{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5001406645619081,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001000281329123816,
      "grad_norm": 0.8429446220397949,
      "learning_rate": 4e-05,
      "loss": 2.1214,
      "step": 1
    },
    {
      "epoch": 0.002000562658247632,
      "grad_norm": 0.8077384829521179,
      "learning_rate": 8e-05,
      "loss": 2.0494,
      "step": 2
    },
    {
      "epoch": 0.003000843987371448,
      "grad_norm": 0.8456265330314636,
      "learning_rate": 0.00012,
      "loss": 2.085,
      "step": 3
    },
    {
      "epoch": 0.004001125316495264,
      "grad_norm": 0.9069010615348816,
      "learning_rate": 0.00016,
      "loss": 1.9829,
      "step": 4
    },
    {
      "epoch": 0.005001406645619081,
      "grad_norm": 1.0074480772018433,
      "learning_rate": 0.0002,
      "loss": 1.9033,
      "step": 5
    },
    {
      "epoch": 0.006001687974742896,
      "grad_norm": 0.8257189393043518,
      "learning_rate": 0.0001999331550802139,
      "loss": 1.5524,
      "step": 6
    },
    {
      "epoch": 0.007001969303866712,
      "grad_norm": 1.083123803138733,
      "learning_rate": 0.00019986631016042782,
      "loss": 1.3415,
      "step": 7
    },
    {
      "epoch": 0.008002250632990529,
      "grad_norm": 1.0079448223114014,
      "learning_rate": 0.00019979946524064174,
      "loss": 1.1143,
      "step": 8
    },
    {
      "epoch": 0.009002531962114344,
      "grad_norm": 1.0429109334945679,
      "learning_rate": 0.00019973262032085563,
      "loss": 0.9258,
      "step": 9
    },
    {
      "epoch": 0.010002813291238161,
      "grad_norm": 0.8113088011741638,
      "learning_rate": 0.00019966577540106952,
      "loss": 0.7895,
      "step": 10
    },
    {
      "epoch": 0.011003094620361977,
      "grad_norm": 0.6412453651428223,
      "learning_rate": 0.00019959893048128344,
      "loss": 0.7063,
      "step": 11
    },
    {
      "epoch": 0.012003375949485792,
      "grad_norm": 0.3962993323802948,
      "learning_rate": 0.00019953208556149733,
      "loss": 0.7163,
      "step": 12
    },
    {
      "epoch": 0.01300365727860961,
      "grad_norm": 0.2532273530960083,
      "learning_rate": 0.00019946524064171124,
      "loss": 0.6578,
      "step": 13
    },
    {
      "epoch": 0.014003938607733425,
      "grad_norm": 0.2674902081489563,
      "learning_rate": 0.00019939839572192514,
      "loss": 0.6686,
      "step": 14
    },
    {
      "epoch": 0.01500421993685724,
      "grad_norm": 0.24159769713878632,
      "learning_rate": 0.00019933155080213905,
      "loss": 0.6986,
      "step": 15
    },
    {
      "epoch": 0.016004501265981057,
      "grad_norm": 0.2500644624233246,
      "learning_rate": 0.00019926470588235294,
      "loss": 0.6651,
      "step": 16
    },
    {
      "epoch": 0.017004782595104875,
      "grad_norm": 0.23079444468021393,
      "learning_rate": 0.00019919786096256686,
      "loss": 0.6605,
      "step": 17
    },
    {
      "epoch": 0.01800506392422869,
      "grad_norm": 0.23093147575855255,
      "learning_rate": 0.00019913101604278075,
      "loss": 0.666,
      "step": 18
    },
    {
      "epoch": 0.019005345253352506,
      "grad_norm": 0.25526249408721924,
      "learning_rate": 0.00019906417112299467,
      "loss": 0.6464,
      "step": 19
    },
    {
      "epoch": 0.020005626582476323,
      "grad_norm": 0.20218677818775177,
      "learning_rate": 0.00019899732620320856,
      "loss": 0.6447,
      "step": 20
    },
    {
      "epoch": 0.021005907911600136,
      "grad_norm": 0.1994040459394455,
      "learning_rate": 0.00019893048128342245,
      "loss": 0.6177,
      "step": 21
    },
    {
      "epoch": 0.022006189240723954,
      "grad_norm": 0.1931009441614151,
      "learning_rate": 0.00019886363636363637,
      "loss": 0.6302,
      "step": 22
    },
    {
      "epoch": 0.02300647056984777,
      "grad_norm": 0.20102368295192719,
      "learning_rate": 0.0001987967914438503,
      "loss": 0.5879,
      "step": 23
    },
    {
      "epoch": 0.024006751898971584,
      "grad_norm": 0.20754167437553406,
      "learning_rate": 0.00019872994652406418,
      "loss": 0.6179,
      "step": 24
    },
    {
      "epoch": 0.0250070332280954,
      "grad_norm": 0.18852552771568298,
      "learning_rate": 0.00019866310160427807,
      "loss": 0.597,
      "step": 25
    },
    {
      "epoch": 0.02600731455721922,
      "grad_norm": 0.1997801512479782,
      "learning_rate": 0.000198596256684492,
      "loss": 0.6095,
      "step": 26
    },
    {
      "epoch": 0.027007595886343033,
      "grad_norm": 0.2071068286895752,
      "learning_rate": 0.0001985294117647059,
      "loss": 0.5877,
      "step": 27
    },
    {
      "epoch": 0.02800787721546685,
      "grad_norm": 0.17418323457241058,
      "learning_rate": 0.0001984625668449198,
      "loss": 0.583,
      "step": 28
    },
    {
      "epoch": 0.029008158544590667,
      "grad_norm": 0.1909712702035904,
      "learning_rate": 0.0001983957219251337,
      "loss": 0.6138,
      "step": 29
    },
    {
      "epoch": 0.03000843987371448,
      "grad_norm": 0.18094871938228607,
      "learning_rate": 0.0001983288770053476,
      "loss": 0.6213,
      "step": 30
    },
    {
      "epoch": 0.031008721202838298,
      "grad_norm": 0.18094347417354584,
      "learning_rate": 0.00019826203208556152,
      "loss": 0.5519,
      "step": 31
    },
    {
      "epoch": 0.032009002531962115,
      "grad_norm": 0.19804947078227997,
      "learning_rate": 0.00019819518716577541,
      "loss": 0.5868,
      "step": 32
    },
    {
      "epoch": 0.03300928386108593,
      "grad_norm": 0.18164557218551636,
      "learning_rate": 0.0001981283422459893,
      "loss": 0.5877,
      "step": 33
    },
    {
      "epoch": 0.03400956519020975,
      "grad_norm": 0.17944936454296112,
      "learning_rate": 0.00019806149732620322,
      "loss": 0.5863,
      "step": 34
    },
    {
      "epoch": 0.03500984651933356,
      "grad_norm": 0.1959485411643982,
      "learning_rate": 0.0001979946524064171,
      "loss": 0.5605,
      "step": 35
    },
    {
      "epoch": 0.03601012784845738,
      "grad_norm": 0.18620513379573822,
      "learning_rate": 0.00019792780748663103,
      "loss": 0.5834,
      "step": 36
    },
    {
      "epoch": 0.037010409177581194,
      "grad_norm": 0.18502476811408997,
      "learning_rate": 0.00019786096256684492,
      "loss": 0.5708,
      "step": 37
    },
    {
      "epoch": 0.03801069050670501,
      "grad_norm": 0.18578067421913147,
      "learning_rate": 0.00019779411764705884,
      "loss": 0.5535,
      "step": 38
    },
    {
      "epoch": 0.03901097183582883,
      "grad_norm": 0.18923674523830414,
      "learning_rate": 0.00019772727272727273,
      "loss": 0.5886,
      "step": 39
    },
    {
      "epoch": 0.040011253164952645,
      "grad_norm": 0.19942790269851685,
      "learning_rate": 0.00019766042780748665,
      "loss": 0.5787,
      "step": 40
    },
    {
      "epoch": 0.041011534494076456,
      "grad_norm": 0.1787114143371582,
      "learning_rate": 0.00019759358288770054,
      "loss": 0.562,
      "step": 41
    },
    {
      "epoch": 0.04201181582320027,
      "grad_norm": 0.18252694606781006,
      "learning_rate": 0.00019752673796791446,
      "loss": 0.5372,
      "step": 42
    },
    {
      "epoch": 0.04301209715232409,
      "grad_norm": 0.17881186306476593,
      "learning_rate": 0.00019745989304812835,
      "loss": 0.5393,
      "step": 43
    },
    {
      "epoch": 0.04401237848144791,
      "grad_norm": 0.17656774818897247,
      "learning_rate": 0.00019739304812834224,
      "loss": 0.5426,
      "step": 44
    },
    {
      "epoch": 0.045012659810571724,
      "grad_norm": 0.17589929699897766,
      "learning_rate": 0.00019732620320855616,
      "loss": 0.5273,
      "step": 45
    },
    {
      "epoch": 0.04601294113969554,
      "grad_norm": 0.19131453335285187,
      "learning_rate": 0.00019725935828877008,
      "loss": 0.5516,
      "step": 46
    },
    {
      "epoch": 0.04701322246881936,
      "grad_norm": 0.19191059470176697,
      "learning_rate": 0.00019719251336898397,
      "loss": 0.5371,
      "step": 47
    },
    {
      "epoch": 0.04801350379794317,
      "grad_norm": 0.1867751181125641,
      "learning_rate": 0.00019712566844919786,
      "loss": 0.5214,
      "step": 48
    },
    {
      "epoch": 0.049013785127066986,
      "grad_norm": 0.1942758411169052,
      "learning_rate": 0.00019705882352941177,
      "loss": 0.5281,
      "step": 49
    },
    {
      "epoch": 0.0500140664561908,
      "grad_norm": 0.19128914177417755,
      "learning_rate": 0.0001969919786096257,
      "loss": 0.5425,
      "step": 50
    },
    {
      "epoch": 0.05101434778531462,
      "grad_norm": 0.20454362034797668,
      "learning_rate": 0.00019692513368983958,
      "loss": 0.5702,
      "step": 51
    },
    {
      "epoch": 0.05201462911443844,
      "grad_norm": 0.19591577351093292,
      "learning_rate": 0.00019685828877005347,
      "loss": 0.5485,
      "step": 52
    },
    {
      "epoch": 0.053014910443562255,
      "grad_norm": 0.185511976480484,
      "learning_rate": 0.0001967914438502674,
      "loss": 0.526,
      "step": 53
    },
    {
      "epoch": 0.054015191772686065,
      "grad_norm": 0.2026601880788803,
      "learning_rate": 0.0001967245989304813,
      "loss": 0.5402,
      "step": 54
    },
    {
      "epoch": 0.05501547310180988,
      "grad_norm": 0.18051393330097198,
      "learning_rate": 0.0001966577540106952,
      "loss": 0.5312,
      "step": 55
    },
    {
      "epoch": 0.0560157544309337,
      "grad_norm": 0.19778816401958466,
      "learning_rate": 0.0001965909090909091,
      "loss": 0.5224,
      "step": 56
    },
    {
      "epoch": 0.05701603576005752,
      "grad_norm": 0.20953774452209473,
      "learning_rate": 0.000196524064171123,
      "loss": 0.5467,
      "step": 57
    },
    {
      "epoch": 0.058016317089181334,
      "grad_norm": 0.1995982676744461,
      "learning_rate": 0.0001964572192513369,
      "loss": 0.5188,
      "step": 58
    },
    {
      "epoch": 0.05901659841830515,
      "grad_norm": 0.18894651532173157,
      "learning_rate": 0.00019639037433155082,
      "loss": 0.5408,
      "step": 59
    },
    {
      "epoch": 0.06001687974742896,
      "grad_norm": 0.2050745040178299,
      "learning_rate": 0.0001963235294117647,
      "loss": 0.5461,
      "step": 60
    },
    {
      "epoch": 0.06101716107655278,
      "grad_norm": 0.20279429852962494,
      "learning_rate": 0.00019625668449197863,
      "loss": 0.522,
      "step": 61
    },
    {
      "epoch": 0.062017442405676595,
      "grad_norm": 0.21156936883926392,
      "learning_rate": 0.00019618983957219252,
      "loss": 0.5508,
      "step": 62
    },
    {
      "epoch": 0.06301772373480041,
      "grad_norm": 0.19698701798915863,
      "learning_rate": 0.00019612299465240644,
      "loss": 0.5399,
      "step": 63
    },
    {
      "epoch": 0.06401800506392423,
      "grad_norm": 0.19573122262954712,
      "learning_rate": 0.00019605614973262033,
      "loss": 0.5331,
      "step": 64
    },
    {
      "epoch": 0.06501828639304805,
      "grad_norm": 0.196864053606987,
      "learning_rate": 0.00019598930481283424,
      "loss": 0.5272,
      "step": 65
    },
    {
      "epoch": 0.06601856772217186,
      "grad_norm": 0.18443772196769714,
      "learning_rate": 0.00019592245989304814,
      "loss": 0.5159,
      "step": 66
    },
    {
      "epoch": 0.06701884905129568,
      "grad_norm": 0.22080574929714203,
      "learning_rate": 0.00019585561497326203,
      "loss": 0.5263,
      "step": 67
    },
    {
      "epoch": 0.0680191303804195,
      "grad_norm": 0.211871936917305,
      "learning_rate": 0.00019578877005347594,
      "loss": 0.5225,
      "step": 68
    },
    {
      "epoch": 0.06901941170954332,
      "grad_norm": 0.20276880264282227,
      "learning_rate": 0.00019572192513368986,
      "loss": 0.5376,
      "step": 69
    },
    {
      "epoch": 0.07001969303866712,
      "grad_norm": 0.2004377543926239,
      "learning_rate": 0.00019565508021390375,
      "loss": 0.4932,
      "step": 70
    },
    {
      "epoch": 0.07101997436779094,
      "grad_norm": 0.23046928644180298,
      "learning_rate": 0.00019558823529411764,
      "loss": 0.5271,
      "step": 71
    },
    {
      "epoch": 0.07202025569691475,
      "grad_norm": 0.19702288508415222,
      "learning_rate": 0.00019552139037433156,
      "loss": 0.5048,
      "step": 72
    },
    {
      "epoch": 0.07302053702603857,
      "grad_norm": 0.19738584756851196,
      "learning_rate": 0.00019545454545454548,
      "loss": 0.5023,
      "step": 73
    },
    {
      "epoch": 0.07402081835516239,
      "grad_norm": 0.19856902956962585,
      "learning_rate": 0.00019538770053475937,
      "loss": 0.5276,
      "step": 74
    },
    {
      "epoch": 0.0750210996842862,
      "grad_norm": 0.20378124713897705,
      "learning_rate": 0.00019532085561497326,
      "loss": 0.5242,
      "step": 75
    },
    {
      "epoch": 0.07602138101341002,
      "grad_norm": 0.20196989178657532,
      "learning_rate": 0.00019525401069518718,
      "loss": 0.5166,
      "step": 76
    },
    {
      "epoch": 0.07702166234253384,
      "grad_norm": 0.20090298354625702,
      "learning_rate": 0.00019518716577540107,
      "loss": 0.4882,
      "step": 77
    },
    {
      "epoch": 0.07802194367165766,
      "grad_norm": 0.2192114293575287,
      "learning_rate": 0.000195120320855615,
      "loss": 0.5271,
      "step": 78
    },
    {
      "epoch": 0.07902222500078147,
      "grad_norm": 0.20573462545871735,
      "learning_rate": 0.00019505347593582888,
      "loss": 0.5046,
      "step": 79
    },
    {
      "epoch": 0.08002250632990529,
      "grad_norm": 0.20574961602687836,
      "learning_rate": 0.0001949866310160428,
      "loss": 0.5249,
      "step": 80
    },
    {
      "epoch": 0.08102278765902911,
      "grad_norm": 0.20281346142292023,
      "learning_rate": 0.0001949197860962567,
      "loss": 0.4962,
      "step": 81
    },
    {
      "epoch": 0.08202306898815291,
      "grad_norm": 0.20971396565437317,
      "learning_rate": 0.0001948529411764706,
      "loss": 0.5017,
      "step": 82
    },
    {
      "epoch": 0.08302335031727673,
      "grad_norm": 0.19994156062602997,
      "learning_rate": 0.0001947860962566845,
      "loss": 0.506,
      "step": 83
    },
    {
      "epoch": 0.08402363164640055,
      "grad_norm": 0.20435181260108948,
      "learning_rate": 0.00019471925133689841,
      "loss": 0.5056,
      "step": 84
    },
    {
      "epoch": 0.08502391297552436,
      "grad_norm": 0.2137042135000229,
      "learning_rate": 0.0001946524064171123,
      "loss": 0.5002,
      "step": 85
    },
    {
      "epoch": 0.08602419430464818,
      "grad_norm": 0.20915071666240692,
      "learning_rate": 0.0001945855614973262,
      "loss": 0.4804,
      "step": 86
    },
    {
      "epoch": 0.087024475633772,
      "grad_norm": 0.21521854400634766,
      "learning_rate": 0.0001945187165775401,
      "loss": 0.5122,
      "step": 87
    },
    {
      "epoch": 0.08802475696289581,
      "grad_norm": 0.19778649508953094,
      "learning_rate": 0.00019445187165775403,
      "loss": 0.4902,
      "step": 88
    },
    {
      "epoch": 0.08902503829201963,
      "grad_norm": 0.2019186168909073,
      "learning_rate": 0.00019438502673796792,
      "loss": 0.5,
      "step": 89
    },
    {
      "epoch": 0.09002531962114345,
      "grad_norm": 0.2087041139602661,
      "learning_rate": 0.0001943181818181818,
      "loss": 0.4998,
      "step": 90
    },
    {
      "epoch": 0.09102560095026727,
      "grad_norm": 0.21541573107242584,
      "learning_rate": 0.00019425133689839573,
      "loss": 0.5051,
      "step": 91
    },
    {
      "epoch": 0.09202588227939108,
      "grad_norm": 0.21951743960380554,
      "learning_rate": 0.00019418449197860965,
      "loss": 0.4685,
      "step": 92
    },
    {
      "epoch": 0.0930261636085149,
      "grad_norm": 0.20836330950260162,
      "learning_rate": 0.00019411764705882354,
      "loss": 0.4959,
      "step": 93
    },
    {
      "epoch": 0.09402644493763872,
      "grad_norm": 0.21466359496116638,
      "learning_rate": 0.00019405080213903743,
      "loss": 0.5293,
      "step": 94
    },
    {
      "epoch": 0.09502672626676252,
      "grad_norm": 0.21750909090042114,
      "learning_rate": 0.00019398395721925135,
      "loss": 0.5136,
      "step": 95
    },
    {
      "epoch": 0.09602700759588634,
      "grad_norm": 0.21766193211078644,
      "learning_rate": 0.00019391711229946527,
      "loss": 0.5151,
      "step": 96
    },
    {
      "epoch": 0.09702728892501016,
      "grad_norm": 0.2209462821483612,
      "learning_rate": 0.00019385026737967916,
      "loss": 0.528,
      "step": 97
    },
    {
      "epoch": 0.09802757025413397,
      "grad_norm": 0.21020911633968353,
      "learning_rate": 0.00019378342245989305,
      "loss": 0.5149,
      "step": 98
    },
    {
      "epoch": 0.09902785158325779,
      "grad_norm": 0.1946028172969818,
      "learning_rate": 0.00019371657754010697,
      "loss": 0.473,
      "step": 99
    },
    {
      "epoch": 0.1000281329123816,
      "grad_norm": 0.22472387552261353,
      "learning_rate": 0.00019364973262032086,
      "loss": 0.4899,
      "step": 100
    },
    {
      "epoch": 0.10102841424150542,
      "grad_norm": 0.1953689157962799,
      "learning_rate": 0.00019358288770053477,
      "loss": 0.5106,
      "step": 101
    },
    {
      "epoch": 0.10202869557062924,
      "grad_norm": 0.19256751239299774,
      "learning_rate": 0.00019351604278074867,
      "loss": 0.501,
      "step": 102
    },
    {
      "epoch": 0.10302897689975306,
      "grad_norm": 0.2179025113582611,
      "learning_rate": 0.00019344919786096258,
      "loss": 0.4926,
      "step": 103
    },
    {
      "epoch": 0.10402925822887688,
      "grad_norm": 0.20246128737926483,
      "learning_rate": 0.00019338235294117647,
      "loss": 0.5008,
      "step": 104
    },
    {
      "epoch": 0.10502953955800069,
      "grad_norm": 0.20797042548656464,
      "learning_rate": 0.0001933155080213904,
      "loss": 0.5112,
      "step": 105
    },
    {
      "epoch": 0.10602982088712451,
      "grad_norm": 0.19968368113040924,
      "learning_rate": 0.00019324866310160428,
      "loss": 0.4929,
      "step": 106
    },
    {
      "epoch": 0.10703010221624833,
      "grad_norm": 0.18989552557468414,
      "learning_rate": 0.0001931818181818182,
      "loss": 0.5067,
      "step": 107
    },
    {
      "epoch": 0.10803038354537213,
      "grad_norm": 0.20914719998836517,
      "learning_rate": 0.0001931149732620321,
      "loss": 0.5264,
      "step": 108
    },
    {
      "epoch": 0.10903066487449595,
      "grad_norm": 0.20500510931015015,
      "learning_rate": 0.00019304812834224598,
      "loss": 0.4998,
      "step": 109
    },
    {
      "epoch": 0.11003094620361976,
      "grad_norm": 0.19594788551330566,
      "learning_rate": 0.0001929812834224599,
      "loss": 0.4878,
      "step": 110
    },
    {
      "epoch": 0.11103122753274358,
      "grad_norm": 0.21065524220466614,
      "learning_rate": 0.00019291443850267382,
      "loss": 0.484,
      "step": 111
    },
    {
      "epoch": 0.1120315088618674,
      "grad_norm": 0.22335033118724823,
      "learning_rate": 0.0001928475935828877,
      "loss": 0.4775,
      "step": 112
    },
    {
      "epoch": 0.11303179019099122,
      "grad_norm": 0.2162753939628601,
      "learning_rate": 0.0001927807486631016,
      "loss": 0.4855,
      "step": 113
    },
    {
      "epoch": 0.11403207152011503,
      "grad_norm": 0.20851221680641174,
      "learning_rate": 0.00019271390374331552,
      "loss": 0.4724,
      "step": 114
    },
    {
      "epoch": 0.11503235284923885,
      "grad_norm": 0.20359084010124207,
      "learning_rate": 0.00019264705882352944,
      "loss": 0.4734,
      "step": 115
    },
    {
      "epoch": 0.11603263417836267,
      "grad_norm": 0.2059461623430252,
      "learning_rate": 0.00019258021390374333,
      "loss": 0.4999,
      "step": 116
    },
    {
      "epoch": 0.11703291550748648,
      "grad_norm": 0.21397243440151215,
      "learning_rate": 0.00019251336898395722,
      "loss": 0.4867,
      "step": 117
    },
    {
      "epoch": 0.1180331968366103,
      "grad_norm": 0.19882655143737793,
      "learning_rate": 0.00019244652406417114,
      "loss": 0.489,
      "step": 118
    },
    {
      "epoch": 0.11903347816573412,
      "grad_norm": 0.2137971669435501,
      "learning_rate": 0.00019237967914438503,
      "loss": 0.5114,
      "step": 119
    },
    {
      "epoch": 0.12003375949485792,
      "grad_norm": 0.19666066765785217,
      "learning_rate": 0.00019231283422459894,
      "loss": 0.5161,
      "step": 120
    },
    {
      "epoch": 0.12103404082398174,
      "grad_norm": 0.196243017911911,
      "learning_rate": 0.00019224598930481283,
      "loss": 0.4726,
      "step": 121
    },
    {
      "epoch": 0.12203432215310556,
      "grad_norm": 0.2171701192855835,
      "learning_rate": 0.00019217914438502675,
      "loss": 0.4873,
      "step": 122
    },
    {
      "epoch": 0.12303460348222937,
      "grad_norm": 0.23819436132907867,
      "learning_rate": 0.00019211229946524064,
      "loss": 0.5001,
      "step": 123
    },
    {
      "epoch": 0.12403488481135319,
      "grad_norm": 0.21381929516792297,
      "learning_rate": 0.00019204545454545456,
      "loss": 0.5254,
      "step": 124
    },
    {
      "epoch": 0.12503516614047702,
      "grad_norm": 0.22323717176914215,
      "learning_rate": 0.00019197860962566845,
      "loss": 0.4833,
      "step": 125
    },
    {
      "epoch": 0.12603544746960083,
      "grad_norm": 0.24949876964092255,
      "learning_rate": 0.00019191176470588237,
      "loss": 0.464,
      "step": 126
    },
    {
      "epoch": 0.12703572879872463,
      "grad_norm": 0.22913573682308197,
      "learning_rate": 0.00019184491978609626,
      "loss": 0.4709,
      "step": 127
    },
    {
      "epoch": 0.12803601012784846,
      "grad_norm": 0.22805753350257874,
      "learning_rate": 0.00019177807486631015,
      "loss": 0.4668,
      "step": 128
    },
    {
      "epoch": 0.12903629145697226,
      "grad_norm": 0.21248556673526764,
      "learning_rate": 0.00019171122994652407,
      "loss": 0.4569,
      "step": 129
    },
    {
      "epoch": 0.1300365727860961,
      "grad_norm": 0.2261638045310974,
      "learning_rate": 0.000191644385026738,
      "loss": 0.5072,
      "step": 130
    },
    {
      "epoch": 0.1310368541152199,
      "grad_norm": 0.2184867113828659,
      "learning_rate": 0.00019157754010695188,
      "loss": 0.4696,
      "step": 131
    },
    {
      "epoch": 0.13203713544434373,
      "grad_norm": 0.24409937858581543,
      "learning_rate": 0.00019151069518716577,
      "loss": 0.4993,
      "step": 132
    },
    {
      "epoch": 0.13303741677346753,
      "grad_norm": 0.24065856635570526,
      "learning_rate": 0.0001914438502673797,
      "loss": 0.5051,
      "step": 133
    },
    {
      "epoch": 0.13403769810259136,
      "grad_norm": 0.21594908833503723,
      "learning_rate": 0.0001913770053475936,
      "loss": 0.5069,
      "step": 134
    },
    {
      "epoch": 0.13503797943171517,
      "grad_norm": 0.2586323022842407,
      "learning_rate": 0.0001913101604278075,
      "loss": 0.4628,
      "step": 135
    },
    {
      "epoch": 0.136038260760839,
      "grad_norm": 0.19704359769821167,
      "learning_rate": 0.0001912433155080214,
      "loss": 0.4882,
      "step": 136
    },
    {
      "epoch": 0.1370385420899628,
      "grad_norm": 0.21977023780345917,
      "learning_rate": 0.0001911764705882353,
      "loss": 0.4608,
      "step": 137
    },
    {
      "epoch": 0.13803882341908663,
      "grad_norm": 0.21616068482398987,
      "learning_rate": 0.00019110962566844922,
      "loss": 0.4787,
      "step": 138
    },
    {
      "epoch": 0.13903910474821043,
      "grad_norm": 0.1988924890756607,
      "learning_rate": 0.0001910427807486631,
      "loss": 0.4587,
      "step": 139
    },
    {
      "epoch": 0.14003938607733424,
      "grad_norm": 0.21710988879203796,
      "learning_rate": 0.000190975935828877,
      "loss": 0.4896,
      "step": 140
    },
    {
      "epoch": 0.14103966740645807,
      "grad_norm": 0.22208404541015625,
      "learning_rate": 0.00019090909090909092,
      "loss": 0.4707,
      "step": 141
    },
    {
      "epoch": 0.14203994873558187,
      "grad_norm": 0.2204628437757492,
      "learning_rate": 0.0001908422459893048,
      "loss": 0.4635,
      "step": 142
    },
    {
      "epoch": 0.1430402300647057,
      "grad_norm": 0.20738142728805542,
      "learning_rate": 0.00019077540106951873,
      "loss": 0.5214,
      "step": 143
    },
    {
      "epoch": 0.1440405113938295,
      "grad_norm": 0.1999579221010208,
      "learning_rate": 0.00019070855614973262,
      "loss": 0.4492,
      "step": 144
    },
    {
      "epoch": 0.14504079272295334,
      "grad_norm": 0.22410143911838531,
      "learning_rate": 0.00019064171122994654,
      "loss": 0.53,
      "step": 145
    },
    {
      "epoch": 0.14604107405207714,
      "grad_norm": 0.21512827277183533,
      "learning_rate": 0.00019057486631016043,
      "loss": 0.507,
      "step": 146
    },
    {
      "epoch": 0.14704135538120097,
      "grad_norm": 0.20054782927036285,
      "learning_rate": 0.00019050802139037435,
      "loss": 0.4672,
      "step": 147
    },
    {
      "epoch": 0.14804163671032478,
      "grad_norm": 0.21756675839424133,
      "learning_rate": 0.00019044117647058824,
      "loss": 0.4843,
      "step": 148
    },
    {
      "epoch": 0.1490419180394486,
      "grad_norm": 0.21544981002807617,
      "learning_rate": 0.00019037433155080216,
      "loss": 0.5066,
      "step": 149
    },
    {
      "epoch": 0.1500421993685724,
      "grad_norm": 0.18704143166542053,
      "learning_rate": 0.00019030748663101605,
      "loss": 0.4827,
      "step": 150
    },
    {
      "epoch": 0.15104248069769624,
      "grad_norm": 0.1997104436159134,
      "learning_rate": 0.00019024064171122994,
      "loss": 0.465,
      "step": 151
    },
    {
      "epoch": 0.15204276202682004,
      "grad_norm": 0.22799299657344818,
      "learning_rate": 0.00019017379679144388,
      "loss": 0.5247,
      "step": 152
    },
    {
      "epoch": 0.15304304335594385,
      "grad_norm": 0.20973342657089233,
      "learning_rate": 0.00019010695187165777,
      "loss": 0.4741,
      "step": 153
    },
    {
      "epoch": 0.15404332468506768,
      "grad_norm": 0.23998720943927765,
      "learning_rate": 0.00019004010695187167,
      "loss": 0.5005,
      "step": 154
    },
    {
      "epoch": 0.15504360601419148,
      "grad_norm": 0.21280887722969055,
      "learning_rate": 0.00018997326203208556,
      "loss": 0.5188,
      "step": 155
    },
    {
      "epoch": 0.1560438873433153,
      "grad_norm": 0.19993798434734344,
      "learning_rate": 0.00018990641711229947,
      "loss": 0.4769,
      "step": 156
    },
    {
      "epoch": 0.15704416867243912,
      "grad_norm": 0.21166694164276123,
      "learning_rate": 0.0001898395721925134,
      "loss": 0.4919,
      "step": 157
    },
    {
      "epoch": 0.15804445000156295,
      "grad_norm": 0.21865564584732056,
      "learning_rate": 0.00018977272727272728,
      "loss": 0.489,
      "step": 158
    },
    {
      "epoch": 0.15904473133068675,
      "grad_norm": 0.21564435958862305,
      "learning_rate": 0.00018970588235294117,
      "loss": 0.4827,
      "step": 159
    },
    {
      "epoch": 0.16004501265981058,
      "grad_norm": 0.2109832763671875,
      "learning_rate": 0.0001896390374331551,
      "loss": 0.4775,
      "step": 160
    },
    {
      "epoch": 0.16104529398893438,
      "grad_norm": 0.20275060832500458,
      "learning_rate": 0.000189572192513369,
      "loss": 0.4926,
      "step": 161
    },
    {
      "epoch": 0.16204557531805822,
      "grad_norm": 0.21038998663425446,
      "learning_rate": 0.0001895053475935829,
      "loss": 0.4966,
      "step": 162
    },
    {
      "epoch": 0.16304585664718202,
      "grad_norm": 0.19608058035373688,
      "learning_rate": 0.0001894385026737968,
      "loss": 0.4709,
      "step": 163
    },
    {
      "epoch": 0.16404613797630582,
      "grad_norm": 0.2212338000535965,
      "learning_rate": 0.0001893716577540107,
      "loss": 0.4776,
      "step": 164
    },
    {
      "epoch": 0.16504641930542965,
      "grad_norm": 0.18833835422992706,
      "learning_rate": 0.0001893048128342246,
      "loss": 0.4533,
      "step": 165
    },
    {
      "epoch": 0.16604670063455346,
      "grad_norm": 0.23317188024520874,
      "learning_rate": 0.00018923796791443852,
      "loss": 0.4628,
      "step": 166
    },
    {
      "epoch": 0.1670469819636773,
      "grad_norm": 0.25615590810775757,
      "learning_rate": 0.0001891711229946524,
      "loss": 0.4873,
      "step": 167
    },
    {
      "epoch": 0.1680472632928011,
      "grad_norm": 0.20285822451114655,
      "learning_rate": 0.00018910427807486633,
      "loss": 0.4651,
      "step": 168
    },
    {
      "epoch": 0.16904754462192492,
      "grad_norm": 0.23778009414672852,
      "learning_rate": 0.00018903743315508022,
      "loss": 0.5072,
      "step": 169
    },
    {
      "epoch": 0.17004782595104873,
      "grad_norm": 0.2112070620059967,
      "learning_rate": 0.00018897058823529413,
      "loss": 0.4691,
      "step": 170
    },
    {
      "epoch": 0.17104810728017256,
      "grad_norm": 0.1959972381591797,
      "learning_rate": 0.00018890374331550803,
      "loss": 0.4627,
      "step": 171
    },
    {
      "epoch": 0.17204838860929636,
      "grad_norm": 0.25435057282447815,
      "learning_rate": 0.00018883689839572194,
      "loss": 0.477,
      "step": 172
    },
    {
      "epoch": 0.1730486699384202,
      "grad_norm": 0.23073731362819672,
      "learning_rate": 0.00018877005347593583,
      "loss": 0.48,
      "step": 173
    },
    {
      "epoch": 0.174048951267544,
      "grad_norm": 0.20949392020702362,
      "learning_rate": 0.00018870320855614973,
      "loss": 0.51,
      "step": 174
    },
    {
      "epoch": 0.17504923259666783,
      "grad_norm": 0.1914493888616562,
      "learning_rate": 0.00018863636363636364,
      "loss": 0.4753,
      "step": 175
    },
    {
      "epoch": 0.17604951392579163,
      "grad_norm": 0.2131194770336151,
      "learning_rate": 0.00018856951871657756,
      "loss": 0.4591,
      "step": 176
    },
    {
      "epoch": 0.17704979525491543,
      "grad_norm": 0.21161939203739166,
      "learning_rate": 0.00018850267379679145,
      "loss": 0.4696,
      "step": 177
    },
    {
      "epoch": 0.17805007658403926,
      "grad_norm": 0.18965165317058563,
      "learning_rate": 0.00018843582887700534,
      "loss": 0.4693,
      "step": 178
    },
    {
      "epoch": 0.17905035791316307,
      "grad_norm": 0.20642141997814178,
      "learning_rate": 0.00018836898395721926,
      "loss": 0.4514,
      "step": 179
    },
    {
      "epoch": 0.1800506392422869,
      "grad_norm": 0.22816504538059235,
      "learning_rate": 0.00018830213903743318,
      "loss": 0.4511,
      "step": 180
    },
    {
      "epoch": 0.1810509205714107,
      "grad_norm": 0.21617086231708527,
      "learning_rate": 0.00018823529411764707,
      "loss": 0.4807,
      "step": 181
    },
    {
      "epoch": 0.18205120190053453,
      "grad_norm": 0.21177679300308228,
      "learning_rate": 0.00018816844919786096,
      "loss": 0.4838,
      "step": 182
    },
    {
      "epoch": 0.18305148322965833,
      "grad_norm": 0.21686269342899323,
      "learning_rate": 0.00018810160427807488,
      "loss": 0.465,
      "step": 183
    },
    {
      "epoch": 0.18405176455878217,
      "grad_norm": 0.23345594108104706,
      "learning_rate": 0.00018803475935828877,
      "loss": 0.5016,
      "step": 184
    },
    {
      "epoch": 0.18505204588790597,
      "grad_norm": 0.2194843292236328,
      "learning_rate": 0.0001879679144385027,
      "loss": 0.4563,
      "step": 185
    },
    {
      "epoch": 0.1860523272170298,
      "grad_norm": 0.22974108159542084,
      "learning_rate": 0.00018790106951871658,
      "loss": 0.462,
      "step": 186
    },
    {
      "epoch": 0.1870526085461536,
      "grad_norm": 0.206747367978096,
      "learning_rate": 0.0001878342245989305,
      "loss": 0.4669,
      "step": 187
    },
    {
      "epoch": 0.18805288987527743,
      "grad_norm": 0.20929698646068573,
      "learning_rate": 0.00018776737967914439,
      "loss": 0.4737,
      "step": 188
    },
    {
      "epoch": 0.18905317120440124,
      "grad_norm": 0.2103349268436432,
      "learning_rate": 0.0001877005347593583,
      "loss": 0.4673,
      "step": 189
    },
    {
      "epoch": 0.19005345253352504,
      "grad_norm": 0.19882595539093018,
      "learning_rate": 0.0001876336898395722,
      "loss": 0.4865,
      "step": 190
    },
    {
      "epoch": 0.19105373386264887,
      "grad_norm": 0.19479382038116455,
      "learning_rate": 0.0001875668449197861,
      "loss": 0.4791,
      "step": 191
    },
    {
      "epoch": 0.19205401519177268,
      "grad_norm": 0.1937156319618225,
      "learning_rate": 0.0001875,
      "loss": 0.4405,
      "step": 192
    },
    {
      "epoch": 0.1930542965208965,
      "grad_norm": 0.21606861054897308,
      "learning_rate": 0.0001874331550802139,
      "loss": 0.494,
      "step": 193
    },
    {
      "epoch": 0.1940545778500203,
      "grad_norm": 0.19409051537513733,
      "learning_rate": 0.00018736631016042784,
      "loss": 0.4702,
      "step": 194
    },
    {
      "epoch": 0.19505485917914414,
      "grad_norm": 0.20704405009746552,
      "learning_rate": 0.00018729946524064173,
      "loss": 0.4593,
      "step": 195
    },
    {
      "epoch": 0.19605514050826794,
      "grad_norm": 0.217378631234169,
      "learning_rate": 0.00018723262032085562,
      "loss": 0.4768,
      "step": 196
    },
    {
      "epoch": 0.19705542183739178,
      "grad_norm": 0.20588012039661407,
      "learning_rate": 0.0001871657754010695,
      "loss": 0.48,
      "step": 197
    },
    {
      "epoch": 0.19805570316651558,
      "grad_norm": 0.24118757247924805,
      "learning_rate": 0.00018709893048128343,
      "loss": 0.4831,
      "step": 198
    },
    {
      "epoch": 0.1990559844956394,
      "grad_norm": 0.1924232840538025,
      "learning_rate": 0.00018703208556149735,
      "loss": 0.4481,
      "step": 199
    },
    {
      "epoch": 0.2000562658247632,
      "grad_norm": 0.20931404829025269,
      "learning_rate": 0.00018696524064171124,
      "loss": 0.4609,
      "step": 200
    },
    {
      "epoch": 0.20105654715388704,
      "grad_norm": 0.24738754332065582,
      "learning_rate": 0.00018689839572192513,
      "loss": 0.4537,
      "step": 201
    },
    {
      "epoch": 0.20205682848301085,
      "grad_norm": 0.20447880029678345,
      "learning_rate": 0.00018683155080213905,
      "loss": 0.463,
      "step": 202
    },
    {
      "epoch": 0.20305710981213465,
      "grad_norm": 0.2098047137260437,
      "learning_rate": 0.00018676470588235297,
      "loss": 0.4576,
      "step": 203
    },
    {
      "epoch": 0.20405739114125848,
      "grad_norm": 0.24068988859653473,
      "learning_rate": 0.00018669786096256686,
      "loss": 0.4533,
      "step": 204
    },
    {
      "epoch": 0.20505767247038229,
      "grad_norm": 0.22675497829914093,
      "learning_rate": 0.00018663101604278075,
      "loss": 0.4559,
      "step": 205
    },
    {
      "epoch": 0.20605795379950612,
      "grad_norm": 0.2235925942659378,
      "learning_rate": 0.00018656417112299467,
      "loss": 0.4823,
      "step": 206
    },
    {
      "epoch": 0.20705823512862992,
      "grad_norm": 0.2981586456298828,
      "learning_rate": 0.00018649732620320856,
      "loss": 0.4811,
      "step": 207
    },
    {
      "epoch": 0.20805851645775375,
      "grad_norm": 0.20550698041915894,
      "learning_rate": 0.00018643048128342247,
      "loss": 0.4616,
      "step": 208
    },
    {
      "epoch": 0.20905879778687755,
      "grad_norm": 0.21166333556175232,
      "learning_rate": 0.00018636363636363636,
      "loss": 0.4347,
      "step": 209
    },
    {
      "epoch": 0.21005907911600138,
      "grad_norm": 0.22437241673469543,
      "learning_rate": 0.00018629679144385028,
      "loss": 0.5031,
      "step": 210
    },
    {
      "epoch": 0.2110593604451252,
      "grad_norm": 0.21663711965084076,
      "learning_rate": 0.00018622994652406417,
      "loss": 0.4691,
      "step": 211
    },
    {
      "epoch": 0.21205964177424902,
      "grad_norm": 0.19696949422359467,
      "learning_rate": 0.0001861631016042781,
      "loss": 0.4468,
      "step": 212
    },
    {
      "epoch": 0.21305992310337282,
      "grad_norm": 0.21785344183444977,
      "learning_rate": 0.000186096256684492,
      "loss": 0.4596,
      "step": 213
    },
    {
      "epoch": 0.21406020443249665,
      "grad_norm": 0.24945218861103058,
      "learning_rate": 0.0001860294117647059,
      "loss": 0.4458,
      "step": 214
    },
    {
      "epoch": 0.21506048576162046,
      "grad_norm": 0.20557279884815216,
      "learning_rate": 0.0001859625668449198,
      "loss": 0.4576,
      "step": 215
    },
    {
      "epoch": 0.21606076709074426,
      "grad_norm": 0.22893811762332916,
      "learning_rate": 0.00018589572192513368,
      "loss": 0.4733,
      "step": 216
    },
    {
      "epoch": 0.2170610484198681,
      "grad_norm": 0.27014100551605225,
      "learning_rate": 0.0001858288770053476,
      "loss": 0.4653,
      "step": 217
    },
    {
      "epoch": 0.2180613297489919,
      "grad_norm": 0.23531532287597656,
      "learning_rate": 0.00018576203208556152,
      "loss": 0.4818,
      "step": 218
    },
    {
      "epoch": 0.21906161107811573,
      "grad_norm": 0.21581542491912842,
      "learning_rate": 0.0001856951871657754,
      "loss": 0.4589,
      "step": 219
    },
    {
      "epoch": 0.22006189240723953,
      "grad_norm": 0.2680102288722992,
      "learning_rate": 0.0001856283422459893,
      "loss": 0.4436,
      "step": 220
    },
    {
      "epoch": 0.22106217373636336,
      "grad_norm": 0.20961466431617737,
      "learning_rate": 0.00018556149732620322,
      "loss": 0.4471,
      "step": 221
    },
    {
      "epoch": 0.22206245506548716,
      "grad_norm": 0.2168712168931961,
      "learning_rate": 0.00018549465240641713,
      "loss": 0.4771,
      "step": 222
    },
    {
      "epoch": 0.223062736394611,
      "grad_norm": 0.2143348902463913,
      "learning_rate": 0.00018542780748663103,
      "loss": 0.4697,
      "step": 223
    },
    {
      "epoch": 0.2240630177237348,
      "grad_norm": 0.2858351767063141,
      "learning_rate": 0.00018536096256684492,
      "loss": 0.4774,
      "step": 224
    },
    {
      "epoch": 0.22506329905285863,
      "grad_norm": 0.22455357015132904,
      "learning_rate": 0.00018529411764705883,
      "loss": 0.4606,
      "step": 225
    },
    {
      "epoch": 0.22606358038198243,
      "grad_norm": 0.2011498063802719,
      "learning_rate": 0.00018522727272727273,
      "loss": 0.4606,
      "step": 226
    },
    {
      "epoch": 0.22706386171110624,
      "grad_norm": 0.23670506477355957,
      "learning_rate": 0.00018516042780748664,
      "loss": 0.4879,
      "step": 227
    },
    {
      "epoch": 0.22806414304023007,
      "grad_norm": 0.21967220306396484,
      "learning_rate": 0.00018509358288770053,
      "loss": 0.4669,
      "step": 228
    },
    {
      "epoch": 0.22906442436935387,
      "grad_norm": 0.22620266675949097,
      "learning_rate": 0.00018502673796791445,
      "loss": 0.4372,
      "step": 229
    },
    {
      "epoch": 0.2300647056984777,
      "grad_norm": 0.21054047346115112,
      "learning_rate": 0.00018495989304812834,
      "loss": 0.4673,
      "step": 230
    },
    {
      "epoch": 0.2310649870276015,
      "grad_norm": 0.20464028418064117,
      "learning_rate": 0.00018489304812834226,
      "loss": 0.422,
      "step": 231
    },
    {
      "epoch": 0.23206526835672533,
      "grad_norm": 0.22431527078151703,
      "learning_rate": 0.00018482620320855615,
      "loss": 0.4628,
      "step": 232
    },
    {
      "epoch": 0.23306554968584914,
      "grad_norm": 0.22445067763328552,
      "learning_rate": 0.00018475935828877007,
      "loss": 0.4506,
      "step": 233
    },
    {
      "epoch": 0.23406583101497297,
      "grad_norm": 0.21331281960010529,
      "learning_rate": 0.00018469251336898396,
      "loss": 0.4683,
      "step": 234
    },
    {
      "epoch": 0.23506611234409677,
      "grad_norm": 0.21585595607757568,
      "learning_rate": 0.00018462566844919785,
      "loss": 0.4576,
      "step": 235
    },
    {
      "epoch": 0.2360663936732206,
      "grad_norm": 0.21789216995239258,
      "learning_rate": 0.0001845588235294118,
      "loss": 0.4551,
      "step": 236
    },
    {
      "epoch": 0.2370666750023444,
      "grad_norm": 0.21649007499217987,
      "learning_rate": 0.0001844919786096257,
      "loss": 0.4705,
      "step": 237
    },
    {
      "epoch": 0.23806695633146824,
      "grad_norm": 0.20883186161518097,
      "learning_rate": 0.00018442513368983958,
      "loss": 0.4834,
      "step": 238
    },
    {
      "epoch": 0.23906723766059204,
      "grad_norm": 0.2125503420829773,
      "learning_rate": 0.00018435828877005347,
      "loss": 0.4653,
      "step": 239
    },
    {
      "epoch": 0.24006751898971584,
      "grad_norm": 0.22874042391777039,
      "learning_rate": 0.00018429144385026739,
      "loss": 0.4716,
      "step": 240
    },
    {
      "epoch": 0.24106780031883968,
      "grad_norm": 0.20108987390995026,
      "learning_rate": 0.0001842245989304813,
      "loss": 0.4502,
      "step": 241
    },
    {
      "epoch": 0.24206808164796348,
      "grad_norm": 0.19356520473957062,
      "learning_rate": 0.0001841577540106952,
      "loss": 0.4643,
      "step": 242
    },
    {
      "epoch": 0.2430683629770873,
      "grad_norm": 0.19938474893569946,
      "learning_rate": 0.00018409090909090909,
      "loss": 0.4473,
      "step": 243
    },
    {
      "epoch": 0.2440686443062111,
      "grad_norm": 0.1998085379600525,
      "learning_rate": 0.000184024064171123,
      "loss": 0.4804,
      "step": 244
    },
    {
      "epoch": 0.24506892563533494,
      "grad_norm": 0.20477314293384552,
      "learning_rate": 0.00018395721925133692,
      "loss": 0.4505,
      "step": 245
    },
    {
      "epoch": 0.24606920696445875,
      "grad_norm": 0.20337258279323578,
      "learning_rate": 0.0001838903743315508,
      "loss": 0.4493,
      "step": 246
    },
    {
      "epoch": 0.24706948829358258,
      "grad_norm": 0.19538693130016327,
      "learning_rate": 0.0001838235294117647,
      "loss": 0.4256,
      "step": 247
    },
    {
      "epoch": 0.24806976962270638,
      "grad_norm": 0.21331952512264252,
      "learning_rate": 0.00018375668449197862,
      "loss": 0.4739,
      "step": 248
    },
    {
      "epoch": 0.2490700509518302,
      "grad_norm": 0.2261391133069992,
      "learning_rate": 0.0001836898395721925,
      "loss": 0.4691,
      "step": 249
    },
    {
      "epoch": 0.25007033228095404,
      "grad_norm": 0.20603296160697937,
      "learning_rate": 0.00018362299465240643,
      "loss": 0.4422,
      "step": 250
    },
    {
      "epoch": 0.2510706136100778,
      "grad_norm": 0.21565261483192444,
      "learning_rate": 0.00018355614973262032,
      "loss": 0.447,
      "step": 251
    },
    {
      "epoch": 0.25207089493920165,
      "grad_norm": 0.25159481167793274,
      "learning_rate": 0.00018348930481283424,
      "loss": 0.4559,
      "step": 252
    },
    {
      "epoch": 0.2530711762683255,
      "grad_norm": 0.2323637157678604,
      "learning_rate": 0.00018342245989304813,
      "loss": 0.4545,
      "step": 253
    },
    {
      "epoch": 0.25407145759744926,
      "grad_norm": 0.20947593450546265,
      "learning_rate": 0.00018335561497326205,
      "loss": 0.4559,
      "step": 254
    },
    {
      "epoch": 0.2550717389265731,
      "grad_norm": 0.2286469042301178,
      "learning_rate": 0.00018328877005347597,
      "loss": 0.4579,
      "step": 255
    },
    {
      "epoch": 0.2560720202556969,
      "grad_norm": 0.23576699197292328,
      "learning_rate": 0.00018322192513368986,
      "loss": 0.4616,
      "step": 256
    },
    {
      "epoch": 0.25707230158482075,
      "grad_norm": 0.19922293722629547,
      "learning_rate": 0.00018315508021390375,
      "loss": 0.4673,
      "step": 257
    },
    {
      "epoch": 0.2580725829139445,
      "grad_norm": 0.1969252973794937,
      "learning_rate": 0.00018308823529411764,
      "loss": 0.4592,
      "step": 258
    },
    {
      "epoch": 0.25907286424306836,
      "grad_norm": 0.2054707407951355,
      "learning_rate": 0.00018302139037433158,
      "loss": 0.4565,
      "step": 259
    },
    {
      "epoch": 0.2600731455721922,
      "grad_norm": 0.21610461175441742,
      "learning_rate": 0.00018295454545454547,
      "loss": 0.5014,
      "step": 260
    },
    {
      "epoch": 0.261073426901316,
      "grad_norm": 0.20420148968696594,
      "learning_rate": 0.00018288770053475936,
      "loss": 0.4535,
      "step": 261
    },
    {
      "epoch": 0.2620737082304398,
      "grad_norm": 0.21572546660900116,
      "learning_rate": 0.00018282085561497326,
      "loss": 0.435,
      "step": 262
    },
    {
      "epoch": 0.2630739895595636,
      "grad_norm": 0.21027761697769165,
      "learning_rate": 0.00018275401069518717,
      "loss": 0.4215,
      "step": 263
    },
    {
      "epoch": 0.26407427088868746,
      "grad_norm": 0.22838610410690308,
      "learning_rate": 0.0001826871657754011,
      "loss": 0.484,
      "step": 264
    },
    {
      "epoch": 0.26507455221781123,
      "grad_norm": 0.20097504556179047,
      "learning_rate": 0.00018262032085561498,
      "loss": 0.4684,
      "step": 265
    },
    {
      "epoch": 0.26607483354693506,
      "grad_norm": 0.19983471930027008,
      "learning_rate": 0.00018255347593582887,
      "loss": 0.4534,
      "step": 266
    },
    {
      "epoch": 0.2670751148760589,
      "grad_norm": 0.24224251508712769,
      "learning_rate": 0.0001824866310160428,
      "loss": 0.4552,
      "step": 267
    },
    {
      "epoch": 0.2680753962051827,
      "grad_norm": 0.1931663602590561,
      "learning_rate": 0.0001824197860962567,
      "loss": 0.4234,
      "step": 268
    },
    {
      "epoch": 0.2690756775343065,
      "grad_norm": 0.2011386901140213,
      "learning_rate": 0.0001823529411764706,
      "loss": 0.4587,
      "step": 269
    },
    {
      "epoch": 0.27007595886343033,
      "grad_norm": 0.1986941248178482,
      "learning_rate": 0.0001822860962566845,
      "loss": 0.4392,
      "step": 270
    },
    {
      "epoch": 0.27107624019255416,
      "grad_norm": 0.2052927017211914,
      "learning_rate": 0.0001822192513368984,
      "loss": 0.4356,
      "step": 271
    },
    {
      "epoch": 0.272076521521678,
      "grad_norm": 0.19200514256954193,
      "learning_rate": 0.0001821524064171123,
      "loss": 0.4549,
      "step": 272
    },
    {
      "epoch": 0.27307680285080177,
      "grad_norm": 0.21522852778434753,
      "learning_rate": 0.00018208556149732622,
      "loss": 0.4643,
      "step": 273
    },
    {
      "epoch": 0.2740770841799256,
      "grad_norm": 0.20202524960041046,
      "learning_rate": 0.0001820187165775401,
      "loss": 0.4507,
      "step": 274
    },
    {
      "epoch": 0.27507736550904943,
      "grad_norm": 0.21286173164844513,
      "learning_rate": 0.00018195187165775403,
      "loss": 0.4599,
      "step": 275
    },
    {
      "epoch": 0.27607764683817326,
      "grad_norm": 0.20431484282016754,
      "learning_rate": 0.00018188502673796792,
      "loss": 0.4495,
      "step": 276
    },
    {
      "epoch": 0.27707792816729704,
      "grad_norm": 0.19780275225639343,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.4789,
      "step": 277
    },
    {
      "epoch": 0.27807820949642087,
      "grad_norm": 0.20637333393096924,
      "learning_rate": 0.00018175133689839575,
      "loss": 0.4481,
      "step": 278
    },
    {
      "epoch": 0.2790784908255447,
      "grad_norm": 0.23893123865127563,
      "learning_rate": 0.00018168449197860964,
      "loss": 0.458,
      "step": 279
    },
    {
      "epoch": 0.2800787721546685,
      "grad_norm": 0.20642457902431488,
      "learning_rate": 0.00018161764705882353,
      "loss": 0.4389,
      "step": 280
    },
    {
      "epoch": 0.2810790534837923,
      "grad_norm": 0.19222602248191833,
      "learning_rate": 0.00018155080213903742,
      "loss": 0.4788,
      "step": 281
    },
    {
      "epoch": 0.28207933481291614,
      "grad_norm": 0.20974920690059662,
      "learning_rate": 0.00018148395721925134,
      "loss": 0.4692,
      "step": 282
    },
    {
      "epoch": 0.28307961614203997,
      "grad_norm": 0.20171569287776947,
      "learning_rate": 0.00018141711229946526,
      "loss": 0.4775,
      "step": 283
    },
    {
      "epoch": 0.28407989747116374,
      "grad_norm": 0.20043973624706268,
      "learning_rate": 0.00018135026737967915,
      "loss": 0.4716,
      "step": 284
    },
    {
      "epoch": 0.2850801788002876,
      "grad_norm": 0.18762481212615967,
      "learning_rate": 0.00018128342245989304,
      "loss": 0.4401,
      "step": 285
    },
    {
      "epoch": 0.2860804601294114,
      "grad_norm": 0.19664841890335083,
      "learning_rate": 0.00018121657754010696,
      "loss": 0.4643,
      "step": 286
    },
    {
      "epoch": 0.28708074145853524,
      "grad_norm": 0.20689429342746735,
      "learning_rate": 0.00018114973262032088,
      "loss": 0.4616,
      "step": 287
    },
    {
      "epoch": 0.288081022787659,
      "grad_norm": 0.20396773517131805,
      "learning_rate": 0.00018108288770053477,
      "loss": 0.4675,
      "step": 288
    },
    {
      "epoch": 0.28908130411678284,
      "grad_norm": 0.20289234817028046,
      "learning_rate": 0.00018101604278074866,
      "loss": 0.4569,
      "step": 289
    },
    {
      "epoch": 0.2900815854459067,
      "grad_norm": 0.19374632835388184,
      "learning_rate": 0.00018094919786096258,
      "loss": 0.4434,
      "step": 290
    },
    {
      "epoch": 0.29108186677503045,
      "grad_norm": 0.192635178565979,
      "learning_rate": 0.00018088235294117647,
      "loss": 0.4327,
      "step": 291
    },
    {
      "epoch": 0.2920821481041543,
      "grad_norm": 0.20430588722229004,
      "learning_rate": 0.00018081550802139039,
      "loss": 0.4477,
      "step": 292
    },
    {
      "epoch": 0.2930824294332781,
      "grad_norm": 0.19839076697826385,
      "learning_rate": 0.00018074866310160428,
      "loss": 0.4511,
      "step": 293
    },
    {
      "epoch": 0.29408271076240194,
      "grad_norm": 0.20053929090499878,
      "learning_rate": 0.0001806818181818182,
      "loss": 0.4721,
      "step": 294
    },
    {
      "epoch": 0.2950829920915257,
      "grad_norm": 0.1941109150648117,
      "learning_rate": 0.00018061497326203209,
      "loss": 0.44,
      "step": 295
    },
    {
      "epoch": 0.29608327342064955,
      "grad_norm": 0.2062315046787262,
      "learning_rate": 0.000180548128342246,
      "loss": 0.4503,
      "step": 296
    },
    {
      "epoch": 0.2970835547497734,
      "grad_norm": 0.1936188042163849,
      "learning_rate": 0.00018048128342245992,
      "loss": 0.4505,
      "step": 297
    },
    {
      "epoch": 0.2980838360788972,
      "grad_norm": 0.20228715240955353,
      "learning_rate": 0.0001804144385026738,
      "loss": 0.4648,
      "step": 298
    },
    {
      "epoch": 0.299084117408021,
      "grad_norm": 0.19537727534770966,
      "learning_rate": 0.0001803475935828877,
      "loss": 0.4266,
      "step": 299
    },
    {
      "epoch": 0.3000843987371448,
      "grad_norm": 0.20438359677791595,
      "learning_rate": 0.0001802807486631016,
      "loss": 0.4758,
      "step": 300
    },
    {
      "epoch": 0.30108468006626865,
      "grad_norm": 0.19648802280426025,
      "learning_rate": 0.00018021390374331554,
      "loss": 0.4658,
      "step": 301
    },
    {
      "epoch": 0.3020849613953925,
      "grad_norm": 0.2045028954744339,
      "learning_rate": 0.00018014705882352943,
      "loss": 0.4667,
      "step": 302
    },
    {
      "epoch": 0.30308524272451626,
      "grad_norm": 0.20261909067630768,
      "learning_rate": 0.00018008021390374332,
      "loss": 0.4754,
      "step": 303
    },
    {
      "epoch": 0.3040855240536401,
      "grad_norm": 0.1957172006368637,
      "learning_rate": 0.0001800133689839572,
      "loss": 0.4281,
      "step": 304
    },
    {
      "epoch": 0.3050858053827639,
      "grad_norm": 0.1988499015569687,
      "learning_rate": 0.00017994652406417113,
      "loss": 0.4499,
      "step": 305
    },
    {
      "epoch": 0.3060860867118877,
      "grad_norm": 0.21877305209636688,
      "learning_rate": 0.00017987967914438505,
      "loss": 0.4589,
      "step": 306
    },
    {
      "epoch": 0.3070863680410115,
      "grad_norm": 0.20068047940731049,
      "learning_rate": 0.00017981283422459894,
      "loss": 0.4408,
      "step": 307
    },
    {
      "epoch": 0.30808664937013536,
      "grad_norm": 0.19758211076259613,
      "learning_rate": 0.00017974598930481283,
      "loss": 0.44,
      "step": 308
    },
    {
      "epoch": 0.3090869306992592,
      "grad_norm": 0.1863931119441986,
      "learning_rate": 0.00017967914438502675,
      "loss": 0.4226,
      "step": 309
    },
    {
      "epoch": 0.31008721202838296,
      "grad_norm": 0.19496728479862213,
      "learning_rate": 0.00017961229946524066,
      "loss": 0.4329,
      "step": 310
    },
    {
      "epoch": 0.3110874933575068,
      "grad_norm": 0.1997639387845993,
      "learning_rate": 0.00017954545454545456,
      "loss": 0.4278,
      "step": 311
    },
    {
      "epoch": 0.3120877746866306,
      "grad_norm": 0.19241994619369507,
      "learning_rate": 0.00017947860962566845,
      "loss": 0.436,
      "step": 312
    },
    {
      "epoch": 0.31308805601575446,
      "grad_norm": 0.20237933099269867,
      "learning_rate": 0.00017941176470588236,
      "loss": 0.4585,
      "step": 313
    },
    {
      "epoch": 0.31408833734487823,
      "grad_norm": 0.19401943683624268,
      "learning_rate": 0.00017934491978609626,
      "loss": 0.4154,
      "step": 314
    },
    {
      "epoch": 0.31508861867400206,
      "grad_norm": 0.19622983038425446,
      "learning_rate": 0.00017927807486631017,
      "loss": 0.4281,
      "step": 315
    },
    {
      "epoch": 0.3160889000031259,
      "grad_norm": 0.20018912851810455,
      "learning_rate": 0.00017921122994652406,
      "loss": 0.449,
      "step": 316
    },
    {
      "epoch": 0.31708918133224967,
      "grad_norm": 0.1948523223400116,
      "learning_rate": 0.00017914438502673798,
      "loss": 0.4558,
      "step": 317
    },
    {
      "epoch": 0.3180894626613735,
      "grad_norm": 0.20339010655879974,
      "learning_rate": 0.00017907754010695187,
      "loss": 0.466,
      "step": 318
    },
    {
      "epoch": 0.31908974399049733,
      "grad_norm": 0.21605317294597626,
      "learning_rate": 0.0001790106951871658,
      "loss": 0.4337,
      "step": 319
    },
    {
      "epoch": 0.32009002531962116,
      "grad_norm": 0.2383742332458496,
      "learning_rate": 0.0001789438502673797,
      "loss": 0.4387,
      "step": 320
    },
    {
      "epoch": 0.32109030664874494,
      "grad_norm": 0.18646642565727234,
      "learning_rate": 0.0001788770053475936,
      "loss": 0.432,
      "step": 321
    },
    {
      "epoch": 0.32209058797786877,
      "grad_norm": 0.22923484444618225,
      "learning_rate": 0.0001788101604278075,
      "loss": 0.4571,
      "step": 322
    },
    {
      "epoch": 0.3230908693069926,
      "grad_norm": 0.26247844099998474,
      "learning_rate": 0.00017874331550802138,
      "loss": 0.4504,
      "step": 323
    },
    {
      "epoch": 0.32409115063611643,
      "grad_norm": 0.19713173806667328,
      "learning_rate": 0.0001786764705882353,
      "loss": 0.4287,
      "step": 324
    },
    {
      "epoch": 0.3250914319652402,
      "grad_norm": 0.21668241918087006,
      "learning_rate": 0.00017860962566844922,
      "loss": 0.4296,
      "step": 325
    },
    {
      "epoch": 0.32609171329436404,
      "grad_norm": 0.20121659338474274,
      "learning_rate": 0.0001785427807486631,
      "loss": 0.406,
      "step": 326
    },
    {
      "epoch": 0.32709199462348787,
      "grad_norm": 0.20360606908798218,
      "learning_rate": 0.000178475935828877,
      "loss": 0.4709,
      "step": 327
    },
    {
      "epoch": 0.32809227595261165,
      "grad_norm": 0.186946302652359,
      "learning_rate": 0.00017840909090909092,
      "loss": 0.4453,
      "step": 328
    },
    {
      "epoch": 0.3290925572817355,
      "grad_norm": 0.19845984876155853,
      "learning_rate": 0.00017834224598930483,
      "loss": 0.4315,
      "step": 329
    },
    {
      "epoch": 0.3300928386108593,
      "grad_norm": 0.20962293446063995,
      "learning_rate": 0.00017827540106951872,
      "loss": 0.428,
      "step": 330
    },
    {
      "epoch": 0.33109311993998314,
      "grad_norm": 0.22066234052181244,
      "learning_rate": 0.00017820855614973262,
      "loss": 0.4644,
      "step": 331
    },
    {
      "epoch": 0.3320934012691069,
      "grad_norm": 0.20558877289295197,
      "learning_rate": 0.00017814171122994653,
      "loss": 0.4694,
      "step": 332
    },
    {
      "epoch": 0.33309368259823074,
      "grad_norm": 0.200545072555542,
      "learning_rate": 0.00017807486631016042,
      "loss": 0.4387,
      "step": 333
    },
    {
      "epoch": 0.3340939639273546,
      "grad_norm": 0.1972920447587967,
      "learning_rate": 0.00017800802139037434,
      "loss": 0.4648,
      "step": 334
    },
    {
      "epoch": 0.3350942452564784,
      "grad_norm": 0.21249648928642273,
      "learning_rate": 0.00017794117647058823,
      "loss": 0.4638,
      "step": 335
    },
    {
      "epoch": 0.3360945265856022,
      "grad_norm": 0.2013329118490219,
      "learning_rate": 0.00017787433155080215,
      "loss": 0.4138,
      "step": 336
    },
    {
      "epoch": 0.337094807914726,
      "grad_norm": 0.21043537557125092,
      "learning_rate": 0.00017780748663101604,
      "loss": 0.4578,
      "step": 337
    },
    {
      "epoch": 0.33809508924384984,
      "grad_norm": 0.2100977599620819,
      "learning_rate": 0.00017774064171122996,
      "loss": 0.4286,
      "step": 338
    },
    {
      "epoch": 0.3390953705729737,
      "grad_norm": 0.2018621563911438,
      "learning_rate": 0.00017767379679144388,
      "loss": 0.4644,
      "step": 339
    },
    {
      "epoch": 0.34009565190209745,
      "grad_norm": 0.20157957077026367,
      "learning_rate": 0.00017760695187165777,
      "loss": 0.4514,
      "step": 340
    },
    {
      "epoch": 0.3410959332312213,
      "grad_norm": 0.20610134303569794,
      "learning_rate": 0.00017754010695187166,
      "loss": 0.457,
      "step": 341
    },
    {
      "epoch": 0.3420962145603451,
      "grad_norm": 0.2001752108335495,
      "learning_rate": 0.00017747326203208555,
      "loss": 0.4417,
      "step": 342
    },
    {
      "epoch": 0.3430964958894689,
      "grad_norm": 0.19040009379386902,
      "learning_rate": 0.0001774064171122995,
      "loss": 0.4564,
      "step": 343
    },
    {
      "epoch": 0.3440967772185927,
      "grad_norm": 0.20176361501216888,
      "learning_rate": 0.00017733957219251339,
      "loss": 0.4767,
      "step": 344
    },
    {
      "epoch": 0.34509705854771655,
      "grad_norm": 0.21339115500450134,
      "learning_rate": 0.00017727272727272728,
      "loss": 0.4668,
      "step": 345
    },
    {
      "epoch": 0.3460973398768404,
      "grad_norm": 0.19743414223194122,
      "learning_rate": 0.00017720588235294117,
      "loss": 0.4347,
      "step": 346
    },
    {
      "epoch": 0.34709762120596416,
      "grad_norm": 0.20072850584983826,
      "learning_rate": 0.00017713903743315509,
      "loss": 0.4467,
      "step": 347
    },
    {
      "epoch": 0.348097902535088,
      "grad_norm": 0.2034348100423813,
      "learning_rate": 0.000177072192513369,
      "loss": 0.4524,
      "step": 348
    },
    {
      "epoch": 0.3490981838642118,
      "grad_norm": 0.1817757487297058,
      "learning_rate": 0.0001770053475935829,
      "loss": 0.4441,
      "step": 349
    },
    {
      "epoch": 0.35009846519333565,
      "grad_norm": 0.1905452013015747,
      "learning_rate": 0.00017693850267379679,
      "loss": 0.4411,
      "step": 350
    },
    {
      "epoch": 0.3510987465224594,
      "grad_norm": 0.19815921783447266,
      "learning_rate": 0.0001768716577540107,
      "loss": 0.4238,
      "step": 351
    },
    {
      "epoch": 0.35209902785158326,
      "grad_norm": 0.1945020854473114,
      "learning_rate": 0.00017680481283422462,
      "loss": 0.4379,
      "step": 352
    },
    {
      "epoch": 0.3530993091807071,
      "grad_norm": 0.22662867605686188,
      "learning_rate": 0.0001767379679144385,
      "loss": 0.4559,
      "step": 353
    },
    {
      "epoch": 0.35409959050983086,
      "grad_norm": 0.20507457852363586,
      "learning_rate": 0.0001766711229946524,
      "loss": 0.4405,
      "step": 354
    },
    {
      "epoch": 0.3550998718389547,
      "grad_norm": 0.1996375322341919,
      "learning_rate": 0.00017660427807486632,
      "loss": 0.4555,
      "step": 355
    },
    {
      "epoch": 0.3561001531680785,
      "grad_norm": 0.1919354647397995,
      "learning_rate": 0.0001765374331550802,
      "loss": 0.4469,
      "step": 356
    },
    {
      "epoch": 0.35710043449720236,
      "grad_norm": 0.19229656457901,
      "learning_rate": 0.00017647058823529413,
      "loss": 0.4481,
      "step": 357
    },
    {
      "epoch": 0.35810071582632613,
      "grad_norm": 0.20606432855129242,
      "learning_rate": 0.00017640374331550802,
      "loss": 0.4317,
      "step": 358
    },
    {
      "epoch": 0.35910099715544996,
      "grad_norm": 0.1877400130033493,
      "learning_rate": 0.00017633689839572194,
      "loss": 0.4258,
      "step": 359
    },
    {
      "epoch": 0.3601012784845738,
      "grad_norm": 0.19377875328063965,
      "learning_rate": 0.00017627005347593583,
      "loss": 0.425,
      "step": 360
    },
    {
      "epoch": 0.3611015598136976,
      "grad_norm": 0.1965295821428299,
      "learning_rate": 0.00017620320855614975,
      "loss": 0.4436,
      "step": 361
    },
    {
      "epoch": 0.3621018411428214,
      "grad_norm": 0.20384399592876434,
      "learning_rate": 0.00017613636363636366,
      "loss": 0.4456,
      "step": 362
    },
    {
      "epoch": 0.36310212247194523,
      "grad_norm": 0.19872906804084778,
      "learning_rate": 0.00017606951871657756,
      "loss": 0.4594,
      "step": 363
    },
    {
      "epoch": 0.36410240380106906,
      "grad_norm": 0.19736897945404053,
      "learning_rate": 0.00017600267379679145,
      "loss": 0.4517,
      "step": 364
    },
    {
      "epoch": 0.3651026851301929,
      "grad_norm": 0.19544851779937744,
      "learning_rate": 0.00017593582887700534,
      "loss": 0.461,
      "step": 365
    },
    {
      "epoch": 0.36610296645931667,
      "grad_norm": 0.1946212351322174,
      "learning_rate": 0.00017586898395721928,
      "loss": 0.4644,
      "step": 366
    },
    {
      "epoch": 0.3671032477884405,
      "grad_norm": 0.1895807534456253,
      "learning_rate": 0.00017580213903743317,
      "loss": 0.4299,
      "step": 367
    },
    {
      "epoch": 0.36810352911756433,
      "grad_norm": 0.21577860414981842,
      "learning_rate": 0.00017573529411764706,
      "loss": 0.4608,
      "step": 368
    },
    {
      "epoch": 0.3691038104466881,
      "grad_norm": 0.20062130689620972,
      "learning_rate": 0.00017566844919786095,
      "loss": 0.4384,
      "step": 369
    },
    {
      "epoch": 0.37010409177581194,
      "grad_norm": 0.18972885608673096,
      "learning_rate": 0.00017560160427807487,
      "loss": 0.4584,
      "step": 370
    },
    {
      "epoch": 0.37110437310493577,
      "grad_norm": 0.20864245295524597,
      "learning_rate": 0.0001755347593582888,
      "loss": 0.4299,
      "step": 371
    },
    {
      "epoch": 0.3721046544340596,
      "grad_norm": 0.19813786447048187,
      "learning_rate": 0.00017546791443850268,
      "loss": 0.4401,
      "step": 372
    },
    {
      "epoch": 0.3731049357631834,
      "grad_norm": 0.20077542960643768,
      "learning_rate": 0.00017540106951871657,
      "loss": 0.4341,
      "step": 373
    },
    {
      "epoch": 0.3741052170923072,
      "grad_norm": 0.2071409523487091,
      "learning_rate": 0.0001753342245989305,
      "loss": 0.4538,
      "step": 374
    },
    {
      "epoch": 0.37510549842143104,
      "grad_norm": 0.19045141339302063,
      "learning_rate": 0.0001752673796791444,
      "loss": 0.4327,
      "step": 375
    },
    {
      "epoch": 0.37610577975055487,
      "grad_norm": 0.1896904855966568,
      "learning_rate": 0.0001752005347593583,
      "loss": 0.4315,
      "step": 376
    },
    {
      "epoch": 0.37710606107967864,
      "grad_norm": 0.19843891263008118,
      "learning_rate": 0.0001751336898395722,
      "loss": 0.454,
      "step": 377
    },
    {
      "epoch": 0.3781063424088025,
      "grad_norm": 0.21727845072746277,
      "learning_rate": 0.0001750668449197861,
      "loss": 0.4627,
      "step": 378
    },
    {
      "epoch": 0.3791066237379263,
      "grad_norm": 0.20218057930469513,
      "learning_rate": 0.000175,
      "loss": 0.4557,
      "step": 379
    },
    {
      "epoch": 0.3801069050670501,
      "grad_norm": 0.21106897294521332,
      "learning_rate": 0.00017493315508021392,
      "loss": 0.4563,
      "step": 380
    },
    {
      "epoch": 0.3811071863961739,
      "grad_norm": 0.20151540637016296,
      "learning_rate": 0.00017486631016042783,
      "loss": 0.4173,
      "step": 381
    },
    {
      "epoch": 0.38210746772529774,
      "grad_norm": 0.19393794238567352,
      "learning_rate": 0.00017479946524064172,
      "loss": 0.4446,
      "step": 382
    },
    {
      "epoch": 0.3831077490544216,
      "grad_norm": 0.1857215315103531,
      "learning_rate": 0.00017473262032085562,
      "loss": 0.412,
      "step": 383
    },
    {
      "epoch": 0.38410803038354535,
      "grad_norm": 0.18503254652023315,
      "learning_rate": 0.00017466577540106953,
      "loss": 0.4212,
      "step": 384
    },
    {
      "epoch": 0.3851083117126692,
      "grad_norm": 0.2113349288702011,
      "learning_rate": 0.00017459893048128345,
      "loss": 0.4844,
      "step": 385
    },
    {
      "epoch": 0.386108593041793,
      "grad_norm": 0.2114599198102951,
      "learning_rate": 0.00017453208556149734,
      "loss": 0.443,
      "step": 386
    },
    {
      "epoch": 0.38710887437091684,
      "grad_norm": 0.19072553515434265,
      "learning_rate": 0.00017446524064171123,
      "loss": 0.4271,
      "step": 387
    },
    {
      "epoch": 0.3881091557000406,
      "grad_norm": 0.2044278234243393,
      "learning_rate": 0.00017439839572192512,
      "loss": 0.4615,
      "step": 388
    },
    {
      "epoch": 0.38910943702916445,
      "grad_norm": 0.18271374702453613,
      "learning_rate": 0.00017433155080213904,
      "loss": 0.4082,
      "step": 389
    },
    {
      "epoch": 0.3901097183582883,
      "grad_norm": 0.19570492208003998,
      "learning_rate": 0.00017426470588235296,
      "loss": 0.4219,
      "step": 390
    },
    {
      "epoch": 0.39110999968741206,
      "grad_norm": 0.2105991542339325,
      "learning_rate": 0.00017419786096256685,
      "loss": 0.4296,
      "step": 391
    },
    {
      "epoch": 0.3921102810165359,
      "grad_norm": 0.20995327830314636,
      "learning_rate": 0.00017413101604278074,
      "loss": 0.4143,
      "step": 392
    },
    {
      "epoch": 0.3931105623456597,
      "grad_norm": 0.19862137734889984,
      "learning_rate": 0.00017406417112299466,
      "loss": 0.4464,
      "step": 393
    },
    {
      "epoch": 0.39411084367478355,
      "grad_norm": 0.22153382003307343,
      "learning_rate": 0.00017399732620320858,
      "loss": 0.4545,
      "step": 394
    },
    {
      "epoch": 0.3951111250039073,
      "grad_norm": 0.1986101269721985,
      "learning_rate": 0.00017393048128342247,
      "loss": 0.4509,
      "step": 395
    },
    {
      "epoch": 0.39611140633303116,
      "grad_norm": 0.21011565625667572,
      "learning_rate": 0.00017386363636363636,
      "loss": 0.4736,
      "step": 396
    },
    {
      "epoch": 0.397111687662155,
      "grad_norm": 0.21717001497745514,
      "learning_rate": 0.00017379679144385028,
      "loss": 0.4297,
      "step": 397
    },
    {
      "epoch": 0.3981119689912788,
      "grad_norm": 0.22421622276306152,
      "learning_rate": 0.00017372994652406417,
      "loss": 0.4431,
      "step": 398
    },
    {
      "epoch": 0.3991122503204026,
      "grad_norm": 0.2027975171804428,
      "learning_rate": 0.00017366310160427809,
      "loss": 0.4203,
      "step": 399
    },
    {
      "epoch": 0.4001125316495264,
      "grad_norm": 0.20555441081523895,
      "learning_rate": 0.000173596256684492,
      "loss": 0.4598,
      "step": 400
    },
    {
      "epoch": 0.40111281297865026,
      "grad_norm": 0.22629684209823608,
      "learning_rate": 0.0001735294117647059,
      "loss": 0.4313,
      "step": 401
    },
    {
      "epoch": 0.4021130943077741,
      "grad_norm": 0.2036045342683792,
      "learning_rate": 0.00017346256684491979,
      "loss": 0.4238,
      "step": 402
    },
    {
      "epoch": 0.40311337563689786,
      "grad_norm": 0.1986338496208191,
      "learning_rate": 0.0001733957219251337,
      "loss": 0.4667,
      "step": 403
    },
    {
      "epoch": 0.4041136569660217,
      "grad_norm": 0.20238147675991058,
      "learning_rate": 0.00017332887700534762,
      "loss": 0.4644,
      "step": 404
    },
    {
      "epoch": 0.4051139382951455,
      "grad_norm": 0.2047211080789566,
      "learning_rate": 0.0001732620320855615,
      "loss": 0.4602,
      "step": 405
    },
    {
      "epoch": 0.4061142196242693,
      "grad_norm": 0.20934055745601654,
      "learning_rate": 0.0001731951871657754,
      "loss": 0.4604,
      "step": 406
    },
    {
      "epoch": 0.40711450095339313,
      "grad_norm": 0.19956743717193604,
      "learning_rate": 0.0001731283422459893,
      "loss": 0.4551,
      "step": 407
    },
    {
      "epoch": 0.40811478228251696,
      "grad_norm": 0.1878136545419693,
      "learning_rate": 0.00017306149732620324,
      "loss": 0.4267,
      "step": 408
    },
    {
      "epoch": 0.4091150636116408,
      "grad_norm": 0.1995856761932373,
      "learning_rate": 0.00017299465240641713,
      "loss": 0.4143,
      "step": 409
    },
    {
      "epoch": 0.41011534494076457,
      "grad_norm": 0.20933692157268524,
      "learning_rate": 0.00017292780748663102,
      "loss": 0.4472,
      "step": 410
    },
    {
      "epoch": 0.4111156262698884,
      "grad_norm": 0.2135707288980484,
      "learning_rate": 0.0001728609625668449,
      "loss": 0.4438,
      "step": 411
    },
    {
      "epoch": 0.41211590759901223,
      "grad_norm": 0.2189939320087433,
      "learning_rate": 0.00017279411764705883,
      "loss": 0.4628,
      "step": 412
    },
    {
      "epoch": 0.41311618892813606,
      "grad_norm": 0.24030010402202606,
      "learning_rate": 0.00017272727272727275,
      "loss": 0.4258,
      "step": 413
    },
    {
      "epoch": 0.41411647025725984,
      "grad_norm": 0.1955292671918869,
      "learning_rate": 0.00017266042780748664,
      "loss": 0.4383,
      "step": 414
    },
    {
      "epoch": 0.41511675158638367,
      "grad_norm": 0.19749368727207184,
      "learning_rate": 0.00017259358288770053,
      "loss": 0.4413,
      "step": 415
    },
    {
      "epoch": 0.4161170329155075,
      "grad_norm": 0.2370544672012329,
      "learning_rate": 0.00017252673796791445,
      "loss": 0.4567,
      "step": 416
    },
    {
      "epoch": 0.4171173142446313,
      "grad_norm": 0.2258642166852951,
      "learning_rate": 0.00017245989304812836,
      "loss": 0.4452,
      "step": 417
    },
    {
      "epoch": 0.4181175955737551,
      "grad_norm": 0.19117842614650726,
      "learning_rate": 0.00017239304812834225,
      "loss": 0.4109,
      "step": 418
    },
    {
      "epoch": 0.41911787690287894,
      "grad_norm": 0.2136865109205246,
      "learning_rate": 0.00017232620320855615,
      "loss": 0.4724,
      "step": 419
    },
    {
      "epoch": 0.42011815823200277,
      "grad_norm": 0.2001347690820694,
      "learning_rate": 0.00017225935828877006,
      "loss": 0.4294,
      "step": 420
    },
    {
      "epoch": 0.42111843956112655,
      "grad_norm": 0.19746099412441254,
      "learning_rate": 0.00017219251336898395,
      "loss": 0.4469,
      "step": 421
    },
    {
      "epoch": 0.4221187208902504,
      "grad_norm": 0.18945355713367462,
      "learning_rate": 0.00017212566844919787,
      "loss": 0.4601,
      "step": 422
    },
    {
      "epoch": 0.4231190022193742,
      "grad_norm": 0.20045214891433716,
      "learning_rate": 0.0001720588235294118,
      "loss": 0.4171,
      "step": 423
    },
    {
      "epoch": 0.42411928354849804,
      "grad_norm": 0.20408783853054047,
      "learning_rate": 0.00017199197860962568,
      "loss": 0.4407,
      "step": 424
    },
    {
      "epoch": 0.4251195648776218,
      "grad_norm": 0.20856668055057526,
      "learning_rate": 0.00017192513368983957,
      "loss": 0.4305,
      "step": 425
    },
    {
      "epoch": 0.42611984620674564,
      "grad_norm": 0.19926683604717255,
      "learning_rate": 0.0001718582887700535,
      "loss": 0.4576,
      "step": 426
    },
    {
      "epoch": 0.4271201275358695,
      "grad_norm": 0.1982923150062561,
      "learning_rate": 0.0001717914438502674,
      "loss": 0.4572,
      "step": 427
    },
    {
      "epoch": 0.4281204088649933,
      "grad_norm": 0.1940682828426361,
      "learning_rate": 0.0001717245989304813,
      "loss": 0.4352,
      "step": 428
    },
    {
      "epoch": 0.4291206901941171,
      "grad_norm": 0.20902183651924133,
      "learning_rate": 0.0001716577540106952,
      "loss": 0.464,
      "step": 429
    },
    {
      "epoch": 0.4301209715232409,
      "grad_norm": 0.20429746806621552,
      "learning_rate": 0.00017159090909090908,
      "loss": 0.4614,
      "step": 430
    },
    {
      "epoch": 0.43112125285236474,
      "grad_norm": 0.1939959079027176,
      "learning_rate": 0.000171524064171123,
      "loss": 0.4529,
      "step": 431
    },
    {
      "epoch": 0.4321215341814885,
      "grad_norm": 0.1874479353427887,
      "learning_rate": 0.00017145721925133692,
      "loss": 0.4299,
      "step": 432
    },
    {
      "epoch": 0.43312181551061235,
      "grad_norm": 0.19031564891338348,
      "learning_rate": 0.0001713903743315508,
      "loss": 0.4217,
      "step": 433
    },
    {
      "epoch": 0.4341220968397362,
      "grad_norm": 0.19260148704051971,
      "learning_rate": 0.0001713235294117647,
      "loss": 0.4185,
      "step": 434
    },
    {
      "epoch": 0.43512237816886,
      "grad_norm": 0.19449837505817413,
      "learning_rate": 0.00017125668449197862,
      "loss": 0.4273,
      "step": 435
    },
    {
      "epoch": 0.4361226594979838,
      "grad_norm": 0.2133646458387375,
      "learning_rate": 0.00017118983957219253,
      "loss": 0.4323,
      "step": 436
    },
    {
      "epoch": 0.4371229408271076,
      "grad_norm": 0.19664239883422852,
      "learning_rate": 0.00017112299465240642,
      "loss": 0.4451,
      "step": 437
    },
    {
      "epoch": 0.43812322215623145,
      "grad_norm": 0.20130179822444916,
      "learning_rate": 0.00017105614973262032,
      "loss": 0.4467,
      "step": 438
    },
    {
      "epoch": 0.4391235034853553,
      "grad_norm": 0.2014348804950714,
      "learning_rate": 0.00017098930481283423,
      "loss": 0.4351,
      "step": 439
    },
    {
      "epoch": 0.44012378481447906,
      "grad_norm": 0.21068580448627472,
      "learning_rate": 0.00017092245989304812,
      "loss": 0.4196,
      "step": 440
    },
    {
      "epoch": 0.4411240661436029,
      "grad_norm": 0.20975010097026825,
      "learning_rate": 0.00017085561497326204,
      "loss": 0.4448,
      "step": 441
    },
    {
      "epoch": 0.4421243474727267,
      "grad_norm": 0.2002321183681488,
      "learning_rate": 0.00017078877005347596,
      "loss": 0.4188,
      "step": 442
    },
    {
      "epoch": 0.4431246288018505,
      "grad_norm": 0.19874513149261475,
      "learning_rate": 0.00017072192513368985,
      "loss": 0.4392,
      "step": 443
    },
    {
      "epoch": 0.4441249101309743,
      "grad_norm": 0.20384036004543304,
      "learning_rate": 0.00017065508021390374,
      "loss": 0.4226,
      "step": 444
    },
    {
      "epoch": 0.44512519146009816,
      "grad_norm": 0.21764497458934784,
      "learning_rate": 0.00017058823529411766,
      "loss": 0.4536,
      "step": 445
    },
    {
      "epoch": 0.446125472789222,
      "grad_norm": 0.20656269788742065,
      "learning_rate": 0.00017052139037433158,
      "loss": 0.4224,
      "step": 446
    },
    {
      "epoch": 0.44712575411834576,
      "grad_norm": 0.19489388167858124,
      "learning_rate": 0.00017045454545454547,
      "loss": 0.428,
      "step": 447
    },
    {
      "epoch": 0.4481260354474696,
      "grad_norm": 0.1967514604330063,
      "learning_rate": 0.00017038770053475936,
      "loss": 0.4237,
      "step": 448
    },
    {
      "epoch": 0.4491263167765934,
      "grad_norm": 0.21867437660694122,
      "learning_rate": 0.00017032085561497325,
      "loss": 0.4268,
      "step": 449
    },
    {
      "epoch": 0.45012659810571726,
      "grad_norm": 0.19590826332569122,
      "learning_rate": 0.0001702540106951872,
      "loss": 0.4297,
      "step": 450
    },
    {
      "epoch": 0.45112687943484103,
      "grad_norm": 0.18361219763755798,
      "learning_rate": 0.00017018716577540109,
      "loss": 0.412,
      "step": 451
    },
    {
      "epoch": 0.45212716076396486,
      "grad_norm": 0.2177550494670868,
      "learning_rate": 0.00017012032085561498,
      "loss": 0.4107,
      "step": 452
    },
    {
      "epoch": 0.4531274420930887,
      "grad_norm": 0.21261854469776154,
      "learning_rate": 0.00017005347593582887,
      "loss": 0.4482,
      "step": 453
    },
    {
      "epoch": 0.45412772342221247,
      "grad_norm": 0.22741486132144928,
      "learning_rate": 0.00016998663101604278,
      "loss": 0.4631,
      "step": 454
    },
    {
      "epoch": 0.4551280047513363,
      "grad_norm": 0.1874597817659378,
      "learning_rate": 0.0001699197860962567,
      "loss": 0.4219,
      "step": 455
    },
    {
      "epoch": 0.45612828608046013,
      "grad_norm": 0.20828260481357574,
      "learning_rate": 0.0001698529411764706,
      "loss": 0.4348,
      "step": 456
    },
    {
      "epoch": 0.45712856740958396,
      "grad_norm": 0.20071493089199066,
      "learning_rate": 0.00016978609625668448,
      "loss": 0.4282,
      "step": 457
    },
    {
      "epoch": 0.45812884873870774,
      "grad_norm": 0.19385039806365967,
      "learning_rate": 0.0001697192513368984,
      "loss": 0.4018,
      "step": 458
    },
    {
      "epoch": 0.45912913006783157,
      "grad_norm": 0.18965497612953186,
      "learning_rate": 0.00016965240641711232,
      "loss": 0.4426,
      "step": 459
    },
    {
      "epoch": 0.4601294113969554,
      "grad_norm": 0.19367608428001404,
      "learning_rate": 0.0001695855614973262,
      "loss": 0.4359,
      "step": 460
    },
    {
      "epoch": 0.46112969272607923,
      "grad_norm": 0.22320422530174255,
      "learning_rate": 0.0001695187165775401,
      "loss": 0.4353,
      "step": 461
    },
    {
      "epoch": 0.462129974055203,
      "grad_norm": 0.2019096165895462,
      "learning_rate": 0.00016945187165775402,
      "loss": 0.4426,
      "step": 462
    },
    {
      "epoch": 0.46313025538432684,
      "grad_norm": 0.20739172399044037,
      "learning_rate": 0.0001693850267379679,
      "loss": 0.4239,
      "step": 463
    },
    {
      "epoch": 0.46413053671345067,
      "grad_norm": 0.19983212649822235,
      "learning_rate": 0.00016931818181818183,
      "loss": 0.4633,
      "step": 464
    },
    {
      "epoch": 0.4651308180425745,
      "grad_norm": 0.20308668911457062,
      "learning_rate": 0.00016925133689839575,
      "loss": 0.4441,
      "step": 465
    },
    {
      "epoch": 0.4661310993716983,
      "grad_norm": 0.1862005889415741,
      "learning_rate": 0.00016918449197860964,
      "loss": 0.4381,
      "step": 466
    },
    {
      "epoch": 0.4671313807008221,
      "grad_norm": 0.1914634108543396,
      "learning_rate": 0.00016911764705882353,
      "loss": 0.4018,
      "step": 467
    },
    {
      "epoch": 0.46813166202994594,
      "grad_norm": 0.1939598172903061,
      "learning_rate": 0.00016905080213903745,
      "loss": 0.4292,
      "step": 468
    },
    {
      "epoch": 0.4691319433590697,
      "grad_norm": 0.20433078706264496,
      "learning_rate": 0.00016898395721925136,
      "loss": 0.4313,
      "step": 469
    },
    {
      "epoch": 0.47013222468819355,
      "grad_norm": 0.19664053618907928,
      "learning_rate": 0.00016891711229946525,
      "loss": 0.4353,
      "step": 470
    },
    {
      "epoch": 0.4711325060173174,
      "grad_norm": 0.20924699306488037,
      "learning_rate": 0.00016885026737967915,
      "loss": 0.4442,
      "step": 471
    },
    {
      "epoch": 0.4721327873464412,
      "grad_norm": 0.19335909187793732,
      "learning_rate": 0.00016878342245989304,
      "loss": 0.4105,
      "step": 472
    },
    {
      "epoch": 0.473133068675565,
      "grad_norm": 0.19859367609024048,
      "learning_rate": 0.00016871657754010698,
      "loss": 0.4345,
      "step": 473
    },
    {
      "epoch": 0.4741333500046888,
      "grad_norm": 0.19565585255622864,
      "learning_rate": 0.00016864973262032087,
      "loss": 0.4318,
      "step": 474
    },
    {
      "epoch": 0.47513363133381264,
      "grad_norm": 0.19261954724788666,
      "learning_rate": 0.00016858288770053476,
      "loss": 0.4298,
      "step": 475
    },
    {
      "epoch": 0.4761339126629365,
      "grad_norm": 0.22386926412582397,
      "learning_rate": 0.00016851604278074865,
      "loss": 0.4469,
      "step": 476
    },
    {
      "epoch": 0.47713419399206025,
      "grad_norm": 0.19618257880210876,
      "learning_rate": 0.00016844919786096257,
      "loss": 0.4209,
      "step": 477
    },
    {
      "epoch": 0.4781344753211841,
      "grad_norm": 0.21180593967437744,
      "learning_rate": 0.0001683823529411765,
      "loss": 0.4337,
      "step": 478
    },
    {
      "epoch": 0.4791347566503079,
      "grad_norm": 0.19489449262619019,
      "learning_rate": 0.00016831550802139038,
      "loss": 0.4389,
      "step": 479
    },
    {
      "epoch": 0.4801350379794317,
      "grad_norm": 0.1886289119720459,
      "learning_rate": 0.00016824866310160427,
      "loss": 0.4426,
      "step": 480
    },
    {
      "epoch": 0.4811353193085555,
      "grad_norm": 0.19214124977588654,
      "learning_rate": 0.0001681818181818182,
      "loss": 0.4494,
      "step": 481
    },
    {
      "epoch": 0.48213560063767935,
      "grad_norm": 0.20083917677402496,
      "learning_rate": 0.0001681149732620321,
      "loss": 0.4544,
      "step": 482
    },
    {
      "epoch": 0.4831358819668032,
      "grad_norm": 0.1927088350057602,
      "learning_rate": 0.000168048128342246,
      "loss": 0.4186,
      "step": 483
    },
    {
      "epoch": 0.48413616329592696,
      "grad_norm": 0.1946125626564026,
      "learning_rate": 0.00016798128342245992,
      "loss": 0.4526,
      "step": 484
    },
    {
      "epoch": 0.4851364446250508,
      "grad_norm": 0.20047086477279663,
      "learning_rate": 0.0001679144385026738,
      "loss": 0.4327,
      "step": 485
    },
    {
      "epoch": 0.4861367259541746,
      "grad_norm": 0.1895369440317154,
      "learning_rate": 0.0001678475935828877,
      "loss": 0.4203,
      "step": 486
    },
    {
      "epoch": 0.48713700728329845,
      "grad_norm": 0.1896108090877533,
      "learning_rate": 0.00016778074866310162,
      "loss": 0.4206,
      "step": 487
    },
    {
      "epoch": 0.4881372886124222,
      "grad_norm": 0.2016773521900177,
      "learning_rate": 0.00016771390374331553,
      "loss": 0.4255,
      "step": 488
    },
    {
      "epoch": 0.48913756994154606,
      "grad_norm": 0.192484512925148,
      "learning_rate": 0.00016764705882352942,
      "loss": 0.4218,
      "step": 489
    },
    {
      "epoch": 0.4901378512706699,
      "grad_norm": 0.20335102081298828,
      "learning_rate": 0.00016758021390374331,
      "loss": 0.4253,
      "step": 490
    },
    {
      "epoch": 0.4911381325997937,
      "grad_norm": 0.2006034553050995,
      "learning_rate": 0.00016751336898395723,
      "loss": 0.4153,
      "step": 491
    },
    {
      "epoch": 0.4921384139289175,
      "grad_norm": 0.20064428448677063,
      "learning_rate": 0.00016744652406417115,
      "loss": 0.4448,
      "step": 492
    },
    {
      "epoch": 0.4931386952580413,
      "grad_norm": 0.2027631551027298,
      "learning_rate": 0.00016737967914438504,
      "loss": 0.4006,
      "step": 493
    },
    {
      "epoch": 0.49413897658716516,
      "grad_norm": 0.19415512681007385,
      "learning_rate": 0.00016731283422459893,
      "loss": 0.4108,
      "step": 494
    },
    {
      "epoch": 0.49513925791628893,
      "grad_norm": 0.19107206165790558,
      "learning_rate": 0.00016724598930481282,
      "loss": 0.4338,
      "step": 495
    },
    {
      "epoch": 0.49613953924541276,
      "grad_norm": 0.2028418481349945,
      "learning_rate": 0.00016717914438502674,
      "loss": 0.4548,
      "step": 496
    },
    {
      "epoch": 0.4971398205745366,
      "grad_norm": 0.19129228591918945,
      "learning_rate": 0.00016711229946524066,
      "loss": 0.4041,
      "step": 497
    },
    {
      "epoch": 0.4981401019036604,
      "grad_norm": 0.20062598586082458,
      "learning_rate": 0.00016704545454545455,
      "loss": 0.4391,
      "step": 498
    },
    {
      "epoch": 0.4991403832327842,
      "grad_norm": 0.18821845948696136,
      "learning_rate": 0.00016697860962566844,
      "loss": 0.4363,
      "step": 499
    },
    {
      "epoch": 0.5001406645619081,
      "grad_norm": 0.19271838665008545,
      "learning_rate": 0.00016691176470588236,
      "loss": 0.4225,
      "step": 500
    }
  ],
  "logging_steps": 1,
  "max_steps": 2997,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.4720940695034266e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}