{
  "best_metric": 0.013029049150645733,
  "best_model_checkpoint": "/tmp/model/checkpoint-129",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 129,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 3.846153846153847e-06,
      "loss": 0.9819,
      "step": 6
    },
    {
      "epoch": 0.09,
      "learning_rate": 8.461538461538462e-06,
      "loss": 0.6736,
      "step": 12
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.3076923076923078e-05,
      "loss": 0.2587,
      "step": 18
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.7692307692307694e-05,
      "loss": 0.142,
      "step": 24
    },
    {
      "epoch": 0.23,
      "learning_rate": 2.230769230769231e-05,
      "loss": 0.0517,
      "step": 30
    },
    {
      "epoch": 0.28,
      "learning_rate": 2.6923076923076923e-05,
      "loss": 0.0392,
      "step": 36
    },
    {
      "epoch": 0.33,
      "learning_rate": 3.153846153846154e-05,
      "loss": 0.0163,
      "step": 42
    },
    {
      "epoch": 0.37,
      "learning_rate": 3.615384615384615e-05,
      "loss": 0.0066,
      "step": 48
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.0769230769230773e-05,
      "loss": 0.0519,
      "step": 54
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.538461538461539e-05,
      "loss": 0.0352,
      "step": 60
    },
    {
      "epoch": 0.51,
      "learning_rate": 5e-05,
      "loss": 0.0083,
      "step": 66
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.9482758620689655e-05,
      "loss": 0.0026,
      "step": 72
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.896551724137931e-05,
      "loss": 0.0058,
      "step": 78
    },
    {
      "epoch": 0.65,
      "learning_rate": 4.844827586206897e-05,
      "loss": 0.0237,
      "step": 84
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.793103448275863e-05,
      "loss": 0.0004,
      "step": 90
    },
    {
      "epoch": 0.74,
      "learning_rate": 4.741379310344828e-05,
      "loss": 0.0015,
      "step": 96
    },
    {
      "epoch": 0.79,
      "learning_rate": 4.689655172413793e-05,
      "loss": 0.0003,
      "step": 102
    },
    {
      "epoch": 0.84,
      "learning_rate": 4.6379310344827586e-05,
      "loss": 0.0052,
      "step": 108
    },
    {
      "epoch": 0.88,
      "learning_rate": 4.586206896551724e-05,
      "loss": 0.0003,
      "step": 114
    },
    {
      "epoch": 0.93,
      "learning_rate": 4.53448275862069e-05,
      "loss": 0.0002,
      "step": 120
    },
    {
      "epoch": 0.98,
      "learning_rate": 4.482758620689655e-05,
      "loss": 0.0002,
      "step": 126
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.997078870496592,
      "eval_auc": 0.9999006951340615,
      "eval_f1": 0.9189189189189189,
      "eval_loss": 0.013029049150645733,
      "eval_precision": 1.0,
      "eval_recall": 0.85,
      "eval_runtime": 5.2869,
      "eval_samples_per_second": 194.255,
      "eval_steps_per_second": 3.216,
      "step": 129
    }
  ],
  "logging_steps": 6,
  "max_steps": 645,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 1080070882252800.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}