{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.2703296703296703,
  "eval_steps": 500,
  "global_step": 345,
  "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
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.29604363441467285,
      "learning_rate": 0.00014235033259423505,
      "loss": 0.8765,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.3350680470466614,
      "learning_rate": 0.0001419068736141907,
      "loss": 0.9751,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.3040972054004669,
      "learning_rate": 0.00014146341463414634,
      "loss": 0.9126,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.36358514428138733,
      "learning_rate": 0.000141019955654102,
      "loss": 0.9055,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.2750164568424225,
      "learning_rate": 0.00014057649667405765,
      "loss": 0.8561,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.28348028659820557,
      "learning_rate": 0.00014013303769401332,
      "loss": 0.9384,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.41886258125305176,
      "learning_rate": 0.00013968957871396897,
      "loss": 0.9259,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.33635079860687256,
      "learning_rate": 0.00013924611973392464,
      "loss": 0.8921,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.45067307353019714,
      "learning_rate": 0.00013880266075388026,
      "loss": 0.8898,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.30932992696762085,
      "learning_rate": 0.00013835920177383593,
      "loss": 0.8852,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.27877306938171387,
      "learning_rate": 0.00013791574279379157,
      "loss": 0.9276,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.3003545105457306,
      "learning_rate": 0.00013747228381374724,
      "loss": 1.071,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.33769211173057556,
      "learning_rate": 0.0001370288248337029,
      "loss": 1.11,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.3046141266822815,
      "learning_rate": 0.00013658536585365856,
      "loss": 0.9579,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.32936060428619385,
      "learning_rate": 0.00013614190687361418,
      "loss": 1.0795,
      "step": 150
    },
    {
      "epoch": 0.9956043956043956,
      "grad_norm": 0.3542172908782959,
      "learning_rate": 0.00013569844789356985,
      "loss": 0.9134,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.4971023499965668,
      "learning_rate": 0.0001352549889135255,
      "loss": 1.0114,
      "step": 152
    },
    {
      "epoch": 1.0065934065934066,
      "grad_norm": 0.3157079219818115,
      "learning_rate": 0.00013481152993348116,
      "loss": 0.681,
      "step": 153
    },
    {
      "epoch": 1.0131868131868131,
      "grad_norm": 0.3333510458469391,
      "learning_rate": 0.0001343680709534368,
      "loss": 0.9601,
      "step": 154
    },
    {
      "epoch": 1.0197802197802197,
      "grad_norm": 0.2971794307231903,
      "learning_rate": 0.00013392461197339248,
      "loss": 0.8716,
      "step": 155
    },
    {
      "epoch": 1.0263736263736263,
      "grad_norm": 0.37250816822052,
      "learning_rate": 0.00013348115299334812,
      "loss": 0.9892,
      "step": 156
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.3490065932273865,
      "learning_rate": 0.00013303769401330377,
      "loss": 1.0808,
      "step": 157
    },
    {
      "epoch": 1.0395604395604396,
      "grad_norm": 0.31214308738708496,
      "learning_rate": 0.00013259423503325944,
      "loss": 0.7196,
      "step": 158
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 0.2932315468788147,
      "learning_rate": 0.00013215077605321509,
      "loss": 0.9077,
      "step": 159
    },
    {
      "epoch": 1.0527472527472528,
      "grad_norm": 0.326726496219635,
      "learning_rate": 0.00013170731707317076,
      "loss": 0.8089,
      "step": 160
    },
    {
      "epoch": 1.0593406593406594,
      "grad_norm": 0.4066810607910156,
      "learning_rate": 0.0001312638580931264,
      "loss": 0.7963,
      "step": 161
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.3206338882446289,
      "learning_rate": 0.00013082039911308205,
      "loss": 0.7908,
      "step": 162
    },
    {
      "epoch": 1.0725274725274725,
      "grad_norm": 0.2856912612915039,
      "learning_rate": 0.0001303769401330377,
      "loss": 0.8669,
      "step": 163
    },
    {
      "epoch": 1.079120879120879,
      "grad_norm": 0.3261955976486206,
      "learning_rate": 0.00012993348115299336,
      "loss": 0.9931,
      "step": 164
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.34742599725723267,
      "learning_rate": 0.000129490022172949,
      "loss": 0.815,
      "step": 165
    },
    {
      "epoch": 1.0923076923076924,
      "grad_norm": 0.34215840697288513,
      "learning_rate": 0.00012904656319290468,
      "loss": 0.8146,
      "step": 166
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 0.3123534917831421,
      "learning_rate": 0.00012860310421286032,
      "loss": 0.739,
      "step": 167
    },
    {
      "epoch": 1.1054945054945056,
      "grad_norm": 0.40804287791252136,
      "learning_rate": 0.00012815964523281597,
      "loss": 0.8001,
      "step": 168
    },
    {
      "epoch": 1.1120879120879121,
      "grad_norm": 0.3819836974143982,
      "learning_rate": 0.0001277161862527716,
      "loss": 0.8957,
      "step": 169
    },
    {
      "epoch": 1.1186813186813187,
      "grad_norm": 0.36181697249412537,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.844,
      "step": 170
    },
    {
      "epoch": 1.1252747252747253,
      "grad_norm": 0.37596753239631653,
      "learning_rate": 0.00012682926829268293,
      "loss": 0.8229,
      "step": 171
    },
    {
      "epoch": 1.1318681318681318,
      "grad_norm": 0.3627302944660187,
      "learning_rate": 0.0001263858093126386,
      "loss": 0.7728,
      "step": 172
    },
    {
      "epoch": 1.1384615384615384,
      "grad_norm": 0.36450669169425964,
      "learning_rate": 0.00012594235033259424,
      "loss": 0.9207,
      "step": 173
    },
    {
      "epoch": 1.145054945054945,
      "grad_norm": 0.3845820426940918,
      "learning_rate": 0.00012549889135254989,
      "loss": 0.9494,
      "step": 174
    },
    {
      "epoch": 1.1516483516483516,
      "grad_norm": 0.4480668306350708,
      "learning_rate": 0.00012505543237250553,
      "loss": 1.0664,
      "step": 175
    },
    {
      "epoch": 1.1582417582417581,
      "grad_norm": 0.36262378096580505,
      "learning_rate": 0.0001246119733924612,
      "loss": 0.7054,
      "step": 176
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 0.3617404103279114,
      "learning_rate": 0.00012416851441241685,
      "loss": 0.6476,
      "step": 177
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 0.4536733329296112,
      "learning_rate": 0.00012372505543237252,
      "loss": 1.0438,
      "step": 178
    },
    {
      "epoch": 1.178021978021978,
      "grad_norm": 0.3417685925960541,
      "learning_rate": 0.00012328159645232816,
      "loss": 0.8648,
      "step": 179
    },
    {
      "epoch": 1.1846153846153846,
      "grad_norm": 0.4170144200325012,
      "learning_rate": 0.0001228381374722838,
      "loss": 1.0141,
      "step": 180
    },
    {
      "epoch": 1.1912087912087912,
      "grad_norm": 0.36972424387931824,
      "learning_rate": 0.00012239467849223948,
      "loss": 0.8179,
      "step": 181
    },
    {
      "epoch": 1.1978021978021978,
      "grad_norm": 0.43088498711586,
      "learning_rate": 0.00012195121951219512,
      "loss": 0.8997,
      "step": 182
    },
    {
      "epoch": 1.2043956043956043,
      "grad_norm": 0.46577104926109314,
      "learning_rate": 0.00012150776053215078,
      "loss": 0.7752,
      "step": 183
    },
    {
      "epoch": 1.210989010989011,
      "grad_norm": 0.41609659790992737,
      "learning_rate": 0.00012106430155210644,
      "loss": 0.8308,
      "step": 184
    },
    {
      "epoch": 1.2175824175824177,
      "grad_norm": 0.49607279896736145,
      "learning_rate": 0.0001206208425720621,
      "loss": 0.8156,
      "step": 185
    },
    {
      "epoch": 1.2241758241758243,
      "grad_norm": 0.4497493505477905,
      "learning_rate": 0.00012017738359201774,
      "loss": 0.7033,
      "step": 186
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.4138677418231964,
      "learning_rate": 0.0001197339246119734,
      "loss": 0.8328,
      "step": 187
    },
    {
      "epoch": 1.2373626373626374,
      "grad_norm": 0.4053924083709717,
      "learning_rate": 0.00011929046563192906,
      "loss": 0.8401,
      "step": 188
    },
    {
      "epoch": 1.243956043956044,
      "grad_norm": 0.39517635107040405,
      "learning_rate": 0.00011884700665188471,
      "loss": 0.6678,
      "step": 189
    },
    {
      "epoch": 1.2505494505494505,
      "grad_norm": 0.3898938298225403,
      "learning_rate": 0.00011840354767184036,
      "loss": 0.7061,
      "step": 190
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.4238574802875519,
      "learning_rate": 0.00011796008869179602,
      "loss": 0.9425,
      "step": 191
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 0.4810243844985962,
      "learning_rate": 0.00011751662971175166,
      "loss": 0.8114,
      "step": 192
    },
    {
      "epoch": 1.2703296703296703,
      "grad_norm": 0.4439259171485901,
      "learning_rate": 0.00011707317073170732,
      "loss": 0.7482,
      "step": 193
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.42339658737182617,
      "learning_rate": 0.00011662971175166298,
      "loss": 0.697,
      "step": 194
    },
    {
      "epoch": 1.2835164835164834,
      "grad_norm": 0.5087814331054688,
      "learning_rate": 0.00011618625277161863,
      "loss": 0.7893,
      "step": 195
    },
    {
      "epoch": 1.2901098901098902,
      "grad_norm": 0.40122854709625244,
      "learning_rate": 0.00011574279379157429,
      "loss": 0.6821,
      "step": 196
    },
    {
      "epoch": 1.2967032967032968,
      "grad_norm": 0.5009786486625671,
      "learning_rate": 0.00011529933481152995,
      "loss": 0.785,
      "step": 197
    },
    {
      "epoch": 1.3032967032967033,
      "grad_norm": 0.39232102036476135,
      "learning_rate": 0.00011485587583148558,
      "loss": 0.7996,
      "step": 198
    },
    {
      "epoch": 1.30989010989011,
      "grad_norm": 0.39284753799438477,
      "learning_rate": 0.00011441241685144124,
      "loss": 0.7809,
      "step": 199
    },
    {
      "epoch": 1.3164835164835165,
      "grad_norm": 0.38429662585258484,
      "learning_rate": 0.0001139689578713969,
      "loss": 0.8158,
      "step": 200
    },
    {
      "epoch": 1.323076923076923,
      "grad_norm": 0.40376120805740356,
      "learning_rate": 0.00011352549889135255,
      "loss": 0.7272,
      "step": 201
    },
    {
      "epoch": 1.3296703296703296,
      "grad_norm": 0.4608078598976135,
      "learning_rate": 0.00011308203991130821,
      "loss": 0.7488,
      "step": 202
    },
    {
      "epoch": 1.3362637362637364,
      "grad_norm": 0.6156324744224548,
      "learning_rate": 0.00011263858093126387,
      "loss": 0.8141,
      "step": 203
    },
    {
      "epoch": 1.342857142857143,
      "grad_norm": 0.453130841255188,
      "learning_rate": 0.00011219512195121953,
      "loss": 0.797,
      "step": 204
    },
    {
      "epoch": 1.3494505494505495,
      "grad_norm": 0.330149382352829,
      "learning_rate": 0.00011175166297117516,
      "loss": 0.5682,
      "step": 205
    },
    {
      "epoch": 1.3560439560439561,
      "grad_norm": 0.45851245522499084,
      "learning_rate": 0.00011130820399113082,
      "loss": 0.8312,
      "step": 206
    },
    {
      "epoch": 1.3626373626373627,
      "grad_norm": 0.47988012433052063,
      "learning_rate": 0.00011086474501108647,
      "loss": 0.8008,
      "step": 207
    },
    {
      "epoch": 1.3692307692307693,
      "grad_norm": 0.40531787276268005,
      "learning_rate": 0.00011042128603104213,
      "loss": 0.714,
      "step": 208
    },
    {
      "epoch": 1.3758241758241758,
      "grad_norm": 0.4897518455982208,
      "learning_rate": 0.00010997782705099779,
      "loss": 0.8161,
      "step": 209
    },
    {
      "epoch": 1.3824175824175824,
      "grad_norm": 0.4496583342552185,
      "learning_rate": 0.00010953436807095345,
      "loss": 0.7545,
      "step": 210
    },
    {
      "epoch": 1.389010989010989,
      "grad_norm": 0.4640255570411682,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.7019,
      "step": 211
    },
    {
      "epoch": 1.3956043956043955,
      "grad_norm": 0.39746615290641785,
      "learning_rate": 0.00010864745011086475,
      "loss": 0.6632,
      "step": 212
    },
    {
      "epoch": 1.402197802197802,
      "grad_norm": 0.4388134479522705,
      "learning_rate": 0.00010820399113082041,
      "loss": 0.7591,
      "step": 213
    },
    {
      "epoch": 1.4087912087912087,
      "grad_norm": 0.4814299941062927,
      "learning_rate": 0.00010776053215077607,
      "loss": 1.051,
      "step": 214
    },
    {
      "epoch": 1.4153846153846155,
      "grad_norm": 0.4823339879512787,
      "learning_rate": 0.00010731707317073172,
      "loss": 0.8942,
      "step": 215
    },
    {
      "epoch": 1.421978021978022,
      "grad_norm": 0.5179139375686646,
      "learning_rate": 0.00010687361419068738,
      "loss": 0.8112,
      "step": 216
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.507037878036499,
      "learning_rate": 0.00010643015521064301,
      "loss": 0.8583,
      "step": 217
    },
    {
      "epoch": 1.4351648351648352,
      "grad_norm": 0.5176422595977783,
      "learning_rate": 0.00010598669623059867,
      "loss": 0.8111,
      "step": 218
    },
    {
      "epoch": 1.4417582417582417,
      "grad_norm": 0.6024381518363953,
      "learning_rate": 0.00010554323725055433,
      "loss": 0.9293,
      "step": 219
    },
    {
      "epoch": 1.4483516483516483,
      "grad_norm": 0.4122229814529419,
      "learning_rate": 0.00010509977827050999,
      "loss": 0.842,
      "step": 220
    },
    {
      "epoch": 1.4549450549450549,
      "grad_norm": 0.4701031446456909,
      "learning_rate": 0.00010465631929046564,
      "loss": 0.8009,
      "step": 221
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.5135300159454346,
      "learning_rate": 0.0001042128603104213,
      "loss": 0.7938,
      "step": 222
    },
    {
      "epoch": 1.4681318681318682,
      "grad_norm": 0.4522818326950073,
      "learning_rate": 0.00010376940133037693,
      "loss": 0.8545,
      "step": 223
    },
    {
      "epoch": 1.4747252747252748,
      "grad_norm": 0.4888346791267395,
      "learning_rate": 0.00010332594235033259,
      "loss": 0.8638,
      "step": 224
    },
    {
      "epoch": 1.4813186813186814,
      "grad_norm": 0.46665793657302856,
      "learning_rate": 0.00010288248337028825,
      "loss": 0.6905,
      "step": 225
    },
    {
      "epoch": 1.487912087912088,
      "grad_norm": 0.46969228982925415,
      "learning_rate": 0.0001024390243902439,
      "loss": 0.7867,
      "step": 226
    },
    {
      "epoch": 1.4945054945054945,
      "grad_norm": 0.5111256837844849,
      "learning_rate": 0.00010199556541019956,
      "loss": 0.8277,
      "step": 227
    },
    {
      "epoch": 1.501098901098901,
      "grad_norm": 0.4777606427669525,
      "learning_rate": 0.00010155210643015522,
      "loss": 0.7611,
      "step": 228
    },
    {
      "epoch": 1.5076923076923077,
      "grad_norm": 0.4318927824497223,
      "learning_rate": 0.00010110864745011087,
      "loss": 0.8813,
      "step": 229
    },
    {
      "epoch": 1.5142857142857142,
      "grad_norm": 0.4096817076206207,
      "learning_rate": 0.00010066518847006652,
      "loss": 0.9615,
      "step": 230
    },
    {
      "epoch": 1.5208791208791208,
      "grad_norm": 0.4937702417373657,
      "learning_rate": 0.00010022172949002218,
      "loss": 0.7473,
      "step": 231
    },
    {
      "epoch": 1.5274725274725274,
      "grad_norm": 0.4224448502063751,
      "learning_rate": 9.977827050997783e-05,
      "loss": 0.7038,
      "step": 232
    },
    {
      "epoch": 1.534065934065934,
      "grad_norm": 0.4882068634033203,
      "learning_rate": 9.933481152993348e-05,
      "loss": 0.8408,
      "step": 233
    },
    {
      "epoch": 1.5406593406593405,
      "grad_norm": 0.39783811569213867,
      "learning_rate": 9.889135254988914e-05,
      "loss": 0.6873,
      "step": 234
    },
    {
      "epoch": 1.5472527472527473,
      "grad_norm": 0.44983282685279846,
      "learning_rate": 9.84478935698448e-05,
      "loss": 0.7325,
      "step": 235
    },
    {
      "epoch": 1.5538461538461539,
      "grad_norm": 0.4892435669898987,
      "learning_rate": 9.800443458980046e-05,
      "loss": 0.733,
      "step": 236
    },
    {
      "epoch": 1.5604395604395604,
      "grad_norm": 0.5203067660331726,
      "learning_rate": 9.75609756097561e-05,
      "loss": 0.9833,
      "step": 237
    },
    {
      "epoch": 1.567032967032967,
      "grad_norm": 0.47970250248908997,
      "learning_rate": 9.711751662971176e-05,
      "loss": 0.7133,
      "step": 238
    },
    {
      "epoch": 1.5736263736263736,
      "grad_norm": 0.43145933747291565,
      "learning_rate": 9.667405764966742e-05,
      "loss": 0.7939,
      "step": 239
    },
    {
      "epoch": 1.5802197802197804,
      "grad_norm": 0.6309040784835815,
      "learning_rate": 9.623059866962306e-05,
      "loss": 0.9507,
      "step": 240
    },
    {
      "epoch": 1.586813186813187,
      "grad_norm": 0.4696212410926819,
      "learning_rate": 9.578713968957872e-05,
      "loss": 0.8723,
      "step": 241
    },
    {
      "epoch": 1.5934065934065935,
      "grad_norm": 0.503027617931366,
      "learning_rate": 9.534368070953438e-05,
      "loss": 0.8146,
      "step": 242
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.5486200451850891,
      "learning_rate": 9.490022172949002e-05,
      "loss": 0.7583,
      "step": 243
    },
    {
      "epoch": 1.6065934065934067,
      "grad_norm": 0.5820600986480713,
      "learning_rate": 9.445676274944568e-05,
      "loss": 0.902,
      "step": 244
    },
    {
      "epoch": 1.6131868131868132,
      "grad_norm": 0.4875508248806,
      "learning_rate": 9.401330376940134e-05,
      "loss": 0.7249,
      "step": 245
    },
    {
      "epoch": 1.6197802197802198,
      "grad_norm": 0.5274914503097534,
      "learning_rate": 9.356984478935698e-05,
      "loss": 0.7836,
      "step": 246
    },
    {
      "epoch": 1.6263736263736264,
      "grad_norm": 0.5331574082374573,
      "learning_rate": 9.312638580931264e-05,
      "loss": 0.757,
      "step": 247
    },
    {
      "epoch": 1.632967032967033,
      "grad_norm": 0.5652505159378052,
      "learning_rate": 9.26829268292683e-05,
      "loss": 0.7652,
      "step": 248
    },
    {
      "epoch": 1.6395604395604395,
      "grad_norm": 0.5296301245689392,
      "learning_rate": 9.223946784922394e-05,
      "loss": 0.8755,
      "step": 249
    },
    {
      "epoch": 1.646153846153846,
      "grad_norm": 0.5754923224449158,
      "learning_rate": 9.17960088691796e-05,
      "loss": 0.803,
      "step": 250
    },
    {
      "epoch": 1.6527472527472526,
      "grad_norm": 0.5134645104408264,
      "learning_rate": 9.135254988913526e-05,
      "loss": 0.8875,
      "step": 251
    },
    {
      "epoch": 1.6593406593406592,
      "grad_norm": 0.5619203448295593,
      "learning_rate": 9.090909090909092e-05,
      "loss": 0.8988,
      "step": 252
    },
    {
      "epoch": 1.6659340659340658,
      "grad_norm": 0.5061798095703125,
      "learning_rate": 9.046563192904656e-05,
      "loss": 0.9079,
      "step": 253
    },
    {
      "epoch": 1.6725274725274726,
      "grad_norm": 0.4390209913253784,
      "learning_rate": 9.002217294900222e-05,
      "loss": 0.8113,
      "step": 254
    },
    {
      "epoch": 1.6791208791208792,
      "grad_norm": 0.4493997395038605,
      "learning_rate": 8.957871396895788e-05,
      "loss": 0.7323,
      "step": 255
    },
    {
      "epoch": 1.6857142857142857,
      "grad_norm": 0.5257946848869324,
      "learning_rate": 8.913525498891354e-05,
      "loss": 0.8049,
      "step": 256
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.48318004608154297,
      "learning_rate": 8.869179600886919e-05,
      "loss": 0.9393,
      "step": 257
    },
    {
      "epoch": 1.6989010989010989,
      "grad_norm": 0.5197221636772156,
      "learning_rate": 8.824833702882484e-05,
      "loss": 0.7044,
      "step": 258
    },
    {
      "epoch": 1.7054945054945057,
      "grad_norm": 0.4740124046802521,
      "learning_rate": 8.78048780487805e-05,
      "loss": 0.833,
      "step": 259
    },
    {
      "epoch": 1.7120879120879122,
      "grad_norm": 0.4457124173641205,
      "learning_rate": 8.736141906873615e-05,
      "loss": 0.8177,
      "step": 260
    },
    {
      "epoch": 1.7186813186813188,
      "grad_norm": 0.4461446702480316,
      "learning_rate": 8.69179600886918e-05,
      "loss": 0.8309,
      "step": 261
    },
    {
      "epoch": 1.7252747252747254,
      "grad_norm": 0.48701727390289307,
      "learning_rate": 8.647450110864746e-05,
      "loss": 0.7668,
      "step": 262
    },
    {
      "epoch": 1.731868131868132,
      "grad_norm": 0.5182144641876221,
      "learning_rate": 8.603104212860311e-05,
      "loss": 0.7493,
      "step": 263
    },
    {
      "epoch": 1.7384615384615385,
      "grad_norm": 0.5598351359367371,
      "learning_rate": 8.558758314855876e-05,
      "loss": 0.9047,
      "step": 264
    },
    {
      "epoch": 1.745054945054945,
      "grad_norm": 0.4855658710002899,
      "learning_rate": 8.514412416851442e-05,
      "loss": 0.8603,
      "step": 265
    },
    {
      "epoch": 1.7516483516483516,
      "grad_norm": 0.4231507182121277,
      "learning_rate": 8.470066518847007e-05,
      "loss": 0.7178,
      "step": 266
    },
    {
      "epoch": 1.7582417582417582,
      "grad_norm": 0.5748950242996216,
      "learning_rate": 8.425720620842572e-05,
      "loss": 0.9283,
      "step": 267
    },
    {
      "epoch": 1.7648351648351648,
      "grad_norm": 0.6212405562400818,
      "learning_rate": 8.381374722838138e-05,
      "loss": 1.0059,
      "step": 268
    },
    {
      "epoch": 1.7714285714285714,
      "grad_norm": 0.5940495729446411,
      "learning_rate": 8.337028824833703e-05,
      "loss": 0.8549,
      "step": 269
    },
    {
      "epoch": 1.778021978021978,
      "grad_norm": 0.4704616069793701,
      "learning_rate": 8.292682926829268e-05,
      "loss": 0.8132,
      "step": 270
    },
    {
      "epoch": 1.7846153846153845,
      "grad_norm": 0.5662758946418762,
      "learning_rate": 8.248337028824834e-05,
      "loss": 0.8417,
      "step": 271
    },
    {
      "epoch": 1.791208791208791,
      "grad_norm": 0.6198431849479675,
      "learning_rate": 8.2039911308204e-05,
      "loss": 0.8411,
      "step": 272
    },
    {
      "epoch": 1.7978021978021979,
      "grad_norm": 0.519121527671814,
      "learning_rate": 8.159645232815965e-05,
      "loss": 0.7893,
      "step": 273
    },
    {
      "epoch": 1.8043956043956044,
      "grad_norm": 0.5829556584358215,
      "learning_rate": 8.11529933481153e-05,
      "loss": 1.0084,
      "step": 274
    },
    {
      "epoch": 1.810989010989011,
      "grad_norm": 0.5641196370124817,
      "learning_rate": 8.070953436807095e-05,
      "loss": 0.8236,
      "step": 275
    },
    {
      "epoch": 1.8175824175824176,
      "grad_norm": 0.5176860690116882,
      "learning_rate": 8.026607538802661e-05,
      "loss": 0.8122,
      "step": 276
    },
    {
      "epoch": 1.8241758241758241,
      "grad_norm": 0.4663509726524353,
      "learning_rate": 7.982261640798227e-05,
      "loss": 0.959,
      "step": 277
    },
    {
      "epoch": 1.830769230769231,
      "grad_norm": 0.5991304516792297,
      "learning_rate": 7.937915742793793e-05,
      "loss": 0.8542,
      "step": 278
    },
    {
      "epoch": 1.8373626373626375,
      "grad_norm": 0.6622920632362366,
      "learning_rate": 7.893569844789357e-05,
      "loss": 1.0734,
      "step": 279
    },
    {
      "epoch": 1.843956043956044,
      "grad_norm": 0.44951921701431274,
      "learning_rate": 7.849223946784923e-05,
      "loss": 0.7857,
      "step": 280
    },
    {
      "epoch": 1.8505494505494506,
      "grad_norm": 0.5131855010986328,
      "learning_rate": 7.804878048780489e-05,
      "loss": 0.9509,
      "step": 281
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.4403367340564728,
      "learning_rate": 7.760532150776053e-05,
      "loss": 0.7827,
      "step": 282
    },
    {
      "epoch": 1.8637362637362638,
      "grad_norm": 0.503652811050415,
      "learning_rate": 7.716186252771619e-05,
      "loss": 0.8107,
      "step": 283
    },
    {
      "epoch": 1.8703296703296703,
      "grad_norm": 0.5205672383308411,
      "learning_rate": 7.671840354767185e-05,
      "loss": 0.7336,
      "step": 284
    },
    {
      "epoch": 1.876923076923077,
      "grad_norm": 0.7026404738426208,
      "learning_rate": 7.627494456762749e-05,
      "loss": 0.7981,
      "step": 285
    },
    {
      "epoch": 1.8835164835164835,
      "grad_norm": 0.6247934699058533,
      "learning_rate": 7.583148558758315e-05,
      "loss": 0.9805,
      "step": 286
    },
    {
      "epoch": 1.89010989010989,
      "grad_norm": 0.46719756722450256,
      "learning_rate": 7.538802660753881e-05,
      "loss": 0.9143,
      "step": 287
    },
    {
      "epoch": 1.8967032967032966,
      "grad_norm": 0.5322892665863037,
      "learning_rate": 7.494456762749445e-05,
      "loss": 0.8499,
      "step": 288
    },
    {
      "epoch": 1.9032967032967032,
      "grad_norm": 0.514388918876648,
      "learning_rate": 7.450110864745011e-05,
      "loss": 0.8748,
      "step": 289
    },
    {
      "epoch": 1.9098901098901098,
      "grad_norm": 0.519920289516449,
      "learning_rate": 7.405764966740577e-05,
      "loss": 0.8578,
      "step": 290
    },
    {
      "epoch": 1.9164835164835163,
      "grad_norm": 0.5433463454246521,
      "learning_rate": 7.361419068736141e-05,
      "loss": 0.7854,
      "step": 291
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.6190493106842041,
      "learning_rate": 7.317073170731707e-05,
      "loss": 0.9326,
      "step": 292
    },
    {
      "epoch": 1.9296703296703297,
      "grad_norm": 0.619138240814209,
      "learning_rate": 7.272727272727273e-05,
      "loss": 1.0913,
      "step": 293
    },
    {
      "epoch": 1.9362637362637363,
      "grad_norm": 0.5144149661064148,
      "learning_rate": 7.228381374722837e-05,
      "loss": 1.0134,
      "step": 294
    },
    {
      "epoch": 1.9428571428571428,
      "grad_norm": 0.5237277150154114,
      "learning_rate": 7.184035476718403e-05,
      "loss": 0.9195,
      "step": 295
    },
    {
      "epoch": 1.9494505494505494,
      "grad_norm": 0.6134456396102905,
      "learning_rate": 7.139689578713969e-05,
      "loss": 0.7312,
      "step": 296
    },
    {
      "epoch": 1.9560439560439562,
      "grad_norm": 0.641844630241394,
      "learning_rate": 7.095343680709535e-05,
      "loss": 0.9015,
      "step": 297
    },
    {
      "epoch": 1.9626373626373628,
      "grad_norm": 0.546023428440094,
      "learning_rate": 7.0509977827051e-05,
      "loss": 0.903,
      "step": 298
    },
    {
      "epoch": 1.9692307692307693,
      "grad_norm": 0.5946680307388306,
      "learning_rate": 7.006651884700666e-05,
      "loss": 0.9984,
      "step": 299
    },
    {
      "epoch": 1.975824175824176,
      "grad_norm": 0.599720299243927,
      "learning_rate": 6.962305986696232e-05,
      "loss": 0.9638,
      "step": 300
    },
    {
      "epoch": 1.9824175824175825,
      "grad_norm": 0.4221124053001404,
      "learning_rate": 6.917960088691796e-05,
      "loss": 0.8195,
      "step": 301
    },
    {
      "epoch": 1.989010989010989,
      "grad_norm": 0.65491783618927,
      "learning_rate": 6.873614190687362e-05,
      "loss": 1.0198,
      "step": 302
    },
    {
      "epoch": 1.9956043956043956,
      "grad_norm": 0.42064300179481506,
      "learning_rate": 6.829268292682928e-05,
      "loss": 0.9191,
      "step": 303
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.8415328860282898,
      "learning_rate": 6.784922394678492e-05,
      "loss": 0.626,
      "step": 304
    },
    {
      "epoch": 2.0065934065934066,
      "grad_norm": 0.5134572982788086,
      "learning_rate": 6.740576496674058e-05,
      "loss": 0.8024,
      "step": 305
    },
    {
      "epoch": 2.013186813186813,
      "grad_norm": 0.4623129665851593,
      "learning_rate": 6.696230598669624e-05,
      "loss": 0.6545,
      "step": 306
    },
    {
      "epoch": 2.0197802197802197,
      "grad_norm": 0.4919341206550598,
      "learning_rate": 6.651884700665188e-05,
      "loss": 0.8851,
      "step": 307
    },
    {
      "epoch": 2.0263736263736263,
      "grad_norm": 0.4394765794277191,
      "learning_rate": 6.607538802660754e-05,
      "loss": 0.6204,
      "step": 308
    },
    {
      "epoch": 2.032967032967033,
      "grad_norm": 0.4931715726852417,
      "learning_rate": 6.56319290465632e-05,
      "loss": 0.5851,
      "step": 309
    },
    {
      "epoch": 2.0395604395604394,
      "grad_norm": 0.5278884172439575,
      "learning_rate": 6.518847006651884e-05,
      "loss": 0.623,
      "step": 310
    },
    {
      "epoch": 2.046153846153846,
      "grad_norm": 0.5538532137870789,
      "learning_rate": 6.47450110864745e-05,
      "loss": 0.6363,
      "step": 311
    },
    {
      "epoch": 2.0527472527472526,
      "grad_norm": 0.530224084854126,
      "learning_rate": 6.430155210643016e-05,
      "loss": 0.7701,
      "step": 312
    },
    {
      "epoch": 2.059340659340659,
      "grad_norm": 0.4873906075954437,
      "learning_rate": 6.38580931263858e-05,
      "loss": 0.7282,
      "step": 313
    },
    {
      "epoch": 2.065934065934066,
      "grad_norm": 0.48935189843177795,
      "learning_rate": 6.341463414634146e-05,
      "loss": 0.7554,
      "step": 314
    },
    {
      "epoch": 2.0725274725274727,
      "grad_norm": 0.550834059715271,
      "learning_rate": 6.297117516629712e-05,
      "loss": 0.6707,
      "step": 315
    },
    {
      "epoch": 2.0791208791208793,
      "grad_norm": 0.5724208354949951,
      "learning_rate": 6.252771618625277e-05,
      "loss": 0.7569,
      "step": 316
    },
    {
      "epoch": 2.085714285714286,
      "grad_norm": 0.5952929854393005,
      "learning_rate": 6.208425720620842e-05,
      "loss": 0.8262,
      "step": 317
    },
    {
      "epoch": 2.0923076923076924,
      "grad_norm": 0.652867317199707,
      "learning_rate": 6.164079822616408e-05,
      "loss": 0.7408,
      "step": 318
    },
    {
      "epoch": 2.098901098901099,
      "grad_norm": 0.4510781764984131,
      "learning_rate": 6.119733924611974e-05,
      "loss": 0.6882,
      "step": 319
    },
    {
      "epoch": 2.1054945054945056,
      "grad_norm": 0.5417594909667969,
      "learning_rate": 6.075388026607539e-05,
      "loss": 0.5536,
      "step": 320
    },
    {
      "epoch": 2.112087912087912,
      "grad_norm": 0.6183019876480103,
      "learning_rate": 6.031042128603105e-05,
      "loss": 0.6601,
      "step": 321
    },
    {
      "epoch": 2.1186813186813187,
      "grad_norm": 0.6414585709571838,
      "learning_rate": 5.98669623059867e-05,
      "loss": 0.8749,
      "step": 322
    },
    {
      "epoch": 2.1252747252747253,
      "grad_norm": 0.6290186643600464,
      "learning_rate": 5.942350332594236e-05,
      "loss": 0.8119,
      "step": 323
    },
    {
      "epoch": 2.131868131868132,
      "grad_norm": 0.5872353911399841,
      "learning_rate": 5.898004434589801e-05,
      "loss": 0.6958,
      "step": 324
    },
    {
      "epoch": 2.1384615384615384,
      "grad_norm": 0.608471691608429,
      "learning_rate": 5.853658536585366e-05,
      "loss": 0.7068,
      "step": 325
    },
    {
      "epoch": 2.145054945054945,
      "grad_norm": 0.7094746828079224,
      "learning_rate": 5.809312638580932e-05,
      "loss": 0.7112,
      "step": 326
    },
    {
      "epoch": 2.1516483516483516,
      "grad_norm": 0.6484392881393433,
      "learning_rate": 5.7649667405764975e-05,
      "loss": 0.8101,
      "step": 327
    },
    {
      "epoch": 2.158241758241758,
      "grad_norm": 0.6416611671447754,
      "learning_rate": 5.720620842572062e-05,
      "loss": 0.6882,
      "step": 328
    },
    {
      "epoch": 2.1648351648351647,
      "grad_norm": 0.5828561186790466,
      "learning_rate": 5.676274944567628e-05,
      "loss": 0.5947,
      "step": 329
    },
    {
      "epoch": 2.1714285714285713,
      "grad_norm": 0.6690956354141235,
      "learning_rate": 5.6319290465631935e-05,
      "loss": 0.6567,
      "step": 330
    },
    {
      "epoch": 2.178021978021978,
      "grad_norm": 0.5497298836708069,
      "learning_rate": 5.587583148558758e-05,
      "loss": 0.6601,
      "step": 331
    },
    {
      "epoch": 2.184615384615385,
      "grad_norm": 0.6187049746513367,
      "learning_rate": 5.543237250554324e-05,
      "loss": 0.7145,
      "step": 332
    },
    {
      "epoch": 2.1912087912087914,
      "grad_norm": 0.7608487606048584,
      "learning_rate": 5.4988913525498895e-05,
      "loss": 0.9618,
      "step": 333
    },
    {
      "epoch": 2.197802197802198,
      "grad_norm": 0.6504568457603455,
      "learning_rate": 5.4545454545454546e-05,
      "loss": 0.6432,
      "step": 334
    },
    {
      "epoch": 2.2043956043956046,
      "grad_norm": 0.677703857421875,
      "learning_rate": 5.4101995565410204e-05,
      "loss": 0.8499,
      "step": 335
    },
    {
      "epoch": 2.210989010989011,
      "grad_norm": 0.5743486285209656,
      "learning_rate": 5.365853658536586e-05,
      "loss": 0.6063,
      "step": 336
    },
    {
      "epoch": 2.2175824175824177,
      "grad_norm": 0.7217883467674255,
      "learning_rate": 5.3215077605321506e-05,
      "loss": 0.8357,
      "step": 337
    },
    {
      "epoch": 2.2241758241758243,
      "grad_norm": 0.5791580080986023,
      "learning_rate": 5.2771618625277164e-05,
      "loss": 0.5829,
      "step": 338
    },
    {
      "epoch": 2.230769230769231,
      "grad_norm": 0.6253702044487,
      "learning_rate": 5.232815964523282e-05,
      "loss": 0.8372,
      "step": 339
    },
    {
      "epoch": 2.2373626373626374,
      "grad_norm": 0.6868003010749817,
      "learning_rate": 5.1884700665188466e-05,
      "loss": 0.6888,
      "step": 340
    },
    {
      "epoch": 2.243956043956044,
      "grad_norm": 0.5958376526832581,
      "learning_rate": 5.1441241685144124e-05,
      "loss": 0.8101,
      "step": 341
    },
    {
      "epoch": 2.2505494505494505,
      "grad_norm": 0.6801559329032898,
      "learning_rate": 5.099778270509978e-05,
      "loss": 0.7141,
      "step": 342
    },
    {
      "epoch": 2.257142857142857,
      "grad_norm": 0.6123746633529663,
      "learning_rate": 5.0554323725055433e-05,
      "loss": 0.8225,
      "step": 343
    },
    {
      "epoch": 2.2637362637362637,
      "grad_norm": 0.6089701056480408,
      "learning_rate": 5.011086474501109e-05,
      "loss": 0.6845,
      "step": 344
    },
    {
      "epoch": 2.2703296703296703,
      "grad_norm": 0.5913880467414856,
      "learning_rate": 4.966740576496674e-05,
      "loss": 0.785,
      "step": 345
    }
  ],
  "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": 5.636098314392371e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}