{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002759857867319833,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005519715734639666,
      "grad_norm": 3.440763473510742,
      "learning_rate": 1e-05,
      "loss": 13.6391,
      "step": 1
    },
    {
      "epoch": 0.0005519715734639666,
      "eval_loss": 14.365503311157227,
      "eval_runtime": 327.54,
      "eval_samples_per_second": 9.318,
      "eval_steps_per_second": 4.659,
      "step": 1
    },
    {
      "epoch": 0.0011039431469279332,
      "grad_norm": 4.411158084869385,
      "learning_rate": 2e-05,
      "loss": 14.442,
      "step": 2
    },
    {
      "epoch": 0.0011039431469279332,
      "eval_loss": 14.261597633361816,
      "eval_runtime": 285.9154,
      "eval_samples_per_second": 10.674,
      "eval_steps_per_second": 5.337,
      "step": 2
    },
    {
      "epoch": 0.0016559147203918999,
      "grad_norm": 4.169095993041992,
      "learning_rate": 3e-05,
      "loss": 12.9944,
      "step": 3
    },
    {
      "epoch": 0.0022078862938558663,
      "grad_norm": 4.371578216552734,
      "learning_rate": 4e-05,
      "loss": 14.4328,
      "step": 4
    },
    {
      "epoch": 0.0022078862938558663,
      "eval_loss": 14.10604476928711,
      "eval_runtime": 403.9966,
      "eval_samples_per_second": 7.555,
      "eval_steps_per_second": 3.777,
      "step": 4
    },
    {
      "epoch": 0.002759857867319833,
      "grad_norm": 4.2114176750183105,
      "learning_rate": 5e-05,
      "loss": 13.1741,
      "step": 5
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3699128496291840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}