{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8901098901098901,
  "eval_steps": 500,
  "global_step": 135,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.6567009687423706,
      "learning_rate": 0.0,
      "loss": 2.767,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.3838800191879272,
      "learning_rate": 4e-05,
      "loss": 2.2945,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.9234319925308228,
      "learning_rate": 8e-05,
      "loss": 2.9474,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.9659762382507324,
      "learning_rate": 0.00012,
      "loss": 2.9853,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 2.1689095497131348,
      "learning_rate": 0.00016,
      "loss": 2.7449,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 2.7526321411132812,
      "learning_rate": 0.0002,
      "loss": 2.4316,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 2.216229200363159,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.5923,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 2.076944589614868,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.4113,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.8331300020217896,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.1678,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 1.4564743041992188,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.4995,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.923876166343689,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.2383,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.8946003317832947,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.153,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.5039580464363098,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.1056,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.5277471542358398,
      "learning_rate": 0.00019645232815964525,
      "loss": 1.0161,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.4442140460014343,
      "learning_rate": 0.00019600886917960092,
      "loss": 0.9613,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.38263705372810364,
      "learning_rate": 0.00019556541019955653,
      "loss": 0.8934,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.42776256799697876,
      "learning_rate": 0.0001951219512195122,
      "loss": 1.0797,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.43527865409851074,
      "learning_rate": 0.00019467849223946785,
      "loss": 0.8707,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.32646483182907104,
      "learning_rate": 0.00019423503325942352,
      "loss": 1.0146,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.40627530217170715,
      "learning_rate": 0.00019379157427937917,
      "loss": 0.9273,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.46039798855781555,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.8705,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.41969212889671326,
      "learning_rate": 0.00019290465631929045,
      "loss": 1.0961,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.4023812413215637,
      "learning_rate": 0.00019246119733924613,
      "loss": 1.1031,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.3344135284423828,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.8892,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.3448273241519928,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.8705,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.2724474370479584,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.8999,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.40961214900016785,
      "learning_rate": 0.00019068736141906876,
      "loss": 1.2188,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.3562145531177521,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.9201,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.3152042031288147,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.936,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.27859261631965637,
      "learning_rate": 0.00018935698447893572,
      "loss": 0.8427,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.2839672565460205,
      "learning_rate": 0.00018891352549889136,
      "loss": 1.0559,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.2582114636898041,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.9073,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.32668337225914,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.9628,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.30008381605148315,
      "learning_rate": 0.00018758314855875832,
      "loss": 1.1248,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.3355301320552826,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.9885,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.29906919598579407,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.8781,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.30698609352111816,
      "learning_rate": 0.00018625277161862528,
      "loss": 1.0222,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.3538931906223297,
      "learning_rate": 0.00018580931263858095,
      "loss": 1.0791,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.37524330615997314,
      "learning_rate": 0.0001853658536585366,
      "loss": 1.1857,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.2466009110212326,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.8989,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.3097603917121887,
      "learning_rate": 0.0001844789356984479,
      "loss": 0.8067,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.33890318870544434,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.9267,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.2851554751396179,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.854,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.3237600326538086,
      "learning_rate": 0.00018314855875831487,
      "loss": 0.8857,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.299290269613266,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.8993,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.2949437201023102,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.8557,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.2869762182235718,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.8459,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.28831377625465393,
      "learning_rate": 0.00018137472283813748,
      "loss": 0.9929,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.2845543324947357,
      "learning_rate": 0.00018093126385809312,
      "loss": 1.0737,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.35254544019699097,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.9845,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.27268919348716736,
      "learning_rate": 0.00018004434589800444,
      "loss": 0.8531,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.2979799807071686,
      "learning_rate": 0.00017960088691796008,
      "loss": 1.0148,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.28734323382377625,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.9678,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.32514873147010803,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.9336,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.3372485935688019,
      "learning_rate": 0.00017827050997782707,
      "loss": 1.0235,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.26649677753448486,
      "learning_rate": 0.00017782705099778271,
      "loss": 1.1352,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.28168147802352905,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.8594,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.3652113974094391,
      "learning_rate": 0.000176940133037694,
      "loss": 1.0333,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.28549066185951233,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.9242,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.3495144546031952,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.9354,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.2963283956050873,
      "learning_rate": 0.000175609756097561,
      "loss": 1.019,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.3170008063316345,
      "learning_rate": 0.00017516629711751663,
      "loss": 1.0356,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.3124063313007355,
      "learning_rate": 0.0001747228381374723,
      "loss": 0.9234,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.24903765320777893,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.8637,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.3188488185405731,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.9132,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.2667141258716583,
      "learning_rate": 0.00017339246119733924,
      "loss": 0.8397,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.3092103600502014,
      "learning_rate": 0.0001729490022172949,
      "loss": 1.1419,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.28331172466278076,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.6945,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.40235045552253723,
      "learning_rate": 0.00017206208425720623,
      "loss": 1.0281,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.35112065076828003,
      "learning_rate": 0.00017161862527716187,
      "loss": 0.9054,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.32497426867485046,
      "learning_rate": 0.00017117516629711752,
      "loss": 1.0846,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.3371214270591736,
      "learning_rate": 0.0001707317073170732,
      "loss": 1.1541,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.3357504606246948,
      "learning_rate": 0.00017028824833702883,
      "loss": 1.0018,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.3269040584564209,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.8198,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.33502882719039917,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.8037,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.26444435119628906,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.9395,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.26372969150543213,
      "learning_rate": 0.00016851441241685144,
      "loss": 0.9298,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.2765997052192688,
      "learning_rate": 0.0001680709534368071,
      "loss": 0.83,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.38125479221343994,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.9544,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.3223702609539032,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.8165,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.29701244831085205,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.8864,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.3128220736980438,
      "learning_rate": 0.00016629711751662974,
      "loss": 0.7918,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.301275372505188,
      "learning_rate": 0.00016585365853658536,
      "loss": 1.2268,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.3119061589241028,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.9242,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.34405505657196045,
      "learning_rate": 0.00016496674057649667,
      "loss": 0.8224,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.3084266781806946,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.8734,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.34335729479789734,
      "learning_rate": 0.000164079822616408,
      "loss": 1.0343,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.3085907995700836,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.9893,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.3688369691371918,
      "learning_rate": 0.0001631929046563193,
      "loss": 1.0162,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.41302305459976196,
      "learning_rate": 0.00016274944567627495,
      "loss": 1.1334,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.31472793221473694,
      "learning_rate": 0.0001623059866962306,
      "loss": 0.9592,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.3053753077983856,
      "learning_rate": 0.00016186252771618626,
      "loss": 0.9114,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.3011174201965332,
      "learning_rate": 0.0001614190687361419,
      "loss": 0.9042,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.28674694895744324,
      "learning_rate": 0.00016097560975609758,
      "loss": 0.9993,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.3339006304740906,
      "learning_rate": 0.00016053215077605322,
      "loss": 0.901,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.32696405053138733,
      "learning_rate": 0.00016008869179600887,
      "loss": 0.9266,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.2887837886810303,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.9244,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.28662651777267456,
      "learning_rate": 0.00015920177383592018,
      "loss": 0.774,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.2676166892051697,
      "learning_rate": 0.00015875831485587586,
      "loss": 1.075,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.5233193635940552,
      "learning_rate": 0.0001583148558758315,
      "loss": 1.1417,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.34248974919319153,
      "learning_rate": 0.00015787139689578714,
      "loss": 0.9957,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.3012807369232178,
      "learning_rate": 0.0001574279379157428,
      "loss": 0.9717,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.3375048041343689,
      "learning_rate": 0.00015698447893569846,
      "loss": 0.9511,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.27296754717826843,
      "learning_rate": 0.0001565410199556541,
      "loss": 0.8283,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.3134506642818451,
      "learning_rate": 0.00015609756097560978,
      "loss": 0.9002,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.29912269115448,
      "learning_rate": 0.00015565410199556542,
      "loss": 0.9801,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.35039985179901123,
      "learning_rate": 0.00015521064301552106,
      "loss": 0.7061,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.3625171482563019,
      "learning_rate": 0.0001547671840354767,
      "loss": 0.9079,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.3082823157310486,
      "learning_rate": 0.00015432372505543238,
      "loss": 1.0375,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.30382442474365234,
      "learning_rate": 0.00015388026607538802,
      "loss": 0.9655,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.34333935379981995,
      "learning_rate": 0.0001534368070953437,
      "loss": 1.1025,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.29243388772010803,
      "learning_rate": 0.00015299334811529934,
      "loss": 0.7142,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.393321692943573,
      "learning_rate": 0.00015254988913525498,
      "loss": 0.9171,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.3505791425704956,
      "learning_rate": 0.00015210643015521066,
      "loss": 0.8922,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.35040605068206787,
      "learning_rate": 0.0001516629711751663,
      "loss": 0.9125,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.3528439700603485,
      "learning_rate": 0.00015121951219512197,
      "loss": 0.9835,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.26055535674095154,
      "learning_rate": 0.00015077605321507762,
      "loss": 0.7501,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.3948929011821747,
      "learning_rate": 0.0001503325942350333,
      "loss": 0.9892,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.3050883412361145,
      "learning_rate": 0.0001498891352549889,
      "loss": 0.9364,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.352852463722229,
      "learning_rate": 0.00014944567627494458,
      "loss": 1.022,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.2735101580619812,
      "learning_rate": 0.00014900221729490022,
      "loss": 0.8561,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.3725152611732483,
      "learning_rate": 0.0001485587583148559,
      "loss": 1.1805,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.3257027268409729,
      "learning_rate": 0.00014811529933481154,
      "loss": 1.1249,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.2660929262638092,
      "learning_rate": 0.0001476718403547672,
      "loss": 0.728,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.27107471227645874,
      "learning_rate": 0.00014722838137472282,
      "loss": 0.7775,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.3075776696205139,
      "learning_rate": 0.0001467849223946785,
      "loss": 0.7897,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.27322521805763245,
      "learning_rate": 0.00014634146341463414,
      "loss": 0.8257,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.31768798828125,
      "learning_rate": 0.0001458980044345898,
      "loss": 0.8999,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.36425843834877014,
      "learning_rate": 0.00014545454545454546,
      "loss": 1.0177,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.34491363167762756,
      "learning_rate": 0.00014501108647450113,
      "loss": 1.0759,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.3355429768562317,
      "learning_rate": 0.00014456762749445675,
      "loss": 0.8247,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.39246925711631775,
      "learning_rate": 0.00014412416851441242,
      "loss": 0.9215,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.31784865260124207,
      "learning_rate": 0.00014368070953436806,
      "loss": 1.0823,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.38987264037132263,
      "learning_rate": 0.00014323725055432373,
      "loss": 0.8492,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.37241673469543457,
      "learning_rate": 0.00014279379157427938,
      "loss": 0.927,
      "step": 135
    }
  ],
  "logging_steps": 1,
  "max_steps": 456,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.2097322828742656e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}