{
  "best_global_step": 432,
  "best_metric": 0.8670062252405206,
  "best_model_checkpoint": "ft_outputs/notebook_model_clf/checkpoint-432",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 432,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.23148148148148148,
      "grad_norm": 34.480255126953125,
      "learning_rate": 9.845758354755784e-06,
      "loss": 0.49710899353027344,
      "step": 50
    },
    {
      "epoch": 0.46296296296296297,
      "grad_norm": 14.985294342041016,
      "learning_rate": 8.560411311053985e-06,
      "loss": 0.4200091552734375,
      "step": 100
    },
    {
      "epoch": 0.6944444444444444,
      "grad_norm": 11.86069393157959,
      "learning_rate": 7.275064267352185e-06,
      "loss": 0.3548846435546875,
      "step": 150
    },
    {
      "epoch": 0.9259259259259259,
      "grad_norm": 14.185436248779297,
      "learning_rate": 5.9897172236503865e-06,
      "loss": 0.3545515060424805,
      "step": 200
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8443478260869566,
      "eval_f1": 0.8380090497737557,
      "eval_loss": 0.3412903845310211,
      "eval_precision": 0.9090314136125655,
      "eval_recall": 0.7772803581421377,
      "eval_roc_auc": 0.9340782513920103,
      "eval_runtime": 19.7364,
      "eval_samples_per_second": 174.804,
      "eval_steps_per_second": 2.736,
      "step": 216
    },
    {
      "epoch": 1.1574074074074074,
      "grad_norm": 33.73603057861328,
      "learning_rate": 4.704370179948586e-06,
      "loss": 0.25113576889038086,
      "step": 250
    },
    {
      "epoch": 1.3888888888888888,
      "grad_norm": 71.73030853271484,
      "learning_rate": 3.4190231362467867e-06,
      "loss": 0.17481367111206056,
      "step": 300
    },
    {
      "epoch": 1.6203703703703702,
      "grad_norm": 35.59589767456055,
      "learning_rate": 2.1336760925449874e-06,
      "loss": 0.1653757858276367,
      "step": 350
    },
    {
      "epoch": 1.8518518518518519,
      "grad_norm": 16.84499740600586,
      "learning_rate": 8.483290488431877e-07,
      "loss": 0.15949118614196778,
      "step": 400
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.863768115942029,
      "eval_f1": 0.8670062252405206,
      "eval_loss": 0.33692029118537903,
      "eval_precision": 0.8769318832283916,
      "eval_recall": 0.8573027420257414,
      "eval_roc_auc": 0.9436943704801936,
      "eval_runtime": 19.6866,
      "eval_samples_per_second": 175.246,
      "eval_steps_per_second": 2.743,
      "step": 432
    },
    {
      "epoch": 2.0,
      "step": 432,
      "total_flos": 9778520136265728.0,
      "train_loss": 0.28536773942134996,
      "train_runtime": 974.0574,
      "train_samples_per_second": 28.327,
      "train_steps_per_second": 0.444
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.863768115942029,
      "eval_f1": 0.8670062252405206,
      "eval_loss": 0.33692029118537903,
      "eval_precision": 0.8769318832283916,
      "eval_recall": 0.8573027420257414,
      "eval_roc_auc": 0.9436943704801936,
      "eval_runtime": 19.3494,
      "eval_samples_per_second": 178.3,
      "eval_steps_per_second": 2.791,
      "step": 432
    }
  ],
  "logging_steps": 50,
  "max_steps": 432,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9778520136265728.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}