{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07765105556903665,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003882552778451832,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 89.7599,
      "step": 1
    },
    {
      "epoch": 0.003882552778451832,
      "eval_loss": NaN,
      "eval_runtime": 13.3378,
      "eval_samples_per_second": 32.539,
      "eval_steps_per_second": 16.27,
      "step": 1
    },
    {
      "epoch": 0.007765105556903664,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 328.8567,
      "step": 2
    },
    {
      "epoch": 0.011647658335355497,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 841.0643,
      "step": 3
    },
    {
      "epoch": 0.015530211113807329,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 4114.8735,
      "step": 4
    },
    {
      "epoch": 0.019412763892259162,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 259.3276,
      "step": 5
    },
    {
      "epoch": 0.019412763892259162,
      "eval_loss": NaN,
      "eval_runtime": 1.0249,
      "eval_samples_per_second": 423.442,
      "eval_steps_per_second": 211.721,
      "step": 5
    },
    {
      "epoch": 0.023295316670710994,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 4191.437,
      "step": 6
    },
    {
      "epoch": 0.027177869449162825,
      "grad_norm": NaN,
      "learning_rate": 7e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.031060422227614657,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.03494297500606649,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 2.3386,
      "step": 9
    },
    {
      "epoch": 0.038825527784518324,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 203.3174,
      "step": 10
    },
    {
      "epoch": 0.038825527784518324,
      "eval_loss": NaN,
      "eval_runtime": 1.0719,
      "eval_samples_per_second": 404.904,
      "eval_steps_per_second": 202.452,
      "step": 10
    },
    {
      "epoch": 0.04270808056297015,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 322.1341,
      "step": 11
    },
    {
      "epoch": 0.04659063334142199,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.050473186119873815,
      "grad_norm": NaN,
      "learning_rate": 7.938926261462366e-05,
      "loss": 12.913,
      "step": 13
    },
    {
      "epoch": 0.05435573889832565,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 73.5757,
      "step": 14
    },
    {
      "epoch": 0.05823829167677748,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.05823829167677748,
      "eval_loss": NaN,
      "eval_runtime": 1.105,
      "eval_samples_per_second": 392.745,
      "eval_steps_per_second": 196.373,
      "step": 15
    },
    {
      "epoch": 0.062120844455229314,
      "grad_norm": NaN,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 74.4313,
      "step": 16
    },
    {
      "epoch": 0.06600339723368115,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.5366,
      "step": 17
    },
    {
      "epoch": 0.06988595001213298,
      "grad_norm": NaN,
      "learning_rate": 9.549150281252633e-06,
      "loss": 604.937,
      "step": 18
    },
    {
      "epoch": 0.0737685027905848,
      "grad_norm": NaN,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1065.1898,
      "step": 19
    },
    {
      "epoch": 0.07765105556903665,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 65.6357,
      "step": 20
    },
    {
      "epoch": 0.07765105556903665,
      "eval_loss": NaN,
      "eval_runtime": 1.0552,
      "eval_samples_per_second": 411.289,
      "eval_steps_per_second": 205.644,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 170367906742272.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}