{
  "model_name": "microsoft/graphcodebert-base",
  "model_dir": "/mnt/d/work2/graphcodebert-code-clone-detection/models/graphcodebert-clone-detection",
  "dataset_name": "PoolC/1-fold-clone-detection-600k-5fold",
  "dataset_split_strategy": {
    "train_split": "train",
    "heldout_split": "val",
    "note": "The repository provides one of 5 predefined folds as `train` + `val`; those groups are disjoint and are kept as-is. `val` is partitioned further into validation/test along problem-group boundaries.",
    "heldout_groups": 59,
    "validation_groups": 29,
    "test_groups": 30,
    "dropped_cross_boundary_pairs": 337398,
    "validation": {
      "num_examples": 483738,
      "negatives_label_0": 157558,
      "positives_label_1": 326180,
      "positive_ratio": 0.674291,
      "num_groups": 29
    },
    "test": {
      "num_examples": 503224,
      "negatives_label_0": 167224,
      "positives_label_1": 336000,
      "positive_ratio": 0.667695,
      "num_groups": 30
    }
  },
  "num_train_examples": 50000,
  "num_validation_examples": 20000,
  "num_test_examples": 20000,
  "class_distributions": {
    "train": {
      "num_examples": 50000,
      "negatives_label_0": 25000,
      "positives_label_1": 25000,
      "positive_ratio": 0.5,
      "num_groups": 240
    },
    "validation": {
      "num_examples": 20000,
      "negatives_label_0": 10000,
      "positives_label_1": 10000,
      "positive_ratio": 0.5,
      "num_groups": 29
    },
    "test": {
      "num_examples": 20000,
      "negatives_label_0": 10000,
      "positives_label_1": 10000,
      "positive_ratio": 0.5,
      "num_groups": 30
    }
  },
  "class_weighting": {
    "mode": "auto",
    "threshold": 0.6,
    "majority_class_share": 0.5,
    "applied": false,
    "weights": null,
    "reason": "Measured majority-class share 0.5000 is within the 0.6 threshold, so weighted cross entropy is NOT used."
  },
  "sequence_length": 512,
  "data_flow_length": 128,
  "total_sequence_length": 640,
  "per_device_train_batch_size": 16,
  "gradient_accumulation_steps": 1,
  "effective_batch_size": 16,
  "learning_rate": 2e-05,
  "num_train_epochs": 3.0,
  "optimizer": "adamw_torch",
  "scheduler": "linear",
  "warmup_ratio": 0.1,
  "warmup_steps": 938,
  "weight_decay": 0.01,
  "max_grad_norm": 1.0,
  "mixed_precision": "fp16",
  "gradient_checkpointing": false,
  "seed": 42,
  "training_time_seconds": 6921.9,
  "training_time_hours": 1.923,
  "train_runtime_metrics": {
    "train_runtime": 6918.8074,
    "train_samples_per_second": 21.68,
    "train_steps_per_second": 1.355,
    "total_flos": 0.0,
    "train_loss": 0.43145505716959637,
    "epoch": 3.0
  },
  "gpu": {
    "cuda_available": true,
    "torch_version": "2.11.0+cu128",
    "transformers_version": "5.17.0",
    "python_version": "3.12.3",
    "platform": "Linux-6.18.33.2-microsoft-standard-WSL2-x86_64-with-glibc2.39",
    "gpu_name": "NVIDIA GeForce RTX 5060 Ti",
    "gpu_count": 1,
    "gpu_total_memory_gb": 15.9,
    "gpu_capability": "12.0",
    "cuda_version": "12.8"
  },
  "parameters": {
    "trainable_parameters": 125236994,
    "total_parameters": 125236994
  },
  "best_validation_f1": 0.8671882190520018,
  "best_checkpoint": "./outputs/checkpoint-9000",
  "validation_metrics": {
    "loss": 0.34459105134010315,
    "accuracy": 0.8557,
    "precision": 0.8032395566922421,
    "recall": 0.9422,
    "f1": 0.8671882190520018,
    "macro_f1": 0.8546121719233737,
    "tp": 9422,
    "tn": 7692,
    "fp": 2308,
    "fn": 578,
    "confusion_matrix": [
      [
        7692,
        2308
      ],
      [
        578,
        9422
      ]
    ],
    "confusion_matrix_layout": "[[TN, FP], [FN, TP]]",
    "support": {
      "num_examples": 20000,
      "label_0": 10000,
      "label_1": 10000
    },
    "runtime": 173.9737,
    "samples_per_second": 114.96,
    "steps_per_second": 3.592,
    "num_examples": 20000,
    "eval_seconds": 174.0
  },
  "test_metrics": {
    "loss": 0.3165612816810608,
    "model_preparation_time": 0.0022,
    "accuracy": 0.87465,
    "precision": 0.8409939018840448,
    "recall": 0.924,
    "f1": 0.8805450993472149,
    "macro_f1": 0.874343974488208,
    "tp": 9240,
    "tn": 8253,
    "fp": 1747,
    "fn": 760,
    "confusion_matrix": [
      [
        8253,
        1747
      ],
      [
        760,
        9240
      ]
    ],
    "confusion_matrix_layout": "[[TN, FP], [FN, TP]]",
    "support": {
      "num_examples": 20000,
      "label_0": 10000,
      "label_1": 10000
    },
    "runtime": 181.6455,
    "samples_per_second": 110.105,
    "steps_per_second": 3.441,
    "num_examples": 20000,
    "eval_seconds": 181.7
  },
  "preprocessing": {
    "snippet_pool": {
      "num_unique_snippets": 44950,
      "scan_seconds": 46.3,
      "snippets_with_multiple_groups": 1,
      "cross_split_snippet_overlap": {
        "train|val:snippets": 0,
        "train|val:groups": 0
      },
      "per_split": {
        "train": {
          "num_examples": 5388622,
          "negatives_label_0": 2694311,
          "positives_label_1": 2694311,
          "positive_ratio": 0.5,
          "num_groups": 240
        },
        "val": {
          "num_examples": 1324360,
          "negatives_label_0": 662180,
          "positives_label_1": 662180,
          "positive_ratio": 0.5,
          "num_groups": 59
        }
      }
    },
    "feature_extraction": {
      "num_snippets": 44950,
      "extraction_seconds": 64.1,
      "status_counts": {
        "ok": 44930,
        "comment_strip_failed": 13,
        "dfg_failed": 7
      },
      "snippets_with_empty_dataflow": 263,
      "dataflow_nodes_mean": 44.22,
      "dataflow_nodes_p50": 33,
      "dataflow_nodes_p95": 127,
      "dataflow_nodes_max": 193,
      "code_tokens_mean": 137.9,
      "code_tokens_truncated": 885,
      "total_dataflow_edges": 2481388,
      "sequence_length": 640
    },
    "subsampling": {
      "train": {
        "subsampled": true,
        "kept": 50000,
        "balanced": true
      },
      "validation": {
        "subsampled": true,
        "kept": 20000,
        "balanced": true
      },
      "test": {
        "subsampled": true,
        "kept": 20000,
        "balanced": true
      }
    }
  },
  "sanity_check": {
    "passed": true,
    "device": "cuda",
    "checks": [
      {
        "check": "1_dataset_loading",
        "passed": true,
        "detail": "train=50000 val=20000 test=20000"
      },
      {
        "check": "2_column_detection",
        "passed": true,
        "detail": "code columns=code1/code2, label=similar; excluded from features: ['code1_group', 'code2_group', 'pair_id', 'question_pair_id']"
      },
      {
        "check": "3_label_correctness",
        "passed": true,
        "detail": "labels in {0,1}; validation positive ratio=0.5"
      },
      {
        "check": "4_tokenisation",
        "passed": true,
        "detail": "<s>...</s> wrapping OK, 93 code tokens, decodes to 'import math a , b , c = map ( int , input ( ) . split ( ) ) '"
      },
      {
        "check": "5_dataflow_extraction",
        "passed": true,
        "detail": "44687/44950 snippets have a non-empty data-flow graph, 2481388 edges, mean nodes=44.22"
      },
      {
        "check": "6_attention_mask",
        "passed": true,
        "detail": "shape=(640, 640) (code_length 512 + data_flow_length 128), 93 code tokens, 30 nodes, density=0.0215, padding rows empty"
      },
      {
        "check": "7_forward_pass",
        "passed": true,
        "detail": "logits shape=(16, 2) for batch of 16 pairs; mask tensor=(16, 640, 640)"
      },
      {
        "check": "8_finite_loss",
        "passed": true,
        "detail": "loss=0.6978 (chance level ~0.6931)"
      },
      {
        "check": "9_training_step",
        "passed": true,
        "detail": "loss=0.6798, grad_norm=2.4929, weights updated (amp=on, dtype=torch.float16)"
      }
    ],
    "parameters": {
      "trainable_parameters": 125236994,
      "total_parameters": 125236994
    },
    "sequence_length": 640
  },
  "test_metrics_provenance": {
    "note": "Re-scored after fixing a transformers v5 dataloader-caching bug: Trainer.get_eval_dataloader caches under the key 'eval' when a Dataset object is passed and dataloader_persistent_workers=True, so the original in-training test evaluation silently re-scored the validation split. evaluate_split now uses Trainer.predict and verifies the returned labels.",
    "superseded_test_f1": 0.8671882190520018,
    "corrected_test_f1": 0.8805450993472149,
    "validation_f1_unchanged": 0.8671882190520018
  }
}