{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 113,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008908685968819599,
      "grad_norm": 47.238216400146484,
      "learning_rate": 4.166666666666666e-08,
      "loss": 1.6878271102905273,
      "step": 1,
      "token_acc": 0.8026243849097867
    },
    {
      "epoch": 0.044543429844097995,
      "grad_norm": 42.44779968261719,
      "learning_rate": 2.0833333333333333e-07,
      "loss": 1.6754802465438843,
      "step": 5,
      "token_acc": 0.7994841162096117
    },
    {
      "epoch": 0.08908685968819599,
      "grad_norm": 49.14453125,
      "learning_rate": 2.4913894091195504e-07,
      "loss": 1.6546676635742188,
      "step": 10,
      "token_acc": 0.7997270914243728
    },
    {
      "epoch": 0.133630289532294,
      "grad_norm": 46.674034118652344,
      "learning_rate": 2.4566120963893017e-07,
      "loss": 1.5866923332214355,
      "step": 15,
      "token_acc": 0.7979928779540304
    },
    {
      "epoch": 0.17817371937639198,
      "grad_norm": 44.81178283691406,
      "learning_rate": 2.3958774686174805e-07,
      "loss": 1.5554664611816407,
      "step": 20,
      "token_acc": 0.799013827848644
    },
    {
      "epoch": 0.22271714922049,
      "grad_norm": 36.78907012939453,
      "learning_rate": 2.3104920831241437e-07,
      "loss": 1.3084081649780273,
      "step": 25,
      "token_acc": 0.803969693735994
    },
    {
      "epoch": 0.267260579064588,
      "grad_norm": 29.89940071105957,
      "learning_rate": 2.2022927981322682e-07,
      "loss": 1.2958971023559571,
      "step": 30,
      "token_acc": 0.8049758404441246
    },
    {
      "epoch": 0.311804008908686,
      "grad_norm": 28.320785522460938,
      "learning_rate": 2.0736072572451387e-07,
      "loss": 1.2554569244384766,
      "step": 35,
      "token_acc": 0.8120755517826825
    },
    {
      "epoch": 0.35634743875278396,
      "grad_norm": 17.16994857788086,
      "learning_rate": 1.9272038158738265e-07,
      "loss": 1.1012828826904297,
      "step": 40,
      "token_acc": 0.8207843959731543
    },
    {
      "epoch": 0.40089086859688194,
      "grad_norm": 14.638218879699707,
      "learning_rate": 1.7662319868254856e-07,
      "loss": 0.8975942611694336,
      "step": 45,
      "token_acc": 0.8407118055555556
    },
    {
      "epoch": 0.44543429844098,
      "grad_norm": 12.209929466247559,
      "learning_rate": 1.5941546862203247e-07,
      "loss": 0.838934326171875,
      "step": 50,
      "token_acc": 0.8435168162647345
    },
    {
      "epoch": 0.48997772828507796,
      "grad_norm": 13.096250534057617,
      "learning_rate": 1.4146737373010233e-07,
      "loss": 0.8201694488525391,
      "step": 55,
      "token_acc": 0.8506590136054422
    },
    {
      "epoch": 0.534521158129176,
      "grad_norm": 11.963576316833496,
      "learning_rate": 1.2316502347383543e-07,
      "loss": 0.8491922378540039,
      "step": 60,
      "token_acc": 0.8426031812038673
    },
    {
      "epoch": 0.579064587973274,
      "grad_norm": 11.79444694519043,
      "learning_rate": 1.0490214826006647e-07,
      "loss": 0.7839408874511719,
      "step": 65,
      "token_acc": 0.8460634547591069
    },
    {
      "epoch": 0.623608017817372,
      "grad_norm": 11.655221939086914,
      "learning_rate": 8.707162928641263e-08,
      "loss": 0.780324649810791,
      "step": 70,
      "token_acc": 0.8450373532550693
    },
    {
      "epoch": 0.6681514476614699,
      "grad_norm": 12.212353706359863,
      "learning_rate": 7.005704666096235e-08,
      "loss": 0.787574577331543,
      "step": 75,
      "token_acc": 0.8394213757935269
    },
    {
      "epoch": 0.7126948775055679,
      "grad_norm": 11.612573623657227,
      "learning_rate": 5.422442761221037e-08,
      "loss": 0.7592183113098144,
      "step": 80,
      "token_acc": 0.8449086161879895
    },
    {
      "epoch": 0.7572383073496659,
      "grad_norm": 11.407973289489746,
      "learning_rate": 3.991437230636718e-08,
      "loss": 0.7407634735107422,
      "step": 85,
      "token_acc": 0.8492975734355045
    },
    {
      "epoch": 0.8017817371937639,
      "grad_norm": 10.480648040771484,
      "learning_rate": 2.7434726665869255e-08,
      "loss": 0.7494807243347168,
      "step": 90,
      "token_acc": 0.8455267110062218
    },
    {
      "epoch": 0.8463251670378619,
      "grad_norm": 11.382109642028809,
      "learning_rate": 1.7053959815522364e-08,
      "loss": 0.7324390411376953,
      "step": 95,
      "token_acc": 0.850085360648741
    },
    {
      "epoch": 0.89086859688196,
      "grad_norm": 12.241870880126953,
      "learning_rate": 8.99538862436322e-09,
      "loss": 0.7613142013549805,
      "step": 100,
      "token_acc": 0.8418187640089657
    },
    {
      "epoch": 0.9354120267260579,
      "grad_norm": 11.869834899902344,
      "learning_rate": 3.432373588130144e-09,
      "loss": 0.761406135559082,
      "step": 105,
      "token_acc": 0.8450719009131941
    },
    {
      "epoch": 0.9799554565701559,
      "grad_norm": 11.23639965057373,
      "learning_rate": 4.845894012080187e-10,
      "loss": 0.7615683078765869,
      "step": 110,
      "token_acc": 0.8465909090909091
    }
  ],
  "logging_steps": 5,
  "max_steps": 113,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.923389119261573e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}