{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9626373626373628,
  "eval_steps": 500,
  "global_step": 450,
  "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
    },
    {
      "epoch": 0.9956043956043956,
      "grad_norm": 0.36371156573295593,
      "learning_rate": 0.00013569844789356985,
      "loss": 1.1873,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.415257066488266,
      "learning_rate": 0.0001352549889135255,
      "loss": 1.121,
      "step": 152
    },
    {
      "epoch": 1.0065934065934066,
      "grad_norm": 0.33504635095596313,
      "learning_rate": 0.00013481152993348116,
      "loss": 0.7273,
      "step": 153
    },
    {
      "epoch": 1.0131868131868131,
      "grad_norm": 0.35514941811561584,
      "learning_rate": 0.0001343680709534368,
      "loss": 1.0279,
      "step": 154
    },
    {
      "epoch": 1.0197802197802197,
      "grad_norm": 0.3266615569591522,
      "learning_rate": 0.00013392461197339248,
      "loss": 1.0364,
      "step": 155
    },
    {
      "epoch": 1.0263736263736263,
      "grad_norm": 0.25707826018333435,
      "learning_rate": 0.00013348115299334812,
      "loss": 0.8594,
      "step": 156
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.26966592669487,
      "learning_rate": 0.00013303769401330377,
      "loss": 0.7586,
      "step": 157
    },
    {
      "epoch": 1.0395604395604396,
      "grad_norm": 0.2870430648326874,
      "learning_rate": 0.00013259423503325944,
      "loss": 0.7098,
      "step": 158
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 0.29999199509620667,
      "learning_rate": 0.00013215077605321509,
      "loss": 0.9942,
      "step": 159
    },
    {
      "epoch": 1.0527472527472528,
      "grad_norm": 0.37641286849975586,
      "learning_rate": 0.00013170731707317076,
      "loss": 1.2464,
      "step": 160
    },
    {
      "epoch": 1.0593406593406594,
      "grad_norm": 0.32532188296318054,
      "learning_rate": 0.0001312638580931264,
      "loss": 0.7937,
      "step": 161
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.31521928310394287,
      "learning_rate": 0.00013082039911308205,
      "loss": 1.0427,
      "step": 162
    },
    {
      "epoch": 1.0725274725274725,
      "grad_norm": 0.33297204971313477,
      "learning_rate": 0.0001303769401330377,
      "loss": 0.8568,
      "step": 163
    },
    {
      "epoch": 1.079120879120879,
      "grad_norm": 0.35677385330200195,
      "learning_rate": 0.00012993348115299336,
      "loss": 0.8601,
      "step": 164
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.3727644979953766,
      "learning_rate": 0.000129490022172949,
      "loss": 1.0262,
      "step": 165
    },
    {
      "epoch": 1.0923076923076924,
      "grad_norm": 0.3876245319843292,
      "learning_rate": 0.00012904656319290468,
      "loss": 1.1115,
      "step": 166
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 0.39254218339920044,
      "learning_rate": 0.00012860310421286032,
      "loss": 0.9547,
      "step": 167
    },
    {
      "epoch": 1.1054945054945056,
      "grad_norm": 0.31263452768325806,
      "learning_rate": 0.00012815964523281597,
      "loss": 0.7943,
      "step": 168
    },
    {
      "epoch": 1.1120879120879121,
      "grad_norm": 0.3517119586467743,
      "learning_rate": 0.0001277161862527716,
      "loss": 0.8993,
      "step": 169
    },
    {
      "epoch": 1.1186813186813187,
      "grad_norm": 0.3954877257347107,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.8927,
      "step": 170
    },
    {
      "epoch": 1.1252747252747253,
      "grad_norm": 0.3255528211593628,
      "learning_rate": 0.00012682926829268293,
      "loss": 0.9613,
      "step": 171
    },
    {
      "epoch": 1.1318681318681318,
      "grad_norm": 0.3862660825252533,
      "learning_rate": 0.0001263858093126386,
      "loss": 0.9771,
      "step": 172
    },
    {
      "epoch": 1.1384615384615384,
      "grad_norm": 0.3914160430431366,
      "learning_rate": 0.00012594235033259424,
      "loss": 0.9576,
      "step": 173
    },
    {
      "epoch": 1.145054945054945,
      "grad_norm": 0.29410216212272644,
      "learning_rate": 0.00012549889135254989,
      "loss": 0.6459,
      "step": 174
    },
    {
      "epoch": 1.1516483516483516,
      "grad_norm": 0.4034622311592102,
      "learning_rate": 0.00012505543237250553,
      "loss": 0.8672,
      "step": 175
    },
    {
      "epoch": 1.1582417582417581,
      "grad_norm": 0.3729837238788605,
      "learning_rate": 0.0001246119733924612,
      "loss": 1.0029,
      "step": 176
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 0.34092825651168823,
      "learning_rate": 0.00012416851441241685,
      "loss": 0.8459,
      "step": 177
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 0.36073145270347595,
      "learning_rate": 0.00012372505543237252,
      "loss": 0.8988,
      "step": 178
    },
    {
      "epoch": 1.178021978021978,
      "grad_norm": 0.34970390796661377,
      "learning_rate": 0.00012328159645232816,
      "loss": 1.0697,
      "step": 179
    },
    {
      "epoch": 1.1846153846153846,
      "grad_norm": 0.3512762188911438,
      "learning_rate": 0.0001228381374722838,
      "loss": 0.8802,
      "step": 180
    },
    {
      "epoch": 1.1912087912087912,
      "grad_norm": 0.34512296319007874,
      "learning_rate": 0.00012239467849223948,
      "loss": 0.8907,
      "step": 181
    },
    {
      "epoch": 1.1978021978021978,
      "grad_norm": 0.36423933506011963,
      "learning_rate": 0.00012195121951219512,
      "loss": 0.8463,
      "step": 182
    },
    {
      "epoch": 1.2043956043956043,
      "grad_norm": 0.43558380007743835,
      "learning_rate": 0.00012150776053215078,
      "loss": 1.3074,
      "step": 183
    },
    {
      "epoch": 1.210989010989011,
      "grad_norm": 0.4091469943523407,
      "learning_rate": 0.00012106430155210644,
      "loss": 0.9455,
      "step": 184
    },
    {
      "epoch": 1.2175824175824177,
      "grad_norm": 0.4077450633049011,
      "learning_rate": 0.0001206208425720621,
      "loss": 1.1189,
      "step": 185
    },
    {
      "epoch": 1.2241758241758243,
      "grad_norm": 0.4614589214324951,
      "learning_rate": 0.00012017738359201774,
      "loss": 0.9535,
      "step": 186
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.3736139237880707,
      "learning_rate": 0.0001197339246119734,
      "loss": 0.9564,
      "step": 187
    },
    {
      "epoch": 1.2373626373626374,
      "grad_norm": 0.4038030505180359,
      "learning_rate": 0.00011929046563192906,
      "loss": 0.8517,
      "step": 188
    },
    {
      "epoch": 1.243956043956044,
      "grad_norm": 0.3699389398097992,
      "learning_rate": 0.00011884700665188471,
      "loss": 1.0089,
      "step": 189
    },
    {
      "epoch": 1.2505494505494505,
      "grad_norm": 0.42219117283821106,
      "learning_rate": 0.00011840354767184036,
      "loss": 0.8046,
      "step": 190
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.3837718367576599,
      "learning_rate": 0.00011796008869179602,
      "loss": 1.0339,
      "step": 191
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 0.4170745015144348,
      "learning_rate": 0.00011751662971175166,
      "loss": 1.1264,
      "step": 192
    },
    {
      "epoch": 1.2703296703296703,
      "grad_norm": 0.41461047530174255,
      "learning_rate": 0.00011707317073170732,
      "loss": 0.9984,
      "step": 193
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.4203866422176361,
      "learning_rate": 0.00011662971175166298,
      "loss": 0.9499,
      "step": 194
    },
    {
      "epoch": 1.2835164835164834,
      "grad_norm": 0.43381527066230774,
      "learning_rate": 0.00011618625277161863,
      "loss": 0.8187,
      "step": 195
    },
    {
      "epoch": 1.2901098901098902,
      "grad_norm": 0.45613041520118713,
      "learning_rate": 0.00011574279379157429,
      "loss": 0.8903,
      "step": 196
    },
    {
      "epoch": 1.2967032967032968,
      "grad_norm": 0.44374486804008484,
      "learning_rate": 0.00011529933481152995,
      "loss": 1.2032,
      "step": 197
    },
    {
      "epoch": 1.3032967032967033,
      "grad_norm": 0.4347747266292572,
      "learning_rate": 0.00011485587583148558,
      "loss": 1.0607,
      "step": 198
    },
    {
      "epoch": 1.30989010989011,
      "grad_norm": 0.4595470428466797,
      "learning_rate": 0.00011441241685144124,
      "loss": 0.8552,
      "step": 199
    },
    {
      "epoch": 1.3164835164835165,
      "grad_norm": 0.44452399015426636,
      "learning_rate": 0.0001139689578713969,
      "loss": 1.0786,
      "step": 200
    },
    {
      "epoch": 1.323076923076923,
      "grad_norm": 0.4181115925312042,
      "learning_rate": 0.00011352549889135255,
      "loss": 1.0302,
      "step": 201
    },
    {
      "epoch": 1.3296703296703296,
      "grad_norm": 0.41853222250938416,
      "learning_rate": 0.00011308203991130821,
      "loss": 0.8107,
      "step": 202
    },
    {
      "epoch": 1.3362637362637364,
      "grad_norm": 0.4403306245803833,
      "learning_rate": 0.00011263858093126387,
      "loss": 0.9088,
      "step": 203
    },
    {
      "epoch": 1.342857142857143,
      "grad_norm": 0.458183228969574,
      "learning_rate": 0.00011219512195121953,
      "loss": 0.9863,
      "step": 204
    },
    {
      "epoch": 1.3494505494505495,
      "grad_norm": 0.3970884680747986,
      "learning_rate": 0.00011175166297117516,
      "loss": 0.9003,
      "step": 205
    },
    {
      "epoch": 1.3560439560439561,
      "grad_norm": 0.42535674571990967,
      "learning_rate": 0.00011130820399113082,
      "loss": 1.0088,
      "step": 206
    },
    {
      "epoch": 1.3626373626373627,
      "grad_norm": 0.4536214768886566,
      "learning_rate": 0.00011086474501108647,
      "loss": 0.8432,
      "step": 207
    },
    {
      "epoch": 1.3692307692307693,
      "grad_norm": 0.4646531343460083,
      "learning_rate": 0.00011042128603104213,
      "loss": 0.8039,
      "step": 208
    },
    {
      "epoch": 1.3758241758241758,
      "grad_norm": 0.4635627865791321,
      "learning_rate": 0.00010997782705099779,
      "loss": 0.9374,
      "step": 209
    },
    {
      "epoch": 1.3824175824175824,
      "grad_norm": 0.5212976932525635,
      "learning_rate": 0.00010953436807095345,
      "loss": 0.8712,
      "step": 210
    },
    {
      "epoch": 1.389010989010989,
      "grad_norm": 0.45170924067497253,
      "learning_rate": 0.00010909090909090909,
      "loss": 1.0036,
      "step": 211
    },
    {
      "epoch": 1.3956043956043955,
      "grad_norm": 0.4766032099723816,
      "learning_rate": 0.00010864745011086475,
      "loss": 1.2042,
      "step": 212
    },
    {
      "epoch": 1.402197802197802,
      "grad_norm": 0.4891017973423004,
      "learning_rate": 0.00010820399113082041,
      "loss": 0.7938,
      "step": 213
    },
    {
      "epoch": 1.4087912087912087,
      "grad_norm": 0.504843533039093,
      "learning_rate": 0.00010776053215077607,
      "loss": 1.1541,
      "step": 214
    },
    {
      "epoch": 1.4153846153846155,
      "grad_norm": 0.36932000517845154,
      "learning_rate": 0.00010731707317073172,
      "loss": 0.7411,
      "step": 215
    },
    {
      "epoch": 1.421978021978022,
      "grad_norm": 0.41932618618011475,
      "learning_rate": 0.00010687361419068738,
      "loss": 1.0316,
      "step": 216
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.4571351706981659,
      "learning_rate": 0.00010643015521064301,
      "loss": 1.0024,
      "step": 217
    },
    {
      "epoch": 1.4351648351648352,
      "grad_norm": 0.42554306983947754,
      "learning_rate": 0.00010598669623059867,
      "loss": 0.9867,
      "step": 218
    },
    {
      "epoch": 1.4417582417582417,
      "grad_norm": 0.4634591042995453,
      "learning_rate": 0.00010554323725055433,
      "loss": 0.9275,
      "step": 219
    },
    {
      "epoch": 1.4483516483516483,
      "grad_norm": 0.511501133441925,
      "learning_rate": 0.00010509977827050999,
      "loss": 0.9143,
      "step": 220
    },
    {
      "epoch": 1.4549450549450549,
      "grad_norm": 0.4719898998737335,
      "learning_rate": 0.00010465631929046564,
      "loss": 0.8417,
      "step": 221
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.5507583618164062,
      "learning_rate": 0.0001042128603104213,
      "loss": 0.8736,
      "step": 222
    },
    {
      "epoch": 1.4681318681318682,
      "grad_norm": 0.5081433653831482,
      "learning_rate": 0.00010376940133037693,
      "loss": 1.036,
      "step": 223
    },
    {
      "epoch": 1.4747252747252748,
      "grad_norm": 0.42683982849121094,
      "learning_rate": 0.00010332594235033259,
      "loss": 1.0983,
      "step": 224
    },
    {
      "epoch": 1.4813186813186814,
      "grad_norm": 0.4597811698913574,
      "learning_rate": 0.00010288248337028825,
      "loss": 0.7445,
      "step": 225
    },
    {
      "epoch": 1.487912087912088,
      "grad_norm": 0.5141137838363647,
      "learning_rate": 0.0001024390243902439,
      "loss": 0.7835,
      "step": 226
    },
    {
      "epoch": 1.4945054945054945,
      "grad_norm": 0.42920419573783875,
      "learning_rate": 0.00010199556541019956,
      "loss": 0.9206,
      "step": 227
    },
    {
      "epoch": 1.501098901098901,
      "grad_norm": 0.5461699962615967,
      "learning_rate": 0.00010155210643015522,
      "loss": 0.9381,
      "step": 228
    },
    {
      "epoch": 1.5076923076923077,
      "grad_norm": 0.4574257731437683,
      "learning_rate": 0.00010110864745011087,
      "loss": 0.8139,
      "step": 229
    },
    {
      "epoch": 1.5142857142857142,
      "grad_norm": 0.49074164032936096,
      "learning_rate": 0.00010066518847006652,
      "loss": 0.855,
      "step": 230
    },
    {
      "epoch": 1.5208791208791208,
      "grad_norm": 0.48996445536613464,
      "learning_rate": 0.00010022172949002218,
      "loss": 0.9652,
      "step": 231
    },
    {
      "epoch": 1.5274725274725274,
      "grad_norm": 0.46916869282722473,
      "learning_rate": 9.977827050997783e-05,
      "loss": 0.8019,
      "step": 232
    },
    {
      "epoch": 1.534065934065934,
      "grad_norm": 0.3496672511100769,
      "learning_rate": 9.933481152993348e-05,
      "loss": 0.6871,
      "step": 233
    },
    {
      "epoch": 1.5406593406593405,
      "grad_norm": 0.49986791610717773,
      "learning_rate": 9.889135254988914e-05,
      "loss": 1.0493,
      "step": 234
    },
    {
      "epoch": 1.5472527472527473,
      "grad_norm": 0.5925995111465454,
      "learning_rate": 9.84478935698448e-05,
      "loss": 1.1353,
      "step": 235
    },
    {
      "epoch": 1.5538461538461539,
      "grad_norm": 0.5230599641799927,
      "learning_rate": 9.800443458980046e-05,
      "loss": 0.9398,
      "step": 236
    },
    {
      "epoch": 1.5604395604395604,
      "grad_norm": 0.539544939994812,
      "learning_rate": 9.75609756097561e-05,
      "loss": 1.0643,
      "step": 237
    },
    {
      "epoch": 1.567032967032967,
      "grad_norm": 0.4955865740776062,
      "learning_rate": 9.711751662971176e-05,
      "loss": 0.9174,
      "step": 238
    },
    {
      "epoch": 1.5736263736263736,
      "grad_norm": 0.519826352596283,
      "learning_rate": 9.667405764966742e-05,
      "loss": 0.812,
      "step": 239
    },
    {
      "epoch": 1.5802197802197804,
      "grad_norm": 0.45419999957084656,
      "learning_rate": 9.623059866962306e-05,
      "loss": 0.9208,
      "step": 240
    },
    {
      "epoch": 1.586813186813187,
      "grad_norm": 0.42484593391418457,
      "learning_rate": 9.578713968957872e-05,
      "loss": 0.8923,
      "step": 241
    },
    {
      "epoch": 1.5934065934065935,
      "grad_norm": 0.5017544627189636,
      "learning_rate": 9.534368070953438e-05,
      "loss": 0.9922,
      "step": 242
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.47221285104751587,
      "learning_rate": 9.490022172949002e-05,
      "loss": 0.9003,
      "step": 243
    },
    {
      "epoch": 1.6065934065934067,
      "grad_norm": 0.49266570806503296,
      "learning_rate": 9.445676274944568e-05,
      "loss": 1.102,
      "step": 244
    },
    {
      "epoch": 1.6131868131868132,
      "grad_norm": 0.511424720287323,
      "learning_rate": 9.401330376940134e-05,
      "loss": 0.9355,
      "step": 245
    },
    {
      "epoch": 1.6197802197802198,
      "grad_norm": 0.46124136447906494,
      "learning_rate": 9.356984478935698e-05,
      "loss": 0.9673,
      "step": 246
    },
    {
      "epoch": 1.6263736263736264,
      "grad_norm": 0.5964862108230591,
      "learning_rate": 9.312638580931264e-05,
      "loss": 1.0091,
      "step": 247
    },
    {
      "epoch": 1.632967032967033,
      "grad_norm": 0.4091043472290039,
      "learning_rate": 9.26829268292683e-05,
      "loss": 0.9867,
      "step": 248
    },
    {
      "epoch": 1.6395604395604395,
      "grad_norm": 0.5584626793861389,
      "learning_rate": 9.223946784922394e-05,
      "loss": 1.0056,
      "step": 249
    },
    {
      "epoch": 1.646153846153846,
      "grad_norm": 0.416415274143219,
      "learning_rate": 9.17960088691796e-05,
      "loss": 0.9604,
      "step": 250
    },
    {
      "epoch": 1.6527472527472526,
      "grad_norm": 0.48294901847839355,
      "learning_rate": 9.135254988913526e-05,
      "loss": 0.7287,
      "step": 251
    },
    {
      "epoch": 1.6593406593406592,
      "grad_norm": 0.5308470129966736,
      "learning_rate": 9.090909090909092e-05,
      "loss": 0.8595,
      "step": 252
    },
    {
      "epoch": 1.6659340659340658,
      "grad_norm": 0.4524170756340027,
      "learning_rate": 9.046563192904656e-05,
      "loss": 0.954,
      "step": 253
    },
    {
      "epoch": 1.6725274725274726,
      "grad_norm": 0.4954875707626343,
      "learning_rate": 9.002217294900222e-05,
      "loss": 0.7876,
      "step": 254
    },
    {
      "epoch": 1.6791208791208792,
      "grad_norm": 0.49578380584716797,
      "learning_rate": 8.957871396895788e-05,
      "loss": 1.1427,
      "step": 255
    },
    {
      "epoch": 1.6857142857142857,
      "grad_norm": 0.4599444568157196,
      "learning_rate": 8.913525498891354e-05,
      "loss": 0.7827,
      "step": 256
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.5834614038467407,
      "learning_rate": 8.869179600886919e-05,
      "loss": 0.7403,
      "step": 257
    },
    {
      "epoch": 1.6989010989010989,
      "grad_norm": 0.5772879719734192,
      "learning_rate": 8.824833702882484e-05,
      "loss": 0.8945,
      "step": 258
    },
    {
      "epoch": 1.7054945054945057,
      "grad_norm": 0.5228119492530823,
      "learning_rate": 8.78048780487805e-05,
      "loss": 0.699,
      "step": 259
    },
    {
      "epoch": 1.7120879120879122,
      "grad_norm": 0.5915874242782593,
      "learning_rate": 8.736141906873615e-05,
      "loss": 0.7997,
      "step": 260
    },
    {
      "epoch": 1.7186813186813188,
      "grad_norm": 0.5183882117271423,
      "learning_rate": 8.69179600886918e-05,
      "loss": 0.8933,
      "step": 261
    },
    {
      "epoch": 1.7252747252747254,
      "grad_norm": 0.4795385003089905,
      "learning_rate": 8.647450110864746e-05,
      "loss": 0.9046,
      "step": 262
    },
    {
      "epoch": 1.731868131868132,
      "grad_norm": 0.5640863180160522,
      "learning_rate": 8.603104212860311e-05,
      "loss": 1.0375,
      "step": 263
    },
    {
      "epoch": 1.7384615384615385,
      "grad_norm": 0.5802732706069946,
      "learning_rate": 8.558758314855876e-05,
      "loss": 1.0106,
      "step": 264
    },
    {
      "epoch": 1.745054945054945,
      "grad_norm": 0.480453222990036,
      "learning_rate": 8.514412416851442e-05,
      "loss": 0.754,
      "step": 265
    },
    {
      "epoch": 1.7516483516483516,
      "grad_norm": 0.5580059885978699,
      "learning_rate": 8.470066518847007e-05,
      "loss": 1.062,
      "step": 266
    },
    {
      "epoch": 1.7582417582417582,
      "grad_norm": 0.46048516035079956,
      "learning_rate": 8.425720620842572e-05,
      "loss": 0.8726,
      "step": 267
    },
    {
      "epoch": 1.7648351648351648,
      "grad_norm": 0.46345800161361694,
      "learning_rate": 8.381374722838138e-05,
      "loss": 1.024,
      "step": 268
    },
    {
      "epoch": 1.7714285714285714,
      "grad_norm": 0.4113773703575134,
      "learning_rate": 8.337028824833703e-05,
      "loss": 0.878,
      "step": 269
    },
    {
      "epoch": 1.778021978021978,
      "grad_norm": 0.574474036693573,
      "learning_rate": 8.292682926829268e-05,
      "loss": 0.8353,
      "step": 270
    },
    {
      "epoch": 1.7846153846153845,
      "grad_norm": 0.5765256881713867,
      "learning_rate": 8.248337028824834e-05,
      "loss": 1.1443,
      "step": 271
    },
    {
      "epoch": 1.791208791208791,
      "grad_norm": 0.513107180595398,
      "learning_rate": 8.2039911308204e-05,
      "loss": 0.885,
      "step": 272
    },
    {
      "epoch": 1.7978021978021979,
      "grad_norm": 0.5188018679618835,
      "learning_rate": 8.159645232815965e-05,
      "loss": 0.9243,
      "step": 273
    },
    {
      "epoch": 1.8043956043956044,
      "grad_norm": 0.5862143635749817,
      "learning_rate": 8.11529933481153e-05,
      "loss": 0.9419,
      "step": 274
    },
    {
      "epoch": 1.810989010989011,
      "grad_norm": 0.5694910287857056,
      "learning_rate": 8.070953436807095e-05,
      "loss": 0.9332,
      "step": 275
    },
    {
      "epoch": 1.8175824175824176,
      "grad_norm": 0.5219365358352661,
      "learning_rate": 8.026607538802661e-05,
      "loss": 1.1052,
      "step": 276
    },
    {
      "epoch": 1.8241758241758241,
      "grad_norm": 0.44020965695381165,
      "learning_rate": 7.982261640798227e-05,
      "loss": 0.9014,
      "step": 277
    },
    {
      "epoch": 1.830769230769231,
      "grad_norm": 0.5831880569458008,
      "learning_rate": 7.937915742793793e-05,
      "loss": 1.0325,
      "step": 278
    },
    {
      "epoch": 1.8373626373626375,
      "grad_norm": 0.45682716369628906,
      "learning_rate": 7.893569844789357e-05,
      "loss": 0.8174,
      "step": 279
    },
    {
      "epoch": 1.843956043956044,
      "grad_norm": 0.5682815909385681,
      "learning_rate": 7.849223946784923e-05,
      "loss": 1.0106,
      "step": 280
    },
    {
      "epoch": 1.8505494505494506,
      "grad_norm": 0.4336985647678375,
      "learning_rate": 7.804878048780489e-05,
      "loss": 0.7305,
      "step": 281
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.7045301795005798,
      "learning_rate": 7.760532150776053e-05,
      "loss": 0.8901,
      "step": 282
    },
    {
      "epoch": 1.8637362637362638,
      "grad_norm": 0.5214325785636902,
      "learning_rate": 7.716186252771619e-05,
      "loss": 0.8628,
      "step": 283
    },
    {
      "epoch": 1.8703296703296703,
      "grad_norm": 0.5112658143043518,
      "learning_rate": 7.671840354767185e-05,
      "loss": 1.1782,
      "step": 284
    },
    {
      "epoch": 1.876923076923077,
      "grad_norm": 0.5727646946907043,
      "learning_rate": 7.627494456762749e-05,
      "loss": 0.9322,
      "step": 285
    },
    {
      "epoch": 1.8835164835164835,
      "grad_norm": 0.5171626806259155,
      "learning_rate": 7.583148558758315e-05,
      "loss": 0.8572,
      "step": 286
    },
    {
      "epoch": 1.89010989010989,
      "grad_norm": 0.5673033595085144,
      "learning_rate": 7.538802660753881e-05,
      "loss": 1.1686,
      "step": 287
    },
    {
      "epoch": 1.8967032967032966,
      "grad_norm": 0.46531832218170166,
      "learning_rate": 7.494456762749445e-05,
      "loss": 1.0621,
      "step": 288
    },
    {
      "epoch": 1.9032967032967032,
      "grad_norm": 0.5543939471244812,
      "learning_rate": 7.450110864745011e-05,
      "loss": 0.9237,
      "step": 289
    },
    {
      "epoch": 1.9098901098901098,
      "grad_norm": 0.5435785055160522,
      "learning_rate": 7.405764966740577e-05,
      "loss": 0.9234,
      "step": 290
    },
    {
      "epoch": 1.9164835164835163,
      "grad_norm": 0.5223327279090881,
      "learning_rate": 7.361419068736141e-05,
      "loss": 0.941,
      "step": 291
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.43840086460113525,
      "learning_rate": 7.317073170731707e-05,
      "loss": 0.7017,
      "step": 292
    },
    {
      "epoch": 1.9296703296703297,
      "grad_norm": 0.568104088306427,
      "learning_rate": 7.272727272727273e-05,
      "loss": 0.9935,
      "step": 293
    },
    {
      "epoch": 1.9362637362637363,
      "grad_norm": 0.5684879422187805,
      "learning_rate": 7.228381374722837e-05,
      "loss": 0.899,
      "step": 294
    },
    {
      "epoch": 1.9428571428571428,
      "grad_norm": 0.5385580062866211,
      "learning_rate": 7.184035476718403e-05,
      "loss": 0.913,
      "step": 295
    },
    {
      "epoch": 1.9494505494505494,
      "grad_norm": 0.43038472533226013,
      "learning_rate": 7.139689578713969e-05,
      "loss": 0.7137,
      "step": 296
    },
    {
      "epoch": 1.9560439560439562,
      "grad_norm": 0.5462937355041504,
      "learning_rate": 7.095343680709535e-05,
      "loss": 1.1156,
      "step": 297
    },
    {
      "epoch": 1.9626373626373628,
      "grad_norm": 0.5892915725708008,
      "learning_rate": 7.0509977827051e-05,
      "loss": 0.8074,
      "step": 298
    },
    {
      "epoch": 1.9692307692307693,
      "grad_norm": 0.4523645043373108,
      "learning_rate": 7.006651884700666e-05,
      "loss": 0.788,
      "step": 299
    },
    {
      "epoch": 1.975824175824176,
      "grad_norm": 0.5740240812301636,
      "learning_rate": 6.962305986696232e-05,
      "loss": 1.0473,
      "step": 300
    },
    {
      "epoch": 1.9824175824175825,
      "grad_norm": 0.6056305766105652,
      "learning_rate": 6.917960088691796e-05,
      "loss": 0.9832,
      "step": 301
    },
    {
      "epoch": 1.989010989010989,
      "grad_norm": 0.49228960275650024,
      "learning_rate": 6.873614190687362e-05,
      "loss": 0.9383,
      "step": 302
    },
    {
      "epoch": 1.9956043956043956,
      "grad_norm": 0.6239444017410278,
      "learning_rate": 6.829268292682928e-05,
      "loss": 1.039,
      "step": 303
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.7136023044586182,
      "learning_rate": 6.784922394678492e-05,
      "loss": 0.7609,
      "step": 304
    },
    {
      "epoch": 2.0065934065934066,
      "grad_norm": 0.554238498210907,
      "learning_rate": 6.740576496674058e-05,
      "loss": 0.7962,
      "step": 305
    },
    {
      "epoch": 2.013186813186813,
      "grad_norm": 0.5447033643722534,
      "learning_rate": 6.696230598669624e-05,
      "loss": 0.7942,
      "step": 306
    },
    {
      "epoch": 2.0197802197802197,
      "grad_norm": 0.5223092436790466,
      "learning_rate": 6.651884700665188e-05,
      "loss": 0.9885,
      "step": 307
    },
    {
      "epoch": 2.0263736263736263,
      "grad_norm": 0.4540101885795593,
      "learning_rate": 6.607538802660754e-05,
      "loss": 0.8201,
      "step": 308
    },
    {
      "epoch": 2.032967032967033,
      "grad_norm": 0.7418407201766968,
      "learning_rate": 6.56319290465632e-05,
      "loss": 0.865,
      "step": 309
    },
    {
      "epoch": 2.0395604395604394,
      "grad_norm": 0.4972262680530548,
      "learning_rate": 6.518847006651884e-05,
      "loss": 0.5972,
      "step": 310
    },
    {
      "epoch": 2.046153846153846,
      "grad_norm": 0.5715733766555786,
      "learning_rate": 6.47450110864745e-05,
      "loss": 0.7237,
      "step": 311
    },
    {
      "epoch": 2.0527472527472526,
      "grad_norm": 0.5403093099594116,
      "learning_rate": 6.430155210643016e-05,
      "loss": 0.885,
      "step": 312
    },
    {
      "epoch": 2.059340659340659,
      "grad_norm": 0.49113500118255615,
      "learning_rate": 6.38580931263858e-05,
      "loss": 0.6013,
      "step": 313
    },
    {
      "epoch": 2.065934065934066,
      "grad_norm": 0.603954017162323,
      "learning_rate": 6.341463414634146e-05,
      "loss": 0.9184,
      "step": 314
    },
    {
      "epoch": 2.0725274725274727,
      "grad_norm": 0.5022772550582886,
      "learning_rate": 6.297117516629712e-05,
      "loss": 0.7799,
      "step": 315
    },
    {
      "epoch": 2.0791208791208793,
      "grad_norm": 0.58995521068573,
      "learning_rate": 6.252771618625277e-05,
      "loss": 0.7576,
      "step": 316
    },
    {
      "epoch": 2.085714285714286,
      "grad_norm": 0.5219099521636963,
      "learning_rate": 6.208425720620842e-05,
      "loss": 0.7627,
      "step": 317
    },
    {
      "epoch": 2.0923076923076924,
      "grad_norm": 0.7215979099273682,
      "learning_rate": 6.164079822616408e-05,
      "loss": 0.7859,
      "step": 318
    },
    {
      "epoch": 2.098901098901099,
      "grad_norm": 0.6033439040184021,
      "learning_rate": 6.119733924611974e-05,
      "loss": 0.7402,
      "step": 319
    },
    {
      "epoch": 2.1054945054945056,
      "grad_norm": 0.6312968134880066,
      "learning_rate": 6.075388026607539e-05,
      "loss": 0.6367,
      "step": 320
    },
    {
      "epoch": 2.112087912087912,
      "grad_norm": 0.6998158097267151,
      "learning_rate": 6.031042128603105e-05,
      "loss": 0.7905,
      "step": 321
    },
    {
      "epoch": 2.1186813186813187,
      "grad_norm": 0.5653964877128601,
      "learning_rate": 5.98669623059867e-05,
      "loss": 0.7408,
      "step": 322
    },
    {
      "epoch": 2.1252747252747253,
      "grad_norm": 0.7255998849868774,
      "learning_rate": 5.942350332594236e-05,
      "loss": 0.9039,
      "step": 323
    },
    {
      "epoch": 2.131868131868132,
      "grad_norm": 0.534074604511261,
      "learning_rate": 5.898004434589801e-05,
      "loss": 0.7128,
      "step": 324
    },
    {
      "epoch": 2.1384615384615384,
      "grad_norm": 0.4847363531589508,
      "learning_rate": 5.853658536585366e-05,
      "loss": 0.7026,
      "step": 325
    },
    {
      "epoch": 2.145054945054945,
      "grad_norm": 0.651093065738678,
      "learning_rate": 5.809312638580932e-05,
      "loss": 0.8576,
      "step": 326
    },
    {
      "epoch": 2.1516483516483516,
      "grad_norm": 0.6876394748687744,
      "learning_rate": 5.7649667405764975e-05,
      "loss": 0.8137,
      "step": 327
    },
    {
      "epoch": 2.158241758241758,
      "grad_norm": 0.6080358624458313,
      "learning_rate": 5.720620842572062e-05,
      "loss": 0.951,
      "step": 328
    },
    {
      "epoch": 2.1648351648351647,
      "grad_norm": 0.6911507844924927,
      "learning_rate": 5.676274944567628e-05,
      "loss": 0.7452,
      "step": 329
    },
    {
      "epoch": 2.1714285714285713,
      "grad_norm": 0.5656284689903259,
      "learning_rate": 5.6319290465631935e-05,
      "loss": 0.8114,
      "step": 330
    },
    {
      "epoch": 2.178021978021978,
      "grad_norm": 0.6504562497138977,
      "learning_rate": 5.587583148558758e-05,
      "loss": 0.7523,
      "step": 331
    },
    {
      "epoch": 2.184615384615385,
      "grad_norm": 0.769294798374176,
      "learning_rate": 5.543237250554324e-05,
      "loss": 0.9235,
      "step": 332
    },
    {
      "epoch": 2.1912087912087914,
      "grad_norm": 0.5610937476158142,
      "learning_rate": 5.4988913525498895e-05,
      "loss": 0.9146,
      "step": 333
    },
    {
      "epoch": 2.197802197802198,
      "grad_norm": 0.6355406641960144,
      "learning_rate": 5.4545454545454546e-05,
      "loss": 0.9637,
      "step": 334
    },
    {
      "epoch": 2.2043956043956046,
      "grad_norm": 0.6437283158302307,
      "learning_rate": 5.4101995565410204e-05,
      "loss": 0.8863,
      "step": 335
    },
    {
      "epoch": 2.210989010989011,
      "grad_norm": 0.5665042400360107,
      "learning_rate": 5.365853658536586e-05,
      "loss": 0.7212,
      "step": 336
    },
    {
      "epoch": 2.2175824175824177,
      "grad_norm": 0.5739551782608032,
      "learning_rate": 5.3215077605321506e-05,
      "loss": 0.5657,
      "step": 337
    },
    {
      "epoch": 2.2241758241758243,
      "grad_norm": 0.7417795062065125,
      "learning_rate": 5.2771618625277164e-05,
      "loss": 0.9396,
      "step": 338
    },
    {
      "epoch": 2.230769230769231,
      "grad_norm": 0.6270789504051208,
      "learning_rate": 5.232815964523282e-05,
      "loss": 0.9357,
      "step": 339
    },
    {
      "epoch": 2.2373626373626374,
      "grad_norm": 0.604964554309845,
      "learning_rate": 5.1884700665188466e-05,
      "loss": 0.7242,
      "step": 340
    },
    {
      "epoch": 2.243956043956044,
      "grad_norm": 0.7559173107147217,
      "learning_rate": 5.1441241685144124e-05,
      "loss": 0.7091,
      "step": 341
    },
    {
      "epoch": 2.2505494505494505,
      "grad_norm": 0.6463924646377563,
      "learning_rate": 5.099778270509978e-05,
      "loss": 0.9065,
      "step": 342
    },
    {
      "epoch": 2.257142857142857,
      "grad_norm": 0.7264363169670105,
      "learning_rate": 5.0554323725055433e-05,
      "loss": 0.8088,
      "step": 343
    },
    {
      "epoch": 2.2637362637362637,
      "grad_norm": 0.6801968812942505,
      "learning_rate": 5.011086474501109e-05,
      "loss": 0.6984,
      "step": 344
    },
    {
      "epoch": 2.2703296703296703,
      "grad_norm": 0.6808285713195801,
      "learning_rate": 4.966740576496674e-05,
      "loss": 1.0425,
      "step": 345
    },
    {
      "epoch": 2.276923076923077,
      "grad_norm": 0.6234519481658936,
      "learning_rate": 4.92239467849224e-05,
      "loss": 0.9834,
      "step": 346
    },
    {
      "epoch": 2.2835164835164834,
      "grad_norm": 0.6983118057250977,
      "learning_rate": 4.878048780487805e-05,
      "loss": 0.8792,
      "step": 347
    },
    {
      "epoch": 2.29010989010989,
      "grad_norm": 0.6692476868629456,
      "learning_rate": 4.833702882483371e-05,
      "loss": 0.9244,
      "step": 348
    },
    {
      "epoch": 2.2967032967032965,
      "grad_norm": 0.6769099235534668,
      "learning_rate": 4.789356984478936e-05,
      "loss": 0.837,
      "step": 349
    },
    {
      "epoch": 2.303296703296703,
      "grad_norm": 0.6694425940513611,
      "learning_rate": 4.745011086474501e-05,
      "loss": 0.8118,
      "step": 350
    },
    {
      "epoch": 2.3098901098901097,
      "grad_norm": 0.47608622908592224,
      "learning_rate": 4.700665188470067e-05,
      "loss": 0.504,
      "step": 351
    },
    {
      "epoch": 2.3164835164835162,
      "grad_norm": 0.7049463391304016,
      "learning_rate": 4.656319290465632e-05,
      "loss": 0.8577,
      "step": 352
    },
    {
      "epoch": 2.3230769230769233,
      "grad_norm": 0.56305992603302,
      "learning_rate": 4.611973392461197e-05,
      "loss": 0.7191,
      "step": 353
    },
    {
      "epoch": 2.32967032967033,
      "grad_norm": 0.6341124176979065,
      "learning_rate": 4.567627494456763e-05,
      "loss": 0.8677,
      "step": 354
    },
    {
      "epoch": 2.3362637362637364,
      "grad_norm": 0.6818892955780029,
      "learning_rate": 4.523281596452328e-05,
      "loss": 0.9166,
      "step": 355
    },
    {
      "epoch": 2.342857142857143,
      "grad_norm": 0.6445220708847046,
      "learning_rate": 4.478935698447894e-05,
      "loss": 0.6717,
      "step": 356
    },
    {
      "epoch": 2.3494505494505495,
      "grad_norm": 0.6255369782447815,
      "learning_rate": 4.4345898004434597e-05,
      "loss": 0.7173,
      "step": 357
    },
    {
      "epoch": 2.356043956043956,
      "grad_norm": 0.6610317826271057,
      "learning_rate": 4.390243902439025e-05,
      "loss": 0.8404,
      "step": 358
    },
    {
      "epoch": 2.3626373626373627,
      "grad_norm": 0.7890368103981018,
      "learning_rate": 4.34589800443459e-05,
      "loss": 0.8042,
      "step": 359
    },
    {
      "epoch": 2.3692307692307693,
      "grad_norm": 0.6693598031997681,
      "learning_rate": 4.301552106430156e-05,
      "loss": 0.7759,
      "step": 360
    },
    {
      "epoch": 2.375824175824176,
      "grad_norm": 0.6135345101356506,
      "learning_rate": 4.257206208425721e-05,
      "loss": 1.0374,
      "step": 361
    },
    {
      "epoch": 2.3824175824175824,
      "grad_norm": 0.6952170729637146,
      "learning_rate": 4.212860310421286e-05,
      "loss": 0.7019,
      "step": 362
    },
    {
      "epoch": 2.389010989010989,
      "grad_norm": 0.6701858639717102,
      "learning_rate": 4.168514412416852e-05,
      "loss": 0.784,
      "step": 363
    },
    {
      "epoch": 2.3956043956043955,
      "grad_norm": 0.6350935101509094,
      "learning_rate": 4.124168514412417e-05,
      "loss": 1.0703,
      "step": 364
    },
    {
      "epoch": 2.402197802197802,
      "grad_norm": 0.748142659664154,
      "learning_rate": 4.0798226164079826e-05,
      "loss": 0.8185,
      "step": 365
    },
    {
      "epoch": 2.4087912087912087,
      "grad_norm": 0.6519116759300232,
      "learning_rate": 4.035476718403548e-05,
      "loss": 0.8457,
      "step": 366
    },
    {
      "epoch": 2.4153846153846152,
      "grad_norm": 0.5505536198616028,
      "learning_rate": 3.9911308203991135e-05,
      "loss": 0.7577,
      "step": 367
    },
    {
      "epoch": 2.421978021978022,
      "grad_norm": 0.6547486782073975,
      "learning_rate": 3.9467849223946786e-05,
      "loss": 0.8723,
      "step": 368
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 0.592620849609375,
      "learning_rate": 3.9024390243902444e-05,
      "loss": 0.7114,
      "step": 369
    },
    {
      "epoch": 2.4351648351648354,
      "grad_norm": 0.5695370435714722,
      "learning_rate": 3.8580931263858095e-05,
      "loss": 0.5432,
      "step": 370
    },
    {
      "epoch": 2.441758241758242,
      "grad_norm": 0.6881359815597534,
      "learning_rate": 3.8137472283813746e-05,
      "loss": 0.9952,
      "step": 371
    },
    {
      "epoch": 2.4483516483516485,
      "grad_norm": 0.8085850477218628,
      "learning_rate": 3.7694013303769404e-05,
      "loss": 0.9768,
      "step": 372
    },
    {
      "epoch": 2.454945054945055,
      "grad_norm": 0.6485409736633301,
      "learning_rate": 3.7250554323725055e-05,
      "loss": 0.6824,
      "step": 373
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.663232147693634,
      "learning_rate": 3.6807095343680706e-05,
      "loss": 0.8643,
      "step": 374
    },
    {
      "epoch": 2.4681318681318682,
      "grad_norm": 0.7680539488792419,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 0.8875,
      "step": 375
    },
    {
      "epoch": 2.474725274725275,
      "grad_norm": 0.7806093692779541,
      "learning_rate": 3.5920177383592015e-05,
      "loss": 0.8963,
      "step": 376
    },
    {
      "epoch": 2.4813186813186814,
      "grad_norm": 0.700349748134613,
      "learning_rate": 3.547671840354767e-05,
      "loss": 0.6713,
      "step": 377
    },
    {
      "epoch": 2.487912087912088,
      "grad_norm": 0.5120465159416199,
      "learning_rate": 3.503325942350333e-05,
      "loss": 0.7667,
      "step": 378
    },
    {
      "epoch": 2.4945054945054945,
      "grad_norm": 0.7177109718322754,
      "learning_rate": 3.458980044345898e-05,
      "loss": 0.8454,
      "step": 379
    },
    {
      "epoch": 2.501098901098901,
      "grad_norm": 0.7509220838546753,
      "learning_rate": 3.414634146341464e-05,
      "loss": 0.8227,
      "step": 380
    },
    {
      "epoch": 2.5076923076923077,
      "grad_norm": 0.6269801259040833,
      "learning_rate": 3.370288248337029e-05,
      "loss": 0.6695,
      "step": 381
    },
    {
      "epoch": 2.5142857142857142,
      "grad_norm": 0.678271472454071,
      "learning_rate": 3.325942350332594e-05,
      "loss": 0.7761,
      "step": 382
    },
    {
      "epoch": 2.520879120879121,
      "grad_norm": 0.7019395232200623,
      "learning_rate": 3.28159645232816e-05,
      "loss": 0.6873,
      "step": 383
    },
    {
      "epoch": 2.5274725274725274,
      "grad_norm": 0.6300935745239258,
      "learning_rate": 3.237250554323725e-05,
      "loss": 0.6276,
      "step": 384
    },
    {
      "epoch": 2.534065934065934,
      "grad_norm": 0.8718366026878357,
      "learning_rate": 3.19290465631929e-05,
      "loss": 0.6987,
      "step": 385
    },
    {
      "epoch": 2.5406593406593405,
      "grad_norm": 0.6894791722297668,
      "learning_rate": 3.148558758314856e-05,
      "loss": 0.7499,
      "step": 386
    },
    {
      "epoch": 2.547252747252747,
      "grad_norm": 0.5740795135498047,
      "learning_rate": 3.104212860310421e-05,
      "loss": 0.8078,
      "step": 387
    },
    {
      "epoch": 2.5538461538461537,
      "grad_norm": 0.8040364980697632,
      "learning_rate": 3.059866962305987e-05,
      "loss": 0.616,
      "step": 388
    },
    {
      "epoch": 2.5604395604395602,
      "grad_norm": 0.6026697158813477,
      "learning_rate": 3.0155210643015524e-05,
      "loss": 0.7575,
      "step": 389
    },
    {
      "epoch": 2.567032967032967,
      "grad_norm": 0.7201363444328308,
      "learning_rate": 2.971175166297118e-05,
      "loss": 0.8515,
      "step": 390
    },
    {
      "epoch": 2.5736263736263734,
      "grad_norm": 0.6634522080421448,
      "learning_rate": 2.926829268292683e-05,
      "loss": 0.727,
      "step": 391
    },
    {
      "epoch": 2.5802197802197804,
      "grad_norm": 0.5928854942321777,
      "learning_rate": 2.8824833702882487e-05,
      "loss": 0.7944,
      "step": 392
    },
    {
      "epoch": 2.586813186813187,
      "grad_norm": 0.6455812454223633,
      "learning_rate": 2.838137472283814e-05,
      "loss": 0.722,
      "step": 393
    },
    {
      "epoch": 2.5934065934065935,
      "grad_norm": 0.6687722206115723,
      "learning_rate": 2.793791574279379e-05,
      "loss": 0.7996,
      "step": 394
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.6591235995292664,
      "learning_rate": 2.7494456762749448e-05,
      "loss": 0.6844,
      "step": 395
    },
    {
      "epoch": 2.6065934065934067,
      "grad_norm": 0.645912766456604,
      "learning_rate": 2.7050997782705102e-05,
      "loss": 0.7961,
      "step": 396
    },
    {
      "epoch": 2.6131868131868132,
      "grad_norm": 0.8186089992523193,
      "learning_rate": 2.6607538802660753e-05,
      "loss": 0.7404,
      "step": 397
    },
    {
      "epoch": 2.61978021978022,
      "grad_norm": 0.6970604062080383,
      "learning_rate": 2.616407982261641e-05,
      "loss": 0.7724,
      "step": 398
    },
    {
      "epoch": 2.6263736263736264,
      "grad_norm": 0.6178171634674072,
      "learning_rate": 2.5720620842572062e-05,
      "loss": 0.7385,
      "step": 399
    },
    {
      "epoch": 2.632967032967033,
      "grad_norm": 0.6191170811653137,
      "learning_rate": 2.5277161862527717e-05,
      "loss": 0.7209,
      "step": 400
    },
    {
      "epoch": 2.6395604395604395,
      "grad_norm": 0.6049971580505371,
      "learning_rate": 2.483370288248337e-05,
      "loss": 0.8001,
      "step": 401
    },
    {
      "epoch": 2.646153846153846,
      "grad_norm": 0.7440412044525146,
      "learning_rate": 2.4390243902439026e-05,
      "loss": 1.1068,
      "step": 402
    },
    {
      "epoch": 2.6527472527472526,
      "grad_norm": 0.7440959215164185,
      "learning_rate": 2.394678492239468e-05,
      "loss": 0.9008,
      "step": 403
    },
    {
      "epoch": 2.659340659340659,
      "grad_norm": 0.7467710971832275,
      "learning_rate": 2.3503325942350335e-05,
      "loss": 0.8009,
      "step": 404
    },
    {
      "epoch": 2.665934065934066,
      "grad_norm": 0.6639044880867004,
      "learning_rate": 2.3059866962305986e-05,
      "loss": 0.6483,
      "step": 405
    },
    {
      "epoch": 2.672527472527473,
      "grad_norm": 0.701781153678894,
      "learning_rate": 2.261640798226164e-05,
      "loss": 0.8274,
      "step": 406
    },
    {
      "epoch": 2.6791208791208794,
      "grad_norm": 0.7489557266235352,
      "learning_rate": 2.2172949002217298e-05,
      "loss": 1.2325,
      "step": 407
    },
    {
      "epoch": 2.685714285714286,
      "grad_norm": 0.6697707176208496,
      "learning_rate": 2.172949002217295e-05,
      "loss": 0.9155,
      "step": 408
    },
    {
      "epoch": 2.6923076923076925,
      "grad_norm": 0.7565432786941528,
      "learning_rate": 2.1286031042128604e-05,
      "loss": 0.914,
      "step": 409
    },
    {
      "epoch": 2.698901098901099,
      "grad_norm": 0.6538195610046387,
      "learning_rate": 2.084257206208426e-05,
      "loss": 0.8207,
      "step": 410
    },
    {
      "epoch": 2.7054945054945057,
      "grad_norm": 0.7591559886932373,
      "learning_rate": 2.0399113082039913e-05,
      "loss": 0.7877,
      "step": 411
    },
    {
      "epoch": 2.7120879120879122,
      "grad_norm": 0.5806507468223572,
      "learning_rate": 1.9955654101995567e-05,
      "loss": 0.7703,
      "step": 412
    },
    {
      "epoch": 2.718681318681319,
      "grad_norm": 0.7648088932037354,
      "learning_rate": 1.9512195121951222e-05,
      "loss": 0.967,
      "step": 413
    },
    {
      "epoch": 2.7252747252747254,
      "grad_norm": 0.7423636317253113,
      "learning_rate": 1.9068736141906873e-05,
      "loss": 0.9386,
      "step": 414
    },
    {
      "epoch": 2.731868131868132,
      "grad_norm": 0.793694019317627,
      "learning_rate": 1.8625277161862528e-05,
      "loss": 0.8659,
      "step": 415
    },
    {
      "epoch": 2.7384615384615385,
      "grad_norm": 0.6148553490638733,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 0.7237,
      "step": 416
    },
    {
      "epoch": 2.745054945054945,
      "grad_norm": 0.7509300708770752,
      "learning_rate": 1.7738359201773837e-05,
      "loss": 0.7167,
      "step": 417
    },
    {
      "epoch": 2.7516483516483516,
      "grad_norm": 0.9551002383232117,
      "learning_rate": 1.729490022172949e-05,
      "loss": 1.0245,
      "step": 418
    },
    {
      "epoch": 2.758241758241758,
      "grad_norm": 0.6584559082984924,
      "learning_rate": 1.6851441241685146e-05,
      "loss": 0.9207,
      "step": 419
    },
    {
      "epoch": 2.764835164835165,
      "grad_norm": 0.7318843007087708,
      "learning_rate": 1.64079822616408e-05,
      "loss": 0.7293,
      "step": 420
    },
    {
      "epoch": 2.7714285714285714,
      "grad_norm": 0.7944698929786682,
      "learning_rate": 1.596452328159645e-05,
      "loss": 0.7165,
      "step": 421
    },
    {
      "epoch": 2.778021978021978,
      "grad_norm": 0.7206577062606812,
      "learning_rate": 1.5521064301552106e-05,
      "loss": 0.7035,
      "step": 422
    },
    {
      "epoch": 2.7846153846153845,
      "grad_norm": 0.7300373315811157,
      "learning_rate": 1.5077605321507762e-05,
      "loss": 0.7695,
      "step": 423
    },
    {
      "epoch": 2.791208791208791,
      "grad_norm": 0.8015923500061035,
      "learning_rate": 1.4634146341463415e-05,
      "loss": 0.8472,
      "step": 424
    },
    {
      "epoch": 2.7978021978021976,
      "grad_norm": 0.753222644329071,
      "learning_rate": 1.419068736141907e-05,
      "loss": 0.8237,
      "step": 425
    },
    {
      "epoch": 2.804395604395604,
      "grad_norm": 0.5037018656730652,
      "learning_rate": 1.3747228381374724e-05,
      "loss": 0.5794,
      "step": 426
    },
    {
      "epoch": 2.8109890109890108,
      "grad_norm": 0.6997185945510864,
      "learning_rate": 1.3303769401330377e-05,
      "loss": 0.79,
      "step": 427
    },
    {
      "epoch": 2.8175824175824173,
      "grad_norm": 0.7490053772926331,
      "learning_rate": 1.2860310421286031e-05,
      "loss": 0.8454,
      "step": 428
    },
    {
      "epoch": 2.824175824175824,
      "grad_norm": 0.7101098299026489,
      "learning_rate": 1.2416851441241686e-05,
      "loss": 0.8285,
      "step": 429
    },
    {
      "epoch": 2.830769230769231,
      "grad_norm": 0.7692782878875732,
      "learning_rate": 1.197339246119734e-05,
      "loss": 0.7228,
      "step": 430
    },
    {
      "epoch": 2.8373626373626375,
      "grad_norm": 0.8246833682060242,
      "learning_rate": 1.1529933481152993e-05,
      "loss": 1.0926,
      "step": 431
    },
    {
      "epoch": 2.843956043956044,
      "grad_norm": 0.6319411993026733,
      "learning_rate": 1.1086474501108649e-05,
      "loss": 0.765,
      "step": 432
    },
    {
      "epoch": 2.8505494505494506,
      "grad_norm": 0.792017936706543,
      "learning_rate": 1.0643015521064302e-05,
      "loss": 0.8851,
      "step": 433
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.6227127313613892,
      "learning_rate": 1.0199556541019956e-05,
      "loss": 0.6433,
      "step": 434
    },
    {
      "epoch": 2.8637362637362638,
      "grad_norm": 0.7408111095428467,
      "learning_rate": 9.756097560975611e-06,
      "loss": 0.7662,
      "step": 435
    },
    {
      "epoch": 2.8703296703296703,
      "grad_norm": 0.7300878167152405,
      "learning_rate": 9.312638580931264e-06,
      "loss": 0.7897,
      "step": 436
    },
    {
      "epoch": 2.876923076923077,
      "grad_norm": 0.6674084663391113,
      "learning_rate": 8.869179600886918e-06,
      "loss": 0.8141,
      "step": 437
    },
    {
      "epoch": 2.8835164835164835,
      "grad_norm": 0.652303159236908,
      "learning_rate": 8.425720620842573e-06,
      "loss": 0.8523,
      "step": 438
    },
    {
      "epoch": 2.89010989010989,
      "grad_norm": 0.6932849884033203,
      "learning_rate": 7.982261640798226e-06,
      "loss": 0.9843,
      "step": 439
    },
    {
      "epoch": 2.8967032967032966,
      "grad_norm": 0.7062202095985413,
      "learning_rate": 7.538802660753881e-06,
      "loss": 0.7117,
      "step": 440
    },
    {
      "epoch": 2.903296703296703,
      "grad_norm": 0.7564737200737,
      "learning_rate": 7.095343680709535e-06,
      "loss": 0.7114,
      "step": 441
    },
    {
      "epoch": 2.9098901098901098,
      "grad_norm": 0.9429522156715393,
      "learning_rate": 6.651884700665188e-06,
      "loss": 0.8678,
      "step": 442
    },
    {
      "epoch": 2.9164835164835163,
      "grad_norm": 0.656097412109375,
      "learning_rate": 6.208425720620843e-06,
      "loss": 0.7932,
      "step": 443
    },
    {
      "epoch": 2.9230769230769234,
      "grad_norm": 0.7174648642539978,
      "learning_rate": 5.7649667405764965e-06,
      "loss": 0.7994,
      "step": 444
    },
    {
      "epoch": 2.92967032967033,
      "grad_norm": 0.7161996960639954,
      "learning_rate": 5.321507760532151e-06,
      "loss": 0.7535,
      "step": 445
    },
    {
      "epoch": 2.9362637362637365,
      "grad_norm": 0.6781159043312073,
      "learning_rate": 4.8780487804878055e-06,
      "loss": 0.8659,
      "step": 446
    },
    {
      "epoch": 2.942857142857143,
      "grad_norm": 0.6201663017272949,
      "learning_rate": 4.434589800443459e-06,
      "loss": 0.6816,
      "step": 447
    },
    {
      "epoch": 2.9494505494505496,
      "grad_norm": 0.7438039183616638,
      "learning_rate": 3.991130820399113e-06,
      "loss": 0.8708,
      "step": 448
    },
    {
      "epoch": 2.956043956043956,
      "grad_norm": 0.8539295792579651,
      "learning_rate": 3.5476718403547673e-06,
      "loss": 0.8256,
      "step": 449
    },
    {
      "epoch": 2.9626373626373628,
      "grad_norm": 0.6789367198944092,
      "learning_rate": 3.1042128603104214e-06,
      "loss": 0.7641,
      "step": 450
    }
  ],
  "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": 7.947707458348646e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}