{
  "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": 0.9548422694206238,
      "learning_rate": 0.0,
      "loss": 2.456,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 0.9033191800117493,
      "learning_rate": 4e-05,
      "loss": 2.7771,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 0.9564813375473022,
      "learning_rate": 8e-05,
      "loss": 2.7839,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.4111387729644775,
      "learning_rate": 0.00012,
      "loss": 3.2357,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 1.9880008697509766,
      "learning_rate": 0.00016,
      "loss": 3.5809,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 2.1871581077575684,
      "learning_rate": 0.0002,
      "loss": 2.9169,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 2.0554776191711426,
      "learning_rate": 0.00019955654101995565,
      "loss": 2.1632,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.8138749599456787,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.6378,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 1.0925194025039673,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.157,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.8452661633491516,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.11,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.9047808051109314,
      "learning_rate": 0.00019778270509977829,
      "loss": 0.903,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.8229642510414124,
      "learning_rate": 0.00019733924611973393,
      "loss": 0.923,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.6836701035499573,
      "learning_rate": 0.0001968957871396896,
      "loss": 0.7578,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.7976304292678833,
      "learning_rate": 0.00019645232815964525,
      "loss": 0.7888,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.5903546214103699,
      "learning_rate": 0.00019600886917960092,
      "loss": 0.7382,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.5188648104667664,
      "learning_rate": 0.00019556541019955653,
      "loss": 0.7559,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.43109938502311707,
      "learning_rate": 0.0001951219512195122,
      "loss": 0.6449,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.5063297748565674,
      "learning_rate": 0.00019467849223946785,
      "loss": 0.7978,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.48597580194473267,
      "learning_rate": 0.00019423503325942352,
      "loss": 0.7311,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.4553968906402588,
      "learning_rate": 0.00019379157427937917,
      "loss": 0.7349,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.4415663778781891,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.5978,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.44407373666763306,
      "learning_rate": 0.00019290465631929045,
      "loss": 0.6434,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.4405691623687744,
      "learning_rate": 0.00019246119733924613,
      "loss": 0.6702,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.45118415355682373,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.6987,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.4140220582485199,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.739,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.3368533253669739,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.6759,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.32022058963775635,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.5563,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.30251631140708923,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.5916,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.33803412318229675,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.5178,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.3477880656719208,
      "learning_rate": 0.00018935698447893572,
      "loss": 0.7149,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.4316825568675995,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.6876,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.3937191665172577,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.6659,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.36258432269096375,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.5481,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.4232417643070221,
      "learning_rate": 0.00018758314855875832,
      "loss": 0.6761,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.3215615749359131,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.6068,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.3615092933177948,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.5814,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.33303868770599365,
      "learning_rate": 0.00018625277161862528,
      "loss": 0.5659,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.34852537512779236,
      "learning_rate": 0.00018580931263858095,
      "loss": 0.5848,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.333442360162735,
      "learning_rate": 0.0001853658536585366,
      "loss": 0.5249,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.3381938636302948,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.6407,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.3696731626987457,
      "learning_rate": 0.0001844789356984479,
      "loss": 0.6736,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.4098624587059021,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.6643,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.3498683273792267,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.5443,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.3131304383277893,
      "learning_rate": 0.00018314855875831487,
      "loss": 0.5232,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.39961516857147217,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.7046,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.4616391360759735,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.6706,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.38573798537254333,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.6662,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.336185097694397,
      "learning_rate": 0.00018137472283813748,
      "loss": 0.5845,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.3926178216934204,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.495,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.36642107367515564,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.5075,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.4265896677970886,
      "learning_rate": 0.00018004434589800444,
      "loss": 0.6636,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.4908406436443329,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.6943,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.3566623032093048,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.5919,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.3888160288333893,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.7048,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.3611518144607544,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.505,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.3949228823184967,
      "learning_rate": 0.00017782705099778271,
      "loss": 0.6138,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.4875071942806244,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.7643,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.44993212819099426,
      "learning_rate": 0.000176940133037694,
      "loss": 0.702,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.34542116522789,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.5463,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.42165201902389526,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.5946,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.3682475984096527,
      "learning_rate": 0.000175609756097561,
      "loss": 0.5548,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.36798593401908875,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.3957,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.4413401186466217,
      "learning_rate": 0.0001747228381374723,
      "loss": 0.6863,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.4089689552783966,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.5794,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.357327938079834,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.5446,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.3936524987220764,
      "learning_rate": 0.00017339246119733924,
      "loss": 0.569,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.4308718144893646,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.608,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.4803222417831421,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.6635,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.4282255470752716,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.5607,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.44135338068008423,
      "learning_rate": 0.00017161862527716187,
      "loss": 0.5048,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.5171645879745483,
      "learning_rate": 0.00017117516629711752,
      "loss": 0.6101,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.4031164348125458,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.5566,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.35505273938179016,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.6453,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.3494785726070404,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.6731,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.4739617109298706,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.5278,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.3757701814174652,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.4467,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.4467487633228302,
      "learning_rate": 0.00016851441241685144,
      "loss": 0.6486,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.4626796543598175,
      "learning_rate": 0.0001680709534368071,
      "loss": 0.4425,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.4805651307106018,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.532,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.6599902510643005,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.6162,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.45104750990867615,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.5708,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.4385611414909363,
      "learning_rate": 0.00016629711751662974,
      "loss": 0.5711,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.4250934422016144,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.6049,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.4899722635746002,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.6084,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.33061057329177856,
      "learning_rate": 0.00016496674057649667,
      "loss": 0.4669,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.4679504632949829,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.643,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.32151514291763306,
      "learning_rate": 0.000164079822616408,
      "loss": 0.3998,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.3151485323905945,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.468,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.3355564773082733,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.4659,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.4314066469669342,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.5191,
      "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": 3.756018851704627e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}