{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.09535160905840286,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01907032181168057,
      "grad_norm": 14.169539451599121,
      "learning_rate": 1e-05,
      "loss": 12.3391,
      "step": 1
    },
    {
      "epoch": 0.01907032181168057,
      "eval_loss": 11.807792663574219,
      "eval_runtime": 166.5241,
      "eval_samples_per_second": 0.534,
      "eval_steps_per_second": 0.27,
      "step": 1
    },
    {
      "epoch": 0.03814064362336114,
      "grad_norm": 12.932425498962402,
      "learning_rate": 2e-05,
      "loss": 12.2518,
      "step": 2
    },
    {
      "epoch": 0.03814064362336114,
      "eval_loss": 11.698576927185059,
      "eval_runtime": 4.9908,
      "eval_samples_per_second": 17.833,
      "eval_steps_per_second": 9.017,
      "step": 2
    },
    {
      "epoch": 0.057210965435041714,
      "grad_norm": 12.602157592773438,
      "learning_rate": 3e-05,
      "loss": 11.3126,
      "step": 3
    },
    {
      "epoch": 0.07628128724672228,
      "grad_norm": 12.895790100097656,
      "learning_rate": 4e-05,
      "loss": 11.9056,
      "step": 4
    },
    {
      "epoch": 0.07628128724672228,
      "eval_loss": 11.039545059204102,
      "eval_runtime": 4.8889,
      "eval_samples_per_second": 18.204,
      "eval_steps_per_second": 9.205,
      "step": 4
    },
    {
      "epoch": 0.09535160905840286,
      "grad_norm": 12.287543296813965,
      "learning_rate": 5e-05,
      "loss": 10.4053,
      "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": 8209574469304320.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}