{
  "best_global_step": 432,
  "best_metric": 0.8724944320712695,
  "best_model_checkpoint": "ft_outputs/notebook_model_clf_nickprock/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": 2.3878402709960938,
      "learning_rate": 9.845758354755784e-06,
      "loss": 0.6022430038452149,
      "step": 50
    },
    {
      "epoch": 0.46296296296296297,
      "grad_norm": 3.0308825969696045,
      "learning_rate": 8.560411311053985e-06,
      "loss": 0.4261514282226562,
      "step": 100
    },
    {
      "epoch": 0.6944444444444444,
      "grad_norm": 2.9950129985809326,
      "learning_rate": 7.275064267352185e-06,
      "loss": 0.32795368194580077,
      "step": 150
    },
    {
      "epoch": 0.9259259259259259,
      "grad_norm": 4.5819549560546875,
      "learning_rate": 5.9897172236503865e-06,
      "loss": 0.3201203155517578,
      "step": 200
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.861159420289855,
      "eval_f1": 0.8607153242221576,
      "eval_loss": 0.3076864182949066,
      "eval_precision": 0.8958837772397095,
      "eval_recall": 0.8282036933407946,
      "eval_roc_auc": 0.9439112437962287,
      "eval_runtime": 3.3937,
      "eval_samples_per_second": 1016.591,
      "eval_steps_per_second": 15.912,
      "step": 216
    },
    {
      "epoch": 1.1574074074074074,
      "grad_norm": 5.071096897125244,
      "learning_rate": 4.704370179948586e-06,
      "loss": 0.29723459243774414,
      "step": 250
    },
    {
      "epoch": 1.3888888888888888,
      "grad_norm": 3.658815860748291,
      "learning_rate": 3.4190231362467867e-06,
      "loss": 0.27226547241210936,
      "step": 300
    },
    {
      "epoch": 1.6203703703703702,
      "grad_norm": 3.3279106616973877,
      "learning_rate": 2.1336760925449874e-06,
      "loss": 0.2632809257507324,
      "step": 350
    },
    {
      "epoch": 1.8518518518518519,
      "grad_norm": 4.419345855712891,
      "learning_rate": 8.483290488431877e-07,
      "loss": 0.26902166366577146,
      "step": 400
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8672463768115942,
      "eval_f1": 0.8724944320712695,
      "eval_loss": 0.30226173996925354,
      "eval_precision": 0.8681440443213296,
      "eval_recall": 0.8768886401790711,
      "eval_roc_auc": 0.9464533220987683,
      "eval_runtime": 3.4089,
      "eval_samples_per_second": 1012.061,
      "eval_steps_per_second": 15.841,
      "step": 432
    },
    {
      "epoch": 2.0,
      "step": 432,
      "total_flos": 1814940059873280.0,
      "train_loss": 0.3404614351413868,
      "train_runtime": 117.3927,
      "train_samples_per_second": 235.04,
      "train_steps_per_second": 3.68
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8672463768115942,
      "eval_f1": 0.8724944320712695,
      "eval_loss": 0.30226173996925354,
      "eval_precision": 0.8681440443213296,
      "eval_recall": 0.8768886401790711,
      "eval_roc_auc": 0.9464533220987683,
      "eval_runtime": 3.3578,
      "eval_samples_per_second": 1027.472,
      "eval_steps_per_second": 16.082,
      "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": 1814940059873280.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}