{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.011347517730496455,
  "eval_steps": 500,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0022695035460992908,
      "grad_norm": 2.885035991668701,
      "learning_rate": 0.0,
      "loss": 2.2016,
      "step": 1
    },
    {
      "epoch": 0.0045390070921985815,
      "grad_norm": 2.447474718093872,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.0893,
      "step": 2
    },
    {
      "epoch": 0.006808510638297872,
      "grad_norm": 2.3197991847991943,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.2062,
      "step": 3
    },
    {
      "epoch": 0.009078014184397163,
      "grad_norm": 3.228630542755127,
      "learning_rate": 6e-06,
      "loss": 2.3485,
      "step": 4
    },
    {
      "epoch": 0.011347517730496455,
      "grad_norm": 2.308619499206543,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.0531,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2437778668118016.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}