{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 189,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 0.9081946484744549,
      "epoch": 0.053015241882041084,
      "grad_norm": 51.5,
      "learning_rate": 3e-06,
      "loss": 2.320839500427246,
      "mean_token_accuracy": 0.5708254482597113,
      "num_tokens": 30761.0,
      "step": 10
    },
    {
      "entropy": 1.032745758444071,
      "epoch": 0.10603048376408217,
      "grad_norm": 21.125,
      "learning_rate": 6.333333333333333e-06,
      "loss": 1.9631355285644532,
      "mean_token_accuracy": 0.5809337079524994,
      "num_tokens": 61277.0,
      "step": 20
    },
    {
      "entropy": 1.2370933540165425,
      "epoch": 0.15904572564612326,
      "grad_norm": 11.0625,
      "learning_rate": 9.666666666666667e-06,
      "loss": 1.4653306961059571,
      "mean_token_accuracy": 0.6311864696443081,
      "num_tokens": 91730.0,
      "step": 30
    },
    {
      "entropy": 1.1646109029650689,
      "epoch": 0.21206096752816433,
      "grad_norm": 8.5625,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 1.200753402709961,
      "mean_token_accuracy": 0.6730783767998219,
      "num_tokens": 122896.0,
      "step": 40
    },
    {
      "entropy": 1.0138436160981654,
      "epoch": 0.26507620941020543,
      "grad_norm": 7.4375,
      "learning_rate": 1.6333333333333335e-05,
      "loss": 1.0109354972839355,
      "mean_token_accuracy": 0.7080431424081326,
      "num_tokens": 153323.0,
      "step": 50
    },
    {
      "entropy": 0.8669569574296474,
      "epoch": 0.31809145129224653,
      "grad_norm": 6.75,
      "learning_rate": 1.9666666666666666e-05,
      "loss": 0.8859419822692871,
      "mean_token_accuracy": 0.7356305047869682,
      "num_tokens": 183928.0,
      "step": 60
    },
    {
      "entropy": 0.856675973534584,
      "epoch": 0.3711066931742876,
      "grad_norm": 7.6875,
      "learning_rate": 1.9666666666666666e-05,
      "loss": 0.8721119880676269,
      "mean_token_accuracy": 0.7318881675601006,
      "num_tokens": 215054.0,
      "step": 70
    },
    {
      "entropy": 0.7872001446783543,
      "epoch": 0.42412193505632867,
      "grad_norm": 7.46875,
      "learning_rate": 1.92962962962963e-05,
      "loss": 0.7920477390289307,
      "mean_token_accuracy": 0.7553018122911453,
      "num_tokens": 245614.0,
      "step": 80
    },
    {
      "entropy": 0.7739131577312947,
      "epoch": 0.47713717693836977,
      "grad_norm": 7.09375,
      "learning_rate": 1.8925925925925928e-05,
      "loss": 0.7949441432952881,
      "mean_token_accuracy": 0.7514781631529331,
      "num_tokens": 276651.0,
      "step": 90
    },
    {
      "entropy": 0.7763891488313674,
      "epoch": 0.5301524188204109,
      "grad_norm": 7.8125,
      "learning_rate": 1.8555555555555557e-05,
      "loss": 0.7867375373840332,
      "mean_token_accuracy": 0.7523738898336887,
      "num_tokens": 308561.0,
      "step": 100
    },
    {
      "entropy": 0.7757978036999702,
      "epoch": 0.583167660702452,
      "grad_norm": 7.21875,
      "learning_rate": 1.8185185185185186e-05,
      "loss": 0.7776416301727295,
      "mean_token_accuracy": 0.7548527352511882,
      "num_tokens": 339537.0,
      "step": 110
    },
    {
      "entropy": 0.7528716944158077,
      "epoch": 0.6361829025844931,
      "grad_norm": 6.28125,
      "learning_rate": 1.7814814814814815e-05,
      "loss": 0.7566296100616455,
      "mean_token_accuracy": 0.7637521453201771,
      "num_tokens": 370938.0,
      "step": 120
    },
    {
      "entropy": 0.7483146995306015,
      "epoch": 0.6891981444665342,
      "grad_norm": 7.0,
      "learning_rate": 1.7444444444444448e-05,
      "loss": 0.7508650302886963,
      "mean_token_accuracy": 0.758705198019743,
      "num_tokens": 402708.0,
      "step": 130
    },
    {
      "entropy": 0.7206243231892586,
      "epoch": 0.7422133863485753,
      "grad_norm": 6.65625,
      "learning_rate": 1.7074074074074077e-05,
      "loss": 0.7531259536743165,
      "mean_token_accuracy": 0.7641572073101998,
      "num_tokens": 433645.0,
      "step": 140
    },
    {
      "entropy": 0.7596748031675815,
      "epoch": 0.7952286282306164,
      "grad_norm": 6.03125,
      "learning_rate": 1.6703703703703703e-05,
      "loss": 0.7591583728790283,
      "mean_token_accuracy": 0.7570627965033054,
      "num_tokens": 465791.0,
      "step": 150
    },
    {
      "entropy": 0.7133973561227321,
      "epoch": 0.8482438701126573,
      "grad_norm": 7.125,
      "learning_rate": 1.6333333333333335e-05,
      "loss": 0.7458220005035401,
      "mean_token_accuracy": 0.7626615799963474,
      "num_tokens": 497296.0,
      "step": 160
    },
    {
      "entropy": 0.7134327009320259,
      "epoch": 0.9012591119946984,
      "grad_norm": 7.0,
      "learning_rate": 1.5962962962962964e-05,
      "loss": 0.7290266990661621,
      "mean_token_accuracy": 0.7681502625346184,
      "num_tokens": 528181.0,
      "step": 170
    },
    {
      "entropy": 0.7324420973658562,
      "epoch": 0.9542743538767395,
      "grad_norm": 7.5,
      "learning_rate": 1.5592592592592593e-05,
      "loss": 0.731742525100708,
      "mean_token_accuracy": 0.7631207950413227,
      "num_tokens": 558915.0,
      "step": 180
    }
  ],
  "logging_steps": 10,
  "max_steps": 600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5671984696049664.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}