{
  "best_metric": 0.07475484162569046,
  "best_model_checkpoint": "md6/checkpoint-500",
  "epoch": 0.8503401360544217,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08503401360544217,
      "grad_norm": 5.368859767913818,
      "learning_rate": 2.1186440677966103e-05,
      "loss": 0.6333,
      "step": 50
    },
    {
      "epoch": 0.08503401360544217,
      "eval_accuracy": 0.6843869731800766,
      "eval_auc": 0.9578225166744362,
      "eval_f1": 0.0,
      "eval_loss": 0.42367079854011536,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 24.9725,
      "eval_samples_per_second": 83.612,
      "eval_steps_per_second": 0.36,
      "step": 50
    },
    {
      "epoch": 0.17006802721088435,
      "grad_norm": 4.515960693359375,
      "learning_rate": 2.4631286176965384e-05,
      "loss": 0.2538,
      "step": 100
    },
    {
      "epoch": 0.17006802721088435,
      "eval_accuracy": 0.9597701149425287,
      "eval_auc": 0.9909335241916044,
      "eval_f1": 0.9345794392523364,
      "eval_loss": 0.13562637567520142,
      "eval_precision": 0.96,
      "eval_recall": 0.9104704097116844,
      "eval_runtime": 24.0986,
      "eval_samples_per_second": 86.644,
      "eval_steps_per_second": 0.373,
      "step": 100
    },
    {
      "epoch": 0.25510204081632654,
      "grad_norm": 14.845756530761719,
      "learning_rate": 2.3218624906923747e-05,
      "loss": 0.1239,
      "step": 150
    },
    {
      "epoch": 0.25510204081632654,
      "eval_accuracy": 0.9722222222222222,
      "eval_auc": 0.9943007992898034,
      "eval_f1": 0.9557926829268293,
      "eval_loss": 0.1052221953868866,
      "eval_precision": 0.9601837672281777,
      "eval_recall": 0.9514415781487102,
      "eval_runtime": 24.0864,
      "eval_samples_per_second": 86.688,
      "eval_steps_per_second": 0.374,
      "step": 150
    },
    {
      "epoch": 0.3401360544217687,
      "grad_norm": 5.2007880210876465,
      "learning_rate": 2.086780970949328e-05,
      "loss": 0.1091,
      "step": 200
    },
    {
      "epoch": 0.3401360544217687,
      "eval_accuracy": 0.9703065134099617,
      "eval_auc": 0.994109657846197,
      "eval_f1": 0.9541420118343196,
      "eval_loss": 0.10181248933076859,
      "eval_precision": 0.9307359307359307,
      "eval_recall": 0.9787556904400607,
      "eval_runtime": 24.0848,
      "eval_samples_per_second": 86.694,
      "eval_steps_per_second": 0.374,
      "step": 200
    },
    {
      "epoch": 0.42517006802721086,
      "grad_norm": 8.922403335571289,
      "learning_rate": 1.778459706269106e-05,
      "loss": 0.0836,
      "step": 250
    },
    {
      "epoch": 0.42517006802721086,
      "eval_accuracy": 0.9736590038314177,
      "eval_auc": 0.9950504985075039,
      "eval_f1": 0.9586776859504132,
      "eval_loss": 0.09886385500431061,
      "eval_precision": 0.9494047619047619,
      "eval_recall": 0.9681335356600911,
      "eval_runtime": 24.0636,
      "eval_samples_per_second": 86.77,
      "eval_steps_per_second": 0.374,
      "step": 250
    },
    {
      "epoch": 0.5102040816326531,
      "grad_norm": 8.102276802062988,
      "learning_rate": 1.4238846960563894e-05,
      "loss": 0.1115,
      "step": 300
    },
    {
      "epoch": 0.5102040816326531,
      "eval_accuracy": 0.975095785440613,
      "eval_auc": 0.9959403681171826,
      "eval_f1": 0.960546282245827,
      "eval_loss": 0.07939205318689346,
      "eval_precision": 0.960546282245827,
      "eval_recall": 0.960546282245827,
      "eval_runtime": 24.1258,
      "eval_samples_per_second": 86.546,
      "eval_steps_per_second": 0.373,
      "step": 300
    },
    {
      "epoch": 0.5952380952380952,
      "grad_norm": 6.65503454208374,
      "learning_rate": 1.0540903259038787e-05,
      "loss": 0.0713,
      "step": 350
    },
    {
      "epoch": 0.5952380952380952,
      "eval_accuracy": 0.9770114942528736,
      "eval_auc": 0.9966529009430707,
      "eval_f1": 0.9636363636363636,
      "eval_loss": 0.08206725120544434,
      "eval_precision": 0.962178517397882,
      "eval_recall": 0.9650986342943855,
      "eval_runtime": 24.0904,
      "eval_samples_per_second": 86.674,
      "eval_steps_per_second": 0.374,
      "step": 350
    },
    {
      "epoch": 0.6802721088435374,
      "grad_norm": 6.062926769256592,
      "learning_rate": 7.014430648033901e-06,
      "loss": 0.0709,
      "step": 400
    },
    {
      "epoch": 0.6802721088435374,
      "eval_accuracy": 0.9779693486590039,
      "eval_auc": 0.9973272054802376,
      "eval_f1": 0.9653614457831325,
      "eval_loss": 0.07299614697694778,
      "eval_precision": 0.9581464872944694,
      "eval_recall": 0.9726858877086495,
      "eval_runtime": 24.0866,
      "eval_samples_per_second": 86.687,
      "eval_steps_per_second": 0.374,
      "step": 400
    },
    {
      "epoch": 0.7653061224489796,
      "grad_norm": 0.09032676368951797,
      "learning_rate": 3.9680857097668264e-06,
      "loss": 0.0492,
      "step": 450
    },
    {
      "epoch": 0.7653061224489796,
      "eval_accuracy": 0.9798850574712644,
      "eval_auc": 0.9972932247791519,
      "eval_f1": 0.9683257918552036,
      "eval_loss": 0.08100325614213943,
      "eval_precision": 0.9625187406296851,
      "eval_recall": 0.9742033383915023,
      "eval_runtime": 24.1867,
      "eval_samples_per_second": 86.329,
      "eval_steps_per_second": 0.372,
      "step": 450
    },
    {
      "epoch": 0.8503401360544217,
      "grad_norm": 12.446375846862793,
      "learning_rate": 1.6685015704858877e-06,
      "loss": 0.0844,
      "step": 500
    },
    {
      "epoch": 0.8503401360544217,
      "eval_accuracy": 0.9798850574712644,
      "eval_auc": 0.9973781765318659,
      "eval_f1": 0.9682779456193353,
      "eval_loss": 0.07475484162569046,
      "eval_precision": 0.9639097744360903,
      "eval_recall": 0.9726858877086495,
      "eval_runtime": 24.1006,
      "eval_samples_per_second": 86.637,
      "eval_steps_per_second": 0.373,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 588,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.01
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8419704905400320.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}