{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.21447721179624665,
  "eval_steps": 20,
  "global_step": 80,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 1.9393939393939395e-05,
      "loss": 2.0524,
      "step": 20
    },
    {
      "epoch": 0.05,
      "eval_loss": 2.070744514465332,
      "eval_runtime": 124.4779,
      "eval_samples_per_second": 2.635,
      "eval_steps_per_second": 1.318,
      "step": 20
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.8585858585858588e-05,
      "loss": 2.059,
      "step": 40
    },
    {
      "epoch": 0.11,
      "eval_loss": 2.068726062774658,
      "eval_runtime": 124.4655,
      "eval_samples_per_second": 2.635,
      "eval_steps_per_second": 1.318,
      "step": 40
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.7777777777777777e-05,
      "loss": 2.0337,
      "step": 60
    },
    {
      "epoch": 0.16,
      "eval_loss": 2.066453218460083,
      "eval_runtime": 124.4729,
      "eval_samples_per_second": 2.635,
      "eval_steps_per_second": 1.318,
      "step": 60
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.6969696969696972e-05,
      "loss": 2.0875,
      "step": 80
    },
    {
      "epoch": 0.21,
      "eval_loss": 2.063451051712036,
      "eval_runtime": 124.438,
      "eval_samples_per_second": 2.636,
      "eval_steps_per_second": 1.318,
      "step": 80
    }
  ],
  "logging_steps": 20,
  "max_steps": 500,
  "num_train_epochs": 2,
  "save_steps": 20,
  "total_flos": 3.037389329006592e+16,
  "trial_name": null,
  "trial_params": null
}