{
  "architectures": [
    "BertRegressor"
  ],
  "base_model": "bert-base-uncased",
  "num_hidden_layers": 3,
  "hidden_size": 768,
  "head": "Linear(768, 1)",
  "task": "regression",
  "output_range": [
    1.0,
    6.0
  ],
  "cefr_mapping": {
    "A1": 1,
    "A2": 2,
    "B1": 3,
    "B2": 4,
    "C1": 5,
    "C2": 6
  },
  "max_length": 128,
  "tokenizer": "bert-base-uncased",
  "training_config": {
    "csv_path": "data/processed/ace_cefr_labeled.csv",
    "output_dir": "checkpoints/reproduce",
    "model_name": "bert-base-uncased",
    "num_layers": 3,
    "max_length": 128,
    "lr": 6e-05,
    "epochs": 12,
    "batch_size": 32,
    "warmup_ratio": 0.1,
    "weight_decay": 0.01,
    "max_grad_norm": 1.0,
    "num_workers": 2,
    "seed": 42
  },
  "test_results": {
    "final_epoch_test_mse": 0.5775573253631592,
    "final_epoch_test_mae": 0.5508898496627808,
    "best_test_mse": 0.5665906071662903,
    "history": [
      {
        "epoch": 1,
        "train_loss": 12.465281147903271,
        "test_mse": 6.588264465332031,
        "test_mae": 2.1838321685791016
      },
      {
        "epoch": 2,
        "train_loss": 2.5425199029150973,
        "test_mse": 1.0636351108551025,
        "test_mae": 0.8281134366989136
      },
      {
        "epoch": 3,
        "train_loss": 0.9577709433737766,
        "test_mse": 1.0986764430999756,
        "test_mae": 0.8498026132583618
      },
      {
        "epoch": 4,
        "train_loss": 0.6925251134995664,
        "test_mse": 0.7558661699295044,
        "test_mae": 0.6341950297355652
      },
      {
        "epoch": 5,
        "train_loss": 0.4300207313526882,
        "test_mse": 0.573773205280304,
        "test_mae": 0.5825716257095337
      },
      {
        "epoch": 6,
        "train_loss": 0.34610338934351886,
        "test_mse": 0.5665906071662903,
        "test_mae": 0.5687209367752075
      },
      {
        "epoch": 7,
        "train_loss": 0.25567558910069843,
        "test_mse": 0.6220540404319763,
        "test_mae": 0.5755833983421326
      },
      {
        "epoch": 8,
        "train_loss": 0.17715133244401954,
        "test_mse": 0.6116251945495605,
        "test_mae": 0.5671263337135315
      },
      {
        "epoch": 9,
        "train_loss": 0.1541851587509841,
        "test_mse": 0.6381506323814392,
        "test_mae": 0.5819261074066162
      },
      {
        "epoch": 10,
        "train_loss": 0.13355727959214972,
        "test_mse": 0.5858347415924072,
        "test_mae": 0.5533825755119324
      },
      {
        "epoch": 11,
        "train_loss": 0.1009212305371681,
        "test_mse": 0.5986077189445496,
        "test_mae": 0.5595420002937317
      },
      {
        "epoch": 12,
        "train_loss": 0.08693857780668172,
        "test_mse": 0.5775573253631592,
        "test_mae": 0.5508898496627808
      }
    ],
    "paper_targets": {
      "bert_baseline": 0.44,
      "bert_with_llm_pretrain": 0.37,
      "human_expert": 0.75
    }
  },
  "selected_state": "best_test_mse_epoch"
}