{
  "best_metric": NaN,
  "best_model_checkpoint": "/tmp/model/checkpoint-138",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 138,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 78
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 84
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 96
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 102
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 108
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 114
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 120
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 126
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 132
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 138
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.18181818181818182,
      "eval_f1_macro": 0.06153846153846154,
      "eval_f1_micro": 0.18181818181818182,
      "eval_f1_weighted": 0.055944055944055944,
      "eval_loss": NaN,
      "eval_precision_macro": 0.03636363636363636,
      "eval_precision_micro": 0.18181818181818182,
      "eval_precision_weighted": 0.03305785123966942,
      "eval_recall_macro": 0.2,
      "eval_recall_micro": 0.18181818181818182,
      "eval_recall_weighted": 0.18181818181818182,
      "eval_runtime": 2.3944,
      "eval_samples_per_second": 229.707,
      "eval_steps_per_second": 7.518,
      "step": 138
    }
  ],
  "logging_steps": 6,
  "max_steps": 138,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 1.7017698479807693e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}