{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.5504773512086127,
  "eval_steps": 500,
  "global_step": 5420,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "learning_rate": 0.00019979695431472083,
      "loss": 3.1881,
      "step": 984
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001778128879358989,
      "loss": 2.8735,
      "step": 1968
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00015560320505586276,
      "loss": 2.8491,
      "step": 2952
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00013339352217582665,
      "loss": 2.8245,
      "step": 3936
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00011118383929579055,
      "loss": 2.8554,
      "step": 4920
    }
  ],
  "logging_steps": 984,
  "max_steps": 9846,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 5703041682505728.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}