{
  "model_base": "Qwen/Qwen2.5-14B-Instruct",
  "model_name": "RegTech-14B-Instruct",
  "dataset": "./train.jsonl",
  "env_file": "/home/ubuntu/sophia-core-server/.tuning/.env.14B",
  "train_samples": 2134,
  "eval_samples": 237,
  "params": {
    "rank": 16,
    "alpha": 16,
    "dropout": 0.1,
    "lr": 2e-05,
    "scheduler": "cosine",
    "epochs": 1,
    "effective_batch": 4,
    "max_seq_length": 4096,
    "neftune_alpha": 5.0,
    "target_modules": [
      "q_proj",
      "k_proj",
      "v_proj",
      "o_proj",
      "gate_proj",
      "up_proj",
      "down_proj"
    ]
  },
  "results": {
    "total_steps": 534,
    "final_train_loss": 1.073,
    "best_eval_loss": 1.098220944404602,
    "best_eval_step": 520,
    "best_token_accuracy": 0.7624,
    "elapsed_minutes": 19.9
  },
  "loss_history": {
    "train": [
      [
        5,
        1.8103
      ],
      [
        10,
        1.9463
      ],
      [
        15,
        1.7076
      ],
      [
        20,
        1.8542
      ],
      [
        25,
        1.9426
      ],
      [
        30,
        2.026
      ],
      [
        35,
        1.9177
      ],
      [
        40,
        1.7516
      ],
      [
        45,
        1.655
      ],
      [
        50,
        1.4414
      ],
      [
        55,
        1.4496
      ],
      [
        60,
        1.3549
      ],
      [
        65,
        1.3485
      ],
      [
        70,
        1.6647
      ],
      [
        75,
        1.3798
      ],
      [
        80,
        1.5445
      ],
      [
        85,
        1.3067
      ],
      [
        90,
        1.3387
      ],
      [
        95,
        1.2908
      ],
      [
        100,
        1.2998
      ],
      [
        105,
        1.3263
      ],
      [
        110,
        1.3664
      ],
      [
        115,
        1.2699
      ],
      [
        120,
        1.3007
      ],
      [
        125,
        1.3573
      ],
      [
        130,
        1.243
      ],
      [
        135,
        1.3071
      ],
      [
        140,
        1.2171
      ],
      [
        145,
        1.1797
      ],
      [
        150,
        1.1813
      ],
      [
        155,
        1.3488
      ],
      [
        160,
        1.1427
      ],
      [
        165,
        1.2909
      ],
      [
        170,
        1.1646
      ],
      [
        175,
        1.0927
      ],
      [
        180,
        1.1764
      ],
      [
        185,
        1.1671
      ],
      [
        190,
        1.2527
      ],
      [
        195,
        1.0971
      ],
      [
        200,
        1.0705
      ],
      [
        205,
        1.1283
      ],
      [
        210,
        1.1866
      ],
      [
        215,
        1.1713
      ],
      [
        220,
        1.0456
      ],
      [
        225,
        1.137
      ],
      [
        230,
        1.074
      ],
      [
        235,
        1.062
      ],
      [
        240,
        1.0085
      ],
      [
        245,
        1.0669
      ],
      [
        250,
        0.9657
      ],
      [
        255,
        1.0515
      ],
      [
        260,
        1.0492
      ],
      [
        265,
        1.1586
      ],
      [
        270,
        1.0454
      ],
      [
        275,
        1.1171
      ],
      [
        280,
        1.0412
      ],
      [
        285,
        0.9569
      ],
      [
        290,
        1.0504
      ],
      [
        295,
        1.0302
      ],
      [
        300,
        1.0497
      ],
      [
        305,
        0.9437
      ],
      [
        310,
        0.9805
      ],
      [
        315,
        1.0755
      ],
      [
        320,
        1.0508
      ],
      [
        325,
        1.0563
      ],
      [
        330,
        0.9653
      ],
      [
        335,
        0.9692
      ],
      [
        340,
        1.1218
      ],
      [
        345,
        1.0367
      ],
      [
        350,
        0.9287
      ],
      [
        355,
        1.0165
      ],
      [
        360,
        1.0356
      ],
      [
        365,
        1.0249
      ],
      [
        370,
        0.9885
      ],
      [
        375,
        0.9588
      ],
      [
        380,
        0.977
      ],
      [
        385,
        0.9921
      ],
      [
        390,
        0.9863
      ],
      [
        395,
        1.0569
      ],
      [
        400,
        0.982
      ],
      [
        405,
        1.0738
      ],
      [
        410,
        1.034
      ],
      [
        415,
        1.067
      ],
      [
        420,
        1.044
      ],
      [
        425,
        0.9622
      ],
      [
        430,
        0.9102
      ],
      [
        435,
        1.0164
      ],
      [
        440,
        0.9833
      ],
      [
        445,
        0.9276
      ],
      [
        450,
        0.8751
      ],
      [
        455,
        1.0087
      ],
      [
        460,
        1.032
      ],
      [
        465,
        1.0099
      ],
      [
        470,
        1.0805
      ],
      [
        475,
        1.0326
      ],
      [
        480,
        0.968
      ],
      [
        485,
        0.948
      ],
      [
        490,
        1.0297
      ],
      [
        495,
        1.0083
      ],
      [
        500,
        0.955
      ],
      [
        505,
        0.967
      ],
      [
        510,
        0.8891
      ],
      [
        515,
        0.9298
      ],
      [
        520,
        0.9516
      ],
      [
        525,
        0.9553
      ],
      [
        530,
        1.073
      ]
    ],
    "eval": [
      [
        40,
        1.9159308671951294
      ],
      [
        80,
        1.5397088527679443
      ],
      [
        120,
        1.398988127708435
      ],
      [
        160,
        1.3029450178146362
      ],
      [
        200,
        1.2370014190673828
      ],
      [
        240,
        1.1978071928024292
      ],
      [
        280,
        1.1654218435287476
      ],
      [
        320,
        1.1381187438964844
      ],
      [
        360,
        1.1211411952972412
      ],
      [
        400,
        1.107499599456787
      ],
      [
        440,
        1.1020454168319702
      ],
      [
        480,
        1.0991754531860352
      ],
      [
        520,
        1.098220944404602
      ]
    ],
    "token_accuracy": [
      [
        40,
        0.6898
      ],
      [
        80,
        0.7085
      ],
      [
        120,
        0.7226
      ],
      [
        160,
        0.7344
      ],
      [
        200,
        0.7426
      ],
      [
        240,
        0.7473
      ],
      [
        280,
        0.7522
      ],
      [
        320,
        0.7564
      ],
      [
        360,
        0.7585
      ],
      [
        400,
        0.7605
      ],
      [
        440,
        0.7618
      ],
      [
        480,
        0.7624
      ],
      [
        520,
        0.7624
      ]
    ]
  }
}