{
  "best_metric": 0.04831862449645996,
  "best_model_checkpoint": "./model/new-14/checkpoint-4410",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 4410,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 1.1337868480725626e-05,
      "loss": 0.4789,
      "step": 100
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.267573696145125e-05,
      "loss": 0.2222,
      "step": 200
    },
    {
      "epoch": 0.07,
      "learning_rate": 3.401360544217687e-05,
      "loss": 0.109,
      "step": 300
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.53514739229025e-05,
      "loss": 0.072,
      "step": 400
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.964792934717747e-05,
      "loss": 0.0751,
      "step": 500
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.905119942713928e-05,
      "loss": 0.0525,
      "step": 600
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.8454469507101085e-05,
      "loss": 0.0604,
      "step": 700
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.78577395870629e-05,
      "loss": 0.0512,
      "step": 800
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.726100966702471e-05,
      "loss": 0.0659,
      "step": 900
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.6664279746986514e-05,
      "loss": 0.0771,
      "step": 1000
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.6067549826948325e-05,
      "loss": 0.0599,
      "step": 1100
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.547081990691014e-05,
      "loss": 0.054,
      "step": 1200
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.487408998687194e-05,
      "loss": 0.0655,
      "step": 1300
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.4277360066833754e-05,
      "loss": 0.0838,
      "step": 1400
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.3680630146795565e-05,
      "loss": 0.0633,
      "step": 1500
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.308390022675737e-05,
      "loss": 0.0608,
      "step": 1600
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.248717030671918e-05,
      "loss": 0.0577,
      "step": 1700
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.1890440386680994e-05,
      "loss": 0.0543,
      "step": 1800
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.12937104666428e-05,
      "loss": 0.0464,
      "step": 1900
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.069698054660461e-05,
      "loss": 0.0422,
      "step": 2000
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.0100250626566415e-05,
      "loss": 0.0642,
      "step": 2100
    },
    {
      "epoch": 0.5,
      "learning_rate": 3.950352070652823e-05,
      "loss": 0.0528,
      "step": 2200
    },
    {
      "epoch": 0.52,
      "learning_rate": 3.890679078649004e-05,
      "loss": 0.0511,
      "step": 2300
    },
    {
      "epoch": 0.54,
      "learning_rate": 3.831006086645185e-05,
      "loss": 0.0706,
      "step": 2400
    },
    {
      "epoch": 0.57,
      "learning_rate": 3.7713330946413655e-05,
      "loss": 0.0474,
      "step": 2500
    },
    {
      "epoch": 0.59,
      "learning_rate": 3.711660102637547e-05,
      "loss": 0.0566,
      "step": 2600
    },
    {
      "epoch": 0.61,
      "learning_rate": 3.651987110633727e-05,
      "loss": 0.0557,
      "step": 2700
    },
    {
      "epoch": 0.63,
      "learning_rate": 3.592314118629908e-05,
      "loss": 0.0537,
      "step": 2800
    },
    {
      "epoch": 0.66,
      "learning_rate": 3.532641126626089e-05,
      "loss": 0.0646,
      "step": 2900
    },
    {
      "epoch": 0.68,
      "learning_rate": 3.4729681346222707e-05,
      "loss": 0.07,
      "step": 3000
    },
    {
      "epoch": 0.7,
      "learning_rate": 3.413295142618451e-05,
      "loss": 0.0508,
      "step": 3100
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.353622150614632e-05,
      "loss": 0.0521,
      "step": 3200
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.293949158610813e-05,
      "loss": 0.0636,
      "step": 3300
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.234276166606994e-05,
      "loss": 0.0657,
      "step": 3400
    },
    {
      "epoch": 0.79,
      "learning_rate": 3.1746031746031745e-05,
      "loss": 0.0532,
      "step": 3500
    },
    {
      "epoch": 0.82,
      "learning_rate": 3.1149301825993556e-05,
      "loss": 0.0574,
      "step": 3600
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.055257190595537e-05,
      "loss": 0.0425,
      "step": 3700
    },
    {
      "epoch": 0.86,
      "learning_rate": 2.9955841985917176e-05,
      "loss": 0.0545,
      "step": 3800
    },
    {
      "epoch": 0.88,
      "learning_rate": 2.9359112065878985e-05,
      "loss": 0.0624,
      "step": 3900
    },
    {
      "epoch": 0.91,
      "learning_rate": 2.8762382145840793e-05,
      "loss": 0.0488,
      "step": 4000
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.81656522258026e-05,
      "loss": 0.0462,
      "step": 4100
    },
    {
      "epoch": 0.95,
      "learning_rate": 2.756892230576441e-05,
      "loss": 0.0531,
      "step": 4200
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.6972192385726218e-05,
      "loss": 0.0476,
      "step": 4300
    },
    {
      "epoch": 1.0,
      "learning_rate": 2.6375462465688033e-05,
      "loss": 0.0537,
      "step": 4400
    },
    {
      "epoch": 1.0,
      "eval_f1_1": {
        "f1": 0.9362880886426593
      },
      "eval_f1_2": {
        "f1": 0.9555555555555556
      },
      "eval_loss": 0.04831862449645996,
      "eval_precision_1": {
        "precision": 0.9548022598870056
      },
      "eval_precision_2": {
        "precision": 0.9666424945612763
      },
      "eval_recall_1": {
        "recall": 0.9184782608695652
      },
      "eval_recall_2": {
        "recall": 0.9447200566973778
      },
      "eval_runtime": 173.0776,
      "eval_samples_per_second": 58.24,
      "eval_steps_per_second": 3.64,
      "step": 4410
    }
  ],
  "logging_steps": 100,
  "max_steps": 8820,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}