{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.005453073744301964,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002726536872150982,
      "grad_norm": 0.03692223131656647,
      "learning_rate": 1e-05,
      "loss": 11.9439,
      "step": 1
    },
    {
      "epoch": 0.0002726536872150982,
      "eval_loss": 11.939325332641602,
      "eval_runtime": 182.8355,
      "eval_samples_per_second": 135.143,
      "eval_steps_per_second": 33.79,
      "step": 1
    },
    {
      "epoch": 0.0005453073744301963,
      "grad_norm": 0.03877516835927963,
      "learning_rate": 2e-05,
      "loss": 11.9402,
      "step": 2
    },
    {
      "epoch": 0.0008179610616452946,
      "grad_norm": 0.044144406914711,
      "learning_rate": 3e-05,
      "loss": 11.9388,
      "step": 3
    },
    {
      "epoch": 0.0010906147488603927,
      "grad_norm": 0.03819985315203667,
      "learning_rate": 4e-05,
      "loss": 11.9382,
      "step": 4
    },
    {
      "epoch": 0.001363268436075491,
      "grad_norm": 0.03880991041660309,
      "learning_rate": 5e-05,
      "loss": 11.9396,
      "step": 5
    },
    {
      "epoch": 0.001363268436075491,
      "eval_loss": 11.939252853393555,
      "eval_runtime": 182.755,
      "eval_samples_per_second": 135.203,
      "eval_steps_per_second": 33.805,
      "step": 5
    },
    {
      "epoch": 0.0016359221232905893,
      "grad_norm": 0.03697334602475166,
      "learning_rate": 6e-05,
      "loss": 11.9357,
      "step": 6
    },
    {
      "epoch": 0.0019085758105056873,
      "grad_norm": 0.04659397527575493,
      "learning_rate": 7e-05,
      "loss": 11.9412,
      "step": 7
    },
    {
      "epoch": 0.0021812294977207854,
      "grad_norm": 0.03356407210230827,
      "learning_rate": 8e-05,
      "loss": 11.9415,
      "step": 8
    },
    {
      "epoch": 0.002453883184935884,
      "grad_norm": 0.037583865225315094,
      "learning_rate": 9e-05,
      "loss": 11.9381,
      "step": 9
    },
    {
      "epoch": 0.002726536872150982,
      "grad_norm": 0.030221182852983475,
      "learning_rate": 0.0001,
      "loss": 11.9351,
      "step": 10
    },
    {
      "epoch": 0.002726536872150982,
      "eval_loss": 11.938981056213379,
      "eval_runtime": 182.6671,
      "eval_samples_per_second": 135.268,
      "eval_steps_per_second": 33.821,
      "step": 10
    },
    {
      "epoch": 0.00299919055936608,
      "grad_norm": 0.03368884697556496,
      "learning_rate": 9.755282581475769e-05,
      "loss": 11.9436,
      "step": 11
    },
    {
      "epoch": 0.0032718442465811785,
      "grad_norm": 0.03182883933186531,
      "learning_rate": 9.045084971874738e-05,
      "loss": 11.9372,
      "step": 12
    },
    {
      "epoch": 0.0035444979337962766,
      "grad_norm": 0.04742654412984848,
      "learning_rate": 7.938926261462366e-05,
      "loss": 11.9381,
      "step": 13
    },
    {
      "epoch": 0.0038171516210113747,
      "grad_norm": 0.03973816707730293,
      "learning_rate": 6.545084971874738e-05,
      "loss": 11.9325,
      "step": 14
    },
    {
      "epoch": 0.004089805308226473,
      "grad_norm": 0.03192592039704323,
      "learning_rate": 5e-05,
      "loss": 11.9413,
      "step": 15
    },
    {
      "epoch": 0.004089805308226473,
      "eval_loss": 11.938648223876953,
      "eval_runtime": 182.7753,
      "eval_samples_per_second": 135.188,
      "eval_steps_per_second": 33.801,
      "step": 15
    },
    {
      "epoch": 0.004362458995441571,
      "grad_norm": 0.03549959138035774,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 11.9375,
      "step": 16
    },
    {
      "epoch": 0.004635112682656669,
      "grad_norm": 0.0373225063085556,
      "learning_rate": 2.061073738537635e-05,
      "loss": 11.9432,
      "step": 17
    },
    {
      "epoch": 0.004907766369871768,
      "grad_norm": 0.03938879817724228,
      "learning_rate": 9.549150281252633e-06,
      "loss": 11.944,
      "step": 18
    },
    {
      "epoch": 0.005180420057086865,
      "grad_norm": 0.041206326335668564,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 11.9442,
      "step": 19
    },
    {
      "epoch": 0.005453073744301964,
      "grad_norm": 0.03595578670501709,
      "learning_rate": 0.0,
      "loss": 11.9405,
      "step": 20
    },
    {
      "epoch": 0.005453073744301964,
      "eval_loss": 11.938558578491211,
      "eval_runtime": 182.5252,
      "eval_samples_per_second": 135.373,
      "eval_steps_per_second": 33.847,
      "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": 479660605440.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}