{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.23076923076923,
  "eval_steps": 500,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.54,
      "learning_rate": 6.666666666666667e-05,
      "loss": 3.3839,
      "step": 10
    },
    {
      "epoch": 3.08,
      "learning_rate": 0.00013333333333333334,
      "loss": 2.6213,
      "step": 20
    },
    {
      "epoch": 4.62,
      "learning_rate": 0.0002,
      "loss": 2.0735,
      "step": 30
    },
    {
      "epoch": 6.15,
      "learning_rate": 0.0002,
      "loss": 1.9831,
      "step": 40
    },
    {
      "epoch": 7.69,
      "learning_rate": 0.0002,
      "loss": 1.8401,
      "step": 50
    },
    {
      "epoch": 9.23,
      "learning_rate": 0.0002,
      "loss": 1.6224,
      "step": 60
    }
  ],
  "logging_steps": 10,
  "max_steps": 150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 25,
  "save_steps": 30,
  "total_flos": 1.3765767134016307e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}