{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0021976512602156447,
  "eval_steps": 2,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005494128150539112,
      "grad_norm": 0.8909298181533813,
      "learning_rate": 1e-05,
      "loss": 23.2604,
      "step": 1
    },
    {
      "epoch": 0.0005494128150539112,
      "eval_loss": 1.7195411920547485,
      "eval_runtime": 260.7917,
      "eval_samples_per_second": 11.757,
      "eval_steps_per_second": 5.878,
      "step": 1
    },
    {
      "epoch": 0.0010988256301078224,
      "grad_norm": 1.0054759979248047,
      "learning_rate": 2e-05,
      "loss": 24.8289,
      "step": 2
    },
    {
      "epoch": 0.0010988256301078224,
      "eval_loss": 1.7166640758514404,
      "eval_runtime": 420.6951,
      "eval_samples_per_second": 7.288,
      "eval_steps_per_second": 3.644,
      "step": 2
    },
    {
      "epoch": 0.0016482384451617334,
      "grad_norm": 1.0694772005081177,
      "learning_rate": 3e-05,
      "loss": 27.0594,
      "step": 3
    },
    {
      "epoch": 0.0021976512602156447,
      "grad_norm": 1.2885613441467285,
      "learning_rate": 4e-05,
      "loss": 26.5673,
      "step": 4
    },
    {
      "epoch": 0.0021976512602156447,
      "eval_loss": 1.7147361040115356,
      "eval_runtime": 1172.5782,
      "eval_samples_per_second": 2.615,
      "eval_steps_per_second": 1.307,
      "step": 4
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9815295346606080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}