{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5934065934065934,
  "eval_steps": 500,
  "global_step": 90,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.0638142824172974,
      "learning_rate": 0.0,
      "loss": 1.0777,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 0.9542151689529419,
      "learning_rate": 9.56e-05,
      "loss": 1.1025,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.0668847560882568,
      "learning_rate": 0.0001912,
      "loss": 1.0405,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.0646922588348389,
      "learning_rate": 0.0002868,
      "loss": 0.9056,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 0.6475369334220886,
      "learning_rate": 0.0003824,
      "loss": 0.8513,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 0.653504490852356,
      "learning_rate": 0.000478,
      "loss": 0.9432,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 0.5652804374694824,
      "learning_rate": 0.00047694013303769406,
      "loss": 0.8951,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 0.38114824891090393,
      "learning_rate": 0.00047588026607538804,
      "loss": 0.8546,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.3202402591705322,
      "learning_rate": 0.0004748203991130821,
      "loss": 0.9013,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.3632391095161438,
      "learning_rate": 0.00047376053215077607,
      "loss": 0.7981,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.38180795311927795,
      "learning_rate": 0.00047270066518847006,
      "loss": 0.8034,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.44034814834594727,
      "learning_rate": 0.0004716407982261641,
      "loss": 0.8194,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.5649089217185974,
      "learning_rate": 0.00047058093126385814,
      "loss": 0.7964,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.4905894994735718,
      "learning_rate": 0.0004695210643015521,
      "loss": 0.7767,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.5945530533790588,
      "learning_rate": 0.00046846119733924617,
      "loss": 0.7485,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.47223448753356934,
      "learning_rate": 0.00046740133037694015,
      "loss": 0.7412,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.4855833053588867,
      "learning_rate": 0.00046634146341463414,
      "loss": 0.7992,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.420284628868103,
      "learning_rate": 0.0004652815964523282,
      "loss": 0.7427,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.517633855342865,
      "learning_rate": 0.0004642217294900222,
      "loss": 0.7918,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.434706449508667,
      "learning_rate": 0.0004631618625277162,
      "loss": 0.7891,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.3698730766773224,
      "learning_rate": 0.00046210199556541025,
      "loss": 0.7076,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.3561922609806061,
      "learning_rate": 0.00046104212860310423,
      "loss": 0.7893,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.3815233111381531,
      "learning_rate": 0.0004599822616407982,
      "loss": 0.7999,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.38611900806427,
      "learning_rate": 0.00045892239467849226,
      "loss": 0.7928,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.29186370968818665,
      "learning_rate": 0.0004578625277161863,
      "loss": 0.724,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.3245350420475006,
      "learning_rate": 0.0004568026607538803,
      "loss": 0.7503,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.3803184926509857,
      "learning_rate": 0.00045574279379157433,
      "loss": 0.7455,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.3178353011608124,
      "learning_rate": 0.00045468292682926826,
      "loss": 0.7207,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.4353942573070526,
      "learning_rate": 0.0004536230598669623,
      "loss": 0.8268,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.3097940981388092,
      "learning_rate": 0.00045256319290465634,
      "loss": 0.6621,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.3318345546722412,
      "learning_rate": 0.00045150332594235033,
      "loss": 0.7092,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.31531524658203125,
      "learning_rate": 0.00045044345898004437,
      "loss": 0.7668,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.3566637933254242,
      "learning_rate": 0.0004493835920177384,
      "loss": 0.7545,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.36444291472435,
      "learning_rate": 0.00044832372505543234,
      "loss": 0.8064,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.3560720980167389,
      "learning_rate": 0.0004472638580931264,
      "loss": 0.7774,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.3715183734893799,
      "learning_rate": 0.0004462039911308204,
      "loss": 0.7131,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.2921788692474365,
      "learning_rate": 0.0004451441241685144,
      "loss": 0.8009,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.29083380103111267,
      "learning_rate": 0.00044408425720620845,
      "loss": 0.7223,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.3140243887901306,
      "learning_rate": 0.0004430243902439025,
      "loss": 0.7196,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.3676493465900421,
      "learning_rate": 0.0004419645232815964,
      "loss": 0.7143,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.3598462641239166,
      "learning_rate": 0.00044090465631929047,
      "loss": 0.7474,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.3195889890193939,
      "learning_rate": 0.0004398447893569845,
      "loss": 0.7229,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.30827897787094116,
      "learning_rate": 0.0004387849223946785,
      "loss": 0.7428,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.38703453540802,
      "learning_rate": 0.00043772505543237253,
      "loss": 0.7169,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.28942254185676575,
      "learning_rate": 0.0004366651884700666,
      "loss": 0.7456,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.35373979806900024,
      "learning_rate": 0.0004356053215077605,
      "loss": 0.7703,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.3619854748249054,
      "learning_rate": 0.00043454545454545455,
      "loss": 0.6991,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.3936954438686371,
      "learning_rate": 0.0004334855875831486,
      "loss": 0.7505,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.31419533491134644,
      "learning_rate": 0.0004324257206208426,
      "loss": 0.7218,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.31622064113616943,
      "learning_rate": 0.0004313658536585366,
      "loss": 0.7133,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.31881847977638245,
      "learning_rate": 0.00043030598669623066,
      "loss": 0.7015,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.29825660586357117,
      "learning_rate": 0.0004292461197339246,
      "loss": 0.7513,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.28996437788009644,
      "learning_rate": 0.00042818625277161863,
      "loss": 0.7417,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.317898690700531,
      "learning_rate": 0.00042712638580931267,
      "loss": 0.7547,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.35207676887512207,
      "learning_rate": 0.00042606651884700666,
      "loss": 0.8215,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.2996538579463959,
      "learning_rate": 0.0004250066518847007,
      "loss": 0.7897,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.35331282019615173,
      "learning_rate": 0.00042394678492239474,
      "loss": 0.7466,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.30339422821998596,
      "learning_rate": 0.00042288691796008867,
      "loss": 0.7079,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.35229793190956116,
      "learning_rate": 0.0004218270509977827,
      "loss": 0.7322,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.3471188545227051,
      "learning_rate": 0.00042076718403547675,
      "loss": 0.6908,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.384351521730423,
      "learning_rate": 0.00041970731707317074,
      "loss": 0.6937,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.34261906147003174,
      "learning_rate": 0.0004186474501108648,
      "loss": 0.694,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.36659127473831177,
      "learning_rate": 0.0004175875831485588,
      "loss": 0.7186,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.3876580595970154,
      "learning_rate": 0.00041652771618625275,
      "loss": 0.7474,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.3435872495174408,
      "learning_rate": 0.0004154678492239468,
      "loss": 0.7313,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.2954373061656952,
      "learning_rate": 0.00041440798226164083,
      "loss": 0.6693,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.2931239604949951,
      "learning_rate": 0.0004133481152993348,
      "loss": 0.7175,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.37997666001319885,
      "learning_rate": 0.00041228824833702886,
      "loss": 0.704,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.3305527865886688,
      "learning_rate": 0.00041122838137472285,
      "loss": 0.7234,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.33284375071525574,
      "learning_rate": 0.00041016851441241683,
      "loss": 0.6931,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.32701659202575684,
      "learning_rate": 0.00040910864745011087,
      "loss": 0.7191,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.32257601618766785,
      "learning_rate": 0.00040804878048780486,
      "loss": 0.6495,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.34117209911346436,
      "learning_rate": 0.0004069889135254989,
      "loss": 0.7386,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.41902703046798706,
      "learning_rate": 0.00040592904656319294,
      "loss": 0.7807,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.3014705181121826,
      "learning_rate": 0.0004048691796008869,
      "loss": 0.6529,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.34272533655166626,
      "learning_rate": 0.00040380931263858097,
      "loss": 0.7318,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.3316797614097595,
      "learning_rate": 0.00040274944567627495,
      "loss": 0.6452,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.290902704000473,
      "learning_rate": 0.00040168957871396894,
      "loss": 0.742,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.34589096903800964,
      "learning_rate": 0.000400629711751663,
      "loss": 0.7207,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.35719630122184753,
      "learning_rate": 0.000399569844789357,
      "loss": 0.7156,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.36912935972213745,
      "learning_rate": 0.000398509977827051,
      "loss": 0.7168,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.3709248900413513,
      "learning_rate": 0.00039745011086474505,
      "loss": 0.7413,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.3554258942604065,
      "learning_rate": 0.00039639024390243904,
      "loss": 0.7422,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.2682874798774719,
      "learning_rate": 0.000395330376940133,
      "loss": 0.6487,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.275944322347641,
      "learning_rate": 0.00039427050997782706,
      "loss": 0.7031,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.3202199935913086,
      "learning_rate": 0.0003932106430155211,
      "loss": 0.6992,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.3686879575252533,
      "learning_rate": 0.0003921507760532151,
      "loss": 0.7499,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.303440660238266,
      "learning_rate": 0.00039109090909090913,
      "loss": 0.7126,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.3335700035095215,
      "learning_rate": 0.0003900310421286031,
      "loss": 0.782,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.33381161093711853,
      "learning_rate": 0.0003889711751662971,
      "loss": 0.6969,
      "step": 90
    }
  ],
  "logging_steps": 1,
  "max_steps": 456,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.112442380506522e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}