{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.09907120743034056,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004953560371517028,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.004953560371517028,
      "eval_loss": NaN,
      "eval_runtime": 90.8413,
      "eval_samples_per_second": 3.743,
      "eval_steps_per_second": 1.871,
      "step": 1
    },
    {
      "epoch": 0.009907120743034056,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 1.802,
      "step": 2
    },
    {
      "epoch": 0.014860681114551083,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.019814241486068113,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.02476780185758514,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 9.0792,
      "step": 5
    },
    {
      "epoch": 0.02476780185758514,
      "eval_loss": NaN,
      "eval_runtime": 10.6167,
      "eval_samples_per_second": 32.025,
      "eval_steps_per_second": 16.013,
      "step": 5
    },
    {
      "epoch": 0.029721362229102165,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0346749226006192,
      "grad_norm": NaN,
      "learning_rate": 7e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.039628482972136225,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.04458204334365325,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.04953560371517028,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.04953560371517028,
      "eval_loss": NaN,
      "eval_runtime": 10.499,
      "eval_samples_per_second": 32.384,
      "eval_steps_per_second": 16.192,
      "step": 10
    },
    {
      "epoch": 0.05448916408668731,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 3.6547,
      "step": 11
    },
    {
      "epoch": 0.05944272445820433,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.06439628482972136,
      "grad_norm": NaN,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.0693498452012384,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 211.5676,
      "step": 14
    },
    {
      "epoch": 0.07430340557275542,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.07430340557275542,
      "eval_loss": NaN,
      "eval_runtime": 12.9686,
      "eval_samples_per_second": 26.217,
      "eval_steps_per_second": 13.109,
      "step": 15
    },
    {
      "epoch": 0.07925696594427245,
      "grad_norm": NaN,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.08421052631578947,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.0891640866873065,
      "grad_norm": NaN,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.09411764705882353,
      "grad_norm": NaN,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.09907120743034056,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.09907120743034056,
      "eval_loss": NaN,
      "eval_runtime": 10.4965,
      "eval_samples_per_second": 32.392,
      "eval_steps_per_second": 16.196,
      "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": 1.4489861203427328e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}