{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 29,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.034482758620689655,
      "grad_norm": 4.296210765838623,
      "learning_rate": 3.333333333333333e-07,
      "loss": 1.5533,
      "mean_token_accuracy": 0.6920064091682434,
      "step": 1
    },
    {
      "epoch": 0.06896551724137931,
      "grad_norm": 5.163259029388428,
      "learning_rate": 6.666666666666666e-07,
      "loss": 1.7853,
      "mean_token_accuracy": 0.6263327598571777,
      "step": 2
    },
    {
      "epoch": 0.10344827586206896,
      "grad_norm": 4.452831745147705,
      "learning_rate": 1e-06,
      "loss": 1.5075,
      "mean_token_accuracy": 0.7126692533493042,
      "step": 3
    },
    {
      "epoch": 0.13793103448275862,
      "grad_norm": 6.790956497192383,
      "learning_rate": 9.963544370490268e-07,
      "loss": 1.9253,
      "mean_token_accuracy": 0.6712393760681152,
      "step": 4
    },
    {
      "epoch": 0.1724137931034483,
      "grad_norm": 3.9182674884796143,
      "learning_rate": 9.85470908713026e-07,
      "loss": 1.6858,
      "mean_token_accuracy": 0.559170126914978,
      "step": 5
    },
    {
      "epoch": 0.20689655172413793,
      "grad_norm": 3.839620351791382,
      "learning_rate": 9.675081213427074e-07,
      "loss": 1.5418,
      "mean_token_accuracy": 0.6354226469993591,
      "step": 6
    },
    {
      "epoch": 0.2413793103448276,
      "grad_norm": 4.464385986328125,
      "learning_rate": 9.427280128266049e-07,
      "loss": 1.5432,
      "mean_token_accuracy": 0.6771755814552307,
      "step": 7
    },
    {
      "epoch": 0.27586206896551724,
      "grad_norm": 3.300748348236084,
      "learning_rate": 9.114919329468282e-07,
      "loss": 1.3202,
      "mean_token_accuracy": 0.6744688153266907,
      "step": 8
    },
    {
      "epoch": 0.3103448275862069,
      "grad_norm": 4.529242515563965,
      "learning_rate": 8.742553740855505e-07,
      "loss": 1.5632,
      "mean_token_accuracy": 0.7091418504714966,
      "step": 9
    },
    {
      "epoch": 0.3448275862068966,
      "grad_norm": 4.9364800453186035,
      "learning_rate": 8.315613291203976e-07,
      "loss": 1.3939,
      "mean_token_accuracy": 0.676058828830719,
      "step": 10
    },
    {
      "epoch": 0.3793103448275862,
      "grad_norm": 4.520140171051025,
      "learning_rate": 7.840323733655778e-07,
      "loss": 1.6434,
      "mean_token_accuracy": 0.6085848808288574,
      "step": 11
    },
    {
      "epoch": 0.41379310344827586,
      "grad_norm": 3.786013126373291,
      "learning_rate": 7.323615860218842e-07,
      "loss": 1.4203,
      "mean_token_accuracy": 0.6495858430862427,
      "step": 12
    },
    {
      "epoch": 0.4482758620689655,
      "grad_norm": 4.0102105140686035,
      "learning_rate": 6.773024435212677e-07,
      "loss": 1.4744,
      "mean_token_accuracy": 0.715476393699646,
      "step": 13
    },
    {
      "epoch": 0.4827586206896552,
      "grad_norm": 6.1422576904296875,
      "learning_rate": 6.196578321437789e-07,
      "loss": 1.7096,
      "mean_token_accuracy": 0.6734651327133179,
      "step": 14
    },
    {
      "epoch": 0.5172413793103449,
      "grad_norm": 4.225828647613525,
      "learning_rate": 5.602683401276614e-07,
      "loss": 1.6184,
      "mean_token_accuracy": 0.6401326656341553,
      "step": 15
    },
    {
      "epoch": 0.5517241379310345,
      "grad_norm": 2.499864101409912,
      "learning_rate": 5e-07,
      "loss": 1.0916,
      "mean_token_accuracy": 0.712737500667572,
      "step": 16
    },
    {
      "epoch": 0.5862068965517241,
      "grad_norm": 3.797278881072998,
      "learning_rate": 4.397316598723385e-07,
      "loss": 1.5532,
      "mean_token_accuracy": 0.6137330532073975,
      "step": 17
    },
    {
      "epoch": 0.6206896551724138,
      "grad_norm": 3.9196736812591553,
      "learning_rate": 3.8034216785622125e-07,
      "loss": 1.5172,
      "mean_token_accuracy": 0.6513392925262451,
      "step": 18
    },
    {
      "epoch": 0.6551724137931034,
      "grad_norm": 3.312458038330078,
      "learning_rate": 3.2269755647873214e-07,
      "loss": 1.4259,
      "mean_token_accuracy": 0.6606206893920898,
      "step": 19
    },
    {
      "epoch": 0.6896551724137931,
      "grad_norm": 4.863149642944336,
      "learning_rate": 2.676384139781157e-07,
      "loss": 1.801,
      "mean_token_accuracy": 0.6028177738189697,
      "step": 20
    },
    {
      "epoch": 0.7241379310344828,
      "grad_norm": 6.340369701385498,
      "learning_rate": 2.1596762663442213e-07,
      "loss": 1.8937,
      "mean_token_accuracy": 0.6635770797729492,
      "step": 21
    },
    {
      "epoch": 0.7586206896551724,
      "grad_norm": 2.400047540664673,
      "learning_rate": 1.6843867087960251e-07,
      "loss": 1.1017,
      "mean_token_accuracy": 0.7170366048812866,
      "step": 22
    },
    {
      "epoch": 0.7931034482758621,
      "grad_norm": 6.618093490600586,
      "learning_rate": 1.257446259144494e-07,
      "loss": 1.8901,
      "mean_token_accuracy": 0.6319121718406677,
      "step": 23
    },
    {
      "epoch": 0.8275862068965517,
      "grad_norm": 3.391517400741577,
      "learning_rate": 8.850806705317182e-08,
      "loss": 1.3663,
      "mean_token_accuracy": 0.6898515224456787,
      "step": 24
    },
    {
      "epoch": 0.8620689655172413,
      "grad_norm": 4.413179874420166,
      "learning_rate": 5.72719871733951e-08,
      "loss": 1.5641,
      "mean_token_accuracy": 0.6674157381057739,
      "step": 25
    },
    {
      "epoch": 0.896551724137931,
      "grad_norm": 4.75150728225708,
      "learning_rate": 3.2491878657292635e-08,
      "loss": 1.6575,
      "mean_token_accuracy": 0.6414722204208374,
      "step": 26
    },
    {
      "epoch": 0.9310344827586207,
      "grad_norm": 3.682435989379883,
      "learning_rate": 1.4529091286973993e-08,
      "loss": 1.3724,
      "mean_token_accuracy": 0.674655020236969,
      "step": 27
    },
    {
      "epoch": 0.9655172413793104,
      "grad_norm": 3.129405975341797,
      "learning_rate": 3.6455629509730135e-09,
      "loss": 1.5536,
      "mean_token_accuracy": 0.5809841752052307,
      "step": 28
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.9102606773376465,
      "learning_rate": 0.0,
      "loss": 1.2491,
      "mean_token_accuracy": 0.6780526041984558,
      "step": 29
    },
    {
      "epoch": 1.0,
      "step": 29,
      "total_flos": 955996483584.0,
      "train_loss": 1.542164264054134,
      "train_runtime": 1339.7897,
      "train_samples_per_second": 0.085,
      "train_steps_per_second": 0.022
    }
  ],
  "logging_steps": 1,
  "max_steps": 29,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 955996483584.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}