{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.913705583756345,
  "eval_steps": 500,
  "global_step": 245,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 5.256492614746094,
      "learning_rate": 9.244916810456821e-05,
      "loss": 2.3741,
      "step": 50
    },
    {
      "epoch": 2.0,
      "grad_norm": 54.87091827392578,
      "learning_rate": 6.720476743745072e-05,
      "loss": 0.5805,
      "step": 100
    },
    {
      "epoch": 3.0,
      "grad_norm": 4.914775371551514,
      "learning_rate": 3.467527329945026e-05,
      "loss": 0.381,
      "step": 150
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.792452335357666,
      "learning_rate": 8.634798372847148e-06,
      "loss": 0.2855,
      "step": 200
    }
  ],
  "logging_steps": 50,
  "max_steps": 245,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 2.315062353906893e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}