{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 779,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 1.769014136493206,
      "epoch": 0.03209757663296421,
      "grad_norm": 0.0654296875,
      "learning_rate": 0.0002,
      "loss": 1.927232666015625,
      "mean_token_accuracy": 0.5845547493547201,
      "num_tokens": 147388.0,
      "step": 25
    },
    {
      "entropy": 1.5947067447006702,
      "epoch": 0.06419515326592842,
      "grad_norm": 0.0703125,
      "learning_rate": 0.00019945941475610623,
      "loss": 1.5756130981445313,
      "mean_token_accuracy": 0.6429479970037937,
      "num_tokens": 291902.0,
      "step": 50
    },
    {
      "entropy": 1.4042670665308834,
      "epoch": 0.09629272989889263,
      "grad_norm": 0.083984375,
      "learning_rate": 0.00019784350367254322,
      "loss": 1.3896011352539062,
      "mean_token_accuracy": 0.6840905399620533,
      "num_tokens": 436739.0,
      "step": 75
    },
    {
      "entropy": 1.2599401247128845,
      "epoch": 0.12839030653185685,
      "grad_norm": 0.07470703125,
      "learning_rate": 0.00019516973750305532,
      "loss": 1.247992630004883,
      "mean_token_accuracy": 0.7115654723346233,
      "num_tokens": 578709.0,
      "step": 100
    },
    {
      "entropy": 1.1777591889351606,
      "epoch": 0.16048788316482104,
      "grad_norm": 0.0859375,
      "learning_rate": 0.0001914670242183795,
      "loss": 1.1679031372070312,
      "mean_token_accuracy": 0.7358129184693099,
      "num_tokens": 723238.0,
      "step": 125
    },
    {
      "entropy": 1.0801194526255131,
      "epoch": 0.19258545979778527,
      "grad_norm": 0.1064453125,
      "learning_rate": 0.00018677539646179707,
      "loss": 1.0448343658447266,
      "mean_token_accuracy": 0.7570553781092166,
      "num_tokens": 866427.0,
      "step": 150
    },
    {
      "entropy": 1.0227313496544956,
      "epoch": 0.22468303643074947,
      "grad_norm": 0.080078125,
      "learning_rate": 0.00018114557872800905,
      "loss": 1.023138198852539,
      "mean_token_accuracy": 0.7729750864207745,
      "num_tokens": 1012131.0,
      "step": 175
    },
    {
      "entropy": 0.8637316187471151,
      "epoch": 0.2567806130637137,
      "grad_norm": 0.09033203125,
      "learning_rate": 0.00017463843894486937,
      "loss": 0.8490833282470703,
      "mean_token_accuracy": 0.8087801007926464,
      "num_tokens": 1157299.0,
      "step": 200
    },
    {
      "entropy": 0.8652995108067989,
      "epoch": 0.2888781896966779,
      "grad_norm": 0.07373046875,
      "learning_rate": 0.00016732433038731242,
      "loss": 0.8502191162109375,
      "mean_token_accuracy": 0.8063283850252628,
      "num_tokens": 1299656.0,
      "step": 225
    },
    {
      "entropy": 0.7840015215892344,
      "epoch": 0.3209757663296421,
      "grad_norm": 0.087890625,
      "learning_rate": 0.0001592823310385073,
      "loss": 0.7785140228271484,
      "mean_token_accuracy": 0.8246484726667405,
      "num_tokens": 1441547.0,
      "step": 250
    },
    {
      "entropy": 0.8248297751229257,
      "epoch": 0.35307334296260634,
      "grad_norm": 0.1279296875,
      "learning_rate": 0.00015059938862204127,
      "loss": 0.8086457824707032,
      "mean_token_accuracy": 0.8171890932321548,
      "num_tokens": 1582972.0,
      "step": 275
    },
    {
      "entropy": 0.770206793518737,
      "epoch": 0.38517091959557054,
      "grad_norm": 0.12890625,
      "learning_rate": 0.00014136938054879283,
      "loss": 0.7686289978027344,
      "mean_token_accuracy": 0.8326107160747052,
      "num_tokens": 1731903.0,
      "step": 300
    },
    {
      "entropy": 0.8494727142900228,
      "epoch": 0.41726849622853474,
      "grad_norm": 0.072265625,
      "learning_rate": 0.0001316920989420703,
      "loss": 0.842440185546875,
      "mean_token_accuracy": 0.812195960432291,
      "num_tokens": 1877046.0,
      "step": 325
    },
    {
      "entropy": 0.7691456920653582,
      "epoch": 0.44936607286149893,
      "grad_norm": 0.08984375,
      "learning_rate": 0.00012167217171462566,
      "loss": 0.7498253631591797,
      "mean_token_accuracy": 0.8340029817819595,
      "num_tokens": 2020060.0,
      "step": 350
    },
    {
      "entropy": 0.6002831929549575,
      "epoch": 0.4814636494944632,
      "grad_norm": 0.09716796875,
      "learning_rate": 0.00011141793136253986,
      "loss": 0.574959716796875,
      "mean_token_accuracy": 0.8719502376019954,
      "num_tokens": 2163196.0,
      "step": 375
    },
    {
      "entropy": 0.5365751892980188,
      "epoch": 0.5135612261274274,
      "grad_norm": 0.060546875,
      "learning_rate": 0.00010104024370624644,
      "loss": 0.5327357482910157,
      "mean_token_accuracy": 0.8794836418330669,
      "num_tokens": 2306310.0,
      "step": 400
    },
    {
      "entropy": 0.6227946990681812,
      "epoch": 0.5456588027603916,
      "grad_norm": 0.08837890625,
      "learning_rate": 9.065130924199998e-05,
      "loss": 0.6111849975585938,
      "mean_token_accuracy": 0.8625345961749553,
      "num_tokens": 2451606.0,
      "step": 425
    },
    {
      "entropy": 0.5804533056542277,
      "epoch": 0.5777563793933558,
      "grad_norm": 0.0654296875,
      "learning_rate": 8.036345006322359e-05,
      "loss": 0.5718699645996094,
      "mean_token_accuracy": 0.8725813579559326,
      "num_tokens": 2597270.0,
      "step": 450
    },
    {
      "entropy": 0.6302943672612309,
      "epoch": 0.60985395602632,
      "grad_norm": 0.06884765625,
      "learning_rate": 7.028789546718326e-05,
      "loss": 0.6353359985351562,
      "mean_token_accuracy": 0.8635560862720013,
      "num_tokens": 2742612.0,
      "step": 475
    },
    {
      "entropy": 0.5299606989277527,
      "epoch": 0.6419515326592842,
      "grad_norm": 0.08935546875,
      "learning_rate": 6.053357937665237e-05,
      "loss": 0.5236670303344727,
      "mean_token_accuracy": 0.8828775423765183,
      "num_tokens": 2887935.0,
      "step": 500
    },
    {
      "entropy": 0.6732268288638443,
      "epoch": 0.6740491092922485,
      "grad_norm": 0.056640625,
      "learning_rate": 5.1205962578487155e-05,
      "loss": 0.6722711181640625,
      "mean_token_accuracy": 0.8543066729605198,
      "num_tokens": 3035549.0,
      "step": 525
    },
    {
      "entropy": 0.4612098385160789,
      "epoch": 0.7061466859252127,
      "grad_norm": 0.041748046875,
      "learning_rate": 4.240589251272342e-05,
      "loss": 0.4541243743896484,
      "mean_token_accuracy": 0.9010929284989834,
      "num_tokens": 3180083.0,
      "step": 550
    },
    {
      "entropy": 0.5990941160498187,
      "epoch": 0.7382442625581769,
      "grad_norm": 0.08935546875,
      "learning_rate": 3.422851293981676e-05,
      "loss": 0.6069795989990234,
      "mean_token_accuracy": 0.8644757103919983,
      "num_tokens": 3325528.0,
      "step": 575
    },
    {
      "entropy": 0.5454245122382417,
      "epoch": 0.7703418391911411,
      "grad_norm": 0.06787109375,
      "learning_rate": 2.6762235274383772e-05,
      "loss": 0.5289861679077148,
      "mean_token_accuracy": 0.8816468404233455,
      "num_tokens": 3469264.0,
      "step": 600
    },
    {
      "entropy": 0.5093659822596237,
      "epoch": 0.8024394158241053,
      "grad_norm": 0.060302734375,
      "learning_rate": 2.008778270707944e-05,
      "loss": 0.503768424987793,
      "mean_token_accuracy": 0.8897754719853401,
      "num_tokens": 3614662.0,
      "step": 625
    },
    {
      "entropy": 0.5269298075186089,
      "epoch": 0.8345369924570695,
      "grad_norm": 0.051025390625,
      "learning_rate": 1.4277317449282834e-05,
      "loss": 0.5159123229980469,
      "mean_token_accuracy": 0.8846879424154759,
      "num_tokens": 3757746.0,
      "step": 650
    },
    {
      "entropy": 0.6054773937677964,
      "epoch": 0.8666345690900337,
      "grad_norm": 0.068359375,
      "learning_rate": 9.393660536564408e-06,
      "loss": 0.5959170532226562,
      "mean_token_accuracy": 0.8715771237760782,
      "num_tokens": 3904293.0,
      "step": 675
    },
    {
      "entropy": 0.4945011454587802,
      "epoch": 0.8987321457229979,
      "grad_norm": 0.06787109375,
      "learning_rate": 5.489612626189245e-06,
      "loss": 0.4754390335083008,
      "mean_token_accuracy": 0.8915398253500462,
      "num_tokens": 4043791.0,
      "step": 700
    },
    {
      "entropy": 0.5794008405366913,
      "epoch": 0.9308297223559622,
      "grad_norm": 0.0703125,
      "learning_rate": 2.607383131993424e-06,
      "loss": 0.5824679565429688,
      "mean_token_accuracy": 0.8722238828241825,
      "num_tokens": 4189274.0,
      "step": 725
    },
    {
      "entropy": 0.5977670075232163,
      "epoch": 0.9629272989889264,
      "grad_norm": 0.053955078125,
      "learning_rate": 7.781338686584927e-07,
      "loss": 0.5879628372192383,
      "mean_token_accuracy": 0.8674677063524723,
      "num_tokens": 4333425.0,
      "step": 750
    },
    {
      "entropy": 0.5161540248058736,
      "epoch": 0.9950248756218906,
      "grad_norm": 0.052978515625,
      "learning_rate": 2.164213936770576e-08,
      "loss": 0.497758674621582,
      "mean_token_accuracy": 0.8871022827923298,
      "num_tokens": 4479844.0,
      "step": 775
    }
  ],
  "logging_steps": 25,
  "max_steps": 779,
  "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": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.9211835200717107e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}