{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 12,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.25,
      "learning_rate": 1.5e-05,
      "loss": 1.3438,
      "step": 1
    },
    {
      "epoch": 0.5,
      "learning_rate": 3e-05,
      "loss": 1.1825,
      "step": 2
    },
    {
      "epoch": 0.75,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 1.2953,
      "step": 3
    },
    {
      "epoch": 1.0,
      "learning_rate": 2.4e-05,
      "loss": 1.2925,
      "step": 4
    },
    {
      "epoch": 1.25,
      "learning_rate": 2.1e-05,
      "loss": 1.1694,
      "step": 5
    },
    {
      "epoch": 1.5,
      "learning_rate": 1.8e-05,
      "loss": 1.1904,
      "step": 6
    },
    {
      "epoch": 1.75,
      "learning_rate": 1.5e-05,
      "loss": 0.9801,
      "step": 7
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.2e-05,
      "loss": 1.103,
      "step": 8
    },
    {
      "epoch": 2.25,
      "learning_rate": 9e-06,
      "loss": 0.9197,
      "step": 9
    },
    {
      "epoch": 2.5,
      "learning_rate": 6e-06,
      "loss": 0.9843,
      "step": 10
    },
    {
      "epoch": 2.75,
      "learning_rate": 3e-06,
      "loss": 1.0406,
      "step": 11
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0,
      "loss": 1.0179,
      "step": 12
    }
  ],
  "logging_steps": 1,
  "max_steps": 12,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 262977777303552.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}