{
  "experiment": "factor_recombination_ladder",
  "model_id": "Qwen/Qwen2.5-Coder-3B-Instruct",
  "revision": "488639f1ff808d1d3d0ba301aef8c11461451ec5",
  "max_new_tokens": 256,
  "max_records": null,
  "suite": "all",
  "jobs": [
    {
      "suite": "core",
      "name": "frozen_trace",
      "split": "seen_iid",
      "condition": "trace",
      "adapter": null,
      "data": "/workspace/experiments/factor_recombination_ladder/data/repair_val_seen_iid.jsonl",
      "output": "/workspace/experiments/factor_recombination_ladder/reports/final/core__frozen_trace__seen_iid.json",
      "command": [
        "/usr/local/bin/python",
        "/workspace/experiments/factor_recombination_ladder/scripts/eval_ladder.py",
        "--data",
        "/workspace/experiments/factor_recombination_ladder/data/repair_val_seen_iid.jsonl",
        "--output",
        "/workspace/experiments/factor_recombination_ladder/reports/final/core__frozen_trace__seen_iid.json",
        "--condition",
        "trace",
        "--model-id",
        "Qwen/Qwen2.5-Coder-3B-Instruct",
        "--revision",
        "488639f1ff808d1d3d0ba301aef8c11461451ec5",
        "--max-new-tokens",
        "256"
      ],
      "status": "completed",
      "started_at": 1782061149.7630968,
      "finished_at": 1782061320.5922377,
      "runtime_seconds": 170.829
    },
    {
      "suite": "core",
      "name": "frozen_trace",
      "split": "format_shift",
      "condition": "trace",
      "adapter": null,
      "data": "/workspace/experiments/factor_recombination_ladder/data/repair_val_format_shift.jsonl",
      "output": "/workspace/experiments/factor_recombination_ladder/reports/final/core__frozen_trace__format_shift.json",
      "command": [
        "/usr/local/bin/python",
        "/workspace/experiments/factor_recombination_ladder/scripts/eval_ladder.py",
        "--data",
        "/workspace/experiments/factor_recombination_ladder/data/repair_val_format_shift.jsonl",
        "--output",
        "/workspace/experiments/factor_recombination_ladder/reports/final/core__frozen_trace__format_shift.json",
        "--condition",
        "trace",
        "--model-id",
        "Qwen/Qwen2.5-Coder-3B-Instruct",
        "--revision",
        "488639f1ff808d1d3d0ba301aef8c11461451ec5",
        "--max-new-tokens",
        "256"
      ],
      "status": "completed",
      "started_at": 1782061320.5931928,
      "finished_at": 1782061489.9837859,
      "runtime_seconds": 169.391
    },
    {
      "suite": "core",
      "name": "frozen_trace",
      "split": "recombination_holdout",
      "condition": "trace",
      "adapter": null,
      "data": "/workspace/experiments/factor_recombination_ladder/data/repair_val_recombination_holdout.jsonl",
      "output": "/workspace/experiments/factor_recombination_ladder/reports/final/core__frozen_trace__recombination_holdout.json",
      "command": [
        "/usr/local/bin/python",
        "/workspace/experiments/factor_recombination_ladder/scripts/eval_ladder.py",
        "--data",
        "/workspace/experiments/factor_recombination_ladder/data/repair_val_recombination_holdout.jsonl",
        "--output",
        "/workspace/experiments/factor_recombination_ladder/reports/final/core__frozen_trace__recombination_holdout.json",
        "--condition",
        "trace",
        "--model-id",
        "Qwen/Qwen2.5-Coder-3B-Instruct",
        "--revision",
        "488639f1ff808d1d3d0ba301aef8c11461451ec5",
        "--max-new-tokens",
        "256"
      ],
      "status": "completed",
      "started_at": 1782061489.9845588,
      "finished_at": 1782061837.13284,
      "runtime_seconds": 347.148
    },
    {
      "suite": "core",
      "name": "ladder_trace",
      "split": "seen_iid",
      "condition": "trace",
      "adapter": "/workspace/large_artifacts/factor_recombination_ladder/models/ladder_trace_lora",
      "data": "/workspace/experiments/factor_recombination_ladder/data/repair_val_seen_iid.jsonl",
      "output": "/workspace/experiments/factor_recombination_ladder/reports/final/core__ladder_trace__seen_iid.json",
      "command": [
        "/usr/local/bin/python",
        "/workspace/experiments/factor_recombination_ladder/scripts/eval_ladder.py",
        "--data",
        "/workspace/experiments/factor_recombination_ladder/data/repair_val_seen_iid.jsonl",
        "--output",
        "/workspace/experiments/factor_recombination_ladder/reports/final/core__ladder_trace__seen_iid.json",
        "--condition",
        "trace",
        "--model-id",
        "Qwen/Qwen2.5-Coder-3B-Instruct",
        "--revision",
        "488639f1ff808d1d3d0ba301aef8c11461451ec5",
        "--max-new-tokens",
        "256",
        "--adapter",
        "/workspace/large_artifacts/factor_recombination_ladder/models/ladder_trace_lora"
      ],
      "status": "completed",
      "started_at": 1782061837.1339333,
      "finished_at": 1782062135.4888463,
      "runtime_seconds": 298.355
    },
    {
      "suite": "core",
      "name": "ladder_trace",
      "split": "format_shift",
      "condition": "trace",
      "adapter": "/workspace/large_artifacts/factor_recombination_ladder/models/ladder_trace_lora",
      "data": "/workspace/experiments/factor_recombination_ladder/data/repair_val_format_shift.jsonl",
      "output": "/workspace/experiments/factor_recombination_ladder/reports/final/core__ladder_trace__format_shift.json",
      "command": [
        "/usr/local/bin/python",
        "/workspace/experiments/factor_recombination_ladder/scripts/eval_ladder.py",
        "--data",
        "/workspace/experiments/factor_recombination_ladder/data/repair_val_format_shift.jsonl",
        "--output",
        "/workspace/experiments/factor_recombination_ladder/reports/final/core__ladder_trace__format_shift.json",
        "--condition",
        "trace",
        "--model-id",
        "Qwen/Qwen2.5-Coder-3B-Instruct",
        "--revision",
        "488639f1ff808d1d3d0ba301aef8c11461451ec5",
        "--max-new-tokens",
        "256",
        "--adapter",
        "/workspace/large_artifacts/factor_recombination_ladder/models/ladder_trace_lora"
      ],
      "status": "completed",
      "started_at": 1782062135.4898653,
      "finished_at": 1782062435.3528948,
      "runtime_seconds": 299.863
    },
    {
      "suite": "core",
      "name": "ladder_trace",
      "split": "recombination_holdout",
      "condition": "trace",
      "adapter": "/workspace/large_artifacts/factor_recombination_ladder/models/ladder_trace_lora",
      "data": "/workspace/experiments/factor_recombination_ladder/data/repair_val_recombination_holdout.jsonl",
      "output": "/workspace/experiments/factor_recombination_ladder/reports/final/core__ladder_trace__recombination_holdout.json",
      "command": [
        "/usr/local/bin/python",
        "/workspace/experiments/factor_recombination_ladder/scripts/eval_ladder.py",
        "--data",
        "/workspace/experiments/factor_recombination_ladder/data/repair_val_recombination_holdout.jsonl",
        "--output",
        "/workspace/experiments/factor_recombination_ladder/reports/final/core__ladder_trace__recombination_holdout.json",
        "--condition",
        "trace",
        "--model-id",
        "Qwen/Qwen2.5-Coder-3B-Instruct",
        "--revision",
        "488639f1ff808d1d3d0ba301aef8c11461451ec5",
        "--max-new-tokens",
        "256",
        "--adapter",
        "/workspace/large_artifacts/factor_recombination_ladder/models/ladder_trace_lora"
      ],
      "status": "completed",
      "started_at": 1782062435.353965,
      "finished_at": 1782063161.9647465,
      "runtime_seconds": 726.611
    },
    {
      "suite": "core",
      "name": "ladder_no_trace",
      "split": "seen_iid",
      "condition": "no_trace",
      "adapter": "/workspace/large_artifacts/factor_recombination_ladder/models/ladder_no_trace_lora",
      "data": "/workspace/experiments/factor_recombination_ladder/data/repair_val_seen_iid.jsonl",
      "output": "/workspace/experiments/factor_recombination_ladder/reports/final/core__ladder_no_trace__seen_iid.json",
      "command": [
        "/usr/local/bin/python",
        "/workspace/experiments/factor_recombination_ladder/scripts/eval_ladder.py",
        "--data",
        "/workspace/experiments/factor_recombination_ladder/data/repair_val_seen_iid.jsonl",
        "--output",
        "/workspace/experiments/factor_recombination_ladder/reports/final/core__ladder_no_trace__seen_iid.json",
        "--condition",
        "no_trace",
        "--model-id",
        "Qwen/Qwen2.5-Coder-3B-Instruct",
        "--revision",
        "488639f1ff808d1d3d0ba301aef8c11461451ec5",
        "--max-new-tokens",
        "256",
        "--adapter",
        "/workspace/large_artifacts/factor_recombination_ladder/models/ladder_no_trace_lora"
      ],
      "status": "completed",
      "started_at": 1782063161.9657657,
      "finished_at": 1782063454.4799206,
      "runtime_seconds": 292.514
    },
    {
      "suite": "core",
      "name": "ladder_no_trace",
      "split": "format_shift",
      "condition": "no_trace",
      "adapter": "/workspace/large_artifacts/factor_recombination_ladder/models/ladder_no_trace_lora",
      "data": "/workspace/experiments/factor_recombination_ladder/data/repair_val_format_shift.jsonl",
      "output": "/workspace/experiments/factor_recombination_ladder/reports/final/core__ladder_no_trace__format_shift.json",
      "command": [
        "/usr/local/bin/python",
        "/workspace/experiments/factor_recombination_ladder/scripts/eval_ladder.py",
        "--data",
        "/workspace/experiments/factor_recombination_ladder/data/repair_val_format_shift.jsonl",
        "--output",
        "/workspace/experiments/factor_recombination_ladder/reports/final/core__ladder_no_trace__format_shift.json",
        "--condition",
        "no_trace",
        "--model-id",
        "Qwen/Qwen2.5-Coder-3B-Instruct",
        "--revision",
        "488639f1ff808d1d3d0ba301aef8c11461451ec5",
        "--max-new-tokens",
        "256",
        "--adapter",
        "/workspace/large_artifacts/factor_recombination_ladder/models/ladder_no_trace_lora"
      ],
      "status": "completed",
      "started_at": 1782063454.4811666,
      "finished_at": 1782063750.4811807,
      "runtime_seconds": 296.0
    },
    {
      "suite": "core",
      "name": "ladder_no_trace",
      "split": "recombination_holdout",
      "condition": "no_trace",
      "adapter": "/workspace/large_artifacts/factor_recombination_ladder/models/ladder_no_trace_lora",
      "data": "/workspace/experiments/factor_recombination_ladder/data/repair_val_recombination_holdout.jsonl",
      "output": "/workspace/experiments/factor_recombination_ladder/reports/final/core__ladder_no_trace__recombination_holdout.json",
      "command": [
        "/usr/local/bin/python",
        "/workspace/experiments/factor_recombination_ladder/scripts/eval_ladder.py",
        "--data",
        "/workspace/experiments/factor_recombination_ladder/data/repair_val_recombination_holdout.jsonl",
        "--output",
        "/workspace/experiments/factor_recombination_ladder/reports/final/core__ladder_no_trace__recombination_holdout.json",
        "--condition",
        "no_trace",
        "--model-id",
        "Qwen/Qwen2.5-Coder-3B-Instruct",
        "--revision",
        "488639f1ff808d1d3d0ba301aef8c11461451ec5",
        "--max-new-tokens",
        "256",
        "--adapter",
        "/workspace/large_artifacts/factor_recombination_ladder/models/ladder_no_trace_lora"
      ],
      "status": "completed",
      "started_at": 1782063750.4824378,
      "finished_at": 1782064470.6342967,
      "runtime_seconds": 720.152
    },
    {
      "suite": "core",
      "name": "ladder_shuffled_trace",
      "split": "seen_iid",
      "condition": "trace",
      "adapter": "/workspace/large_artifacts/factor_recombination_ladder/models/ladder_shuffled_trace_lora",
      "data": "/workspace/experiments/factor_recombination_ladder/data/repair_val_seen_iid.jsonl",
      "output": "/workspace/experiments/factor_recombination_ladder/reports/final/core__ladder_shuffled_trace__seen_iid.json",
      "command": [
        "/usr/local/bin/python",
        "/workspace/experiments/factor_recombination_ladder/scripts/eval_ladder.py",
        "--data",
        "/workspace/experiments/factor_recombination_ladder/data/repair_val_seen_iid.jsonl",
        "--output",
        "/workspace/experiments/factor_recombination_ladder/reports/final/core__ladder_shuffled_trace__seen_iid.json",
        "--condition",
        "trace",
        "--model-id",
        "Qwen/Qwen2.5-Coder-3B-Instruct",
        "--revision",
        "488639f1ff808d1d3d0ba301aef8c11461451ec5",
        "--max-new-tokens",
        "256",
        "--adapter",
        "/workspace/large_artifacts/factor_recombination_ladder/models/ladder_shuffled_trace_lora"
      ],
      "status": "completed",
      "started_at": 1782064470.6354291,
      "finished_at": 1782064773.0381799,
      "runtime_seconds": 302.403
    },
    {
      "suite": "core",
      "name": "ladder_shuffled_trace",
      "split": "format_shift",
      "condition": "trace",
      "adapter": "/workspace/large_artifacts/factor_recombination_ladder/models/ladder_shuffled_trace_lora",
      "data": "/workspace/experiments/factor_recombination_ladder/data/repair_val_format_shift.jsonl",
      "output": "/workspace/experiments/factor_recombination_ladder/reports/final/core__ladder_shuffled_trace__format_shift.json",
      "command": [
        "/usr/local/bin/python",
        "/workspace/experiments/factor_recombination_ladder/scripts/eval_ladder.py",
        "--data",
        "/workspace/experiments/factor_recombination_ladder/data/repair_val_format_shift.jsonl",
        "--output",
        "/workspace/experiments/factor_recombination_ladder/reports/final/core__ladder_shuffled_trace__format_shift.json",
        "--condition",
        "trace",
        "--model-id",
        "Qwen/Qwen2.5-Coder-3B-Instruct",
        "--revision",
        "488639f1ff808d1d3d0ba301aef8c11461451ec5",
        "--max-new-tokens",
        "256",
        "--adapter",
        "/workspace/large_artifacts/factor_recombination_ladder/models/ladder_shuffled_trace_lora"
      ],
      "status": "completed",
      "started_at": 1782064773.0397005,
      "finished_at": 1782065068.730292,
      "runtime_seconds": 295.691
    },
    {
      "suite": "core",
      "name": "ladder_shuffled_trace",
      "split": "recombination_holdout",
      "condition": "trace",
      "adapter": "/workspace/large_artifacts/factor_recombination_ladder/models/ladder_shuffled_trace_lora",
      "data": "/workspace/experiments/factor_recombination_ladder/data/repair_val_recombination_holdout.jsonl",
      "output": "/workspace/experiments/factor_recombination_ladder/reports/final/core__ladder_shuffled_trace__recombination_holdout.json",
      "command": [
        "/usr/local/bin/python",
        "/workspace/experiments/factor_recombination_ladder/scripts/eval_ladder.py",
        "--data",
        "/workspace/experiments/factor_recombination_ladder/data/repair_val_recombination_holdout.jsonl",
        "--output",
        "/workspace/experiments/factor_recombination_ladder/reports/final/core__ladder_shuffled_trace__recombination_holdout.json",
        "--condition",
        "trace",
        "--model-id",
        "Qwen/Qwen2.5-Coder-3B-Instruct",
        "--revision",
        "488639f1ff808d1d3d0ba301aef8c11461451ec5",
        "--max-new-tokens",
        "256",
        "--adapter",
        "/workspace/large_artifacts/factor_recombination_ladder/models/ladder_shuffled_trace_lora"
      ],
      "status": "completed",
      "started_at": 1782065068.7313035,
      "finished_at": 1782065775.9480278,
      "runtime_seconds": 707.217
    },
    {
      "suite": "core",
      "name": "labelled_trace",
      "split": "seen_iid",
      "condition": "trace",
      "adapter": "/workspace/large_artifacts/factor_recombination_ladder/models/labelled_trace_lora",
      "data": "/workspace/experiments/factor_recombination_ladder/data/repair_val_seen_iid_labelled.jsonl",
      "output": "/workspace/experiments/factor_recombination_ladder/reports/final/core__labelled_trace__seen_iid.json",
      "command": [
        "/usr/local/bin/python",
        "/workspace/experiments/factor_recombination_ladder/scripts/eval_ladder.py",
        "--data",
        "/workspace/experiments/factor_recombination_ladder/data/repair_val_seen_iid_labelled.jsonl",
        "--output",
        "/workspace/experiments/factor_recombination_ladder/reports/final/core__labelled_trace__seen_iid.json",
        "--condition",
        "trace",
        "--model-id",
        "Qwen/Qwen2.5-Coder-3B-Instruct",
        "--revision",
        "488639f1ff808d1d3d0ba301aef8c11461451ec5",
        "--max-new-tokens",
        "256",
        "--adapter",
        "/workspace/large_artifacts/factor_recombination_ladder/models/labelled_trace_lora"
      ],
      "status": "completed",
      "started_at": 1782065775.9490652,
      "finished_at": 1782066073.5960262,
      "runtime_seconds": 297.647
    },
    {
      "suite": "core",
      "name": "labelled_trace",
      "split": "format_shift",
      "condition": "trace",
      "adapter": "/workspace/large_artifacts/factor_recombination_ladder/models/labelled_trace_lora",
      "data": "/workspace/experiments/factor_recombination_ladder/data/repair_val_format_shift_labelled.jsonl",
      "output": "/workspace/experiments/factor_recombination_ladder/reports/final/core__labelled_trace__format_shift.json",
      "command": [
        "/usr/local/bin/python",
        "/workspace/experiments/factor_recombination_ladder/scripts/eval_ladder.py",
        "--data",
        "/workspace/experiments/factor_recombination_ladder/data/repair_val_format_shift_labelled.jsonl",
        "--output",
        "/workspace/experiments/factor_recombination_ladder/reports/final/core__labelled_trace__format_shift.json",
        "--condition",
        "trace",
        "--model-id",
        "Qwen/Qwen2.5-Coder-3B-Instruct",
        "--revision",
        "488639f1ff808d1d3d0ba301aef8c11461451ec5",
        "--max-new-tokens",
        "256",
        "--adapter",
        "/workspace/large_artifacts/factor_recombination_ladder/models/labelled_trace_lora"
      ],
      "status": "completed",
      "started_at": 1782066073.5977829,
      "finished_at": 1782066373.9173322,
      "runtime_seconds": 300.32
    },
    {
      "suite": "core",
      "name": "labelled_trace",
      "split": "recombination_holdout",
      "condition": "trace",
      "adapter": "/workspace/large_artifacts/factor_recombination_ladder/models/labelled_trace_lora",
      "data": "/workspace/experiments/factor_recombination_ladder/data/repair_val_recombination_holdout_labelled.jsonl",
      "output": "/workspace/experiments/factor_recombination_ladder/reports/final/core__labelled_trace__recombination_holdout.json",
      "command": [
        "/usr/local/bin/python",
        "/workspace/experiments/factor_recombination_ladder/scripts/eval_ladder.py",
        "--data",
        "/workspace/experiments/factor_recombination_ladder/data/repair_val_recombination_holdout_labelled.jsonl",
        "--output",
        "/workspace/experiments/factor_recombination_ladder/reports/final/core__labelled_trace__recombination_holdout.json",
        "--condition",
        "trace",
        "--model-id",
        "Qwen/Qwen2.5-Coder-3B-Instruct",
        "--revision",
        "488639f1ff808d1d3d0ba301aef8c11461451ec5",
        "--max-new-tokens",
        "256",
        "--adapter",
        "/workspace/large_artifacts/factor_recombination_ladder/models/labelled_trace_lora"
      ],
      "status": "completed",
      "started_at": 1782066373.9187138,
      "finished_at": 1782067059.7678633,
      "runtime_seconds": 685.849
    },
    {
      "suite": "ablation",
      "name": "ladder_trace_no_trace_prompt",
      "split": "seen_iid",
      "condition": "no_trace",
      "adapter": "/workspace/large_artifacts/factor_recombination_ladder/models/ladder_trace_lora",
      "data": "/workspace/experiments/factor_recombination_ladder/data/repair_val_seen_iid.jsonl",
      "output": "/workspace/experiments/factor_recombination_ladder/reports/final/ablation__ladder_trace_no_trace_prompt__seen_iid.json",
      "command": [
        "/usr/local/bin/python",
        "/workspace/experiments/factor_recombination_ladder/scripts/eval_ladder.py",
        "--data",
        "/workspace/experiments/factor_recombination_ladder/data/repair_val_seen_iid.jsonl",
        "--output",
        "/workspace/experiments/factor_recombination_ladder/reports/final/ablation__ladder_trace_no_trace_prompt__seen_iid.json",
        "--condition",
        "no_trace",
        "--model-id",
        "Qwen/Qwen2.5-Coder-3B-Instruct",
        "--revision",
        "488639f1ff808d1d3d0ba301aef8c11461451ec5",
        "--max-new-tokens",
        "256",
        "--adapter",
        "/workspace/large_artifacts/factor_recombination_ladder/models/ladder_trace_lora"
      ],
      "status": "completed",
      "started_at": 1782067059.7695916,
      "finished_at": 1782067361.1903079,
      "runtime_seconds": 301.421
    },
    {
      "suite": "ablation",
      "name": "ladder_trace_no_trace_prompt",
      "split": "format_shift",
      "condition": "no_trace",
      "adapter": "/workspace/large_artifacts/factor_recombination_ladder/models/ladder_trace_lora",
      "data": "/workspace/experiments/factor_recombination_ladder/data/repair_val_format_shift.jsonl",
      "output": "/workspace/experiments/factor_recombination_ladder/reports/final/ablation__ladder_trace_no_trace_prompt__format_shift.json",
      "command": [
        "/usr/local/bin/python",
        "/workspace/experiments/factor_recombination_ladder/scripts/eval_ladder.py",
        "--data",
        "/workspace/experiments/factor_recombination_ladder/data/repair_val_format_shift.jsonl",
        "--output",
        "/workspace/experiments/factor_recombination_ladder/reports/final/ablation__ladder_trace_no_trace_prompt__format_shift.json",
        "--condition",
        "no_trace",
        "--model-id",
        "Qwen/Qwen2.5-Coder-3B-Instruct",
        "--revision",
        "488639f1ff808d1d3d0ba301aef8c11461451ec5",
        "--max-new-tokens",
        "256",
        "--adapter",
        "/workspace/large_artifacts/factor_recombination_ladder/models/ladder_trace_lora"
      ],
      "status": "completed",
      "started_at": 1782067361.1920936,
      "finished_at": 1782067672.799909,
      "runtime_seconds": 311.608
    },
    {
      "suite": "ablation",
      "name": "ladder_trace_no_trace_prompt",
      "split": "recombination_holdout",
      "condition": "no_trace",
      "adapter": "/workspace/large_artifacts/factor_recombination_ladder/models/ladder_trace_lora",
      "data": "/workspace/experiments/factor_recombination_ladder/data/repair_val_recombination_holdout.jsonl",
      "output": "/workspace/experiments/factor_recombination_ladder/reports/final/ablation__ladder_trace_no_trace_prompt__recombination_holdout.json",
      "command": [
        "/usr/local/bin/python",
        "/workspace/experiments/factor_recombination_ladder/scripts/eval_ladder.py",
        "--data",
        "/workspace/experiments/factor_recombination_ladder/data/repair_val_recombination_holdout.jsonl",
        "--output",
        "/workspace/experiments/factor_recombination_ladder/reports/final/ablation__ladder_trace_no_trace_prompt__recombination_holdout.json",
        "--condition",
        "no_trace",
        "--model-id",
        "Qwen/Qwen2.5-Coder-3B-Instruct",
        "--revision",
        "488639f1ff808d1d3d0ba301aef8c11461451ec5",
        "--max-new-tokens",
        "256",
        "--adapter",
        "/workspace/large_artifacts/factor_recombination_ladder/models/ladder_trace_lora"
      ],
      "status": "completed",
      "started_at": 1782067672.801898,
      "finished_at": 1782068344.133274,
      "runtime_seconds": 671.331
    },
    {
      "suite": "ablation",
      "name": "ladder_trace_shuffled_trace_prompt",
      "split": "seen_iid",
      "condition": "shuffled_trace",
      "adapter": "/workspace/large_artifacts/factor_recombination_ladder/models/ladder_trace_lora",
      "data": "/workspace/experiments/factor_recombination_ladder/data/repair_val_seen_iid.jsonl",
      "output": "/workspace/experiments/factor_recombination_ladder/reports/final/ablation__ladder_trace_shuffled_trace_prompt__seen_iid.json",
      "command": [
        "/usr/local/bin/python",
        "/workspace/experiments/factor_recombination_ladder/scripts/eval_ladder.py",
        "--data",
        "/workspace/experiments/factor_recombination_ladder/data/repair_val_seen_iid.jsonl",
        "--output",
        "/workspace/experiments/factor_recombination_ladder/reports/final/ablation__ladder_trace_shuffled_trace_prompt__seen_iid.json",
        "--condition",
        "shuffled_trace",
        "--model-id",
        "Qwen/Qwen2.5-Coder-3B-Instruct",
        "--revision",
        "488639f1ff808d1d3d0ba301aef8c11461451ec5",
        "--max-new-tokens",
        "256",
        "--adapter",
        "/workspace/large_artifacts/factor_recombination_ladder/models/ladder_trace_lora"
      ],
      "status": "completed",
      "started_at": 1782068344.1351874,
      "finished_at": 1782068643.0699136,
      "runtime_seconds": 298.935
    },
    {
      "suite": "ablation",
      "name": "ladder_trace_shuffled_trace_prompt",
      "split": "format_shift",
      "condition": "shuffled_trace",
      "adapter": "/workspace/large_artifacts/factor_recombination_ladder/models/ladder_trace_lora",
      "data": "/workspace/experiments/factor_recombination_ladder/data/repair_val_format_shift.jsonl",
      "output": "/workspace/experiments/factor_recombination_ladder/reports/final/ablation__ladder_trace_shuffled_trace_prompt__format_shift.json",
      "command": [
        "/usr/local/bin/python",
        "/workspace/experiments/factor_recombination_ladder/scripts/eval_ladder.py",
        "--data",
        "/workspace/experiments/factor_recombination_ladder/data/repair_val_format_shift.jsonl",
        "--output",
        "/workspace/experiments/factor_recombination_ladder/reports/final/ablation__ladder_trace_shuffled_trace_prompt__format_shift.json",
        "--condition",
        "shuffled_trace",
        "--model-id",
        "Qwen/Qwen2.5-Coder-3B-Instruct",
        "--revision",
        "488639f1ff808d1d3d0ba301aef8c11461451ec5",
        "--max-new-tokens",
        "256",
        "--adapter",
        "/workspace/large_artifacts/factor_recombination_ladder/models/ladder_trace_lora"
      ],
      "status": "completed",
      "started_at": 1782068643.0712097,
      "finished_at": 1782068944.1270254,
      "runtime_seconds": 301.056
    },
    {
      "suite": "ablation",
      "name": "ladder_trace_shuffled_trace_prompt",
      "split": "recombination_holdout",
      "condition": "shuffled_trace",
      "adapter": "/workspace/large_artifacts/factor_recombination_ladder/models/ladder_trace_lora",
      "data": "/workspace/experiments/factor_recombination_ladder/data/repair_val_recombination_holdout.jsonl",
      "output": "/workspace/experiments/factor_recombination_ladder/reports/final/ablation__ladder_trace_shuffled_trace_prompt__recombination_holdout.json",
      "command": [
        "/usr/local/bin/python",
        "/workspace/experiments/factor_recombination_ladder/scripts/eval_ladder.py",
        "--data",
        "/workspace/experiments/factor_recombination_ladder/data/repair_val_recombination_holdout.jsonl",
        "--output",
        "/workspace/experiments/factor_recombination_ladder/reports/final/ablation__ladder_trace_shuffled_trace_prompt__recombination_holdout.json",
        "--condition",
        "shuffled_trace",
        "--model-id",
        "Qwen/Qwen2.5-Coder-3B-Instruct",
        "--revision",
        "488639f1ff808d1d3d0ba301aef8c11461451ec5",
        "--max-new-tokens",
        "256",
        "--adapter",
        "/workspace/large_artifacts/factor_recombination_ladder/models/ladder_trace_lora"
      ],
      "status": "completed",
      "started_at": 1782068944.128465,
      "finished_at": 1782069658.740786,
      "runtime_seconds": 714.612
    },
    {
      "suite": "ablation",
      "name": "labelled_trace_labels_removed",
      "split": "seen_iid",
      "condition": "trace",
      "adapter": "/workspace/large_artifacts/factor_recombination_ladder/models/labelled_trace_lora",
      "data": "/workspace/experiments/factor_recombination_ladder/data/repair_val_seen_iid.jsonl",
      "output": "/workspace/experiments/factor_recombination_ladder/reports/final/ablation__labelled_trace_labels_removed__seen_iid.json",
      "command": [
        "/usr/local/bin/python",
        "/workspace/experiments/factor_recombination_ladder/scripts/eval_ladder.py",
        "--data",
        "/workspace/experiments/factor_recombination_ladder/data/repair_val_seen_iid.jsonl",
        "--output",
        "/workspace/experiments/factor_recombination_ladder/reports/final/ablation__labelled_trace_labels_removed__seen_iid.json",
        "--condition",
        "trace",
        "--model-id",
        "Qwen/Qwen2.5-Coder-3B-Instruct",
        "--revision",
        "488639f1ff808d1d3d0ba301aef8c11461451ec5",
        "--max-new-tokens",
        "256",
        "--adapter",
        "/workspace/large_artifacts/factor_recombination_ladder/models/labelled_trace_lora"
      ],
      "status": "completed",
      "started_at": 1782069658.7428713,
      "finished_at": 1782069955.478625,
      "runtime_seconds": 296.736
    },
    {
      "suite": "ablation",
      "name": "labelled_trace_labels_removed",
      "split": "format_shift",
      "condition": "trace",
      "adapter": "/workspace/large_artifacts/factor_recombination_ladder/models/labelled_trace_lora",
      "data": "/workspace/experiments/factor_recombination_ladder/data/repair_val_format_shift.jsonl",
      "output": "/workspace/experiments/factor_recombination_ladder/reports/final/ablation__labelled_trace_labels_removed__format_shift.json",
      "command": [
        "/usr/local/bin/python",
        "/workspace/experiments/factor_recombination_ladder/scripts/eval_ladder.py",
        "--data",
        "/workspace/experiments/factor_recombination_ladder/data/repair_val_format_shift.jsonl",
        "--output",
        "/workspace/experiments/factor_recombination_ladder/reports/final/ablation__labelled_trace_labels_removed__format_shift.json",
        "--condition",
        "trace",
        "--model-id",
        "Qwen/Qwen2.5-Coder-3B-Instruct",
        "--revision",
        "488639f1ff808d1d3d0ba301aef8c11461451ec5",
        "--max-new-tokens",
        "256",
        "--adapter",
        "/workspace/large_artifacts/factor_recombination_ladder/models/labelled_trace_lora"
      ],
      "status": "completed",
      "started_at": 1782069955.4808207,
      "finished_at": 1782070250.979725,
      "runtime_seconds": 295.499
    },
    {
      "suite": "ablation",
      "name": "labelled_trace_labels_removed",
      "split": "recombination_holdout",
      "condition": "trace",
      "adapter": "/workspace/large_artifacts/factor_recombination_ladder/models/labelled_trace_lora",
      "data": "/workspace/experiments/factor_recombination_ladder/data/repair_val_recombination_holdout.jsonl",
      "output": "/workspace/experiments/factor_recombination_ladder/reports/final/ablation__labelled_trace_labels_removed__recombination_holdout.json",
      "command": [
        "/usr/local/bin/python",
        "/workspace/experiments/factor_recombination_ladder/scripts/eval_ladder.py",
        "--data",
        "/workspace/experiments/factor_recombination_ladder/data/repair_val_recombination_holdout.jsonl",
        "--output",
        "/workspace/experiments/factor_recombination_ladder/reports/final/ablation__labelled_trace_labels_removed__recombination_holdout.json",
        "--condition",
        "trace",
        "--model-id",
        "Qwen/Qwen2.5-Coder-3B-Instruct",
        "--revision",
        "488639f1ff808d1d3d0ba301aef8c11461451ec5",
        "--max-new-tokens",
        "256",
        "--adapter",
        "/workspace/large_artifacts/factor_recombination_ladder/models/labelled_trace_lora"
      ],
      "status": "completed",
      "started_at": 1782070250.9820485,
      "finished_at": 1782070960.2131915,
      "runtime_seconds": 709.231
    },
    {
      "suite": "ablation",
      "name": "labelled_trace_no_trace_prompt",
      "split": "seen_iid",
      "condition": "no_trace",
      "adapter": "/workspace/large_artifacts/factor_recombination_ladder/models/labelled_trace_lora",
      "data": "/workspace/experiments/factor_recombination_ladder/data/repair_val_seen_iid.jsonl",
      "output": "/workspace/experiments/factor_recombination_ladder/reports/final/ablation__labelled_trace_no_trace_prompt__seen_iid.json",
      "command": [
        "/usr/local/bin/python",
        "/workspace/experiments/factor_recombination_ladder/scripts/eval_ladder.py",
        "--data",
        "/workspace/experiments/factor_recombination_ladder/data/repair_val_seen_iid.jsonl",
        "--output",
        "/workspace/experiments/factor_recombination_ladder/reports/final/ablation__labelled_trace_no_trace_prompt__seen_iid.json",
        "--condition",
        "no_trace",
        "--model-id",
        "Qwen/Qwen2.5-Coder-3B-Instruct",
        "--revision",
        "488639f1ff808d1d3d0ba301aef8c11461451ec5",
        "--max-new-tokens",
        "256",
        "--adapter",
        "/workspace/large_artifacts/factor_recombination_ladder/models/labelled_trace_lora"
      ],
      "status": "completed",
      "started_at": 1782070960.215457,
      "finished_at": 1782071255.0382059,
      "runtime_seconds": 294.823
    },
    {
      "suite": "ablation",
      "name": "labelled_trace_no_trace_prompt",
      "split": "format_shift",
      "condition": "no_trace",
      "adapter": "/workspace/large_artifacts/factor_recombination_ladder/models/labelled_trace_lora",
      "data": "/workspace/experiments/factor_recombination_ladder/data/repair_val_format_shift.jsonl",
      "output": "/workspace/experiments/factor_recombination_ladder/reports/final/ablation__labelled_trace_no_trace_prompt__format_shift.json",
      "command": [
        "/usr/local/bin/python",
        "/workspace/experiments/factor_recombination_ladder/scripts/eval_ladder.py",
        "--data",
        "/workspace/experiments/factor_recombination_ladder/data/repair_val_format_shift.jsonl",
        "--output",
        "/workspace/experiments/factor_recombination_ladder/reports/final/ablation__labelled_trace_no_trace_prompt__format_shift.json",
        "--condition",
        "no_trace",
        "--model-id",
        "Qwen/Qwen2.5-Coder-3B-Instruct",
        "--revision",
        "488639f1ff808d1d3d0ba301aef8c11461451ec5",
        "--max-new-tokens",
        "256",
        "--adapter",
        "/workspace/large_artifacts/factor_recombination_ladder/models/labelled_trace_lora"
      ],
      "status": "completed",
      "started_at": 1782071255.0401914,
      "finished_at": 1782071552.6680527,
      "runtime_seconds": 297.628
    },
    {
      "suite": "ablation",
      "name": "labelled_trace_no_trace_prompt",
      "split": "recombination_holdout",
      "condition": "no_trace",
      "adapter": "/workspace/large_artifacts/factor_recombination_ladder/models/labelled_trace_lora",
      "data": "/workspace/experiments/factor_recombination_ladder/data/repair_val_recombination_holdout.jsonl",
      "output": "/workspace/experiments/factor_recombination_ladder/reports/final/ablation__labelled_trace_no_trace_prompt__recombination_holdout.json",
      "command": [
        "/usr/local/bin/python",
        "/workspace/experiments/factor_recombination_ladder/scripts/eval_ladder.py",
        "--data",
        "/workspace/experiments/factor_recombination_ladder/data/repair_val_recombination_holdout.jsonl",
        "--output",
        "/workspace/experiments/factor_recombination_ladder/reports/final/ablation__labelled_trace_no_trace_prompt__recombination_holdout.json",
        "--condition",
        "no_trace",
        "--model-id",
        "Qwen/Qwen2.5-Coder-3B-Instruct",
        "--revision",
        "488639f1ff808d1d3d0ba301aef8c11461451ec5",
        "--max-new-tokens",
        "256",
        "--adapter",
        "/workspace/large_artifacts/factor_recombination_ladder/models/labelled_trace_lora"
      ],
      "status": "completed",
      "started_at": 1782071552.6702955,
      "finished_at": 1782072182.8307223,
      "runtime_seconds": 630.16
    },
    {
      "suite": "ablation",
      "name": "labelled_trace_shuffled_trace_prompt",
      "split": "seen_iid",
      "condition": "shuffled_trace",
      "adapter": "/workspace/large_artifacts/factor_recombination_ladder/models/labelled_trace_lora",
      "data": "/workspace/experiments/factor_recombination_ladder/data/repair_val_seen_iid.jsonl",
      "output": "/workspace/experiments/factor_recombination_ladder/reports/final/ablation__labelled_trace_shuffled_trace_prompt__seen_iid.json",
      "command": [
        "/usr/local/bin/python",
        "/workspace/experiments/factor_recombination_ladder/scripts/eval_ladder.py",
        "--data",
        "/workspace/experiments/factor_recombination_ladder/data/repair_val_seen_iid.jsonl",
        "--output",
        "/workspace/experiments/factor_recombination_ladder/reports/final/ablation__labelled_trace_shuffled_trace_prompt__seen_iid.json",
        "--condition",
        "shuffled_trace",
        "--model-id",
        "Qwen/Qwen2.5-Coder-3B-Instruct",
        "--revision",
        "488639f1ff808d1d3d0ba301aef8c11461451ec5",
        "--max-new-tokens",
        "256",
        "--adapter",
        "/workspace/large_artifacts/factor_recombination_ladder/models/labelled_trace_lora"
      ],
      "status": "completed",
      "started_at": 1782072182.832099,
      "finished_at": 1782072477.099715,
      "runtime_seconds": 294.268
    },
    {
      "suite": "ablation",
      "name": "labelled_trace_shuffled_trace_prompt",
      "split": "format_shift",
      "condition": "shuffled_trace",
      "adapter": "/workspace/large_artifacts/factor_recombination_ladder/models/labelled_trace_lora",
      "data": "/workspace/experiments/factor_recombination_ladder/data/repair_val_format_shift.jsonl",
      "output": "/workspace/experiments/factor_recombination_ladder/reports/final/ablation__labelled_trace_shuffled_trace_prompt__format_shift.json",
      "command": [
        "/usr/local/bin/python",
        "/workspace/experiments/factor_recombination_ladder/scripts/eval_ladder.py",
        "--data",
        "/workspace/experiments/factor_recombination_ladder/data/repair_val_format_shift.jsonl",
        "--output",
        "/workspace/experiments/factor_recombination_ladder/reports/final/ablation__labelled_trace_shuffled_trace_prompt__format_shift.json",
        "--condition",
        "shuffled_trace",
        "--model-id",
        "Qwen/Qwen2.5-Coder-3B-Instruct",
        "--revision",
        "488639f1ff808d1d3d0ba301aef8c11461451ec5",
        "--max-new-tokens",
        "256",
        "--adapter",
        "/workspace/large_artifacts/factor_recombination_ladder/models/labelled_trace_lora"
      ],
      "status": "completed",
      "started_at": 1782072477.1019127,
      "finished_at": 1782072773.5047557,
      "runtime_seconds": 296.403
    },
    {
      "suite": "ablation",
      "name": "labelled_trace_shuffled_trace_prompt",
      "split": "recombination_holdout",
      "condition": "shuffled_trace",
      "adapter": "/workspace/large_artifacts/factor_recombination_ladder/models/labelled_trace_lora",
      "data": "/workspace/experiments/factor_recombination_ladder/data/repair_val_recombination_holdout.jsonl",
      "output": "/workspace/experiments/factor_recombination_ladder/reports/final/ablation__labelled_trace_shuffled_trace_prompt__recombination_holdout.json",
      "command": [
        "/usr/local/bin/python",
        "/workspace/experiments/factor_recombination_ladder/scripts/eval_ladder.py",
        "--data",
        "/workspace/experiments/factor_recombination_ladder/data/repair_val_recombination_holdout.jsonl",
        "--output",
        "/workspace/experiments/factor_recombination_ladder/reports/final/ablation__labelled_trace_shuffled_trace_prompt__recombination_holdout.json",
        "--condition",
        "shuffled_trace",
        "--model-id",
        "Qwen/Qwen2.5-Coder-3B-Instruct",
        "--revision",
        "488639f1ff808d1d3d0ba301aef8c11461451ec5",
        "--max-new-tokens",
        "256",
        "--adapter",
        "/workspace/large_artifacts/factor_recombination_ladder/models/labelled_trace_lora"
      ],
      "status": "completed",
      "started_at": 1782072773.5062768,
      "finished_at": 1782073479.1610734,
      "runtime_seconds": 705.655
    }
  ]
}