{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.3824175824175824,
  "eval_steps": 500,
  "global_step": 210,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 2.303626298904419,
      "learning_rate": 0.0,
      "loss": 3.6085,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.439454436302185,
      "learning_rate": 4e-05,
      "loss": 2.4913,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.7588273286819458,
      "learning_rate": 8e-05,
      "loss": 2.6433,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.5198580026626587,
      "learning_rate": 0.00012,
      "loss": 2.3145,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 1.8622243404388428,
      "learning_rate": 0.00016,
      "loss": 2.4423,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 2.6957828998565674,
      "learning_rate": 0.0002,
      "loss": 2.1699,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 2.3653955459594727,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.5512,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.867249846458435,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.4124,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.9426868557929993,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.4026,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 1.105395793914795,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.2543,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.788772702217102,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.2154,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.53281569480896,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.2039,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.40713539719581604,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.0836,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.5409032702445984,
      "learning_rate": 0.00019645232815964525,
      "loss": 1.1098,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.47973766922950745,
      "learning_rate": 0.00019600886917960092,
      "loss": 1.19,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.5039457678794861,
      "learning_rate": 0.00019556541019955653,
      "loss": 1.1809,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.432468056678772,
      "learning_rate": 0.0001951219512195122,
      "loss": 1.1579,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.49248069524765015,
      "learning_rate": 0.00019467849223946785,
      "loss": 1.0721,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.506483256816864,
      "learning_rate": 0.00019423503325942352,
      "loss": 1.2076,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.3699564039707184,
      "learning_rate": 0.00019379157427937917,
      "loss": 0.8558,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.40447086095809937,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.9758,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.42658472061157227,
      "learning_rate": 0.00019290465631929045,
      "loss": 1.062,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.3948553204536438,
      "learning_rate": 0.00019246119733924613,
      "loss": 0.9631,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.32725754380226135,
      "learning_rate": 0.00019201773835920177,
      "loss": 1.0747,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.33828970789909363,
      "learning_rate": 0.00019157427937915744,
      "loss": 1.0653,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.27442067861557007,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.9254,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.27329978346824646,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.9075,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.41785359382629395,
      "learning_rate": 0.0001902439024390244,
      "loss": 1.0079,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.282429963350296,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.8602,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.37518325448036194,
      "learning_rate": 0.00018935698447893572,
      "loss": 1.0907,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.2990609407424927,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.8994,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.33431681990623474,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.9115,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.31373974680900574,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.9089,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.2787388563156128,
      "learning_rate": 0.00018758314855875832,
      "loss": 1.0808,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.3206472396850586,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.9184,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.2402617186307907,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.7528,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.34411153197288513,
      "learning_rate": 0.00018625277161862528,
      "loss": 0.9755,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.34733089804649353,
      "learning_rate": 0.00018580931263858095,
      "loss": 1.0181,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.3262622356414795,
      "learning_rate": 0.0001853658536585366,
      "loss": 1.0464,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.24500015377998352,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.9446,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.2835443913936615,
      "learning_rate": 0.0001844789356984479,
      "loss": 0.9856,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.27747032046318054,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.9622,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.34073948860168457,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.9465,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.26712504029273987,
      "learning_rate": 0.00018314855875831487,
      "loss": 1.0602,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.37089070677757263,
      "learning_rate": 0.00018270509977827052,
      "loss": 1.0997,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.30469098687171936,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.9438,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.31314560770988464,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.8367,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.33173537254333496,
      "learning_rate": 0.00018137472283813748,
      "loss": 1.0277,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.2833123803138733,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.7779,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.28676313161849976,
      "learning_rate": 0.0001804878048780488,
      "loss": 1.0172,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.25923117995262146,
      "learning_rate": 0.00018004434589800444,
      "loss": 0.7737,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.2750239074230194,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.8973,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.30605781078338623,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.9545,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.2281476855278015,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.7999,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.3172890245914459,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.893,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.38381415605545044,
      "learning_rate": 0.00017782705099778271,
      "loss": 1.0448,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.3915952146053314,
      "learning_rate": 0.00017738359201773839,
      "loss": 1.0564,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.33569052815437317,
      "learning_rate": 0.000176940133037694,
      "loss": 1.0455,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.4101047217845917,
      "learning_rate": 0.00017649667405764967,
      "loss": 1.0923,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.42315059900283813,
      "learning_rate": 0.00017605321507760532,
      "loss": 1.0163,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.2661890387535095,
      "learning_rate": 0.000175609756097561,
      "loss": 0.7853,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.3342932462692261,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.9406,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.3210691809654236,
      "learning_rate": 0.0001747228381374723,
      "loss": 0.8858,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.2718408703804016,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.9452,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.36029088497161865,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.8777,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.35389444231987,
      "learning_rate": 0.00017339246119733924,
      "loss": 1.0064,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.3141503930091858,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.8785,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.27303633093833923,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.8559,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.3359520137310028,
      "learning_rate": 0.00017206208425720623,
      "loss": 1.096,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.30675244331359863,
      "learning_rate": 0.00017161862527716187,
      "loss": 1.0009,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.3307923972606659,
      "learning_rate": 0.00017117516629711752,
      "loss": 1.0056,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.24969322979450226,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.8563,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.24619445204734802,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.8386,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.3848130702972412,
      "learning_rate": 0.0001698447893569845,
      "loss": 1.2539,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.35728219151496887,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.9608,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.41609638929367065,
      "learning_rate": 0.00016895787139689582,
      "loss": 1.1981,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.3290999233722687,
      "learning_rate": 0.00016851441241685144,
      "loss": 1.0885,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.3357957899570465,
      "learning_rate": 0.0001680709534368071,
      "loss": 0.9842,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.37297511100769043,
      "learning_rate": 0.00016762749445676275,
      "loss": 1.0532,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.333650678396225,
      "learning_rate": 0.00016718403547671842,
      "loss": 1.0956,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.3169361650943756,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.9588,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.28924304246902466,
      "learning_rate": 0.00016629711751662974,
      "loss": 0.9038,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.2601667046546936,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.7903,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.28349757194519043,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.8989,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.37565159797668457,
      "learning_rate": 0.00016496674057649667,
      "loss": 1.1042,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.38468965888023376,
      "learning_rate": 0.00016452328159645234,
      "loss": 1.1407,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.28541499376296997,
      "learning_rate": 0.000164079822616408,
      "loss": 0.8125,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.2994617223739624,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.9195,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.3976408839225769,
      "learning_rate": 0.0001631929046563193,
      "loss": 1.0156,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.30622562766075134,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.9982,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.28931549191474915,
      "learning_rate": 0.0001623059866962306,
      "loss": 0.928,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.31948480010032654,
      "learning_rate": 0.00016186252771618626,
      "loss": 1.0779,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.33104556798934937,
      "learning_rate": 0.0001614190687361419,
      "loss": 1.0611,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.43478959798812866,
      "learning_rate": 0.00016097560975609758,
      "loss": 0.9161,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.32590118050575256,
      "learning_rate": 0.00016053215077605322,
      "loss": 1.1696,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.25838395953178406,
      "learning_rate": 0.00016008869179600887,
      "loss": 0.7856,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.3152015507221222,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.7904,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.34387698769569397,
      "learning_rate": 0.00015920177383592018,
      "loss": 0.991,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.2822190821170807,
      "learning_rate": 0.00015875831485587586,
      "loss": 0.9494,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.26281842589378357,
      "learning_rate": 0.0001583148558758315,
      "loss": 0.9059,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.42032739520072937,
      "learning_rate": 0.00015787139689578714,
      "loss": 1.0635,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.2608965337276459,
      "learning_rate": 0.0001574279379157428,
      "loss": 0.6873,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.25404682755470276,
      "learning_rate": 0.00015698447893569846,
      "loss": 0.9051,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.34183400869369507,
      "learning_rate": 0.0001565410199556541,
      "loss": 0.9823,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.29854243993759155,
      "learning_rate": 0.00015609756097560978,
      "loss": 0.9067,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.3323337435722351,
      "learning_rate": 0.00015565410199556542,
      "loss": 0.8381,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.30771464109420776,
      "learning_rate": 0.00015521064301552106,
      "loss": 0.8658,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.26583606004714966,
      "learning_rate": 0.0001547671840354767,
      "loss": 0.8458,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.2765386402606964,
      "learning_rate": 0.00015432372505543238,
      "loss": 0.7864,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.33523914217948914,
      "learning_rate": 0.00015388026607538802,
      "loss": 0.9053,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.3297010660171509,
      "learning_rate": 0.0001534368070953437,
      "loss": 0.8264,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.2933356761932373,
      "learning_rate": 0.00015299334811529934,
      "loss": 0.8524,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.31128862500190735,
      "learning_rate": 0.00015254988913525498,
      "loss": 0.891,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.37845343351364136,
      "learning_rate": 0.00015210643015521066,
      "loss": 1.2966,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.3646884560585022,
      "learning_rate": 0.0001516629711751663,
      "loss": 1.0198,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.3193872570991516,
      "learning_rate": 0.00015121951219512197,
      "loss": 1.1952,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.25547274947166443,
      "learning_rate": 0.00015077605321507762,
      "loss": 0.9888,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.2840863764286041,
      "learning_rate": 0.0001503325942350333,
      "loss": 0.8643,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.349303662776947,
      "learning_rate": 0.0001498891352549889,
      "loss": 0.7961,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.25125086307525635,
      "learning_rate": 0.00014944567627494458,
      "loss": 0.8055,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.2910859286785126,
      "learning_rate": 0.00014900221729490022,
      "loss": 0.6735,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.28555774688720703,
      "learning_rate": 0.0001485587583148559,
      "loss": 0.864,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.28217050433158875,
      "learning_rate": 0.00014811529933481154,
      "loss": 0.8938,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.33504718542099,
      "learning_rate": 0.0001476718403547672,
      "loss": 0.9377,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.2877736985683441,
      "learning_rate": 0.00014722838137472282,
      "loss": 0.9173,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.3107459247112274,
      "learning_rate": 0.0001467849223946785,
      "loss": 0.828,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.33110880851745605,
      "learning_rate": 0.00014634146341463414,
      "loss": 0.8686,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.30587294697761536,
      "learning_rate": 0.0001458980044345898,
      "loss": 1.0425,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.3741580843925476,
      "learning_rate": 0.00014545454545454546,
      "loss": 1.0715,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.3586806654930115,
      "learning_rate": 0.00014501108647450113,
      "loss": 1.1221,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.36812883615493774,
      "learning_rate": 0.00014456762749445675,
      "loss": 1.0742,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.32173845171928406,
      "learning_rate": 0.00014412416851441242,
      "loss": 1.0443,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.38413581252098083,
      "learning_rate": 0.00014368070953436806,
      "loss": 1.0525,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.46863028407096863,
      "learning_rate": 0.00014323725055432373,
      "loss": 0.8269,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.3614848256111145,
      "learning_rate": 0.00014279379157427938,
      "loss": 1.0206,
      "step": 135
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.2927537262439728,
      "learning_rate": 0.00014235033259423505,
      "loss": 0.9561,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.42427268624305725,
      "learning_rate": 0.0001419068736141907,
      "loss": 1.0297,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.3389011025428772,
      "learning_rate": 0.00014146341463414634,
      "loss": 0.8741,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.3461213707923889,
      "learning_rate": 0.000141019955654102,
      "loss": 0.9779,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.4119606912136078,
      "learning_rate": 0.00014057649667405765,
      "loss": 1.0071,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.27475905418395996,
      "learning_rate": 0.00014013303769401332,
      "loss": 0.8762,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.36642834544181824,
      "learning_rate": 0.00013968957871396897,
      "loss": 0.9655,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.3168472945690155,
      "learning_rate": 0.00013924611973392464,
      "loss": 0.8674,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.5073333382606506,
      "learning_rate": 0.00013880266075388026,
      "loss": 0.7491,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.2707488536834717,
      "learning_rate": 0.00013835920177383593,
      "loss": 1.0252,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.3995589315891266,
      "learning_rate": 0.00013791574279379157,
      "loss": 0.93,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.3536117672920227,
      "learning_rate": 0.00013747228381374724,
      "loss": 0.9061,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.34937381744384766,
      "learning_rate": 0.0001370288248337029,
      "loss": 0.9136,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.29199913144111633,
      "learning_rate": 0.00013658536585365856,
      "loss": 0.9812,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.37444406747817993,
      "learning_rate": 0.00013614190687361418,
      "loss": 0.9576,
      "step": 150
    },
    {
      "epoch": 0.9956043956043956,
      "grad_norm": 0.3482721149921417,
      "learning_rate": 0.00013569844789356985,
      "loss": 0.9318,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.3411265015602112,
      "learning_rate": 0.0001352549889135255,
      "loss": 0.7835,
      "step": 152
    },
    {
      "epoch": 1.0065934065934066,
      "grad_norm": 0.3751468062400818,
      "learning_rate": 0.00013481152993348116,
      "loss": 0.9466,
      "step": 153
    },
    {
      "epoch": 1.0131868131868131,
      "grad_norm": 0.2971190810203552,
      "learning_rate": 0.0001343680709534368,
      "loss": 0.7348,
      "step": 154
    },
    {
      "epoch": 1.0197802197802197,
      "grad_norm": 0.3237416744232178,
      "learning_rate": 0.00013392461197339248,
      "loss": 0.8655,
      "step": 155
    },
    {
      "epoch": 1.0263736263736263,
      "grad_norm": 0.29400381445884705,
      "learning_rate": 0.00013348115299334812,
      "loss": 1.0433,
      "step": 156
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.31784510612487793,
      "learning_rate": 0.00013303769401330377,
      "loss": 0.9537,
      "step": 157
    },
    {
      "epoch": 1.0395604395604396,
      "grad_norm": 0.29349464178085327,
      "learning_rate": 0.00013259423503325944,
      "loss": 0.8429,
      "step": 158
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 0.28283601999282837,
      "learning_rate": 0.00013215077605321509,
      "loss": 0.7495,
      "step": 159
    },
    {
      "epoch": 1.0527472527472528,
      "grad_norm": 0.3360508680343628,
      "learning_rate": 0.00013170731707317076,
      "loss": 0.8179,
      "step": 160
    },
    {
      "epoch": 1.0593406593406594,
      "grad_norm": 0.3243735432624817,
      "learning_rate": 0.0001312638580931264,
      "loss": 0.8491,
      "step": 161
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.2543736696243286,
      "learning_rate": 0.00013082039911308205,
      "loss": 0.8473,
      "step": 162
    },
    {
      "epoch": 1.0725274725274725,
      "grad_norm": 0.41662824153900146,
      "learning_rate": 0.0001303769401330377,
      "loss": 1.0799,
      "step": 163
    },
    {
      "epoch": 1.079120879120879,
      "grad_norm": 0.36721354722976685,
      "learning_rate": 0.00012993348115299336,
      "loss": 0.9888,
      "step": 164
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.38682231307029724,
      "learning_rate": 0.000129490022172949,
      "loss": 0.8444,
      "step": 165
    },
    {
      "epoch": 1.0923076923076924,
      "grad_norm": 0.3763047754764557,
      "learning_rate": 0.00012904656319290468,
      "loss": 0.7915,
      "step": 166
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 0.3762548565864563,
      "learning_rate": 0.00012860310421286032,
      "loss": 0.8605,
      "step": 167
    },
    {
      "epoch": 1.1054945054945056,
      "grad_norm": 0.34774428606033325,
      "learning_rate": 0.00012815964523281597,
      "loss": 0.8596,
      "step": 168
    },
    {
      "epoch": 1.1120879120879121,
      "grad_norm": 0.33537760376930237,
      "learning_rate": 0.0001277161862527716,
      "loss": 1.0133,
      "step": 169
    },
    {
      "epoch": 1.1186813186813187,
      "grad_norm": 0.37760505080223083,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.8969,
      "step": 170
    },
    {
      "epoch": 1.1252747252747253,
      "grad_norm": 0.40093833208084106,
      "learning_rate": 0.00012682926829268293,
      "loss": 0.7781,
      "step": 171
    },
    {
      "epoch": 1.1318681318681318,
      "grad_norm": 0.37234511971473694,
      "learning_rate": 0.0001263858093126386,
      "loss": 0.8151,
      "step": 172
    },
    {
      "epoch": 1.1384615384615384,
      "grad_norm": 0.383432000875473,
      "learning_rate": 0.00012594235033259424,
      "loss": 0.8534,
      "step": 173
    },
    {
      "epoch": 1.145054945054945,
      "grad_norm": 0.4024796783924103,
      "learning_rate": 0.00012549889135254989,
      "loss": 0.8456,
      "step": 174
    },
    {
      "epoch": 1.1516483516483516,
      "grad_norm": 0.42926251888275146,
      "learning_rate": 0.00012505543237250553,
      "loss": 0.7341,
      "step": 175
    },
    {
      "epoch": 1.1582417582417581,
      "grad_norm": 0.38404402136802673,
      "learning_rate": 0.0001246119733924612,
      "loss": 0.9299,
      "step": 176
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 0.3822978436946869,
      "learning_rate": 0.00012416851441241685,
      "loss": 0.8499,
      "step": 177
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 0.3729138672351837,
      "learning_rate": 0.00012372505543237252,
      "loss": 0.8227,
      "step": 178
    },
    {
      "epoch": 1.178021978021978,
      "grad_norm": 0.3332406282424927,
      "learning_rate": 0.00012328159645232816,
      "loss": 0.8247,
      "step": 179
    },
    {
      "epoch": 1.1846153846153846,
      "grad_norm": 0.38172462582588196,
      "learning_rate": 0.0001228381374722838,
      "loss": 0.9185,
      "step": 180
    },
    {
      "epoch": 1.1912087912087912,
      "grad_norm": 0.40163788199424744,
      "learning_rate": 0.00012239467849223948,
      "loss": 0.8539,
      "step": 181
    },
    {
      "epoch": 1.1978021978021978,
      "grad_norm": 0.36429041624069214,
      "learning_rate": 0.00012195121951219512,
      "loss": 0.9113,
      "step": 182
    },
    {
      "epoch": 1.2043956043956043,
      "grad_norm": 0.413580983877182,
      "learning_rate": 0.00012150776053215078,
      "loss": 0.819,
      "step": 183
    },
    {
      "epoch": 1.210989010989011,
      "grad_norm": 0.4143903851509094,
      "learning_rate": 0.00012106430155210644,
      "loss": 0.8512,
      "step": 184
    },
    {
      "epoch": 1.2175824175824177,
      "grad_norm": 0.4125838875770569,
      "learning_rate": 0.0001206208425720621,
      "loss": 0.9585,
      "step": 185
    },
    {
      "epoch": 1.2241758241758243,
      "grad_norm": 0.3720792233943939,
      "learning_rate": 0.00012017738359201774,
      "loss": 0.7881,
      "step": 186
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.49924013018608093,
      "learning_rate": 0.0001197339246119734,
      "loss": 0.9763,
      "step": 187
    },
    {
      "epoch": 1.2373626373626374,
      "grad_norm": 0.39625343680381775,
      "learning_rate": 0.00011929046563192906,
      "loss": 0.7851,
      "step": 188
    },
    {
      "epoch": 1.243956043956044,
      "grad_norm": 0.33806920051574707,
      "learning_rate": 0.00011884700665188471,
      "loss": 0.8916,
      "step": 189
    },
    {
      "epoch": 1.2505494505494505,
      "grad_norm": 0.43014171719551086,
      "learning_rate": 0.00011840354767184036,
      "loss": 0.7832,
      "step": 190
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.37463000416755676,
      "learning_rate": 0.00011796008869179602,
      "loss": 0.9113,
      "step": 191
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 0.34547415375709534,
      "learning_rate": 0.00011751662971175166,
      "loss": 0.9936,
      "step": 192
    },
    {
      "epoch": 1.2703296703296703,
      "grad_norm": 0.4263266324996948,
      "learning_rate": 0.00011707317073170732,
      "loss": 0.8082,
      "step": 193
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.4370916783809662,
      "learning_rate": 0.00011662971175166298,
      "loss": 0.7088,
      "step": 194
    },
    {
      "epoch": 1.2835164835164834,
      "grad_norm": 0.48510512709617615,
      "learning_rate": 0.00011618625277161863,
      "loss": 0.873,
      "step": 195
    },
    {
      "epoch": 1.2901098901098902,
      "grad_norm": 0.43364349007606506,
      "learning_rate": 0.00011574279379157429,
      "loss": 0.9497,
      "step": 196
    },
    {
      "epoch": 1.2967032967032968,
      "grad_norm": 0.4251789450645447,
      "learning_rate": 0.00011529933481152995,
      "loss": 0.8802,
      "step": 197
    },
    {
      "epoch": 1.3032967032967033,
      "grad_norm": 0.42555809020996094,
      "learning_rate": 0.00011485587583148558,
      "loss": 0.8027,
      "step": 198
    },
    {
      "epoch": 1.30989010989011,
      "grad_norm": 0.4067121148109436,
      "learning_rate": 0.00011441241685144124,
      "loss": 0.8642,
      "step": 199
    },
    {
      "epoch": 1.3164835164835165,
      "grad_norm": 0.42258256673812866,
      "learning_rate": 0.0001139689578713969,
      "loss": 0.9318,
      "step": 200
    },
    {
      "epoch": 1.323076923076923,
      "grad_norm": 0.4275679886341095,
      "learning_rate": 0.00011352549889135255,
      "loss": 0.8968,
      "step": 201
    },
    {
      "epoch": 1.3296703296703296,
      "grad_norm": 0.49644041061401367,
      "learning_rate": 0.00011308203991130821,
      "loss": 0.7946,
      "step": 202
    },
    {
      "epoch": 1.3362637362637364,
      "grad_norm": 0.4212213456630707,
      "learning_rate": 0.00011263858093126387,
      "loss": 0.9027,
      "step": 203
    },
    {
      "epoch": 1.342857142857143,
      "grad_norm": 0.3859935402870178,
      "learning_rate": 0.00011219512195121953,
      "loss": 0.7549,
      "step": 204
    },
    {
      "epoch": 1.3494505494505495,
      "grad_norm": 0.42257729172706604,
      "learning_rate": 0.00011175166297117516,
      "loss": 0.9584,
      "step": 205
    },
    {
      "epoch": 1.3560439560439561,
      "grad_norm": 0.4249301850795746,
      "learning_rate": 0.00011130820399113082,
      "loss": 0.977,
      "step": 206
    },
    {
      "epoch": 1.3626373626373627,
      "grad_norm": 0.4894404709339142,
      "learning_rate": 0.00011086474501108647,
      "loss": 1.0573,
      "step": 207
    },
    {
      "epoch": 1.3692307692307693,
      "grad_norm": 0.44024428725242615,
      "learning_rate": 0.00011042128603104213,
      "loss": 0.938,
      "step": 208
    },
    {
      "epoch": 1.3758241758241758,
      "grad_norm": 0.568278431892395,
      "learning_rate": 0.00010997782705099779,
      "loss": 0.7926,
      "step": 209
    },
    {
      "epoch": 1.3824175824175824,
      "grad_norm": 0.45056864619255066,
      "learning_rate": 0.00010953436807095345,
      "loss": 0.6928,
      "step": 210
    }
  ],
  "logging_steps": 1,
  "max_steps": 456,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.424069517102285e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}