{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1434,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.0921465968586386,
      "grad_norm": 110.41195678710938,
      "learning_rate": 6.520223152022316e-06,
      "loss": -84.5178,
      "step": 500
    },
    {
      "epoch": 4.184293193717277,
      "grad_norm": 88.54283142089844,
      "learning_rate": 3.0334728033472805e-06,
      "loss": -150.6505,
      "step": 1000
    }
  ],
  "logging_steps": 500,
  "max_steps": 1434,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}