{
  "best_metric": 0.0227875504642725,
  "best_model_checkpoint": "autotrain-advi6-ry9ri/checkpoint-21",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 21,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 8.617305755615234,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.7572,
      "step": 1
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 6.040043354034424,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.7081,
      "step": 2
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 8.274687767028809,
      "learning_rate": 5e-05,
      "loss": 0.65,
      "step": 3
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 5.714233875274658,
      "learning_rate": 4.722222222222222e-05,
      "loss": 0.5231,
      "step": 4
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 15.41068172454834,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.4632,
      "step": 5
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 15.767964363098145,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.4134,
      "step": 6
    },
    {
      "epoch": 1.0,
      "grad_norm": 22.311086654663086,
      "learning_rate": 3.888888888888889e-05,
      "loss": 0.2814,
      "step": 7
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9230769230769231,
      "eval_auc": 1.0,
      "eval_f1": 0.9411764705882353,
      "eval_loss": 0.19895704090595245,
      "eval_precision": 0.8888888888888888,
      "eval_recall": 1.0,
      "eval_runtime": 2.6313,
      "eval_samples_per_second": 4.94,
      "eval_steps_per_second": 0.38,
      "step": 7
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 27.7358341217041,
      "learning_rate": 3.611111111111111e-05,
      "loss": 0.6625,
      "step": 8
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 2.2699501514434814,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.1144,
      "step": 9
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 3.8326809406280518,
      "learning_rate": 3.055555555555556e-05,
      "loss": 0.0896,
      "step": 10
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 73.82262420654297,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.4205,
      "step": 11
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 1.1242291927337646,
      "learning_rate": 2.5e-05,
      "loss": 0.0564,
      "step": 12
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 13.962393760681152,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.7057,
      "step": 13
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.1181535720825195,
      "learning_rate": 1.9444444444444445e-05,
      "loss": 0.0326,
      "step": 14
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 1.0,
      "eval_auc": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.03868802636861801,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 2.9974,
      "eval_samples_per_second": 4.337,
      "eval_steps_per_second": 0.334,
      "step": 14
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 0.6562063694000244,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.0337,
      "step": 15
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 3.6587820053100586,
      "learning_rate": 1.388888888888889e-05,
      "loss": 0.0578,
      "step": 16
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 15.621935844421387,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.5406,
      "step": 17
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 1.0285580158233643,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.0476,
      "step": 18
    },
    {
      "epoch": 2.7142857142857144,
      "grad_norm": 9.763413429260254,
      "learning_rate": 5.555555555555556e-06,
      "loss": 0.1891,
      "step": 19
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.5249605178833008,
      "learning_rate": 2.777777777777778e-06,
      "loss": 0.0219,
      "step": 20
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.8130949139595032,
      "learning_rate": 0.0,
      "loss": 0.017,
      "step": 21
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 1.0,
      "eval_auc": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.0227875504642725,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 2.5382,
      "eval_samples_per_second": 5.122,
      "eval_steps_per_second": 0.394,
      "step": 21
    }
  ],
  "logging_steps": 1,
  "max_steps": 21,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9669331284480.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}