{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.5802197802197804,
  "eval_steps": 500,
  "global_step": 240,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.276628851890564,
      "learning_rate": 0.0,
      "loss": 2.2249,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.8965637683868408,
      "learning_rate": 4e-05,
      "loss": 2.9398,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.0756678581237793,
      "learning_rate": 8e-05,
      "loss": 2.2805,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.4522080421447754,
      "learning_rate": 0.00012,
      "loss": 2.4587,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 2.267936944961548,
      "learning_rate": 0.00016,
      "loss": 2.7199,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 2.5036749839782715,
      "learning_rate": 0.0002,
      "loss": 2.6136,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 2.603842258453369,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.8867,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.7314811944961548,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.7122,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 1.2087041139602661,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.3281,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 1.2565605640411377,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.2634,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 1.3084511756896973,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.3822,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.5777367353439331,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.2763,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.41326773166656494,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.0083,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.3794688582420349,
      "learning_rate": 0.00019645232815964525,
      "loss": 1.0039,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.4300615191459656,
      "learning_rate": 0.00019600886917960092,
      "loss": 1.0871,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.5444045662879944,
      "learning_rate": 0.00019556541019955653,
      "loss": 1.2196,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.3883669376373291,
      "learning_rate": 0.0001951219512195122,
      "loss": 1.046,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.3480859696865082,
      "learning_rate": 0.00019467849223946785,
      "loss": 1.1989,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.4945982098579407,
      "learning_rate": 0.00019423503325942352,
      "loss": 1.1578,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.3624681532382965,
      "learning_rate": 0.00019379157427937917,
      "loss": 1.0371,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.33874213695526123,
      "learning_rate": 0.00019334811529933484,
      "loss": 1.1418,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.3623351752758026,
      "learning_rate": 0.00019290465631929045,
      "loss": 0.9795,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.3544716238975525,
      "learning_rate": 0.00019246119733924613,
      "loss": 1.1517,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.3639620542526245,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.9038,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.3429097533226013,
      "learning_rate": 0.00019157427937915744,
      "loss": 1.2654,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.3469904065132141,
      "learning_rate": 0.00019113082039911309,
      "loss": 1.0942,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.31158897280693054,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.9849,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.360698938369751,
      "learning_rate": 0.0001902439024390244,
      "loss": 1.1911,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.307934045791626,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.9332,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.3456997573375702,
      "learning_rate": 0.00018935698447893572,
      "loss": 0.8887,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.3178318738937378,
      "learning_rate": 0.00018891352549889136,
      "loss": 1.096,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.3246353268623352,
      "learning_rate": 0.00018847006651884703,
      "loss": 1.0265,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.32288020849227905,
      "learning_rate": 0.00018802660753880268,
      "loss": 1.1026,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.3587368130683899,
      "learning_rate": 0.00018758314855875832,
      "loss": 1.0147,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.35794976353645325,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.8294,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.3202354907989502,
      "learning_rate": 0.00018669623059866964,
      "loss": 1.0115,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.39045482873916626,
      "learning_rate": 0.00018625277161862528,
      "loss": 1.0501,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.3386252820491791,
      "learning_rate": 0.00018580931263858095,
      "loss": 1.032,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.3127234876155853,
      "learning_rate": 0.0001853658536585366,
      "loss": 0.9169,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.33366769552230835,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.9192,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.29174473881721497,
      "learning_rate": 0.0001844789356984479,
      "loss": 1.0063,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.29834258556365967,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.9911,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.3175811171531677,
      "learning_rate": 0.0001835920177383592,
      "loss": 1.0529,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.37180864810943604,
      "learning_rate": 0.00018314855875831487,
      "loss": 1.0766,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.3089708685874939,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.9967,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.3001553416252136,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.9681,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.36786341667175293,
      "learning_rate": 0.00018181818181818183,
      "loss": 1.1808,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.33892518281936646,
      "learning_rate": 0.00018137472283813748,
      "loss": 0.993,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.37353309988975525,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.9254,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.3374471068382263,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.8039,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.35015958547592163,
      "learning_rate": 0.00018004434589800444,
      "loss": 1.0343,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.6764574646949768,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.8912,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.3225049376487732,
      "learning_rate": 0.00017915742793791575,
      "loss": 1.0477,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.38042157888412476,
      "learning_rate": 0.0001787139689578714,
      "loss": 1.1136,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.2846735417842865,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.9663,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.3068177402019501,
      "learning_rate": 0.00017782705099778271,
      "loss": 0.8277,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.3181379735469818,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.8302,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.29783740639686584,
      "learning_rate": 0.000176940133037694,
      "loss": 0.9198,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.2617000341415405,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.8633,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.32726994156837463,
      "learning_rate": 0.00017605321507760532,
      "loss": 1.0882,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.2992764413356781,
      "learning_rate": 0.000175609756097561,
      "loss": 0.8702,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.3218694031238556,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.9147,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.3782860338687897,
      "learning_rate": 0.0001747228381374723,
      "loss": 1.1205,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.2852671444416046,
      "learning_rate": 0.00017427937915742792,
      "loss": 1.0163,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.2889496982097626,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.954,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.3589063584804535,
      "learning_rate": 0.00017339246119733924,
      "loss": 0.8852,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.2851206362247467,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.9634,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.34732353687286377,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.9464,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.3914244771003723,
      "learning_rate": 0.00017206208425720623,
      "loss": 1.0521,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.3204376995563507,
      "learning_rate": 0.00017161862527716187,
      "loss": 1.0175,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.3486352264881134,
      "learning_rate": 0.00017117516629711752,
      "loss": 0.9382,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.35134875774383545,
      "learning_rate": 0.0001707317073170732,
      "loss": 1.009,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.28274664282798767,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.9402,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.304936021566391,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.9479,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.309792697429657,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.9571,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.26235175132751465,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.9205,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.29319170117378235,
      "learning_rate": 0.00016851441241685144,
      "loss": 0.893,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.31189513206481934,
      "learning_rate": 0.0001680709534368071,
      "loss": 1.0442,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.28744086623191833,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.9213,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.3388351500034332,
      "learning_rate": 0.00016718403547671842,
      "loss": 1.0627,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.286472350358963,
      "learning_rate": 0.00016674057649667407,
      "loss": 1.0228,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.39154326915740967,
      "learning_rate": 0.00016629711751662974,
      "loss": 0.9795,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.3573135733604431,
      "learning_rate": 0.00016585365853658536,
      "loss": 1.0314,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.3346281349658966,
      "learning_rate": 0.00016541019955654103,
      "loss": 1.0756,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.32586076855659485,
      "learning_rate": 0.00016496674057649667,
      "loss": 0.8417,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.31192702054977417,
      "learning_rate": 0.00016452328159645234,
      "loss": 1.0462,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.34713441133499146,
      "learning_rate": 0.000164079822616408,
      "loss": 0.9765,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.3601307272911072,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.9863,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.3456384241580963,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.9127,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.2803562879562378,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.8911,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.29616042971611023,
      "learning_rate": 0.0001623059866962306,
      "loss": 0.8337,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.32056528329849243,
      "learning_rate": 0.00016186252771618626,
      "loss": 0.9557,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.29565393924713135,
      "learning_rate": 0.0001614190687361419,
      "loss": 1.0692,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.3128349781036377,
      "learning_rate": 0.00016097560975609758,
      "loss": 0.9821,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.29564058780670166,
      "learning_rate": 0.00016053215077605322,
      "loss": 0.9285,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.3469644784927368,
      "learning_rate": 0.00016008869179600887,
      "loss": 1.0785,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.3313232958316803,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.9541,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.32982274889945984,
      "learning_rate": 0.00015920177383592018,
      "loss": 0.9847,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.3338361382484436,
      "learning_rate": 0.00015875831485587586,
      "loss": 0.9039,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.3076937198638916,
      "learning_rate": 0.0001583148558758315,
      "loss": 0.9202,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.3110261857509613,
      "learning_rate": 0.00015787139689578714,
      "loss": 0.9329,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.35034114122390747,
      "learning_rate": 0.0001574279379157428,
      "loss": 1.1377,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.3166506290435791,
      "learning_rate": 0.00015698447893569846,
      "loss": 0.8738,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.3227419853210449,
      "learning_rate": 0.0001565410199556541,
      "loss": 1.0179,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.38018763065338135,
      "learning_rate": 0.00015609756097560978,
      "loss": 0.8218,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.3387452960014343,
      "learning_rate": 0.00015565410199556542,
      "loss": 0.941,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.36907076835632324,
      "learning_rate": 0.00015521064301552106,
      "loss": 1.1635,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.3184981942176819,
      "learning_rate": 0.0001547671840354767,
      "loss": 1.0603,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.31189945340156555,
      "learning_rate": 0.00015432372505543238,
      "loss": 0.9893,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.2853548228740692,
      "learning_rate": 0.00015388026607538802,
      "loss": 0.9381,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.30955153703689575,
      "learning_rate": 0.0001534368070953437,
      "loss": 0.9608,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.3228888213634491,
      "learning_rate": 0.00015299334811529934,
      "loss": 0.9847,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.31553468108177185,
      "learning_rate": 0.00015254988913525498,
      "loss": 0.8394,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.3272542357444763,
      "learning_rate": 0.00015210643015521066,
      "loss": 0.948,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.3000577390193939,
      "learning_rate": 0.0001516629711751663,
      "loss": 0.9311,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.29430148005485535,
      "learning_rate": 0.00015121951219512197,
      "loss": 0.921,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.3130577504634857,
      "learning_rate": 0.00015077605321507762,
      "loss": 0.991,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.3301986753940582,
      "learning_rate": 0.0001503325942350333,
      "loss": 0.977,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.3065156042575836,
      "learning_rate": 0.0001498891352549889,
      "loss": 0.86,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.3444720208644867,
      "learning_rate": 0.00014944567627494458,
      "loss": 1.0065,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.3519897758960724,
      "learning_rate": 0.00014900221729490022,
      "loss": 1.0163,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.3462337851524353,
      "learning_rate": 0.0001485587583148559,
      "loss": 0.848,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.3681805431842804,
      "learning_rate": 0.00014811529933481154,
      "loss": 0.8667,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.3052239716053009,
      "learning_rate": 0.0001476718403547672,
      "loss": 0.9655,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.3414475917816162,
      "learning_rate": 0.00014722838137472282,
      "loss": 0.8422,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.33679068088531494,
      "learning_rate": 0.0001467849223946785,
      "loss": 0.987,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.32141727209091187,
      "learning_rate": 0.00014634146341463414,
      "loss": 0.9898,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.34999319911003113,
      "learning_rate": 0.0001458980044345898,
      "loss": 0.9962,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.35051655769348145,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.9688,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.33805355429649353,
      "learning_rate": 0.00014501108647450113,
      "loss": 0.918,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.36494380235671997,
      "learning_rate": 0.00014456762749445675,
      "loss": 1.005,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.37841951847076416,
      "learning_rate": 0.00014412416851441242,
      "loss": 0.953,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.34467488527297974,
      "learning_rate": 0.00014368070953436806,
      "loss": 0.9606,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.3734540343284607,
      "learning_rate": 0.00014323725055432373,
      "loss": 0.9997,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.30393826961517334,
      "learning_rate": 0.00014279379157427938,
      "loss": 1.0236,
      "step": 135
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.33223313093185425,
      "learning_rate": 0.00014235033259423505,
      "loss": 0.9263,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.34765636920928955,
      "learning_rate": 0.0001419068736141907,
      "loss": 1.0353,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.36897042393684387,
      "learning_rate": 0.00014146341463414634,
      "loss": 1.0196,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.331625759601593,
      "learning_rate": 0.000141019955654102,
      "loss": 0.944,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.35499122738838196,
      "learning_rate": 0.00014057649667405765,
      "loss": 1.0195,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.34511762857437134,
      "learning_rate": 0.00014013303769401332,
      "loss": 1.0835,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.3462699055671692,
      "learning_rate": 0.00013968957871396897,
      "loss": 1.1026,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.40795978903770447,
      "learning_rate": 0.00013924611973392464,
      "loss": 1.0358,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.3753316104412079,
      "learning_rate": 0.00013880266075388026,
      "loss": 0.9453,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.3037593960762024,
      "learning_rate": 0.00013835920177383593,
      "loss": 0.8033,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.30207523703575134,
      "learning_rate": 0.00013791574279379157,
      "loss": 1.0717,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.31364524364471436,
      "learning_rate": 0.00013747228381374724,
      "loss": 0.8424,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.36423608660697937,
      "learning_rate": 0.0001370288248337029,
      "loss": 0.9304,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.33277976512908936,
      "learning_rate": 0.00013658536585365856,
      "loss": 0.8836,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.30385881662368774,
      "learning_rate": 0.00013614190687361418,
      "loss": 0.897,
      "step": 150
    },
    {
      "epoch": 0.9956043956043956,
      "grad_norm": 0.29546377062797546,
      "learning_rate": 0.00013569844789356985,
      "loss": 0.888,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.45832559466362,
      "learning_rate": 0.0001352549889135255,
      "loss": 0.958,
      "step": 152
    },
    {
      "epoch": 1.0065934065934066,
      "grad_norm": 0.33893418312072754,
      "learning_rate": 0.00013481152993348116,
      "loss": 0.8783,
      "step": 153
    },
    {
      "epoch": 1.0131868131868131,
      "grad_norm": 0.27605369687080383,
      "learning_rate": 0.0001343680709534368,
      "loss": 0.8294,
      "step": 154
    },
    {
      "epoch": 1.0197802197802197,
      "grad_norm": 0.4289993941783905,
      "learning_rate": 0.00013392461197339248,
      "loss": 1.0991,
      "step": 155
    },
    {
      "epoch": 1.0263736263736263,
      "grad_norm": 0.33854013681411743,
      "learning_rate": 0.00013348115299334812,
      "loss": 0.846,
      "step": 156
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.29544690251350403,
      "learning_rate": 0.00013303769401330377,
      "loss": 0.8749,
      "step": 157
    },
    {
      "epoch": 1.0395604395604396,
      "grad_norm": 0.30724477767944336,
      "learning_rate": 0.00013259423503325944,
      "loss": 0.9186,
      "step": 158
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 0.31859660148620605,
      "learning_rate": 0.00013215077605321509,
      "loss": 0.8953,
      "step": 159
    },
    {
      "epoch": 1.0527472527472528,
      "grad_norm": 0.38985756039619446,
      "learning_rate": 0.00013170731707317076,
      "loss": 1.0299,
      "step": 160
    },
    {
      "epoch": 1.0593406593406594,
      "grad_norm": 0.36841949820518494,
      "learning_rate": 0.0001312638580931264,
      "loss": 1.0398,
      "step": 161
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.3244284987449646,
      "learning_rate": 0.00013082039911308205,
      "loss": 0.853,
      "step": 162
    },
    {
      "epoch": 1.0725274725274725,
      "grad_norm": 0.3542915880680084,
      "learning_rate": 0.0001303769401330377,
      "loss": 0.8081,
      "step": 163
    },
    {
      "epoch": 1.079120879120879,
      "grad_norm": 0.35428130626678467,
      "learning_rate": 0.00012993348115299336,
      "loss": 0.7807,
      "step": 164
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.3320915400981903,
      "learning_rate": 0.000129490022172949,
      "loss": 0.8336,
      "step": 165
    },
    {
      "epoch": 1.0923076923076924,
      "grad_norm": 0.3837350606918335,
      "learning_rate": 0.00012904656319290468,
      "loss": 0.9419,
      "step": 166
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 0.3874458968639374,
      "learning_rate": 0.00012860310421286032,
      "loss": 1.0188,
      "step": 167
    },
    {
      "epoch": 1.1054945054945056,
      "grad_norm": 0.3773362338542938,
      "learning_rate": 0.00012815964523281597,
      "loss": 0.9942,
      "step": 168
    },
    {
      "epoch": 1.1120879120879121,
      "grad_norm": 0.3637266457080841,
      "learning_rate": 0.0001277161862527716,
      "loss": 0.8265,
      "step": 169
    },
    {
      "epoch": 1.1186813186813187,
      "grad_norm": 0.3646593987941742,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.8206,
      "step": 170
    },
    {
      "epoch": 1.1252747252747253,
      "grad_norm": 0.4047824442386627,
      "learning_rate": 0.00012682926829268293,
      "loss": 0.9209,
      "step": 171
    },
    {
      "epoch": 1.1318681318681318,
      "grad_norm": 0.44273439049720764,
      "learning_rate": 0.0001263858093126386,
      "loss": 0.9087,
      "step": 172
    },
    {
      "epoch": 1.1384615384615384,
      "grad_norm": 0.3809082806110382,
      "learning_rate": 0.00012594235033259424,
      "loss": 0.843,
      "step": 173
    },
    {
      "epoch": 1.145054945054945,
      "grad_norm": 0.47830790281295776,
      "learning_rate": 0.00012549889135254989,
      "loss": 0.9272,
      "step": 174
    },
    {
      "epoch": 1.1516483516483516,
      "grad_norm": 0.4307577610015869,
      "learning_rate": 0.00012505543237250553,
      "loss": 0.9515,
      "step": 175
    },
    {
      "epoch": 1.1582417582417581,
      "grad_norm": 0.3636133074760437,
      "learning_rate": 0.0001246119733924612,
      "loss": 0.7293,
      "step": 176
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 0.42534151673316956,
      "learning_rate": 0.00012416851441241685,
      "loss": 0.9304,
      "step": 177
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 0.4143664538860321,
      "learning_rate": 0.00012372505543237252,
      "loss": 0.7723,
      "step": 178
    },
    {
      "epoch": 1.178021978021978,
      "grad_norm": 0.38298025727272034,
      "learning_rate": 0.00012328159645232816,
      "loss": 0.7632,
      "step": 179
    },
    {
      "epoch": 1.1846153846153846,
      "grad_norm": 0.4359869360923767,
      "learning_rate": 0.0001228381374722838,
      "loss": 0.9222,
      "step": 180
    },
    {
      "epoch": 1.1912087912087912,
      "grad_norm": 0.4264501631259918,
      "learning_rate": 0.00012239467849223948,
      "loss": 0.974,
      "step": 181
    },
    {
      "epoch": 1.1978021978021978,
      "grad_norm": 0.3985500931739807,
      "learning_rate": 0.00012195121951219512,
      "loss": 0.9541,
      "step": 182
    },
    {
      "epoch": 1.2043956043956043,
      "grad_norm": 0.37315240502357483,
      "learning_rate": 0.00012150776053215078,
      "loss": 0.8645,
      "step": 183
    },
    {
      "epoch": 1.210989010989011,
      "grad_norm": 0.40954989194869995,
      "learning_rate": 0.00012106430155210644,
      "loss": 0.9458,
      "step": 184
    },
    {
      "epoch": 1.2175824175824177,
      "grad_norm": 0.3739243745803833,
      "learning_rate": 0.0001206208425720621,
      "loss": 1.0359,
      "step": 185
    },
    {
      "epoch": 1.2241758241758243,
      "grad_norm": 0.3813992440700531,
      "learning_rate": 0.00012017738359201774,
      "loss": 0.9204,
      "step": 186
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.40818166732788086,
      "learning_rate": 0.0001197339246119734,
      "loss": 0.9119,
      "step": 187
    },
    {
      "epoch": 1.2373626373626374,
      "grad_norm": 0.39503997564315796,
      "learning_rate": 0.00011929046563192906,
      "loss": 0.8078,
      "step": 188
    },
    {
      "epoch": 1.243956043956044,
      "grad_norm": 0.42741236090660095,
      "learning_rate": 0.00011884700665188471,
      "loss": 0.8588,
      "step": 189
    },
    {
      "epoch": 1.2505494505494505,
      "grad_norm": 0.4359978437423706,
      "learning_rate": 0.00011840354767184036,
      "loss": 0.8642,
      "step": 190
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.4243920147418976,
      "learning_rate": 0.00011796008869179602,
      "loss": 0.8186,
      "step": 191
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 0.4763306677341461,
      "learning_rate": 0.00011751662971175166,
      "loss": 0.7971,
      "step": 192
    },
    {
      "epoch": 1.2703296703296703,
      "grad_norm": 0.4615596532821655,
      "learning_rate": 0.00011707317073170732,
      "loss": 0.7447,
      "step": 193
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.48839759826660156,
      "learning_rate": 0.00011662971175166298,
      "loss": 0.9778,
      "step": 194
    },
    {
      "epoch": 1.2835164835164834,
      "grad_norm": 0.4759836792945862,
      "learning_rate": 0.00011618625277161863,
      "loss": 0.843,
      "step": 195
    },
    {
      "epoch": 1.2901098901098902,
      "grad_norm": 0.46743670105934143,
      "learning_rate": 0.00011574279379157429,
      "loss": 0.8872,
      "step": 196
    },
    {
      "epoch": 1.2967032967032968,
      "grad_norm": 0.5169059634208679,
      "learning_rate": 0.00011529933481152995,
      "loss": 0.9692,
      "step": 197
    },
    {
      "epoch": 1.3032967032967033,
      "grad_norm": 0.4832102954387665,
      "learning_rate": 0.00011485587583148558,
      "loss": 0.8834,
      "step": 198
    },
    {
      "epoch": 1.30989010989011,
      "grad_norm": 0.42049071192741394,
      "learning_rate": 0.00011441241685144124,
      "loss": 0.7274,
      "step": 199
    },
    {
      "epoch": 1.3164835164835165,
      "grad_norm": 0.4799596965312958,
      "learning_rate": 0.0001139689578713969,
      "loss": 0.8989,
      "step": 200
    },
    {
      "epoch": 1.323076923076923,
      "grad_norm": 0.4756583869457245,
      "learning_rate": 0.00011352549889135255,
      "loss": 0.8468,
      "step": 201
    },
    {
      "epoch": 1.3296703296703296,
      "grad_norm": 0.5470879673957825,
      "learning_rate": 0.00011308203991130821,
      "loss": 0.9634,
      "step": 202
    },
    {
      "epoch": 1.3362637362637364,
      "grad_norm": 0.5013769865036011,
      "learning_rate": 0.00011263858093126387,
      "loss": 0.9073,
      "step": 203
    },
    {
      "epoch": 1.342857142857143,
      "grad_norm": 0.4730985462665558,
      "learning_rate": 0.00011219512195121953,
      "loss": 0.8026,
      "step": 204
    },
    {
      "epoch": 1.3494505494505495,
      "grad_norm": 0.4935849606990814,
      "learning_rate": 0.00011175166297117516,
      "loss": 0.8067,
      "step": 205
    },
    {
      "epoch": 1.3560439560439561,
      "grad_norm": 0.4122132658958435,
      "learning_rate": 0.00011130820399113082,
      "loss": 0.8679,
      "step": 206
    },
    {
      "epoch": 1.3626373626373627,
      "grad_norm": 0.4359850287437439,
      "learning_rate": 0.00011086474501108647,
      "loss": 0.7514,
      "step": 207
    },
    {
      "epoch": 1.3692307692307693,
      "grad_norm": 0.4690372049808502,
      "learning_rate": 0.00011042128603104213,
      "loss": 0.7689,
      "step": 208
    },
    {
      "epoch": 1.3758241758241758,
      "grad_norm": 0.3960561752319336,
      "learning_rate": 0.00010997782705099779,
      "loss": 0.7386,
      "step": 209
    },
    {
      "epoch": 1.3824175824175824,
      "grad_norm": 0.47814756631851196,
      "learning_rate": 0.00010953436807095345,
      "loss": 0.8392,
      "step": 210
    },
    {
      "epoch": 1.389010989010989,
      "grad_norm": 0.4434049725532532,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.8844,
      "step": 211
    },
    {
      "epoch": 1.3956043956043955,
      "grad_norm": 0.4652855396270752,
      "learning_rate": 0.00010864745011086475,
      "loss": 0.7684,
      "step": 212
    },
    {
      "epoch": 1.402197802197802,
      "grad_norm": 0.48689475655555725,
      "learning_rate": 0.00010820399113082041,
      "loss": 0.7259,
      "step": 213
    },
    {
      "epoch": 1.4087912087912087,
      "grad_norm": 0.48998069763183594,
      "learning_rate": 0.00010776053215077607,
      "loss": 0.8018,
      "step": 214
    },
    {
      "epoch": 1.4153846153846155,
      "grad_norm": 0.48650839924812317,
      "learning_rate": 0.00010731707317073172,
      "loss": 0.7999,
      "step": 215
    },
    {
      "epoch": 1.421978021978022,
      "grad_norm": 0.4734992980957031,
      "learning_rate": 0.00010687361419068738,
      "loss": 0.8062,
      "step": 216
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.4985850751399994,
      "learning_rate": 0.00010643015521064301,
      "loss": 1.0213,
      "step": 217
    },
    {
      "epoch": 1.4351648351648352,
      "grad_norm": 0.5349339246749878,
      "learning_rate": 0.00010598669623059867,
      "loss": 0.8831,
      "step": 218
    },
    {
      "epoch": 1.4417582417582417,
      "grad_norm": 0.4729473888874054,
      "learning_rate": 0.00010554323725055433,
      "loss": 0.8617,
      "step": 219
    },
    {
      "epoch": 1.4483516483516483,
      "grad_norm": 0.5094092488288879,
      "learning_rate": 0.00010509977827050999,
      "loss": 1.0035,
      "step": 220
    },
    {
      "epoch": 1.4549450549450549,
      "grad_norm": 0.4768781363964081,
      "learning_rate": 0.00010465631929046564,
      "loss": 0.8857,
      "step": 221
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.5049788355827332,
      "learning_rate": 0.0001042128603104213,
      "loss": 1.0736,
      "step": 222
    },
    {
      "epoch": 1.4681318681318682,
      "grad_norm": 0.539951503276825,
      "learning_rate": 0.00010376940133037693,
      "loss": 1.0088,
      "step": 223
    },
    {
      "epoch": 1.4747252747252748,
      "grad_norm": 0.42862042784690857,
      "learning_rate": 0.00010332594235033259,
      "loss": 0.7344,
      "step": 224
    },
    {
      "epoch": 1.4813186813186814,
      "grad_norm": 0.5013957619667053,
      "learning_rate": 0.00010288248337028825,
      "loss": 0.8877,
      "step": 225
    },
    {
      "epoch": 1.487912087912088,
      "grad_norm": 0.5533934235572815,
      "learning_rate": 0.0001024390243902439,
      "loss": 0.8115,
      "step": 226
    },
    {
      "epoch": 1.4945054945054945,
      "grad_norm": 0.5452039241790771,
      "learning_rate": 0.00010199556541019956,
      "loss": 0.9144,
      "step": 227
    },
    {
      "epoch": 1.501098901098901,
      "grad_norm": 0.5263413786888123,
      "learning_rate": 0.00010155210643015522,
      "loss": 0.8542,
      "step": 228
    },
    {
      "epoch": 1.5076923076923077,
      "grad_norm": 0.4966578185558319,
      "learning_rate": 0.00010110864745011087,
      "loss": 0.9064,
      "step": 229
    },
    {
      "epoch": 1.5142857142857142,
      "grad_norm": 0.4929255247116089,
      "learning_rate": 0.00010066518847006652,
      "loss": 0.8505,
      "step": 230
    },
    {
      "epoch": 1.5208791208791208,
      "grad_norm": 0.538100004196167,
      "learning_rate": 0.00010022172949002218,
      "loss": 1.0468,
      "step": 231
    },
    {
      "epoch": 1.5274725274725274,
      "grad_norm": 0.5180509090423584,
      "learning_rate": 9.977827050997783e-05,
      "loss": 0.9878,
      "step": 232
    },
    {
      "epoch": 1.534065934065934,
      "grad_norm": 0.5397039651870728,
      "learning_rate": 9.933481152993348e-05,
      "loss": 0.8995,
      "step": 233
    },
    {
      "epoch": 1.5406593406593405,
      "grad_norm": 0.5842252969741821,
      "learning_rate": 9.889135254988914e-05,
      "loss": 0.8934,
      "step": 234
    },
    {
      "epoch": 1.5472527472527473,
      "grad_norm": 0.5972124338150024,
      "learning_rate": 9.84478935698448e-05,
      "loss": 0.9348,
      "step": 235
    },
    {
      "epoch": 1.5538461538461539,
      "grad_norm": 0.5490299463272095,
      "learning_rate": 9.800443458980046e-05,
      "loss": 0.8169,
      "step": 236
    },
    {
      "epoch": 1.5604395604395604,
      "grad_norm": 0.45538854598999023,
      "learning_rate": 9.75609756097561e-05,
      "loss": 0.9701,
      "step": 237
    },
    {
      "epoch": 1.567032967032967,
      "grad_norm": 0.5684420466423035,
      "learning_rate": 9.711751662971176e-05,
      "loss": 0.8857,
      "step": 238
    },
    {
      "epoch": 1.5736263736263736,
      "grad_norm": 0.48955586552619934,
      "learning_rate": 9.667405764966742e-05,
      "loss": 0.8786,
      "step": 239
    },
    {
      "epoch": 1.5802197802197804,
      "grad_norm": 0.5659365057945251,
      "learning_rate": 9.623059866962306e-05,
      "loss": 0.8682,
      "step": 240
    }
  ],
  "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": 3.2897803344838656e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}