{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 432,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.93,
      "learning_rate": 2.6851851851851855e-05,
      "loss": 3.6154,
      "step": 200
    },
    {
      "epoch": 1.85,
      "learning_rate": 3.7037037037037037e-06,
      "loss": 3.2032,
      "step": 400
    },
    {
      "epoch": 2.0,
      "step": 432,
      "total_flos": 450998191521792.0,
      "train_loss": 3.38958450599953,
      "train_runtime": 386.6866,
      "train_samples_per_second": 4.464,
      "train_steps_per_second": 1.117
    }
  ],
  "logging_steps": 200,
  "max_steps": 432,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 450998191521792.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}