{
  "best_metric": 0.08392839133739471,
  "best_model_checkpoint": "./models/results_funlines_and_human_microedit_paper_2023_693/checkpoint-200",
  "epoch": 0.774818401937046,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.6859,
      "step": 8
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.6827,
      "step": 16
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.2e-05,
      "loss": 0.6877,
      "step": 24
    },
    {
      "epoch": 0.1,
      "eval_accuracy": 0.5563559322033899,
      "eval_f1": 0.7149469098829294,
      "eval_loss": 0.6760356426239014,
      "eval_precision": 0.5563559322033899,
      "eval_recall": 1.0,
      "eval_runtime": 15.2381,
      "eval_samples_per_second": 154.875,
      "eval_steps_per_second": 19.359,
      "step": 25
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.6647,
      "step": 32
    },
    {
      "epoch": 0.15,
      "learning_rate": 2e-05,
      "loss": 0.543,
      "step": 40
    },
    {
      "epoch": 0.19,
      "learning_rate": 2.4e-05,
      "loss": 0.3736,
      "step": 48
    },
    {
      "epoch": 0.19,
      "eval_accuracy": 0.8635593220338983,
      "eval_f1": 0.8649328859060402,
      "eval_loss": 0.31369638442993164,
      "eval_precision": 0.9626517273576097,
      "eval_recall": 0.7852246763137852,
      "eval_runtime": 15.1929,
      "eval_samples_per_second": 155.336,
      "eval_steps_per_second": 19.417,
      "step": 50
    },
    {
      "epoch": 0.22,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.3738,
      "step": 56
    },
    {
      "epoch": 0.25,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.2697,
      "step": 64
    },
    {
      "epoch": 0.28,
      "learning_rate": 3.6e-05,
      "loss": 0.1821,
      "step": 72
    },
    {
      "epoch": 0.29,
      "eval_accuracy": 0.9555084745762712,
      "eval_f1": 0.9600608596424496,
      "eval_loss": 0.13926365971565247,
      "eval_precision": 0.958966565349544,
      "eval_recall": 0.9611576542269612,
      "eval_runtime": 15.1835,
      "eval_samples_per_second": 155.432,
      "eval_steps_per_second": 19.429,
      "step": 75
    },
    {
      "epoch": 0.31,
      "learning_rate": 3.9000000000000006e-05,
      "loss": 0.1583,
      "step": 80
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.3e-05,
      "loss": 0.1845,
      "step": 88
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.7e-05,
      "loss": 0.1605,
      "step": 96
    },
    {
      "epoch": 0.39,
      "eval_accuracy": 0.9593220338983051,
      "eval_f1": 0.9625,
      "eval_loss": 0.13289286196231842,
      "eval_precision": 0.9879711307137129,
      "eval_recall": 0.9383092155369384,
      "eval_runtime": 15.1752,
      "eval_samples_per_second": 155.517,
      "eval_steps_per_second": 19.44,
      "step": 100
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.936708860759494e-05,
      "loss": 0.1174,
      "step": 104
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.683544303797468e-05,
      "loss": 0.1111,
      "step": 112
    },
    {
      "epoch": 0.46,
      "learning_rate": 4.430379746835443e-05,
      "loss": 0.158,
      "step": 120
    },
    {
      "epoch": 0.48,
      "eval_accuracy": 0.9567796610169491,
      "eval_f1": 0.9617977528089888,
      "eval_loss": 0.11806055903434753,
      "eval_precision": 0.94620486366986,
      "eval_recall": 0.9779131759329779,
      "eval_runtime": 15.1814,
      "eval_samples_per_second": 155.454,
      "eval_steps_per_second": 19.432,
      "step": 125
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.177215189873418e-05,
      "loss": 0.1373,
      "step": 128
    },
    {
      "epoch": 0.53,
      "learning_rate": 3.924050632911392e-05,
      "loss": 0.1306,
      "step": 136
    },
    {
      "epoch": 0.56,
      "learning_rate": 3.670886075949367e-05,
      "loss": 0.1261,
      "step": 144
    },
    {
      "epoch": 0.58,
      "eval_accuracy": 0.9669491525423729,
      "eval_f1": 0.9698841698841698,
      "eval_loss": 0.09348666667938232,
      "eval_precision": 0.9835552075176194,
      "eval_recall": 0.9565879664889566,
      "eval_runtime": 15.1738,
      "eval_samples_per_second": 155.531,
      "eval_steps_per_second": 19.441,
      "step": 150
    },
    {
      "epoch": 0.59,
      "learning_rate": 3.4177215189873416e-05,
      "loss": 0.1048,
      "step": 152
    },
    {
      "epoch": 0.62,
      "learning_rate": 3.1645569620253167e-05,
      "loss": 0.1109,
      "step": 160
    },
    {
      "epoch": 0.65,
      "learning_rate": 2.9113924050632914e-05,
      "loss": 0.0743,
      "step": 168
    },
    {
      "epoch": 0.68,
      "eval_accuracy": 0.9703389830508474,
      "eval_f1": 0.9728682170542636,
      "eval_loss": 0.10754456371068954,
      "eval_precision": 0.9905288082083662,
      "eval_recall": 0.9558263518659559,
      "eval_runtime": 15.1659,
      "eval_samples_per_second": 155.612,
      "eval_steps_per_second": 19.451,
      "step": 175
    },
    {
      "epoch": 0.68,
      "learning_rate": 2.6582278481012658e-05,
      "loss": 0.1677,
      "step": 176
    },
    {
      "epoch": 0.71,
      "learning_rate": 2.4050632911392405e-05,
      "loss": 0.0963,
      "step": 184
    },
    {
      "epoch": 0.74,
      "learning_rate": 2.1518987341772153e-05,
      "loss": 0.0954,
      "step": 192
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.89873417721519e-05,
      "loss": 0.1263,
      "step": 200
    },
    {
      "epoch": 0.77,
      "eval_accuracy": 0.9699152542372881,
      "eval_f1": 0.9728904161893853,
      "eval_loss": 0.08392839133739471,
      "eval_precision": 0.9754977029096478,
      "eval_recall": 0.9702970297029703,
      "eval_runtime": 15.2112,
      "eval_samples_per_second": 155.148,
      "eval_steps_per_second": 19.394,
      "step": 200
    }
  ],
  "max_steps": 258,
  "num_train_epochs": 1,
  "total_flos": 289422160896000.0,
  "trial_name": null,
  "trial_params": null
}