{
  "experiment": "dinov3_gyuyig_tsugdri_sub_warmstart",
  "run_subdir": null,
  "task": "gyuyig_tsugdri_binary_classification",
  "balanced_parquet_dir": null,
  "balanced_dataset_repo": "BDRC/gyuyig-tsugdri-binary-balanced-script-classification-dataset",
  "data_source": "hf",
  "benchmark_dataset_repo": null,
  "benchmark_per_parent": 60,
  "preprocess": {
    "train": "resize_letterbox",
    "val": "resize_letterbox",
    "test": "resize_letterbox",
    "size": 448
  },
  "pooling": "cls_token",
  "training_config": {
    "lr_head_a": 0.0005,
    "lr_backbone_b": 1e-05,
    "lr_head_b": 0.0001,
    "lr_backbone_c": 1.5e-05,
    "lr_head_c": 5e-05,
    "epochs_a": 7,
    "epochs_b": 10,
    "epochs_c": 12,
    "unfreeze_blocks_b": 4,
    "unfreeze_blocks_c": 8,
    "skip_stage_c": false,
    "scheduler": "cosine_warmup",
    "warmup_epochs_a": 0,
    "warmup_epochs_b": 1,
    "warmup_epochs_c": 1,
    "warmup_start_factor": 0.01,
    "min_lr_ratio": 0.01,
    "weight_decay": 0.02,
    "grad_clip_norm": 1.0,
    "class_weight_mode": "custom",
    "class_weights": [
      1.0,
      1.0
    ],
    "label_smoothing": 0.05,
    "dropout": 0.1,
    "early_stop_patience": 6,
    "early_stop_min_delta": 0.001,
    "resolved_class_weights": [
      1.0,
      1.0
    ],
    "pooling": "cls_token",
    "lambda_consistency": 0.0,
    "flip_op": "rot180"
  },
  "resolved_class_weights": [
    1.0,
    1.0
  ],
  "warmstart": {
    "warmstart_repo": "BDRC/4-class-balanced-script-classifier",
    "warmstart_checkpoint": null,
    "warmstart_checkpoint_file": "final_model.pt",
    "checkpoint_test_metrics": {
      "loss": 0.6574946736847913,
      "accuracy": 0.825925925925926,
      "macro_f1": 0.8326187473728457,
      "weighted_f1": 0.82908384875598
    },
    "warmstart_pooling": "cls_token"
  },
  "checkpoint_selection": {
    "method": "best_val_macro_f1"
  },
  "best_checkpoint": {
    "path": "best_stage_c_last_blocks.pt",
    "epoch": 7,
    "val_macro_f1": 0.849624060150376
  },
  "val_metrics": {
    "loss": 0.45204214652379354,
    "accuracy": 0.85,
    "macro_f1": 0.849624060150376,
    "weighted_f1": 0.849624060150376,
    "auc_roc": 0.9022222222222223
  },
  "val_confusion_matrix": [
    [
      24,
      6
    ],
    [
      3,
      27
    ]
  ],
  "val_report": "              precision    recall  f1-score   support\n\n      Gyuyig       0.89      0.80      0.84        30\n     Tsugdri       0.82      0.90      0.86        30\n\n    accuracy                           0.85        60\n   macro avg       0.85      0.85      0.85        60\nweighted avg       0.85      0.85      0.85        60\n",
  "test_metrics": {
    "loss": 0.5353951374689738,
    "accuracy": 0.8083333333333333,
    "macro_f1": 0.8082134667500521,
    "weighted_f1": 0.8082134667500521,
    "auc_roc": 0.8677777777777778
  },
  "test_confusion_matrix": [
    [
      50,
      10
    ],
    [
      13,
      47
    ]
  ],
  "test_report": "              precision    recall  f1-score   support\n\n      Gyuyig       0.79      0.83      0.81        60\n     Tsugdri       0.82      0.78      0.80        60\n\n    accuracy                           0.81       120\n   macro avg       0.81      0.81      0.81       120\nweighted avg       0.81      0.81      0.81       120\n",
  "history": {
    "stage_a": [
      {
        "epoch": 1,
        "train_loss": 0.868421577271961,
        "train_acc": 0.39880952380952384,
        "lr_head": 5e-06,
        "val_loss": 0.8907806555430094,
        "val_accuracy": 0.3,
        "val_macro_f1": 0.28,
        "val_weighted_f1": 0.28
      },
      {
        "epoch": 2,
        "train_loss": 0.6925251398767743,
        "train_acc": 0.5744047619047619,
        "lr_head": 0.0005,
        "val_loss": 0.6001647631327311,
        "val_accuracy": 0.6166666666666667,
        "val_macro_f1": 0.5911111111111111,
        "val_weighted_f1": 0.5911111111111111
      },
      {
        "epoch": 3,
        "train_loss": 0.5732808538845607,
        "train_acc": 0.6964285714285714,
        "lr_head": 0.0004668412874366486,
        "val_loss": 0.5495736837387085,
        "val_accuracy": 0.7166666666666667,
        "val_macro_f1": 0.7165879410947485,
        "val_weighted_f1": 0.7165879410947485
      },
      {
        "epoch": 4,
        "train_loss": 0.5409448828016009,
        "train_acc": 0.7351190476190477,
        "lr_head": 0.00037624999999999996,
        "val_loss": 0.5596829652786255,
        "val_accuracy": 0.7166666666666667,
        "val_macro_f1": 0.7127569698676429,
        "val_weighted_f1": 0.7127569698676429
      },
      {
        "epoch": 5,
        "train_loss": 0.517706477925891,
        "train_acc": 0.7380952380952381,
        "lr_head": 0.0002525,
        "val_loss": 0.570094374815623,
        "val_accuracy": 0.6833333333333333,
        "val_macro_f1": 0.6723196320781835,
        "val_weighted_f1": 0.6723196320781833
      },
      {
        "epoch": 6,
        "train_loss": 0.5244638267017546,
        "train_acc": 0.7529761904761905,
        "lr_head": 0.00012875000000000007,
        "val_loss": 0.5446342428525289,
        "val_accuracy": 0.7166666666666667,
        "val_macro_f1": 0.7159565580618212,
        "val_weighted_f1": 0.7159565580618211
      },
      {
        "epoch": 7,
        "train_loss": 0.49209926100004286,
        "train_acc": 0.7797619047619048,
        "lr_head": 3.815871256335142e-05,
        "val_loss": 0.5444834152857463,
        "val_accuracy": 0.7166666666666667,
        "val_macro_f1": 0.7159565580618212,
        "val_weighted_f1": 0.7159565580618211
      }
    ],
    "stage_b": [
      {
        "epoch": 1,
        "train_loss": 0.5235937989893413,
        "train_acc": 0.75,
        "lr_head": 1.0000000000000002e-06,
        "lr_backbone": 1.0000000000000001e-07,
        "val_loss": 0.5491747617721557,
        "val_accuracy": 0.7166666666666667,
        "val_macro_f1": 0.7165879410947485,
        "val_weighted_f1": 0.7165879410947485
      },
      {
        "epoch": 2,
        "train_loss": 0.5453660388787588,
        "train_acc": 0.7529761904761905,
        "lr_head": 0.0001,
        "lr_backbone": 1e-05,
        "val_loss": 0.5492973128954569,
        "val_accuracy": 0.7333333333333333,
        "val_macro_f1": 0.7306397306397306,
        "val_weighted_f1": 0.7306397306397305
      },
      {
        "epoch": 3,
        "train_loss": 0.49581416731788996,
        "train_acc": 0.7916666666666666,
        "lr_head": 9.701478472890248e-05,
        "lr_backbone": 9.701478472890248e-06,
        "val_loss": 0.538078244527181,
        "val_accuracy": 0.7166666666666667,
        "val_macro_f1": 0.7165879410947485,
        "val_weighted_f1": 0.7165879410947485
      },
      {
        "epoch": 4,
        "train_loss": 0.4958783601011549,
        "train_acc": 0.7678571428571429,
        "lr_head": 8.84191999343894e-05,
        "lr_backbone": 8.841919993438941e-06,
        "val_loss": 0.5364969690640767,
        "val_accuracy": 0.7333333333333333,
        "val_macro_f1": 0.7321428571428572,
        "val_weighted_f1": 0.7321428571428572
      },
      {
        "epoch": 5,
        "train_loss": 0.4718715477557409,
        "train_acc": 0.7946428571428571,
        "lr_head": 7.525e-05,
        "lr_backbone": 7.525e-06,
        "val_loss": 0.5267467339833577,
        "val_accuracy": 0.7333333333333333,
        "val_macro_f1": 0.7321428571428572,
        "val_weighted_f1": 0.7321428571428572
      },
      {
        "epoch": 6,
        "train_loss": 0.4493213253361838,
        "train_acc": 0.8244047619047619,
        "lr_head": 5.909558479451306e-05,
        "lr_backbone": 5.909558479451306e-06,
        "val_loss": 0.5186658461888631,
        "val_accuracy": 0.7166666666666667,
        "val_macro_f1": 0.7159565580618212,
        "val_weighted_f1": 0.7159565580618211
      },
      {
        "epoch": 7,
        "train_loss": 0.43445002465021043,
        "train_acc": 0.8184523809523809,
        "lr_head": 4.190441520548695e-05,
        "lr_backbone": 4.190441520548696e-06,
        "val_loss": 0.5154884020487468,
        "val_accuracy": 0.7166666666666667,
        "val_macro_f1": 0.7159565580618212,
        "val_weighted_f1": 0.7159565580618211
      },
      {
        "epoch": 8,
        "train_loss": 0.42955496197655085,
        "train_acc": 0.8273809523809523,
        "lr_head": 2.5750000000000013e-05,
        "lr_backbone": 2.575000000000001e-06,
        "val_loss": 0.5194342851638794,
        "val_accuracy": 0.7666666666666667,
        "val_macro_f1": 0.7643097643097643,
        "val_weighted_f1": 0.7643097643097643
      },
      {
        "epoch": 9,
        "train_loss": 0.4368310116586231,
        "train_acc": 0.8154761904761905,
        "lr_head": 1.2580800065610596e-05,
        "lr_backbone": 1.2580800065610596e-06,
        "val_loss": 0.5142494519551595,
        "val_accuracy": 0.7333333333333333,
        "val_macro_f1": 0.7321428571428572,
        "val_weighted_f1": 0.7321428571428572
      },
      {
        "epoch": 10,
        "train_loss": 0.4370355563504355,
        "train_acc": 0.8125,
        "lr_head": 3.985215271097539e-06,
        "lr_backbone": 3.985215271097539e-07,
        "val_loss": 0.5129753907521566,
        "val_accuracy": 0.7333333333333333,
        "val_macro_f1": 0.7321428571428572,
        "val_weighted_f1": 0.7321428571428572
      }
    ],
    "stage_c": [
      {
        "epoch": 1,
        "train_loss": 0.4291627889587766,
        "train_acc": 0.8273809523809523,
        "lr_head": 5.000000000000001e-07,
        "lr_backbone": 1.5000000000000002e-07,
        "val_loss": 0.5183799107869466,
        "val_accuracy": 0.7666666666666667,
        "val_macro_f1": 0.7643097643097643,
        "val_weighted_f1": 0.7643097643097643
      },
      {
        "epoch": 2,
        "train_loss": 0.42413380600157236,
        "train_acc": 0.8154761904761905,
        "lr_head": 5e-05,
        "lr_backbone": 1.5e-05,
        "val_loss": 0.5204356749852498,
        "val_accuracy": 0.7166666666666667,
        "val_macro_f1": 0.7101449275362319,
        "val_weighted_f1": 0.7101449275362319
      },
      {
        "epoch": 3,
        "train_loss": 0.37433484338578726,
        "train_acc": 0.875,
        "lr_head": 4.899745109695881e-05,
        "lr_backbone": 1.4699235329087644e-05,
        "val_loss": 0.48167786995569867,
        "val_accuracy": 0.7666666666666667,
        "val_macro_f1": 0.7643097643097643,
        "val_weighted_f1": 0.7643097643097643
      },
      {
        "epoch": 4,
        "train_loss": 0.335602682970819,
        "train_acc": 0.8839285714285714,
        "lr_head": 4.6071024937571735e-05,
        "lr_backbone": 1.3821307481271522e-05,
        "val_loss": 0.45847638448079425,
        "val_accuracy": 0.8166666666666667,
        "val_macro_f1": 0.8153846153846154,
        "val_weighted_f1": 0.8153846153846154
      },
      {
        "epoch": 5,
        "train_loss": 0.2807346156665257,
        "train_acc": 0.9255952380952381,
        "lr_head": 4.145780316514581e-05,
        "lr_backbone": 1.2437340949543742e-05,
        "val_loss": 0.4557582457860311,
        "val_accuracy": 0.8,
        "val_macro_f1": 0.7991071428571428,
        "val_weighted_f1": 0.7991071428571428
      },
      {
        "epoch": 6,
        "train_loss": 0.2691161029395603,
        "train_acc": 0.9375,
        "lr_head": 3.5531521571796694e-05,
        "lr_backbone": 1.0659456471539008e-05,
        "val_loss": 0.44928998152414956,
        "val_accuracy": 0.8333333333333334,
        "val_macro_f1": 0.8331479421579533,
        "val_weighted_f1": 0.8331479421579533
      },
      {
        "epoch": 7,
        "train_loss": 0.23485895210788363,
        "train_acc": 0.9375,
        "lr_head": 2.877229224726381e-05,
        "lr_backbone": 8.631687674179142e-06,
        "val_loss": 0.45204214652379354,
        "val_accuracy": 0.85,
        "val_macro_f1": 0.849624060150376,
        "val_weighted_f1": 0.849624060150376
      },
      {
        "epoch": 8,
        "train_loss": 0.22606890329292842,
        "train_acc": 0.9553571428571429,
        "lr_head": 2.1727707752736196e-05,
        "lr_backbone": 6.518312325820858e-06,
        "val_loss": 0.4554001530011495,
        "val_accuracy": 0.7833333333333333,
        "val_macro_f1": 0.783273131425396,
        "val_weighted_f1": 0.783273131425396
      },
      {
        "epoch": 9,
        "train_loss": 0.19964813192685446,
        "train_acc": 0.9672619047619048,
        "lr_head": 1.4968478428203314e-05,
        "lr_backbone": 4.490543528460994e-06,
        "val_loss": 0.45547234614690146,
        "val_accuracy": 0.8333333333333334,
        "val_macro_f1": 0.8325892857142857,
        "val_weighted_f1": 0.8325892857142857
      },
      {
        "epoch": 10,
        "train_loss": 0.21034001807371774,
        "train_acc": 0.9583333333333334,
        "lr_head": 9.042196834854196e-06,
        "lr_backbone": 2.712659050456259e-06,
        "val_loss": 0.45674578348795575,
        "val_accuracy": 0.8333333333333334,
        "val_macro_f1": 0.8325892857142857,
        "val_weighted_f1": 0.8325892857142857
      },
      {
        "epoch": 11,
        "train_loss": 0.1949910166717711,
        "train_acc": 0.9702380952380952,
        "lr_head": 4.428975062428262e-06,
        "lr_backbone": 1.3286925187284787e-06,
        "val_loss": 0.4595174193382263,
        "val_accuracy": 0.8166666666666667,
        "val_macro_f1": 0.8153846153846154,
        "val_weighted_f1": 0.8153846153846154
      },
      {
        "epoch": 12,
        "train_loss": 0.1842061841771716,
        "train_acc": 0.9761904761904762,
        "lr_head": 1.502548903041193e-06,
        "lr_backbone": 4.5076467091235787e-07,
        "val_loss": 0.4608180999755859,
        "val_accuracy": 0.8166666666666667,
        "val_macro_f1": 0.8153846153846154,
        "val_weighted_f1": 0.8153846153846154
      }
    ]
  },
  "confusion_matrix": [
    [
      50,
      10
    ],
    [
      13,
      47
    ]
  ],
  "report": "              precision    recall  f1-score   support\n\n      Gyuyig       0.79      0.83      0.81        60\n     Tsugdri       0.82      0.78      0.80        60\n\n    accuracy                           0.81       120\n   macro avg       0.81      0.81      0.81       120\nweighted avg       0.81      0.81      0.81       120\n",
  "idx_to_label": {
    "0": "Gyuyig",
    "1": "Tsugdri"
  },
  "label_to_idx": {
    "Gyuyig": 0,
    "Tsugdri": 1
  },
  "model_id": "facebook/dinov3-vits16-pretrain-lvd1689m"
}