{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.6153846153846154,
  "eval_steps": 500,
  "global_step": 2,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 1.2766305208206177,
      "learning_rate": 0.0001,
      "loss": 8.999,
      "step": 1
    },
    {
      "epoch": 1.6153846153846154,
      "grad_norm": 1.5327303409576416,
      "learning_rate": 0.0,
      "loss": 10.065,
      "step": 2
    },
    {
      "epoch": 1.6153846153846154,
      "step": 2,
      "total_flos": 5593954544832.0,
      "train_loss": 9.532014846801758,
      "train_runtime": 18.5492,
      "train_samples_per_second": 2.696,
      "train_steps_per_second": 0.108
    }
  ],
  "logging_steps": 1,
  "max_steps": 2,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 5593954544832.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}