{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 18,
  "global_step": 94,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02127659574468085,
      "grad_norm": 0.29000455141067505,
      "learning_rate": 0.0,
      "loss": 1.6797,
      "step": 1
    },
    {
      "epoch": 0.0425531914893617,
      "grad_norm": 0.22746272385120392,
      "learning_rate": 4e-05,
      "loss": 1.6836,
      "step": 2
    },
    {
      "epoch": 0.06382978723404255,
      "grad_norm": 0.25914642214775085,
      "learning_rate": 8e-05,
      "loss": 1.7539,
      "step": 3
    },
    {
      "epoch": 0.0851063829787234,
      "grad_norm": 0.22040939331054688,
      "learning_rate": 0.00012,
      "loss": 1.6445,
      "step": 4
    },
    {
      "epoch": 0.10638297872340426,
      "grad_norm": 0.15772981941699982,
      "learning_rate": 0.00016,
      "loss": 1.5469,
      "step": 5
    },
    {
      "epoch": 0.1276595744680851,
      "grad_norm": 0.1341920644044876,
      "learning_rate": 0.0002,
      "loss": 1.5498,
      "step": 6
    },
    {
      "epoch": 0.14893617021276595,
      "grad_norm": 0.2578749656677246,
      "learning_rate": 0.00019994393560357804,
      "loss": 1.4473,
      "step": 7
    },
    {
      "epoch": 0.1702127659574468,
      "grad_norm": 0.20642879605293274,
      "learning_rate": 0.00019977581226356873,
      "loss": 1.4766,
      "step": 8
    },
    {
      "epoch": 0.19148936170212766,
      "grad_norm": 0.1336732804775238,
      "learning_rate": 0.00019949583944071838,
      "loss": 1.4033,
      "step": 9
    },
    {
      "epoch": 0.2127659574468085,
      "grad_norm": 0.07306341826915741,
      "learning_rate": 0.00019910436594630087,
      "loss": 1.415,
      "step": 10
    },
    {
      "epoch": 0.23404255319148937,
      "grad_norm": 0.08282851427793503,
      "learning_rate": 0.00019860187950754252,
      "loss": 1.3926,
      "step": 11
    },
    {
      "epoch": 0.2553191489361702,
      "grad_norm": 0.09610556811094284,
      "learning_rate": 0.0001979890061599743,
      "loss": 1.3584,
      "step": 12
    },
    {
      "epoch": 0.2765957446808511,
      "grad_norm": 0.09108196198940277,
      "learning_rate": 0.00019726650946746995,
      "loss": 1.3242,
      "step": 13
    },
    {
      "epoch": 0.2978723404255319,
      "grad_norm": 0.079231858253479,
      "learning_rate": 0.00019643528957094016,
      "loss": 1.252,
      "step": 14
    },
    {
      "epoch": 0.3191489361702128,
      "grad_norm": 0.0699169933795929,
      "learning_rate": 0.0001954963820668692,
      "loss": 1.3174,
      "step": 15
    },
    {
      "epoch": 0.3404255319148936,
      "grad_norm": 0.08960508555173874,
      "learning_rate": 0.00019445095671709065,
      "loss": 1.417,
      "step": 16
    },
    {
      "epoch": 0.3617021276595745,
      "grad_norm": 0.06929978728294373,
      "learning_rate": 0.00019330031599140991,
      "loss": 1.2988,
      "step": 17
    },
    {
      "epoch": 0.3829787234042553,
      "grad_norm": 0.065662682056427,
      "learning_rate": 0.00019204589344488877,
      "loss": 1.3096,
      "step": 18
    },
    {
      "epoch": 0.40425531914893614,
      "grad_norm": 0.042669378221035004,
      "learning_rate": 0.00019068925193181457,
      "loss": 1.1141,
      "step": 19
    },
    {
      "epoch": 0.425531914893617,
      "grad_norm": 0.05591333657503128,
      "learning_rate": 0.0001892320816585782,
      "loss": 1.2617,
      "step": 20
    },
    {
      "epoch": 0.44680851063829785,
      "grad_norm": 0.06592351198196411,
      "learning_rate": 0.0001876761980778876,
      "loss": 1.2207,
      "step": 21
    },
    {
      "epoch": 0.46808510638297873,
      "grad_norm": 0.06798592954874039,
      "learning_rate": 0.00018602353962693938,
      "loss": 1.2598,
      "step": 22
    },
    {
      "epoch": 0.46808510638297873,
      "eval_loss": 1.21337890625,
      "eval_runtime": 5.4519,
      "eval_samples_per_second": 0.734,
      "eval_steps_per_second": 0.183,
      "step": 22
    },
    {
      "epoch": 0.48936170212765956,
      "grad_norm": 0.052718475461006165,
      "learning_rate": 0.000184276165312368,
      "loss": 1.2275,
      "step": 23
    },
    {
      "epoch": 0.5106382978723404,
      "grad_norm": 0.04465296119451523,
      "learning_rate": 0.00018243625214497933,
      "loss": 1.251,
      "step": 24
    },
    {
      "epoch": 0.5319148936170213,
      "grad_norm": 0.04210865870118141,
      "learning_rate": 0.00018050609242746673,
      "loss": 1.2988,
      "step": 25
    },
    {
      "epoch": 0.5531914893617021,
      "grad_norm": 0.05770853906869888,
      "learning_rate": 0.0001784880908984871,
      "loss": 1.2554,
      "step": 26
    },
    {
      "epoch": 0.574468085106383,
      "grad_norm": 0.04600943997502327,
      "learning_rate": 0.000176384761736656,
      "loss": 1.1875,
      "step": 27
    },
    {
      "epoch": 0.5957446808510638,
      "grad_norm": 0.04314780980348587,
      "learning_rate": 0.00017419872542819424,
      "loss": 1.1738,
      "step": 28
    },
    {
      "epoch": 0.6170212765957447,
      "grad_norm": 0.05138669162988663,
      "learning_rate": 0.0001719327055021282,
      "loss": 1.1406,
      "step": 29
    },
    {
      "epoch": 0.6382978723404256,
      "grad_norm": 0.04068281874060631,
      "learning_rate": 0.00016958952513711206,
      "loss": 1.1699,
      "step": 30
    },
    {
      "epoch": 0.6595744680851063,
      "grad_norm": 0.044186729937791824,
      "learning_rate": 0.00016717210364409848,
      "loss": 1.2002,
      "step": 31
    },
    {
      "epoch": 0.6808510638297872,
      "grad_norm": 0.05163154751062393,
      "learning_rate": 0.00016468345282924092,
      "loss": 1.2402,
      "step": 32
    },
    {
      "epoch": 0.7021276595744681,
      "grad_norm": 0.05365516617894173,
      "learning_rate": 0.000162126673241558,
      "loss": 1.1348,
      "step": 33
    },
    {
      "epoch": 0.723404255319149,
      "grad_norm": 0.03528141602873802,
      "learning_rate": 0.00015950495031003572,
      "loss": 1.2041,
      "step": 34
    },
    {
      "epoch": 0.7446808510638298,
      "grad_norm": 0.04087606444954872,
      "learning_rate": 0.0001568215503749794,
      "loss": 1.106,
      "step": 35
    },
    {
      "epoch": 0.7659574468085106,
      "grad_norm": 0.04214077442884445,
      "learning_rate": 0.00015407981661856056,
      "loss": 1.1602,
      "step": 36
    },
    {
      "epoch": 0.7872340425531915,
      "grad_norm": 0.03790733590722084,
      "learning_rate": 0.00015128316489962815,
      "loss": 1.1143,
      "step": 37
    },
    {
      "epoch": 0.8085106382978723,
      "grad_norm": 0.03618357330560684,
      "learning_rate": 0.00014843507949797383,
      "loss": 1.1221,
      "step": 38
    },
    {
      "epoch": 0.8297872340425532,
      "grad_norm": 0.0360189713537693,
      "learning_rate": 0.00014553910877335323,
      "loss": 1.0957,
      "step": 39
    },
    {
      "epoch": 0.851063829787234,
      "grad_norm": 0.03670095279812813,
      "learning_rate": 0.00014259886074467144,
      "loss": 1.1548,
      "step": 40
    },
    {
      "epoch": 0.851063829787234,
      "eval_loss": 1.117919921875,
      "eval_runtime": 5.4457,
      "eval_samples_per_second": 0.735,
      "eval_steps_per_second": 0.184,
      "step": 40
    },
    {
      "epoch": 0.8723404255319149,
      "grad_norm": 0.04061957448720932,
      "learning_rate": 0.0001396179985948409,
      "loss": 1.0205,
      "step": 41
    },
    {
      "epoch": 0.8936170212765957,
      "grad_norm": 0.03239031881093979,
      "learning_rate": 0.0001366002361069116,
      "loss": 1.1685,
      "step": 42
    },
    {
      "epoch": 0.9148936170212766,
      "grad_norm": 0.03184492141008377,
      "learning_rate": 0.00013354933303715965,
      "loss": 1.1602,
      "step": 43
    },
    {
      "epoch": 0.9361702127659575,
      "grad_norm": 0.035948608070611954,
      "learning_rate": 0.00013046909043089959,
      "loss": 1.1438,
      "step": 44
    },
    {
      "epoch": 0.9574468085106383,
      "grad_norm": 0.03945741802453995,
      "learning_rate": 0.00012736334588685471,
      "loss": 1.0933,
      "step": 45
    },
    {
      "epoch": 0.9787234042553191,
      "grad_norm": 0.03920970484614372,
      "learning_rate": 0.00012423596877598737,
      "loss": 1.0835,
      "step": 46
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.04158036783337593,
      "learning_rate": 0.00012109085542074427,
      "loss": 1.043,
      "step": 47
    },
    {
      "epoch": 1.0212765957446808,
      "grad_norm": 0.040141962468624115,
      "learning_rate": 0.00011793192424072419,
      "loss": 1.0078,
      "step": 48
    },
    {
      "epoch": 1.0425531914893618,
      "grad_norm": 0.03587280586361885,
      "learning_rate": 0.00011476311087081468,
      "loss": 1.0615,
      "step": 49
    },
    {
      "epoch": 1.0638297872340425,
      "grad_norm": 0.03701433911919594,
      "learning_rate": 0.0001115883632578816,
      "loss": 1.1162,
      "step": 50
    },
    {
      "epoch": 1.0851063829787233,
      "grad_norm": 0.03837170451879501,
      "learning_rate": 0.00010841163674211843,
      "loss": 1.0894,
      "step": 51
    },
    {
      "epoch": 1.1063829787234043,
      "grad_norm": 0.03820248320698738,
      "learning_rate": 0.00010523688912918532,
      "loss": 1.0566,
      "step": 52
    },
    {
      "epoch": 1.127659574468085,
      "grad_norm": 0.03253014013171196,
      "learning_rate": 0.00010206807575927589,
      "loss": 1.1235,
      "step": 53
    },
    {
      "epoch": 1.148936170212766,
      "grad_norm": 0.04357115924358368,
      "learning_rate": 9.890914457925572e-05,
      "loss": 1.0381,
      "step": 54
    },
    {
      "epoch": 1.1702127659574468,
      "grad_norm": 0.03911568596959114,
      "learning_rate": 9.576403122401265e-05,
      "loss": 1.0977,
      "step": 55
    },
    {
      "epoch": 1.1914893617021276,
      "grad_norm": 0.035097163170576096,
      "learning_rate": 9.263665411314528e-05,
      "loss": 1.0952,
      "step": 56
    },
    {
      "epoch": 1.2127659574468086,
      "grad_norm": 0.034438036382198334,
      "learning_rate": 8.953090956910044e-05,
      "loss": 1.1431,
      "step": 57
    },
    {
      "epoch": 1.2340425531914894,
      "grad_norm": 0.03736001253128052,
      "learning_rate": 8.645066696284037e-05,
      "loss": 1.1069,
      "step": 58
    },
    {
      "epoch": 1.2340425531914894,
      "eval_loss": 1.076416015625,
      "eval_runtime": 5.4506,
      "eval_samples_per_second": 0.734,
      "eval_steps_per_second": 0.183,
      "step": 58
    },
    {
      "epoch": 1.2553191489361701,
      "grad_norm": 0.04189908504486084,
      "learning_rate": 8.339976389308844e-05,
      "loss": 1.083,
      "step": 59
    },
    {
      "epoch": 1.2765957446808511,
      "grad_norm": 0.0367116816341877,
      "learning_rate": 8.03820014051591e-05,
      "loss": 1.0581,
      "step": 60
    },
    {
      "epoch": 1.297872340425532,
      "grad_norm": 0.0420914888381958,
      "learning_rate": 7.74011392553286e-05,
      "loss": 0.999,
      "step": 61
    },
    {
      "epoch": 1.3191489361702127,
      "grad_norm": 0.035260096192359924,
      "learning_rate": 7.44608912266468e-05,
      "loss": 1.0967,
      "step": 62
    },
    {
      "epoch": 1.3404255319148937,
      "grad_norm": 0.03531453758478165,
      "learning_rate": 7.156492050202615e-05,
      "loss": 1.2246,
      "step": 63
    },
    {
      "epoch": 1.3617021276595744,
      "grad_norm": 0.032513417303562164,
      "learning_rate": 6.871683510037184e-05,
      "loss": 1.1084,
      "step": 64
    },
    {
      "epoch": 1.3829787234042552,
      "grad_norm": 0.033178091049194336,
      "learning_rate": 6.592018338143946e-05,
      "loss": 1.1313,
      "step": 65
    },
    {
      "epoch": 1.4042553191489362,
      "grad_norm": 0.03073359839618206,
      "learning_rate": 6.317844962502062e-05,
      "loss": 0.9706,
      "step": 66
    },
    {
      "epoch": 1.425531914893617,
      "grad_norm": 0.034078359603881836,
      "learning_rate": 6.049504968996429e-05,
      "loss": 1.082,
      "step": 67
    },
    {
      "epoch": 1.4468085106382977,
      "grad_norm": 0.03381915017962456,
      "learning_rate": 5.787332675844198e-05,
      "loss": 1.0474,
      "step": 68
    },
    {
      "epoch": 1.4680851063829787,
      "grad_norm": 0.033045776188373566,
      "learning_rate": 5.531654717075911e-05,
      "loss": 1.104,
      "step": 69
    },
    {
      "epoch": 1.4893617021276595,
      "grad_norm": 0.03237929940223694,
      "learning_rate": 5.282789635590153e-05,
      "loss": 1.084,
      "step": 70
    },
    {
      "epoch": 1.5106382978723403,
      "grad_norm": 0.03266558423638344,
      "learning_rate": 5.041047486288797e-05,
      "loss": 1.1094,
      "step": 71
    },
    {
      "epoch": 1.5319148936170213,
      "grad_norm": 0.030977871268987656,
      "learning_rate": 4.8067294497871814e-05,
      "loss": 1.1738,
      "step": 72
    },
    {
      "epoch": 1.5531914893617023,
      "grad_norm": 0.0328492596745491,
      "learning_rate": 4.580127457180581e-05,
      "loss": 1.1279,
      "step": 73
    },
    {
      "epoch": 1.574468085106383,
      "grad_norm": 0.034149572253227234,
      "learning_rate": 4.3615238263344006e-05,
      "loss": 1.0562,
      "step": 74
    },
    {
      "epoch": 1.5957446808510638,
      "grad_norm": 0.03442554175853729,
      "learning_rate": 4.151190910151291e-05,
      "loss": 1.0552,
      "step": 75
    },
    {
      "epoch": 1.6170212765957448,
      "grad_norm": 0.03945354372262955,
      "learning_rate": 3.949390757253327e-05,
      "loss": 1.0137,
      "step": 76
    },
    {
      "epoch": 1.6170212765957448,
      "eval_loss": 1.05859375,
      "eval_runtime": 5.4455,
      "eval_samples_per_second": 0.735,
      "eval_steps_per_second": 0.184,
      "step": 76
    },
    {
      "epoch": 1.6382978723404256,
      "grad_norm": 0.035424698144197464,
      "learning_rate": 3.75637478550207e-05,
      "loss": 1.0552,
      "step": 77
    },
    {
      "epoch": 1.6595744680851063,
      "grad_norm": 0.03549226000905037,
      "learning_rate": 3.572383468763205e-05,
      "loss": 1.0894,
      "step": 78
    },
    {
      "epoch": 1.6808510638297873,
      "grad_norm": 0.03182533383369446,
      "learning_rate": 3.3976460373060625e-05,
      "loss": 1.1489,
      "step": 79
    },
    {
      "epoch": 1.702127659574468,
      "grad_norm": 0.040143564343452454,
      "learning_rate": 3.2323801922112436e-05,
      "loss": 1.04,
      "step": 80
    },
    {
      "epoch": 1.7234042553191489,
      "grad_norm": 0.035153862088918686,
      "learning_rate": 3.07679183414218e-05,
      "loss": 1.1113,
      "step": 81
    },
    {
      "epoch": 1.7446808510638299,
      "grad_norm": 0.04102678224444389,
      "learning_rate": 2.931074806818545e-05,
      "loss": 1.0063,
      "step": 82
    },
    {
      "epoch": 1.7659574468085106,
      "grad_norm": 0.036094531416893005,
      "learning_rate": 2.795410655511125e-05,
      "loss": 1.0767,
      "step": 83
    },
    {
      "epoch": 1.7872340425531914,
      "grad_norm": 0.037124305963516235,
      "learning_rate": 2.6699684008590114e-05,
      "loss": 1.0273,
      "step": 84
    },
    {
      "epoch": 1.8085106382978724,
      "grad_norm": 0.03859342262148857,
      "learning_rate": 2.5549043282909353e-05,
      "loss": 1.0371,
      "step": 85
    },
    {
      "epoch": 1.8297872340425532,
      "grad_norm": 0.04163049906492233,
      "learning_rate": 2.4503617933130828e-05,
      "loss": 1.0137,
      "step": 86
    },
    {
      "epoch": 1.851063829787234,
      "grad_norm": 0.03678214177489281,
      "learning_rate": 2.356471042905987e-05,
      "loss": 1.0825,
      "step": 87
    },
    {
      "epoch": 1.872340425531915,
      "grad_norm": 0.03787471354007721,
      "learning_rate": 2.2733490532530066e-05,
      "loss": 0.9424,
      "step": 88
    },
    {
      "epoch": 1.8936170212765957,
      "grad_norm": 0.033675018697977066,
      "learning_rate": 2.2010993840025705e-05,
      "loss": 1.1016,
      "step": 89
    },
    {
      "epoch": 1.9148936170212765,
      "grad_norm": 0.03139219060540199,
      "learning_rate": 2.13981204924575e-05,
      "loss": 1.0967,
      "step": 90
    },
    {
      "epoch": 1.9361702127659575,
      "grad_norm": 0.041046664118766785,
      "learning_rate": 2.0895634053699114e-05,
      "loss": 1.08,
      "step": 91
    },
    {
      "epoch": 1.9574468085106385,
      "grad_norm": 0.037067461758852005,
      "learning_rate": 2.0504160559281628e-05,
      "loss": 1.0278,
      "step": 92
    },
    {
      "epoch": 1.978723404255319,
      "grad_norm": 0.03774382174015045,
      "learning_rate": 2.022418773643126e-05,
      "loss": 1.0234,
      "step": 93
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.04042135924100876,
      "learning_rate": 2.0056064396421964e-05,
      "loss": 0.9795,
      "step": 94
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.052490234375,
      "eval_runtime": 5.4523,
      "eval_samples_per_second": 0.734,
      "eval_steps_per_second": 0.183,
      "step": 94
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 94,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.117757501069328e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}