{
  "best_global_step": null,
  "best_metric": Infinity,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 47,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 0.8770920187234879,
      "epoch": 0.02127659574468085,
      "grad_norm": 101.38615417480469,
      "learning_rate": 0.0,
      "loss": 11.496590614318848,
      "mean_token_accuracy": 0.22714237496256828,
      "num_tokens": 2486.0,
      "step": 1
    },
    {
      "entropy": 0.9114853590726852,
      "epoch": 0.0425531914893617,
      "grad_norm": 96.85296630859375,
      "learning_rate": 4e-05,
      "loss": 11.215909004211426,
      "mean_token_accuracy": 0.2649671100080013,
      "num_tokens": 4959.0,
      "step": 2
    },
    {
      "entropy": 1.2038442194461823,
      "epoch": 0.06382978723404255,
      "grad_norm": 73.84027862548828,
      "learning_rate": 8e-05,
      "loss": 9.273573875427246,
      "mean_token_accuracy": 0.37812498956918716,
      "num_tokens": 7552.0,
      "step": 3
    },
    {
      "entropy": 1.0524671226739883,
      "epoch": 0.0851063829787234,
      "grad_norm": 30.00477409362793,
      "learning_rate": 0.00012,
      "loss": 6.997811317443848,
      "mean_token_accuracy": 0.5748837292194366,
      "num_tokens": 10017.0,
      "step": 4
    },
    {
      "entropy": 1.0943913161754608,
      "epoch": 0.10638297872340426,
      "grad_norm": 29.77185821533203,
      "learning_rate": 0.00016,
      "loss": 5.874476432800293,
      "mean_token_accuracy": 0.6206140369176865,
      "num_tokens": 12542.0,
      "step": 5
    },
    {
      "entropy": 0.690106213092804,
      "epoch": 0.1276595744680851,
      "grad_norm": 28.456193923950195,
      "learning_rate": 0.0002,
      "loss": 4.93742036819458,
      "mean_token_accuracy": 0.7391025722026825,
      "num_tokens": 15108.0,
      "step": 6
    },
    {
      "entropy": 0.42824630439281464,
      "epoch": 0.14893617021276595,
      "grad_norm": 8.46117877960205,
      "learning_rate": 0.00019993770622619782,
      "loss": 4.776185512542725,
      "mean_token_accuracy": 0.7670790255069733,
      "num_tokens": 17715.0,
      "step": 7
    },
    {
      "entropy": 0.6275453418493271,
      "epoch": 0.1702127659574468,
      "grad_norm": 7.040255069732666,
      "learning_rate": 0.00019975090251507638,
      "loss": 4.601991653442383,
      "mean_token_accuracy": 0.7641165554523468,
      "num_tokens": 20143.0,
      "step": 8
    },
    {
      "entropy": 0.49182429164648056,
      "epoch": 0.19148936170212766,
      "grad_norm": 4.624846458435059,
      "learning_rate": 0.0001994398216007982,
      "loss": 4.511226654052734,
      "mean_token_accuracy": 0.7724626064300537,
      "num_tokens": 22656.0,
      "step": 9
    },
    {
      "entropy": 0.626158207654953,
      "epoch": 0.2127659574468085,
      "grad_norm": 7.813827037811279,
      "learning_rate": 0.00019900485105144543,
      "loss": 4.358890533447266,
      "mean_token_accuracy": 0.7753759473562241,
      "num_tokens": 25094.0,
      "step": 10
    },
    {
      "entropy": 0.5334508866071701,
      "epoch": 0.23404255319148937,
      "grad_norm": 3.6953277587890625,
      "learning_rate": 0.00019844653278615833,
      "loss": 4.273573875427246,
      "mean_token_accuracy": 0.7838225364685059,
      "num_tokens": 27456.0,
      "step": 11
    },
    {
      "entropy": 0.43513786792755127,
      "epoch": 0.2553191489361702,
      "grad_norm": 2.8964409828186035,
      "learning_rate": 0.00019776556239997146,
      "loss": 4.085248947143555,
      "mean_token_accuracy": 0.8868782967329025,
      "num_tokens": 29914.0,
      "step": 12
    },
    {
      "entropy": 0.3346208333969116,
      "epoch": 0.2765957446808511,
      "grad_norm": 5.369524955749512,
      "learning_rate": 0.00019696278829718883,
      "loss": 3.968517303466797,
      "mean_token_accuracy": 0.8908246159553528,
      "num_tokens": 32448.0,
      "step": 13
    },
    {
      "entropy": 0.33365894854068756,
      "epoch": 0.2978723404255319,
      "grad_norm": 2.550203800201416,
      "learning_rate": 0.00019603921063437793,
      "loss": 4.0511908531188965,
      "mean_token_accuracy": 0.8805366605520248,
      "num_tokens": 34909.0,
      "step": 14
    },
    {
      "entropy": 0.25230497866868973,
      "epoch": 0.3191489361702128,
      "grad_norm": 3.365182876586914,
      "learning_rate": 0.0001949959800742991,
      "loss": 4.221365928649902,
      "mean_token_accuracy": 0.8763548880815506,
      "num_tokens": 37476.0,
      "step": 15
    },
    {
      "entropy": 0.21353815868496895,
      "epoch": 0.3404255319148936,
      "grad_norm": 1.1460461616516113,
      "learning_rate": 0.00019383439635232294,
      "loss": 4.106394290924072,
      "mean_token_accuracy": 0.8868418335914612,
      "num_tokens": 39881.0,
      "step": 16
    },
    {
      "entropy": 0.21475103124976158,
      "epoch": 0.3617021276595745,
      "grad_norm": 3.043959617614746,
      "learning_rate": 0.00019255590665712214,
      "loss": 4.265631675720215,
      "mean_token_accuracy": 0.8690433949232101,
      "num_tokens": 42235.0,
      "step": 17
    },
    {
      "entropy": 0.1718740463256836,
      "epoch": 0.3829787234042553,
      "grad_norm": 0.8078291416168213,
      "learning_rate": 0.0001911621038276542,
      "loss": 4.106135368347168,
      "mean_token_accuracy": 0.892671525478363,
      "num_tokens": 44687.0,
      "step": 18
    },
    {
      "entropy": 0.16231479868292809,
      "epoch": 0.40425531914893614,
      "grad_norm": 0.9561502933502197,
      "learning_rate": 0.00018965472436868286,
      "loss": 4.120131015777588,
      "mean_token_accuracy": 0.8869824111461639,
      "num_tokens": 47206.0,
      "step": 19
    },
    {
      "entropy": 0.14364850148558617,
      "epoch": 0.425531914893617,
      "grad_norm": 0.9734947681427002,
      "learning_rate": 0.00018803564628730915,
      "loss": 4.03128719329834,
      "mean_token_accuracy": 0.8906020969152451,
      "num_tokens": 49799.0,
      "step": 20
    },
    {
      "entropy": 0.13312280178070068,
      "epoch": 0.44680851063829785,
      "grad_norm": 0.4489222764968872,
      "learning_rate": 0.00018630688675320842,
      "loss": 4.058135032653809,
      "mean_token_accuracy": 0.8986841887235641,
      "num_tokens": 52291.0,
      "step": 21
    },
    {
      "entropy": 0.13586510717868805,
      "epoch": 0.46808510638297873,
      "grad_norm": 0.7964894771575928,
      "learning_rate": 0.0001844705995854882,
      "loss": 3.965346574783325,
      "mean_token_accuracy": 0.8940518647432327,
      "num_tokens": 54812.0,
      "step": 22
    },
    {
      "entropy": 0.15179748088121414,
      "epoch": 0.48936170212765956,
      "grad_norm": 1.6409692764282227,
      "learning_rate": 0.00018252907256929775,
      "loss": 4.181431293487549,
      "mean_token_accuracy": 0.8783541172742844,
      "num_tokens": 57280.0,
      "step": 23
    },
    {
      "entropy": 0.11831228621304035,
      "epoch": 0.5106382978723404,
      "grad_norm": 0.7683380842208862,
      "learning_rate": 0.00018048472460553257,
      "loss": 4.24875545501709,
      "mean_token_accuracy": 0.8903311938047409,
      "num_tokens": 59802.0,
      "step": 24
    },
    {
      "entropy": 0.15002421662211418,
      "epoch": 0.5319148936170213,
      "grad_norm": 2.176997661590576,
      "learning_rate": 0.00017834010269718526,
      "loss": 4.15623664855957,
      "mean_token_accuracy": 0.8820056915283203,
      "num_tokens": 62271.0,
      "step": 25
    },
    {
      "entropy": 0.11383292451500893,
      "epoch": 0.5531914893617021,
      "grad_norm": 0.5305500030517578,
      "learning_rate": 0.0001760978787760968,
      "loss": 4.076779365539551,
      "mean_token_accuracy": 0.8941320031881332,
      "num_tokens": 64751.0,
      "step": 26
    },
    {
      "entropy": 0.13319513201713562,
      "epoch": 0.574468085106383,
      "grad_norm": 1.0374587774276733,
      "learning_rate": 0.00017376084637406222,
      "loss": 4.014706611633301,
      "mean_token_accuracy": 0.8837339729070663,
      "num_tokens": 67220.0,
      "step": 27
    },
    {
      "entropy": 0.13686015084385872,
      "epoch": 0.5957446808510638,
      "grad_norm": 1.387152075767517,
      "learning_rate": 0.00017133191714243805,
      "loss": 4.015310764312744,
      "mean_token_accuracy": 0.8779295533895493,
      "num_tokens": 69678.0,
      "step": 28
    },
    {
      "entropy": 0.13596300408244133,
      "epoch": 0.6170212765957447,
      "grad_norm": 1.2698324918746948,
      "learning_rate": 0.00016881411722458688,
      "loss": 3.992821455001831,
      "mean_token_accuracy": 0.8992939442396164,
      "num_tokens": 72158.0,
      "step": 29
    },
    {
      "entropy": 0.13812873139977455,
      "epoch": 0.6382978723404256,
      "grad_norm": 1.9082021713256836,
      "learning_rate": 0.00016621058348568007,
      "loss": 4.059752464294434,
      "mean_token_accuracy": 0.886225238442421,
      "num_tokens": 74621.0,
      "step": 30
    },
    {
      "entropy": 0.1471228487789631,
      "epoch": 0.6595744680851063,
      "grad_norm": 1.0790090560913086,
      "learning_rate": 0.00016352455960455387,
      "loss": 3.956774950027466,
      "mean_token_accuracy": 0.8888719379901886,
      "num_tokens": 77122.0,
      "step": 31
    },
    {
      "entropy": 0.13649508357048035,
      "epoch": 0.6808510638297872,
      "grad_norm": 0.8638296127319336,
      "learning_rate": 0.0001607593920324899,
      "loss": 4.1457977294921875,
      "mean_token_accuracy": 0.8863866329193115,
      "num_tokens": 79658.0,
      "step": 32
    },
    {
      "entropy": 0.13422205485403538,
      "epoch": 0.7021276595744681,
      "grad_norm": 0.8206593990325928,
      "learning_rate": 0.00015791852582395334,
      "loss": 4.104636192321777,
      "mean_token_accuracy": 0.893946647644043,
      "num_tokens": 82198.0,
      "step": 33
    },
    {
      "entropy": 0.13717253133654594,
      "epoch": 0.723404255319149,
      "grad_norm": 0.43719571828842163,
      "learning_rate": 0.00015500550034448413,
      "loss": 4.031332015991211,
      "mean_token_accuracy": 0.894197016954422,
      "num_tokens": 84670.0,
      "step": 34
    },
    {
      "entropy": 0.1137513667345047,
      "epoch": 0.7446808510638298,
      "grad_norm": 1.8441417217254639,
      "learning_rate": 0.0001520239448610882,
      "loss": 4.112149715423584,
      "mean_token_accuracy": 0.8909876793622971,
      "num_tokens": 87292.0,
      "step": 35
    },
    {
      "entropy": 0.11223667673766613,
      "epoch": 0.7659574468085106,
      "grad_norm": 0.4776930809020996,
      "learning_rate": 0.00014897757402062284,
      "loss": 4.026741027832031,
      "mean_token_accuracy": 0.8924113065004349,
      "num_tokens": 89830.0,
      "step": 36
    },
    {
      "entropy": 0.12275257520377636,
      "epoch": 0.7872340425531915,
      "grad_norm": 0.9828954935073853,
      "learning_rate": 0.00014587018322180905,
      "loss": 4.183655738830566,
      "mean_token_accuracy": 0.8827805668115616,
      "num_tokens": 92344.0,
      "step": 37
    },
    {
      "entropy": 0.12380701676011086,
      "epoch": 0.8085106382978723,
      "grad_norm": 1.3710100650787354,
      "learning_rate": 0.0001427056438866376,
      "loss": 4.003378868103027,
      "mean_token_accuracy": 0.8812988549470901,
      "num_tokens": 94826.0,
      "step": 38
    },
    {
      "entropy": 0.10968485288321972,
      "epoch": 0.8297872340425532,
      "grad_norm": 0.37869715690612793,
      "learning_rate": 0.00013948789863705912,
      "loss": 4.050682067871094,
      "mean_token_accuracy": 0.8941126763820648,
      "num_tokens": 97290.0,
      "step": 39
    },
    {
      "entropy": 0.12006617523729801,
      "epoch": 0.851063829787234,
      "grad_norm": 0.5866818428039551,
      "learning_rate": 0.00013622095638296826,
      "loss": 4.113466262817383,
      "mean_token_accuracy": 0.8894326388835907,
      "num_tokens": 99776.0,
      "step": 40
    },
    {
      "entropy": 0.09959963150322437,
      "epoch": 0.8723404255319149,
      "grad_norm": 0.4211389422416687,
      "learning_rate": 0.000132908887327601,
      "loss": 3.8911352157592773,
      "mean_token_accuracy": 0.8987201750278473,
      "num_tokens": 102278.0,
      "step": 41
    },
    {
      "entropy": 0.10989912413060665,
      "epoch": 0.8936170212765957,
      "grad_norm": 1.014770746231079,
      "learning_rate": 0.00012955581789656843,
      "loss": 4.067371845245361,
      "mean_token_accuracy": 0.8916666656732559,
      "num_tokens": 104764.0,
      "step": 42
    },
    {
      "entropy": 0.11506957560777664,
      "epoch": 0.9148936170212766,
      "grad_norm": 0.4580586552619934,
      "learning_rate": 0.0001261659255968441,
      "loss": 4.101069927215576,
      "mean_token_accuracy": 0.8936023861169815,
      "num_tokens": 107201.0,
      "step": 43
    },
    {
      "entropy": 0.10838168673217297,
      "epoch": 0.9361702127659575,
      "grad_norm": 0.4166942536830902,
      "learning_rate": 0.00012274343381211066,
      "loss": 4.025703430175781,
      "mean_token_accuracy": 0.8947224318981171,
      "num_tokens": 109660.0,
      "step": 44
    },
    {
      "entropy": 0.09614014439284801,
      "epoch": 0.9574468085106383,
      "grad_norm": 0.9769757390022278,
      "learning_rate": 0.00011929260654094969,
      "loss": 4.121439456939697,
      "mean_token_accuracy": 0.8903171271085739,
      "num_tokens": 112117.0,
      "step": 45
    },
    {
      "entropy": 0.11138966307044029,
      "epoch": 0.9787234042553191,
      "grad_norm": 1.5290015935897827,
      "learning_rate": 0.0001158177430844304,
      "loss": 4.022660732269287,
      "mean_token_accuracy": 0.8867548704147339,
      "num_tokens": 114595.0,
      "step": 46
    },
    {
      "entropy": 0.10535211116075516,
      "epoch": 1.0,
      "grad_norm": 0.6933005452156067,
      "learning_rate": 0.00011232317268971585,
      "loss": 4.150263786315918,
      "mean_token_accuracy": 0.8926616609096527,
      "num_tokens": 117080.0,
      "step": 47
    },
    {
      "epoch": 1.0,
      "eval_entropy": 0.0,
      "eval_loss": NaN,
      "eval_mean_token_accuracy": 0.0,
      "eval_num_tokens": 117080.0,
      "eval_runtime": 14.1972,
      "eval_samples_per_second": 21.131,
      "eval_steps_per_second": 5.283,
      "step": 47
    }
  ],
  "logging_steps": 1,
  "max_steps": 94,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 196239614279680.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}