{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1841,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.27159152634437805,
      "grad_norm": 5.407573699951172,
      "learning_rate": 3.64204236827811e-05,
      "loss": 4.9175,
      "step": 500
    },
    {
      "epoch": 0.5431830526887561,
      "grad_norm": 6.625548839569092,
      "learning_rate": 2.2840847365562197e-05,
      "loss": 4.1645,
      "step": 1000
    },
    {
      "epoch": 0.8147745790331342,
      "grad_norm": 8.091059684753418,
      "learning_rate": 9.261271048343292e-06,
      "loss": 3.9251,
      "step": 1500
    }
  ],
  "logging_steps": 500,
  "max_steps": 1841,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1347900847854912.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}