{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.989010989010989,
  "eval_steps": 500,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.7352408170700073,
      "learning_rate": 0.0,
      "loss": 2.8522,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.4486565589904785,
      "learning_rate": 4e-05,
      "loss": 3.169,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.0702540874481201,
      "learning_rate": 8e-05,
      "loss": 2.408,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.1687052249908447,
      "learning_rate": 0.00012,
      "loss": 2.0497,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 2.2542476654052734,
      "learning_rate": 0.00016,
      "loss": 2.7493,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 2.3287904262542725,
      "learning_rate": 0.0002,
      "loss": 2.1949,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 1.9626232385635376,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.7247,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.387238621711731,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.3098,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.8520089387893677,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.0429,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 1.6577852964401245,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.6674,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 1.2114418745040894,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.3176,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.4807603657245636,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.3711,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.47582772374153137,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.3459,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.41599684953689575,
      "learning_rate": 0.00019645232815964525,
      "loss": 1.2554,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.6119060516357422,
      "learning_rate": 0.00019600886917960092,
      "loss": 1.4466,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.40542635321617126,
      "learning_rate": 0.00019556541019955653,
      "loss": 1.2895,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.41910651326179504,
      "learning_rate": 0.0001951219512195122,
      "loss": 1.2139,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.4188455641269684,
      "learning_rate": 0.00019467849223946785,
      "loss": 0.9895,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.3762384057044983,
      "learning_rate": 0.00019423503325942352,
      "loss": 1.0847,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.31877341866493225,
      "learning_rate": 0.00019379157427937917,
      "loss": 1.0702,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.3400358259677887,
      "learning_rate": 0.00019334811529933484,
      "loss": 1.0285,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.32345882058143616,
      "learning_rate": 0.00019290465631929045,
      "loss": 1.0278,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.3499467968940735,
      "learning_rate": 0.00019246119733924613,
      "loss": 1.177,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.30673080682754517,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.865,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.4953795075416565,
      "learning_rate": 0.00019157427937915744,
      "loss": 1.1651,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.2853710353374481,
      "learning_rate": 0.00019113082039911309,
      "loss": 1.1413,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.3122055232524872,
      "learning_rate": 0.00019068736141906876,
      "loss": 1.0441,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.3624468147754669,
      "learning_rate": 0.0001902439024390244,
      "loss": 1.2172,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.28935009241104126,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.9787,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.36901548504829407,
      "learning_rate": 0.00018935698447893572,
      "loss": 1.3225,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.31275656819343567,
      "learning_rate": 0.00018891352549889136,
      "loss": 1.2915,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.42839211225509644,
      "learning_rate": 0.00018847006651884703,
      "loss": 1.0436,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.26850372552871704,
      "learning_rate": 0.00018802660753880268,
      "loss": 1.0722,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.36042699217796326,
      "learning_rate": 0.00018758314855875832,
      "loss": 1.1253,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.28001224994659424,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.9574,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.3492620885372162,
      "learning_rate": 0.00018669623059866964,
      "loss": 1.0201,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.3073531687259674,
      "learning_rate": 0.00018625277161862528,
      "loss": 1.343,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.32127225399017334,
      "learning_rate": 0.00018580931263858095,
      "loss": 0.9489,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.39669620990753174,
      "learning_rate": 0.0001853658536585366,
      "loss": 1.2342,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.3713603913784027,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.9283,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.29546988010406494,
      "learning_rate": 0.0001844789356984479,
      "loss": 1.1932,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.2921528220176697,
      "learning_rate": 0.00018403547671840356,
      "loss": 1.1134,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.34131723642349243,
      "learning_rate": 0.0001835920177383592,
      "loss": 1.086,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.2900494635105133,
      "learning_rate": 0.00018314855875831487,
      "loss": 1.2366,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.2531304657459259,
      "learning_rate": 0.00018270509977827052,
      "loss": 1.0213,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.3356711268424988,
      "learning_rate": 0.00018226164079822616,
      "loss": 1.5558,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.3397180140018463,
      "learning_rate": 0.00018181818181818183,
      "loss": 1.2211,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.26618894934654236,
      "learning_rate": 0.00018137472283813748,
      "loss": 1.0424,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.224151611328125,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.9274,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.23920287191867828,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.891,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.28520718216896057,
      "learning_rate": 0.00018004434589800444,
      "loss": 1.191,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.3044593930244446,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.9438,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.3386774957180023,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.8332,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.2599007487297058,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.8841,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.31952711939811707,
      "learning_rate": 0.00017827050997782707,
      "loss": 1.0752,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.29915735125541687,
      "learning_rate": 0.00017782705099778271,
      "loss": 0.8285,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.3165893852710724,
      "learning_rate": 0.00017738359201773839,
      "loss": 1.1922,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.2801388204097748,
      "learning_rate": 0.000176940133037694,
      "loss": 1.0728,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.2965599298477173,
      "learning_rate": 0.00017649667405764967,
      "loss": 1.0071,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.3237171769142151,
      "learning_rate": 0.00017605321507760532,
      "loss": 1.0324,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.298601359128952,
      "learning_rate": 0.000175609756097561,
      "loss": 1.0664,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.2842566668987274,
      "learning_rate": 0.00017516629711751663,
      "loss": 1.0195,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.27053070068359375,
      "learning_rate": 0.0001747228381374723,
      "loss": 0.7934,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.3908388316631317,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.9806,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.2827537953853607,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.98,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.3323328495025635,
      "learning_rate": 0.00017339246119733924,
      "loss": 1.3464,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.4051510989665985,
      "learning_rate": 0.0001729490022172949,
      "loss": 1.0039,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.31627437472343445,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.9009,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.26257163286209106,
      "learning_rate": 0.00017206208425720623,
      "loss": 1.0065,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.3478996157646179,
      "learning_rate": 0.00017161862527716187,
      "loss": 0.9857,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.295265793800354,
      "learning_rate": 0.00017117516629711752,
      "loss": 0.8994,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.26476070284843445,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.8383,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.29510369896888733,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.847,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.3598829507827759,
      "learning_rate": 0.0001698447893569845,
      "loss": 1.2644,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.3148934543132782,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.9587,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.27720341086387634,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.9812,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.28033679723739624,
      "learning_rate": 0.00016851441241685144,
      "loss": 1.0359,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.37113821506500244,
      "learning_rate": 0.0001680709534368071,
      "loss": 1.1006,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.3252990245819092,
      "learning_rate": 0.00016762749445676275,
      "loss": 1.0863,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.2812971770763397,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.8634,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.29631471633911133,
      "learning_rate": 0.00016674057649667407,
      "loss": 1.1306,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.3373422920703888,
      "learning_rate": 0.00016629711751662974,
      "loss": 1.1394,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.3303433060646057,
      "learning_rate": 0.00016585365853658536,
      "loss": 1.1193,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.3455532193183899,
      "learning_rate": 0.00016541019955654103,
      "loss": 1.3642,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.28859150409698486,
      "learning_rate": 0.00016496674057649667,
      "loss": 1.2377,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.29475292563438416,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.983,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.4004489481449127,
      "learning_rate": 0.000164079822616408,
      "loss": 1.0643,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.2510679364204407,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.8841,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.24756520986557007,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.8481,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.3182165026664734,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.9904,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.4293341338634491,
      "learning_rate": 0.0001623059866962306,
      "loss": 0.9611,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.4090866446495056,
      "learning_rate": 0.00016186252771618626,
      "loss": 1.1459,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.3115290105342865,
      "learning_rate": 0.0001614190687361419,
      "loss": 1.2889,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.27534812688827515,
      "learning_rate": 0.00016097560975609758,
      "loss": 0.8152,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.28921276330947876,
      "learning_rate": 0.00016053215077605322,
      "loss": 1.2137,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.3336808383464813,
      "learning_rate": 0.00016008869179600887,
      "loss": 0.9006,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.25946861505508423,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.875,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.344741553068161,
      "learning_rate": 0.00015920177383592018,
      "loss": 1.0005,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.29897916316986084,
      "learning_rate": 0.00015875831485587586,
      "loss": 0.8467,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.31322357058525085,
      "learning_rate": 0.0001583148558758315,
      "loss": 0.9429,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.3123408257961273,
      "learning_rate": 0.00015787139689578714,
      "loss": 1.0514,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.2901889979839325,
      "learning_rate": 0.0001574279379157428,
      "loss": 0.9956,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.3106645345687866,
      "learning_rate": 0.00015698447893569846,
      "loss": 0.9133,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.28252625465393066,
      "learning_rate": 0.0001565410199556541,
      "loss": 0.9292,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.30795255303382874,
      "learning_rate": 0.00015609756097560978,
      "loss": 0.9956,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.3440392017364502,
      "learning_rate": 0.00015565410199556542,
      "loss": 1.0907,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.33299505710601807,
      "learning_rate": 0.00015521064301552106,
      "loss": 1.2411,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.27721455693244934,
      "learning_rate": 0.0001547671840354767,
      "loss": 0.9861,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.35272037982940674,
      "learning_rate": 0.00015432372505543238,
      "loss": 1.0007,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.32182958722114563,
      "learning_rate": 0.00015388026607538802,
      "loss": 1.2388,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.31311723589897156,
      "learning_rate": 0.0001534368070953437,
      "loss": 0.9561,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.4048290252685547,
      "learning_rate": 0.00015299334811529934,
      "loss": 1.2042,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.29820093512535095,
      "learning_rate": 0.00015254988913525498,
      "loss": 0.9652,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.31341466307640076,
      "learning_rate": 0.00015210643015521066,
      "loss": 1.1486,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.31646299362182617,
      "learning_rate": 0.0001516629711751663,
      "loss": 0.8865,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.3182319104671478,
      "learning_rate": 0.00015121951219512197,
      "loss": 1.108,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.23394735157489777,
      "learning_rate": 0.00015077605321507762,
      "loss": 0.8012,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.3006887137889862,
      "learning_rate": 0.0001503325942350333,
      "loss": 1.2336,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.3598942756652832,
      "learning_rate": 0.0001498891352549889,
      "loss": 1.1689,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.355162113904953,
      "learning_rate": 0.00014944567627494458,
      "loss": 1.0129,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.29940107464790344,
      "learning_rate": 0.00014900221729490022,
      "loss": 1.0254,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.277706116437912,
      "learning_rate": 0.0001485587583148559,
      "loss": 0.8711,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.34179016947746277,
      "learning_rate": 0.00014811529933481154,
      "loss": 0.9705,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.33881035447120667,
      "learning_rate": 0.0001476718403547672,
      "loss": 1.2317,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.2907496690750122,
      "learning_rate": 0.00014722838137472282,
      "loss": 0.8678,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.25325828790664673,
      "learning_rate": 0.0001467849223946785,
      "loss": 0.8778,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.3223305940628052,
      "learning_rate": 0.00014634146341463414,
      "loss": 1.0607,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.35531964898109436,
      "learning_rate": 0.0001458980044345898,
      "loss": 0.9523,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.3222889304161072,
      "learning_rate": 0.00014545454545454546,
      "loss": 1.016,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.2622178792953491,
      "learning_rate": 0.00014501108647450113,
      "loss": 0.9652,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.3121354877948761,
      "learning_rate": 0.00014456762749445675,
      "loss": 0.8575,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.31900012493133545,
      "learning_rate": 0.00014412416851441242,
      "loss": 1.2497,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.30143916606903076,
      "learning_rate": 0.00014368070953436806,
      "loss": 0.8387,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.34604671597480774,
      "learning_rate": 0.00014323725055432373,
      "loss": 1.0801,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.3418114483356476,
      "learning_rate": 0.00014279379157427938,
      "loss": 0.8665,
      "step": 135
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.30303439497947693,
      "learning_rate": 0.00014235033259423505,
      "loss": 1.1594,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.27274811267852783,
      "learning_rate": 0.0001419068736141907,
      "loss": 0.9804,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.3320262134075165,
      "learning_rate": 0.00014146341463414634,
      "loss": 1.1487,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.3386929929256439,
      "learning_rate": 0.000141019955654102,
      "loss": 1.0053,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.2829763889312744,
      "learning_rate": 0.00014057649667405765,
      "loss": 0.8789,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.25782448053359985,
      "learning_rate": 0.00014013303769401332,
      "loss": 0.9112,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.2781846523284912,
      "learning_rate": 0.00013968957871396897,
      "loss": 0.8281,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.3462756872177124,
      "learning_rate": 0.00013924611973392464,
      "loss": 1.0596,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.3318636417388916,
      "learning_rate": 0.00013880266075388026,
      "loss": 1.0474,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.3512427806854248,
      "learning_rate": 0.00013835920177383593,
      "loss": 1.1012,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.34367895126342773,
      "learning_rate": 0.00013791574279379157,
      "loss": 0.9938,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.4002191126346588,
      "learning_rate": 0.00013747228381374724,
      "loss": 0.9466,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.3430136740207672,
      "learning_rate": 0.0001370288248337029,
      "loss": 0.9489,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.3685528635978699,
      "learning_rate": 0.00013658536585365856,
      "loss": 1.0603,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.4152441918849945,
      "learning_rate": 0.00013614190687361418,
      "loss": 1.0476,
      "step": 150
    }
  ],
  "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": 2.6319628618973184e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}