{
  "best_metric": 0.24507267773151398,
  "best_model_checkpoint": "autotrain-aws-bot/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": 0.14,
      "grad_norm": 0.9906547665596008,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.6706,
      "step": 1
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.8777462840080261,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.6796,
      "step": 2
    },
    {
      "epoch": 0.43,
      "grad_norm": 1.4442048072814941,
      "learning_rate": 5e-05,
      "loss": 0.6768,
      "step": 3
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.9797923564910889,
      "learning_rate": 4.722222222222222e-05,
      "loss": 0.6439,
      "step": 4
    },
    {
      "epoch": 0.71,
      "grad_norm": 1.10081148147583,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.5882,
      "step": 5
    },
    {
      "epoch": 0.86,
      "grad_norm": 1.303324818611145,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.5857,
      "step": 6
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.0864627361297607,
      "learning_rate": 3.888888888888889e-05,
      "loss": 0.4485,
      "step": 7
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7692307692307693,
      "eval_auc": 1.0,
      "eval_f1": 0.5714285714285715,
      "eval_loss": 0.5035242438316345,
      "eval_precision": 1.0,
      "eval_recall": 0.4,
      "eval_runtime": 2.7698,
      "eval_samples_per_second": 4.694,
      "eval_steps_per_second": 0.361,
      "step": 7
    },
    {
      "epoch": 1.14,
      "grad_norm": 1.2023175954818726,
      "learning_rate": 3.611111111111111e-05,
      "loss": 0.4929,
      "step": 8
    },
    {
      "epoch": 1.29,
      "grad_norm": 1.3308582305908203,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.4956,
      "step": 9
    },
    {
      "epoch": 1.43,
      "grad_norm": 1.4266738891601562,
      "learning_rate": 3.055555555555556e-05,
      "loss": 0.4785,
      "step": 10
    },
    {
      "epoch": 1.57,
      "grad_norm": 1.225010871887207,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.4103,
      "step": 11
    },
    {
      "epoch": 1.71,
      "grad_norm": 1.222987413406372,
      "learning_rate": 2.5e-05,
      "loss": 0.3671,
      "step": 12
    },
    {
      "epoch": 1.86,
      "grad_norm": 1.9384844303131104,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.374,
      "step": 13
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.558770775794983,
      "learning_rate": 1.9444444444444445e-05,
      "loss": 0.2794,
      "step": 14
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 1.0,
      "eval_auc": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.30896323919296265,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 2.7788,
      "eval_samples_per_second": 4.678,
      "eval_steps_per_second": 0.36,
      "step": 14
    },
    {
      "epoch": 2.14,
      "grad_norm": 1.2155436277389526,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.354,
      "step": 15
    },
    {
      "epoch": 2.29,
      "grad_norm": 1.1273193359375,
      "learning_rate": 1.388888888888889e-05,
      "loss": 0.3029,
      "step": 16
    },
    {
      "epoch": 2.43,
      "grad_norm": 2.222987413406372,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.3328,
      "step": 17
    },
    {
      "epoch": 2.57,
      "grad_norm": 1.1043330430984497,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.2863,
      "step": 18
    },
    {
      "epoch": 2.71,
      "grad_norm": 1.2547301054000854,
      "learning_rate": 5.555555555555556e-06,
      "loss": 0.3237,
      "step": 19
    },
    {
      "epoch": 2.86,
      "grad_norm": 1.096131443977356,
      "learning_rate": 2.777777777777778e-06,
      "loss": 0.3023,
      "step": 20
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.4694621562957764,
      "learning_rate": 0.0,
      "loss": 0.2381,
      "step": 21
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 1.0,
      "eval_auc": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.24507267773151398,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 2.9112,
      "eval_samples_per_second": 4.466,
      "eval_steps_per_second": 0.344,
      "step": 21
    }
  ],
  "logging_steps": 1,
  "max_steps": 21,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 9669331284480.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}