      "id": 383,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 385,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 392,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 393,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 407,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 409,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "pass",
      "lora-no-feedback": "pass",
      "nofb-trained-feedback": "pass",
      "nofb-trained-no-feedback": "pass"
    },
    {
      "id": 417,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 421,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 428,
      "base-feedback": "pass",
      "base-no-feedback": "pass",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 430,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 453,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 457,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "pass",
      "lora-no-feedback": "pass",
      "nofb-trained-feedback": "pass",
      "nofb-trained-no-feedback": "pass"
    },
    {
      "id": 461,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 464,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "pass",
      "lora-no-feedback": "pass",
      "nofb-trained-feedback": "pass",
      "nofb-trained-no-feedback": "pass"
    },
    {
      "id": 468,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 476,
      "base-feedback": "pass",
      "base-no-feedback": "pass",
      "lora-feedback": "pass",
      "lora-no-feedback": "pass",
      "nofb-trained-feedback": "pass",
      "nofb-trained-no-feedback": "pass"
    },
    {
      "id": 482,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "pass",
      "lora-no-feedback": "pass",
      "nofb-trained-feedback": "pass",
      "nofb-trained-no-feedback": "pass"
    },
    {
      "id": 483,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "error",
      "nofb-trained-no-feedback": "error"
    },
    {
      "id": 486,
      "base-feedback": "fail",
      "base-no-feedback": "pass",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 488,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 492,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "pass",
      "lora-no-feedback": "pass",
      "nofb-trained-feedback": "pass",
      "nofb-trained-no-feedback": "pass"
    },
    {
      "id": 495,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "pass",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 496,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    },
    {
      "id": 506,
      "base-feedback": "fail",
      "base-no-feedback": "fail",
      "lora-feedback": "fail",
      "lora-no-feedback": "fail",
      "nofb-trained-feedback": "fail",
      "nofb-trained-no-feedback": "fail"
    }
  ],
  "no_feedback_training_control": {
    "train_pairs": 259,
    "dev_selected_epoch": 3,
    "dev_pass": 16,
    "dev_total": 71,
    "test_results": "same eligible 85 tasks",
    "note": "same data and labels; error details replaced during training; post-hoc exploratory control; selected checkpoint has 777 optimizer steps versus 518 for feedback-trained checkpoint"
  }
}
