{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0002813291238162,
  "eval_steps": 500,
  "global_step": 1000,
  "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
    },
    {
      "epoch": 0.5011409458910319,
      "grad_norm": 0.19656792283058167,
      "learning_rate": 0.00016684491978609628,
      "loss": 0.4349,
      "step": 501
    },
    {
      "epoch": 0.5021412272201556,
      "grad_norm": 0.20056000351905823,
      "learning_rate": 0.00016677807486631017,
      "loss": 0.4194,
      "step": 502
    },
    {
      "epoch": 0.5031415085492795,
      "grad_norm": 0.19737061858177185,
      "learning_rate": 0.00016671122994652406,
      "loss": 0.4238,
      "step": 503
    },
    {
      "epoch": 0.5041417898784033,
      "grad_norm": 0.1933743804693222,
      "learning_rate": 0.00016664438502673798,
      "loss": 0.4163,
      "step": 504
    },
    {
      "epoch": 0.5051420712075271,
      "grad_norm": 0.20754431188106537,
      "learning_rate": 0.00016657754010695187,
      "loss": 0.4322,
      "step": 505
    },
    {
      "epoch": 0.506142352536651,
      "grad_norm": 0.20065879821777344,
      "learning_rate": 0.00016651069518716578,
      "loss": 0.4361,
      "step": 506
    },
    {
      "epoch": 0.5071426338657747,
      "grad_norm": 0.19843894243240356,
      "learning_rate": 0.0001664438502673797,
      "loss": 0.4,
      "step": 507
    },
    {
      "epoch": 0.5081429151948985,
      "grad_norm": 0.19468681514263153,
      "learning_rate": 0.0001663770053475936,
      "loss": 0.4059,
      "step": 508
    },
    {
      "epoch": 0.5091431965240224,
      "grad_norm": 0.21459750831127167,
      "learning_rate": 0.00016631016042780748,
      "loss": 0.4251,
      "step": 509
    },
    {
      "epoch": 0.5101434778531462,
      "grad_norm": 0.20848138630390167,
      "learning_rate": 0.0001662433155080214,
      "loss": 0.4449,
      "step": 510
    },
    {
      "epoch": 0.5111437591822701,
      "grad_norm": 0.20533929765224457,
      "learning_rate": 0.00016617647058823532,
      "loss": 0.409,
      "step": 511
    },
    {
      "epoch": 0.5121440405113938,
      "grad_norm": 0.19327139854431152,
      "learning_rate": 0.0001661096256684492,
      "loss": 0.4376,
      "step": 512
    },
    {
      "epoch": 0.5131443218405176,
      "grad_norm": 0.18897230923175812,
      "learning_rate": 0.0001660427807486631,
      "loss": 0.4286,
      "step": 513
    },
    {
      "epoch": 0.5141446031696415,
      "grad_norm": 0.21532893180847168,
      "learning_rate": 0.000165975935828877,
      "loss": 0.4231,
      "step": 514
    },
    {
      "epoch": 0.5151448844987653,
      "grad_norm": 0.20096831023693085,
      "learning_rate": 0.00016590909090909094,
      "loss": 0.4278,
      "step": 515
    },
    {
      "epoch": 0.516145165827889,
      "grad_norm": 0.20147015154361725,
      "learning_rate": 0.00016584224598930483,
      "loss": 0.4305,
      "step": 516
    },
    {
      "epoch": 0.5171454471570129,
      "grad_norm": 0.19544675946235657,
      "learning_rate": 0.00016577540106951872,
      "loss": 0.4156,
      "step": 517
    },
    {
      "epoch": 0.5181457284861367,
      "grad_norm": 0.2213355451822281,
      "learning_rate": 0.0001657085561497326,
      "loss": 0.3922,
      "step": 518
    },
    {
      "epoch": 0.5191460098152605,
      "grad_norm": 0.187484011054039,
      "learning_rate": 0.00016564171122994653,
      "loss": 0.4011,
      "step": 519
    },
    {
      "epoch": 0.5201462911443844,
      "grad_norm": 0.19706779718399048,
      "learning_rate": 0.00016557486631016045,
      "loss": 0.4403,
      "step": 520
    },
    {
      "epoch": 0.5211465724735082,
      "grad_norm": 0.20429472625255585,
      "learning_rate": 0.00016550802139037434,
      "loss": 0.421,
      "step": 521
    },
    {
      "epoch": 0.522146853802632,
      "grad_norm": 0.18656040728092194,
      "learning_rate": 0.00016544117647058823,
      "loss": 0.4244,
      "step": 522
    },
    {
      "epoch": 0.5231471351317558,
      "grad_norm": 0.1814328134059906,
      "learning_rate": 0.00016537433155080215,
      "loss": 0.4131,
      "step": 523
    },
    {
      "epoch": 0.5241474164608796,
      "grad_norm": 0.19031472504138947,
      "learning_rate": 0.00016530748663101606,
      "loss": 0.4269,
      "step": 524
    },
    {
      "epoch": 0.5251476977900035,
      "grad_norm": 0.19180405139923096,
      "learning_rate": 0.00016524064171122995,
      "loss": 0.4283,
      "step": 525
    },
    {
      "epoch": 0.5261479791191273,
      "grad_norm": 0.18831825256347656,
      "learning_rate": 0.00016517379679144387,
      "loss": 0.4198,
      "step": 526
    },
    {
      "epoch": 0.527148260448251,
      "grad_norm": 0.19034171104431152,
      "learning_rate": 0.00016510695187165776,
      "loss": 0.4226,
      "step": 527
    },
    {
      "epoch": 0.5281485417773749,
      "grad_norm": 0.18813656270503998,
      "learning_rate": 0.00016504010695187165,
      "loss": 0.4121,
      "step": 528
    },
    {
      "epoch": 0.5291488231064987,
      "grad_norm": 0.19949543476104736,
      "learning_rate": 0.00016497326203208557,
      "loss": 0.466,
      "step": 529
    },
    {
      "epoch": 0.5301491044356225,
      "grad_norm": 0.18942514061927795,
      "learning_rate": 0.0001649064171122995,
      "loss": 0.4066,
      "step": 530
    },
    {
      "epoch": 0.5311493857647464,
      "grad_norm": 0.20220667123794556,
      "learning_rate": 0.00016483957219251338,
      "loss": 0.4241,
      "step": 531
    },
    {
      "epoch": 0.5321496670938701,
      "grad_norm": 0.19204725325107574,
      "learning_rate": 0.00016477272727272727,
      "loss": 0.4116,
      "step": 532
    },
    {
      "epoch": 0.533149948422994,
      "grad_norm": 0.18696919083595276,
      "learning_rate": 0.0001647058823529412,
      "loss": 0.4064,
      "step": 533
    },
    {
      "epoch": 0.5341502297521178,
      "grad_norm": 0.17832158505916595,
      "learning_rate": 0.0001646390374331551,
      "loss": 0.4149,
      "step": 534
    },
    {
      "epoch": 0.5351505110812416,
      "grad_norm": 0.1932826191186905,
      "learning_rate": 0.000164572192513369,
      "loss": 0.4066,
      "step": 535
    },
    {
      "epoch": 0.5361507924103655,
      "grad_norm": 0.18070964515209198,
      "learning_rate": 0.0001645053475935829,
      "loss": 0.4246,
      "step": 536
    },
    {
      "epoch": 0.5371510737394892,
      "grad_norm": 0.1925908774137497,
      "learning_rate": 0.00016443850267379678,
      "loss": 0.419,
      "step": 537
    },
    {
      "epoch": 0.538151355068613,
      "grad_norm": 0.19492492079734802,
      "learning_rate": 0.0001643716577540107,
      "loss": 0.4367,
      "step": 538
    },
    {
      "epoch": 0.5391516363977369,
      "grad_norm": 0.18963052332401276,
      "learning_rate": 0.00016430481283422462,
      "loss": 0.4177,
      "step": 539
    },
    {
      "epoch": 0.5401519177268607,
      "grad_norm": 0.17578846216201782,
      "learning_rate": 0.0001642379679144385,
      "loss": 0.3913,
      "step": 540
    },
    {
      "epoch": 0.5411521990559846,
      "grad_norm": 0.18971838057041168,
      "learning_rate": 0.0001641711229946524,
      "loss": 0.4286,
      "step": 541
    },
    {
      "epoch": 0.5421524803851083,
      "grad_norm": 0.1947614997625351,
      "learning_rate": 0.00016410427807486631,
      "loss": 0.4025,
      "step": 542
    },
    {
      "epoch": 0.5431527617142321,
      "grad_norm": 0.21655721962451935,
      "learning_rate": 0.00016403743315508023,
      "loss": 0.4017,
      "step": 543
    },
    {
      "epoch": 0.544153043043356,
      "grad_norm": 0.21091024577617645,
      "learning_rate": 0.00016397058823529412,
      "loss": 0.4361,
      "step": 544
    },
    {
      "epoch": 0.5451533243724798,
      "grad_norm": 0.19978757202625275,
      "learning_rate": 0.00016390374331550801,
      "loss": 0.4159,
      "step": 545
    },
    {
      "epoch": 0.5461536057016035,
      "grad_norm": 0.2090614140033722,
      "learning_rate": 0.00016383689839572193,
      "loss": 0.4299,
      "step": 546
    },
    {
      "epoch": 0.5471538870307274,
      "grad_norm": 0.18880675733089447,
      "learning_rate": 0.00016377005347593582,
      "loss": 0.4176,
      "step": 547
    },
    {
      "epoch": 0.5481541683598512,
      "grad_norm": 0.1911989003419876,
      "learning_rate": 0.00016370320855614974,
      "loss": 0.4341,
      "step": 548
    },
    {
      "epoch": 0.549154449688975,
      "grad_norm": 0.20136778056621552,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.4322,
      "step": 549
    },
    {
      "epoch": 0.5501547310180989,
      "grad_norm": 0.2132529318332672,
      "learning_rate": 0.00016356951871657755,
      "loss": 0.4338,
      "step": 550
    },
    {
      "epoch": 0.5511550123472226,
      "grad_norm": 0.190921813249588,
      "learning_rate": 0.00016350267379679144,
      "loss": 0.4202,
      "step": 551
    },
    {
      "epoch": 0.5521552936763465,
      "grad_norm": 0.18725930154323578,
      "learning_rate": 0.00016343582887700536,
      "loss": 0.4367,
      "step": 552
    },
    {
      "epoch": 0.5531555750054703,
      "grad_norm": 0.19544881582260132,
      "learning_rate": 0.00016336898395721928,
      "loss": 0.4223,
      "step": 553
    },
    {
      "epoch": 0.5541558563345941,
      "grad_norm": 0.2086367905139923,
      "learning_rate": 0.00016330213903743317,
      "loss": 0.4226,
      "step": 554
    },
    {
      "epoch": 0.555156137663718,
      "grad_norm": 0.20172438025474548,
      "learning_rate": 0.00016323529411764706,
      "loss": 0.4464,
      "step": 555
    },
    {
      "epoch": 0.5561564189928417,
      "grad_norm": 0.1924048811197281,
      "learning_rate": 0.00016316844919786095,
      "loss": 0.4063,
      "step": 556
    },
    {
      "epoch": 0.5571567003219655,
      "grad_norm": 0.20100219547748566,
      "learning_rate": 0.0001631016042780749,
      "loss": 0.4167,
      "step": 557
    },
    {
      "epoch": 0.5581569816510894,
      "grad_norm": 0.2113865464925766,
      "learning_rate": 0.00016303475935828878,
      "loss": 0.4154,
      "step": 558
    },
    {
      "epoch": 0.5591572629802132,
      "grad_norm": 0.21103252470493317,
      "learning_rate": 0.00016296791443850268,
      "loss": 0.4186,
      "step": 559
    },
    {
      "epoch": 0.560157544309337,
      "grad_norm": 0.20455509424209595,
      "learning_rate": 0.00016290106951871657,
      "loss": 0.4069,
      "step": 560
    },
    {
      "epoch": 0.5611578256384608,
      "grad_norm": 0.19757798314094543,
      "learning_rate": 0.00016283422459893048,
      "loss": 0.4438,
      "step": 561
    },
    {
      "epoch": 0.5621581069675846,
      "grad_norm": 0.21342839300632477,
      "learning_rate": 0.0001627673796791444,
      "loss": 0.4202,
      "step": 562
    },
    {
      "epoch": 0.5631583882967085,
      "grad_norm": 0.22245363891124725,
      "learning_rate": 0.0001627005347593583,
      "loss": 0.4658,
      "step": 563
    },
    {
      "epoch": 0.5641586696258323,
      "grad_norm": 0.1922263205051422,
      "learning_rate": 0.00016263368983957218,
      "loss": 0.4304,
      "step": 564
    },
    {
      "epoch": 0.565158950954956,
      "grad_norm": 0.19954454898834229,
      "learning_rate": 0.0001625668449197861,
      "loss": 0.43,
      "step": 565
    },
    {
      "epoch": 0.5661592322840799,
      "grad_norm": 0.21509230136871338,
      "learning_rate": 0.00016250000000000002,
      "loss": 0.4316,
      "step": 566
    },
    {
      "epoch": 0.5671595136132037,
      "grad_norm": 0.20861805975437164,
      "learning_rate": 0.0001624331550802139,
      "loss": 0.4076,
      "step": 567
    },
    {
      "epoch": 0.5681597949423275,
      "grad_norm": 0.20317140221595764,
      "learning_rate": 0.00016236631016042783,
      "loss": 0.3865,
      "step": 568
    },
    {
      "epoch": 0.5691600762714514,
      "grad_norm": 0.21329276263713837,
      "learning_rate": 0.00016229946524064172,
      "loss": 0.4211,
      "step": 569
    },
    {
      "epoch": 0.5701603576005752,
      "grad_norm": 0.21291124820709229,
      "learning_rate": 0.0001622326203208556,
      "loss": 0.4421,
      "step": 570
    },
    {
      "epoch": 0.5711606389296989,
      "grad_norm": 0.20930252969264984,
      "learning_rate": 0.00016216577540106953,
      "loss": 0.4177,
      "step": 571
    },
    {
      "epoch": 0.5721609202588228,
      "grad_norm": 0.19011874496936798,
      "learning_rate": 0.00016209893048128345,
      "loss": 0.4268,
      "step": 572
    },
    {
      "epoch": 0.5731612015879466,
      "grad_norm": 0.2085164338350296,
      "learning_rate": 0.00016203208556149734,
      "loss": 0.4393,
      "step": 573
    },
    {
      "epoch": 0.5741614829170705,
      "grad_norm": 0.23111028969287872,
      "learning_rate": 0.00016196524064171123,
      "loss": 0.4426,
      "step": 574
    },
    {
      "epoch": 0.5751617642461943,
      "grad_norm": 0.19172526895999908,
      "learning_rate": 0.00016189839572192515,
      "loss": 0.456,
      "step": 575
    },
    {
      "epoch": 0.576162045575318,
      "grad_norm": 0.21097679436206818,
      "learning_rate": 0.00016183155080213906,
      "loss": 0.416,
      "step": 576
    },
    {
      "epoch": 0.5771623269044419,
      "grad_norm": 0.18923287093639374,
      "learning_rate": 0.00016176470588235295,
      "loss": 0.4063,
      "step": 577
    },
    {
      "epoch": 0.5781626082335657,
      "grad_norm": 0.2181912660598755,
      "learning_rate": 0.00016169786096256684,
      "loss": 0.4044,
      "step": 578
    },
    {
      "epoch": 0.5791628895626895,
      "grad_norm": 0.2063039243221283,
      "learning_rate": 0.00016163101604278074,
      "loss": 0.4332,
      "step": 579
    },
    {
      "epoch": 0.5801631708918134,
      "grad_norm": 0.187129408121109,
      "learning_rate": 0.00016156417112299468,
      "loss": 0.4049,
      "step": 580
    },
    {
      "epoch": 0.5811634522209371,
      "grad_norm": 0.20413397252559662,
      "learning_rate": 0.00016149732620320857,
      "loss": 0.418,
      "step": 581
    },
    {
      "epoch": 0.5821637335500609,
      "grad_norm": 0.19758477807044983,
      "learning_rate": 0.00016143048128342246,
      "loss": 0.4221,
      "step": 582
    },
    {
      "epoch": 0.5831640148791848,
      "grad_norm": 0.19809985160827637,
      "learning_rate": 0.00016136363636363635,
      "loss": 0.4067,
      "step": 583
    },
    {
      "epoch": 0.5841642962083086,
      "grad_norm": 0.18739382922649384,
      "learning_rate": 0.00016129679144385027,
      "loss": 0.4192,
      "step": 584
    },
    {
      "epoch": 0.5851645775374325,
      "grad_norm": 0.19074848294258118,
      "learning_rate": 0.0001612299465240642,
      "loss": 0.4197,
      "step": 585
    },
    {
      "epoch": 0.5861648588665562,
      "grad_norm": 0.20200254023075104,
      "learning_rate": 0.00016116310160427808,
      "loss": 0.4066,
      "step": 586
    },
    {
      "epoch": 0.58716514019568,
      "grad_norm": 0.19068248569965363,
      "learning_rate": 0.000161096256684492,
      "loss": 0.4158,
      "step": 587
    },
    {
      "epoch": 0.5881654215248039,
      "grad_norm": 0.20269031822681427,
      "learning_rate": 0.0001610294117647059,
      "loss": 0.4303,
      "step": 588
    },
    {
      "epoch": 0.5891657028539277,
      "grad_norm": 0.2095469832420349,
      "learning_rate": 0.0001609625668449198,
      "loss": 0.4476,
      "step": 589
    },
    {
      "epoch": 0.5901659841830514,
      "grad_norm": 0.2007177770137787,
      "learning_rate": 0.0001608957219251337,
      "loss": 0.4175,
      "step": 590
    },
    {
      "epoch": 0.5911662655121753,
      "grad_norm": 0.20014688372612,
      "learning_rate": 0.00016082887700534762,
      "loss": 0.4524,
      "step": 591
    },
    {
      "epoch": 0.5921665468412991,
      "grad_norm": 0.19988134503364563,
      "learning_rate": 0.0001607620320855615,
      "loss": 0.4258,
      "step": 592
    },
    {
      "epoch": 0.5931668281704229,
      "grad_norm": 0.1872769296169281,
      "learning_rate": 0.0001606951871657754,
      "loss": 0.4048,
      "step": 593
    },
    {
      "epoch": 0.5941671094995468,
      "grad_norm": 0.19716571271419525,
      "learning_rate": 0.00016062834224598931,
      "loss": 0.4003,
      "step": 594
    },
    {
      "epoch": 0.5951673908286705,
      "grad_norm": 0.19314983487129211,
      "learning_rate": 0.00016056149732620323,
      "loss": 0.4128,
      "step": 595
    },
    {
      "epoch": 0.5961676721577944,
      "grad_norm": 0.19966118037700653,
      "learning_rate": 0.00016049465240641712,
      "loss": 0.4187,
      "step": 596
    },
    {
      "epoch": 0.5971679534869182,
      "grad_norm": 0.19854962825775146,
      "learning_rate": 0.00016042780748663101,
      "loss": 0.4242,
      "step": 597
    },
    {
      "epoch": 0.598168234816042,
      "grad_norm": 0.2061505913734436,
      "learning_rate": 0.00016036096256684493,
      "loss": 0.3882,
      "step": 598
    },
    {
      "epoch": 0.5991685161451659,
      "grad_norm": 0.19743064045906067,
      "learning_rate": 0.00016029411764705885,
      "loss": 0.4019,
      "step": 599
    },
    {
      "epoch": 0.6001687974742896,
      "grad_norm": 0.21287234127521515,
      "learning_rate": 0.00016022727272727274,
      "loss": 0.435,
      "step": 600
    },
    {
      "epoch": 0.6011690788034134,
      "grad_norm": 0.21128612756729126,
      "learning_rate": 0.00016016042780748663,
      "loss": 0.4121,
      "step": 601
    },
    {
      "epoch": 0.6021693601325373,
      "grad_norm": 0.2014809250831604,
      "learning_rate": 0.00016009358288770052,
      "loss": 0.4415,
      "step": 602
    },
    {
      "epoch": 0.6031696414616611,
      "grad_norm": 0.18564432859420776,
      "learning_rate": 0.00016002673796791444,
      "loss": 0.4137,
      "step": 603
    },
    {
      "epoch": 0.604169922790785,
      "grad_norm": 0.21706810593605042,
      "learning_rate": 0.00015995989304812836,
      "loss": 0.4146,
      "step": 604
    },
    {
      "epoch": 0.6051702041199087,
      "grad_norm": 0.19561977684497833,
      "learning_rate": 0.00015989304812834225,
      "loss": 0.4403,
      "step": 605
    },
    {
      "epoch": 0.6061704854490325,
      "grad_norm": 0.20120753347873688,
      "learning_rate": 0.00015982620320855614,
      "loss": 0.4276,
      "step": 606
    },
    {
      "epoch": 0.6071707667781564,
      "grad_norm": 0.19712668657302856,
      "learning_rate": 0.00015975935828877006,
      "loss": 0.402,
      "step": 607
    },
    {
      "epoch": 0.6081710481072802,
      "grad_norm": 0.18773560225963593,
      "learning_rate": 0.00015969251336898398,
      "loss": 0.4403,
      "step": 608
    },
    {
      "epoch": 0.609171329436404,
      "grad_norm": 0.1966264843940735,
      "learning_rate": 0.00015962566844919787,
      "loss": 0.4236,
      "step": 609
    },
    {
      "epoch": 0.6101716107655278,
      "grad_norm": 0.19131089746952057,
      "learning_rate": 0.00015955882352941178,
      "loss": 0.4017,
      "step": 610
    },
    {
      "epoch": 0.6111718920946516,
      "grad_norm": 0.19304153323173523,
      "learning_rate": 0.00015949197860962568,
      "loss": 0.423,
      "step": 611
    },
    {
      "epoch": 0.6121721734237754,
      "grad_norm": 0.21584953367710114,
      "learning_rate": 0.00015942513368983957,
      "loss": 0.4294,
      "step": 612
    },
    {
      "epoch": 0.6131724547528993,
      "grad_norm": 0.1817302107810974,
      "learning_rate": 0.00015935828877005348,
      "loss": 0.4125,
      "step": 613
    },
    {
      "epoch": 0.614172736082023,
      "grad_norm": 0.1943361461162567,
      "learning_rate": 0.0001592914438502674,
      "loss": 0.4078,
      "step": 614
    },
    {
      "epoch": 0.6151730174111469,
      "grad_norm": 0.19811980426311493,
      "learning_rate": 0.0001592245989304813,
      "loss": 0.4357,
      "step": 615
    },
    {
      "epoch": 0.6161732987402707,
      "grad_norm": 0.2187698781490326,
      "learning_rate": 0.00015915775401069518,
      "loss": 0.4311,
      "step": 616
    },
    {
      "epoch": 0.6171735800693945,
      "grad_norm": 0.1992914378643036,
      "learning_rate": 0.0001590909090909091,
      "loss": 0.4064,
      "step": 617
    },
    {
      "epoch": 0.6181738613985184,
      "grad_norm": 0.19837424159049988,
      "learning_rate": 0.00015902406417112302,
      "loss": 0.4228,
      "step": 618
    },
    {
      "epoch": 0.6191741427276422,
      "grad_norm": 0.18851952254772186,
      "learning_rate": 0.0001589572192513369,
      "loss": 0.4016,
      "step": 619
    },
    {
      "epoch": 0.6201744240567659,
      "grad_norm": 0.2011716067790985,
      "learning_rate": 0.0001588903743315508,
      "loss": 0.4177,
      "step": 620
    },
    {
      "epoch": 0.6211747053858898,
      "grad_norm": 0.1978669911623001,
      "learning_rate": 0.0001588235294117647,
      "loss": 0.4367,
      "step": 621
    },
    {
      "epoch": 0.6221749867150136,
      "grad_norm": 0.19149920344352722,
      "learning_rate": 0.00015875668449197864,
      "loss": 0.4163,
      "step": 622
    },
    {
      "epoch": 0.6231752680441374,
      "grad_norm": 0.19444184005260468,
      "learning_rate": 0.00015868983957219253,
      "loss": 0.4207,
      "step": 623
    },
    {
      "epoch": 0.6241755493732613,
      "grad_norm": 0.2174759954214096,
      "learning_rate": 0.00015862299465240642,
      "loss": 0.4249,
      "step": 624
    },
    {
      "epoch": 0.625175830702385,
      "grad_norm": 0.1940513253211975,
      "learning_rate": 0.0001585561497326203,
      "loss": 0.41,
      "step": 625
    },
    {
      "epoch": 0.6261761120315089,
      "grad_norm": 0.19293572008609772,
      "learning_rate": 0.00015848930481283423,
      "loss": 0.3987,
      "step": 626
    },
    {
      "epoch": 0.6271763933606327,
      "grad_norm": 0.19239608943462372,
      "learning_rate": 0.00015842245989304815,
      "loss": 0.4013,
      "step": 627
    },
    {
      "epoch": 0.6281766746897565,
      "grad_norm": 0.21359312534332275,
      "learning_rate": 0.00015835561497326204,
      "loss": 0.404,
      "step": 628
    },
    {
      "epoch": 0.6291769560188804,
      "grad_norm": 0.19094659388065338,
      "learning_rate": 0.00015828877005347595,
      "loss": 0.4199,
      "step": 629
    },
    {
      "epoch": 0.6301772373480041,
      "grad_norm": 0.20200002193450928,
      "learning_rate": 0.00015822192513368984,
      "loss": 0.4119,
      "step": 630
    },
    {
      "epoch": 0.6311775186771279,
      "grad_norm": 0.22112160921096802,
      "learning_rate": 0.00015815508021390376,
      "loss": 0.4104,
      "step": 631
    },
    {
      "epoch": 0.6321778000062518,
      "grad_norm": 0.183325856924057,
      "learning_rate": 0.00015808823529411765,
      "loss": 0.3967,
      "step": 632
    },
    {
      "epoch": 0.6331780813353756,
      "grad_norm": 0.19795946776866913,
      "learning_rate": 0.00015802139037433157,
      "loss": 0.4199,
      "step": 633
    },
    {
      "epoch": 0.6341783626644993,
      "grad_norm": 0.1972920149564743,
      "learning_rate": 0.00015795454545454546,
      "loss": 0.4332,
      "step": 634
    },
    {
      "epoch": 0.6351786439936232,
      "grad_norm": 0.2010953575372696,
      "learning_rate": 0.00015788770053475935,
      "loss": 0.4252,
      "step": 635
    },
    {
      "epoch": 0.636178925322747,
      "grad_norm": 0.21317847073078156,
      "learning_rate": 0.00015782085561497327,
      "loss": 0.3955,
      "step": 636
    },
    {
      "epoch": 0.6371792066518709,
      "grad_norm": 0.18925467133522034,
      "learning_rate": 0.0001577540106951872,
      "loss": 0.4106,
      "step": 637
    },
    {
      "epoch": 0.6381794879809947,
      "grad_norm": 0.18963564932346344,
      "learning_rate": 0.00015768716577540108,
      "loss": 0.4092,
      "step": 638
    },
    {
      "epoch": 0.6391797693101184,
      "grad_norm": 0.19623884558677673,
      "learning_rate": 0.00015762032085561497,
      "loss": 0.3926,
      "step": 639
    },
    {
      "epoch": 0.6401800506392423,
      "grad_norm": 0.21643273532390594,
      "learning_rate": 0.0001575534759358289,
      "loss": 0.4183,
      "step": 640
    },
    {
      "epoch": 0.6411803319683661,
      "grad_norm": 0.21248869597911835,
      "learning_rate": 0.0001574866310160428,
      "loss": 0.4017,
      "step": 641
    },
    {
      "epoch": 0.6421806132974899,
      "grad_norm": 0.19180509448051453,
      "learning_rate": 0.0001574197860962567,
      "loss": 0.4229,
      "step": 642
    },
    {
      "epoch": 0.6431808946266138,
      "grad_norm": 0.19765090942382812,
      "learning_rate": 0.0001573529411764706,
      "loss": 0.4245,
      "step": 643
    },
    {
      "epoch": 0.6441811759557375,
      "grad_norm": 0.22481298446655273,
      "learning_rate": 0.00015728609625668448,
      "loss": 0.443,
      "step": 644
    },
    {
      "epoch": 0.6451814572848613,
      "grad_norm": 0.20505894720554352,
      "learning_rate": 0.0001572192513368984,
      "loss": 0.432,
      "step": 645
    },
    {
      "epoch": 0.6461817386139852,
      "grad_norm": 0.2146381288766861,
      "learning_rate": 0.00015715240641711231,
      "loss": 0.4394,
      "step": 646
    },
    {
      "epoch": 0.647182019943109,
      "grad_norm": 0.1944749355316162,
      "learning_rate": 0.0001570855614973262,
      "loss": 0.4224,
      "step": 647
    },
    {
      "epoch": 0.6481823012722329,
      "grad_norm": 0.19812066853046417,
      "learning_rate": 0.0001570187165775401,
      "loss": 0.4058,
      "step": 648
    },
    {
      "epoch": 0.6491825826013566,
      "grad_norm": 0.17709974944591522,
      "learning_rate": 0.00015695187165775401,
      "loss": 0.3886,
      "step": 649
    },
    {
      "epoch": 0.6501828639304804,
      "grad_norm": 0.18233494460582733,
      "learning_rate": 0.00015688502673796793,
      "loss": 0.4023,
      "step": 650
    },
    {
      "epoch": 0.6511831452596043,
      "grad_norm": 0.2211703658103943,
      "learning_rate": 0.00015681818181818182,
      "loss": 0.446,
      "step": 651
    },
    {
      "epoch": 0.6521834265887281,
      "grad_norm": 0.21147893369197845,
      "learning_rate": 0.00015675133689839574,
      "loss": 0.4408,
      "step": 652
    },
    {
      "epoch": 0.6531837079178519,
      "grad_norm": 0.19703680276870728,
      "learning_rate": 0.00015668449197860963,
      "loss": 0.4036,
      "step": 653
    },
    {
      "epoch": 0.6541839892469757,
      "grad_norm": 0.1938186138868332,
      "learning_rate": 0.00015661764705882352,
      "loss": 0.405,
      "step": 654
    },
    {
      "epoch": 0.6551842705760995,
      "grad_norm": 0.20539699494838715,
      "learning_rate": 0.00015655080213903744,
      "loss": 0.4504,
      "step": 655
    },
    {
      "epoch": 0.6561845519052233,
      "grad_norm": 0.20340494811534882,
      "learning_rate": 0.00015648395721925136,
      "loss": 0.4387,
      "step": 656
    },
    {
      "epoch": 0.6571848332343472,
      "grad_norm": 0.19433771073818207,
      "learning_rate": 0.00015641711229946525,
      "loss": 0.4081,
      "step": 657
    },
    {
      "epoch": 0.658185114563471,
      "grad_norm": 0.22444796562194824,
      "learning_rate": 0.00015635026737967914,
      "loss": 0.4468,
      "step": 658
    },
    {
      "epoch": 0.6591853958925948,
      "grad_norm": 0.19663526117801666,
      "learning_rate": 0.00015628342245989306,
      "loss": 0.4173,
      "step": 659
    },
    {
      "epoch": 0.6601856772217186,
      "grad_norm": 0.21389231085777283,
      "learning_rate": 0.00015621657754010698,
      "loss": 0.4086,
      "step": 660
    },
    {
      "epoch": 0.6611859585508424,
      "grad_norm": 0.2016345113515854,
      "learning_rate": 0.00015614973262032087,
      "loss": 0.4158,
      "step": 661
    },
    {
      "epoch": 0.6621862398799663,
      "grad_norm": 0.18254131078720093,
      "learning_rate": 0.00015608288770053476,
      "loss": 0.3699,
      "step": 662
    },
    {
      "epoch": 0.66318652120909,
      "grad_norm": 0.19809594750404358,
      "learning_rate": 0.00015601604278074865,
      "loss": 0.4198,
      "step": 663
    },
    {
      "epoch": 0.6641868025382138,
      "grad_norm": 0.22484511137008667,
      "learning_rate": 0.0001559491978609626,
      "loss": 0.3903,
      "step": 664
    },
    {
      "epoch": 0.6651870838673377,
      "grad_norm": 0.2212168574333191,
      "learning_rate": 0.00015588235294117648,
      "loss": 0.4259,
      "step": 665
    },
    {
      "epoch": 0.6661873651964615,
      "grad_norm": 0.19827373325824738,
      "learning_rate": 0.00015581550802139037,
      "loss": 0.4165,
      "step": 666
    },
    {
      "epoch": 0.6671876465255854,
      "grad_norm": 0.19069035351276398,
      "learning_rate": 0.00015574866310160427,
      "loss": 0.4184,
      "step": 667
    },
    {
      "epoch": 0.6681879278547092,
      "grad_norm": 0.18512091040611267,
      "learning_rate": 0.00015568181818181818,
      "loss": 0.3882,
      "step": 668
    },
    {
      "epoch": 0.6691882091838329,
      "grad_norm": 0.19668161869049072,
      "learning_rate": 0.0001556149732620321,
      "loss": 0.4129,
      "step": 669
    },
    {
      "epoch": 0.6701884905129568,
      "grad_norm": 0.19963647425174713,
      "learning_rate": 0.000155548128342246,
      "loss": 0.4235,
      "step": 670
    },
    {
      "epoch": 0.6711887718420806,
      "grad_norm": 0.1999901980161667,
      "learning_rate": 0.0001554812834224599,
      "loss": 0.4244,
      "step": 671
    },
    {
      "epoch": 0.6721890531712044,
      "grad_norm": 0.20518022775650024,
      "learning_rate": 0.0001554144385026738,
      "loss": 0.422,
      "step": 672
    },
    {
      "epoch": 0.6731893345003283,
      "grad_norm": 0.19251032173633575,
      "learning_rate": 0.00015534759358288772,
      "loss": 0.3999,
      "step": 673
    },
    {
      "epoch": 0.674189615829452,
      "grad_norm": 0.18975438177585602,
      "learning_rate": 0.0001552807486631016,
      "loss": 0.4305,
      "step": 674
    },
    {
      "epoch": 0.6751898971585758,
      "grad_norm": 0.1829996407032013,
      "learning_rate": 0.00015521390374331553,
      "loss": 0.4034,
      "step": 675
    },
    {
      "epoch": 0.6761901784876997,
      "grad_norm": 0.1942373365163803,
      "learning_rate": 0.00015514705882352942,
      "loss": 0.4399,
      "step": 676
    },
    {
      "epoch": 0.6771904598168235,
      "grad_norm": 0.19765040278434753,
      "learning_rate": 0.0001550802139037433,
      "loss": 0.435,
      "step": 677
    },
    {
      "epoch": 0.6781907411459474,
      "grad_norm": 0.18772929906845093,
      "learning_rate": 0.00015501336898395723,
      "loss": 0.4253,
      "step": 678
    },
    {
      "epoch": 0.6791910224750711,
      "grad_norm": 0.20005156099796295,
      "learning_rate": 0.00015494652406417115,
      "loss": 0.4358,
      "step": 679
    },
    {
      "epoch": 0.6801913038041949,
      "grad_norm": 0.18797992169857025,
      "learning_rate": 0.00015487967914438504,
      "loss": 0.4198,
      "step": 680
    },
    {
      "epoch": 0.6811915851333188,
      "grad_norm": 0.18686774373054504,
      "learning_rate": 0.00015481283422459893,
      "loss": 0.4115,
      "step": 681
    },
    {
      "epoch": 0.6821918664624426,
      "grad_norm": 0.2020418494939804,
      "learning_rate": 0.00015474598930481284,
      "loss": 0.4035,
      "step": 682
    },
    {
      "epoch": 0.6831921477915663,
      "grad_norm": 0.17885395884513855,
      "learning_rate": 0.00015467914438502676,
      "loss": 0.4004,
      "step": 683
    },
    {
      "epoch": 0.6841924291206902,
      "grad_norm": 0.19854307174682617,
      "learning_rate": 0.00015461229946524065,
      "loss": 0.4413,
      "step": 684
    },
    {
      "epoch": 0.685192710449814,
      "grad_norm": 0.19115328788757324,
      "learning_rate": 0.00015454545454545454,
      "loss": 0.4147,
      "step": 685
    },
    {
      "epoch": 0.6861929917789378,
      "grad_norm": 0.20121394097805023,
      "learning_rate": 0.00015447860962566844,
      "loss": 0.413,
      "step": 686
    },
    {
      "epoch": 0.6871932731080617,
      "grad_norm": 0.1890256702899933,
      "learning_rate": 0.00015441176470588238,
      "loss": 0.3916,
      "step": 687
    },
    {
      "epoch": 0.6881935544371854,
      "grad_norm": 0.18655836582183838,
      "learning_rate": 0.00015434491978609627,
      "loss": 0.4119,
      "step": 688
    },
    {
      "epoch": 0.6891938357663093,
      "grad_norm": 0.19385652244091034,
      "learning_rate": 0.00015427807486631016,
      "loss": 0.4044,
      "step": 689
    },
    {
      "epoch": 0.6901941170954331,
      "grad_norm": 0.1924891173839569,
      "learning_rate": 0.00015421122994652405,
      "loss": 0.4113,
      "step": 690
    },
    {
      "epoch": 0.6911943984245569,
      "grad_norm": 0.19801472127437592,
      "learning_rate": 0.00015414438502673797,
      "loss": 0.4019,
      "step": 691
    },
    {
      "epoch": 0.6921946797536808,
      "grad_norm": 0.20131009817123413,
      "learning_rate": 0.0001540775401069519,
      "loss": 0.4375,
      "step": 692
    },
    {
      "epoch": 0.6931949610828045,
      "grad_norm": 0.20007281005382538,
      "learning_rate": 0.00015401069518716578,
      "loss": 0.4299,
      "step": 693
    },
    {
      "epoch": 0.6941952424119283,
      "grad_norm": 0.20760390162467957,
      "learning_rate": 0.0001539438502673797,
      "loss": 0.4352,
      "step": 694
    },
    {
      "epoch": 0.6951955237410522,
      "grad_norm": 0.19812342524528503,
      "learning_rate": 0.0001538770053475936,
      "loss": 0.4143,
      "step": 695
    },
    {
      "epoch": 0.696195805070176,
      "grad_norm": 0.19777828454971313,
      "learning_rate": 0.0001538101604278075,
      "loss": 0.412,
      "step": 696
    },
    {
      "epoch": 0.6971960863992998,
      "grad_norm": 0.20043079555034637,
      "learning_rate": 0.0001537433155080214,
      "loss": 0.4085,
      "step": 697
    },
    {
      "epoch": 0.6981963677284236,
      "grad_norm": 0.19350604712963104,
      "learning_rate": 0.00015367647058823531,
      "loss": 0.3949,
      "step": 698
    },
    {
      "epoch": 0.6991966490575474,
      "grad_norm": 0.1868661791086197,
      "learning_rate": 0.0001536096256684492,
      "loss": 0.4074,
      "step": 699
    },
    {
      "epoch": 0.7001969303866713,
      "grad_norm": 0.19784660637378693,
      "learning_rate": 0.0001535427807486631,
      "loss": 0.4339,
      "step": 700
    },
    {
      "epoch": 0.7011972117157951,
      "grad_norm": 0.19306881725788116,
      "learning_rate": 0.00015347593582887701,
      "loss": 0.4004,
      "step": 701
    },
    {
      "epoch": 0.7021974930449189,
      "grad_norm": 0.19934973120689392,
      "learning_rate": 0.00015340909090909093,
      "loss": 0.3999,
      "step": 702
    },
    {
      "epoch": 0.7031977743740427,
      "grad_norm": 0.19438371062278748,
      "learning_rate": 0.00015334224598930482,
      "loss": 0.3841,
      "step": 703
    },
    {
      "epoch": 0.7041980557031665,
      "grad_norm": 0.18885186314582825,
      "learning_rate": 0.00015327540106951871,
      "loss": 0.4179,
      "step": 704
    },
    {
      "epoch": 0.7051983370322903,
      "grad_norm": 0.20008157193660736,
      "learning_rate": 0.00015320855614973263,
      "loss": 0.4243,
      "step": 705
    },
    {
      "epoch": 0.7061986183614142,
      "grad_norm": 0.18620654940605164,
      "learning_rate": 0.00015314171122994655,
      "loss": 0.412,
      "step": 706
    },
    {
      "epoch": 0.707198899690538,
      "grad_norm": 0.1964969038963318,
      "learning_rate": 0.00015307486631016044,
      "loss": 0.4114,
      "step": 707
    },
    {
      "epoch": 0.7081991810196617,
      "grad_norm": 0.1912650316953659,
      "learning_rate": 0.00015300802139037433,
      "loss": 0.4086,
      "step": 708
    },
    {
      "epoch": 0.7091994623487856,
      "grad_norm": 0.18431147933006287,
      "learning_rate": 0.00015294117647058822,
      "loss": 0.3927,
      "step": 709
    },
    {
      "epoch": 0.7101997436779094,
      "grad_norm": 0.18856145441532135,
      "learning_rate": 0.00015287433155080214,
      "loss": 0.4158,
      "step": 710
    },
    {
      "epoch": 0.7112000250070333,
      "grad_norm": 0.1948367953300476,
      "learning_rate": 0.00015280748663101606,
      "loss": 0.3989,
      "step": 711
    },
    {
      "epoch": 0.712200306336157,
      "grad_norm": 0.1820988953113556,
      "learning_rate": 0.00015274064171122995,
      "loss": 0.3875,
      "step": 712
    },
    {
      "epoch": 0.7132005876652808,
      "grad_norm": 0.20130835473537445,
      "learning_rate": 0.00015267379679144387,
      "loss": 0.4291,
      "step": 713
    },
    {
      "epoch": 0.7142008689944047,
      "grad_norm": 0.18851028382778168,
      "learning_rate": 0.00015260695187165776,
      "loss": 0.4426,
      "step": 714
    },
    {
      "epoch": 0.7152011503235285,
      "grad_norm": 0.19229646027088165,
      "learning_rate": 0.00015254010695187168,
      "loss": 0.3945,
      "step": 715
    },
    {
      "epoch": 0.7162014316526523,
      "grad_norm": 0.19848079979419708,
      "learning_rate": 0.00015247326203208557,
      "loss": 0.4168,
      "step": 716
    },
    {
      "epoch": 0.7172017129817762,
      "grad_norm": 0.18817974627017975,
      "learning_rate": 0.00015240641711229948,
      "loss": 0.396,
      "step": 717
    },
    {
      "epoch": 0.7182019943108999,
      "grad_norm": 0.19745159149169922,
      "learning_rate": 0.00015233957219251337,
      "loss": 0.3993,
      "step": 718
    },
    {
      "epoch": 0.7192022756400237,
      "grad_norm": 0.20078255236148834,
      "learning_rate": 0.00015227272727272727,
      "loss": 0.4239,
      "step": 719
    },
    {
      "epoch": 0.7202025569691476,
      "grad_norm": 0.19862700998783112,
      "learning_rate": 0.00015220588235294118,
      "loss": 0.4227,
      "step": 720
    },
    {
      "epoch": 0.7212028382982714,
      "grad_norm": 0.1999097466468811,
      "learning_rate": 0.0001521390374331551,
      "loss": 0.4007,
      "step": 721
    },
    {
      "epoch": 0.7222031196273953,
      "grad_norm": 0.19367538392543793,
      "learning_rate": 0.000152072192513369,
      "loss": 0.4059,
      "step": 722
    },
    {
      "epoch": 0.723203400956519,
      "grad_norm": 0.20289233326911926,
      "learning_rate": 0.00015200534759358288,
      "loss": 0.4129,
      "step": 723
    },
    {
      "epoch": 0.7242036822856428,
      "grad_norm": 0.19397608935832977,
      "learning_rate": 0.0001519385026737968,
      "loss": 0.3934,
      "step": 724
    },
    {
      "epoch": 0.7252039636147667,
      "grad_norm": 0.198171466588974,
      "learning_rate": 0.00015187165775401072,
      "loss": 0.4144,
      "step": 725
    },
    {
      "epoch": 0.7262042449438905,
      "grad_norm": 0.19133004546165466,
      "learning_rate": 0.0001518048128342246,
      "loss": 0.4111,
      "step": 726
    },
    {
      "epoch": 0.7272045262730142,
      "grad_norm": 0.18946494162082672,
      "learning_rate": 0.0001517379679144385,
      "loss": 0.4131,
      "step": 727
    },
    {
      "epoch": 0.7282048076021381,
      "grad_norm": 0.1890711784362793,
      "learning_rate": 0.0001516711229946524,
      "loss": 0.4078,
      "step": 728
    },
    {
      "epoch": 0.7292050889312619,
      "grad_norm": 0.19632087647914886,
      "learning_rate": 0.00015160427807486634,
      "loss": 0.4217,
      "step": 729
    },
    {
      "epoch": 0.7302053702603858,
      "grad_norm": 0.19930745661258698,
      "learning_rate": 0.00015153743315508023,
      "loss": 0.4207,
      "step": 730
    },
    {
      "epoch": 0.7312056515895096,
      "grad_norm": 0.19354170560836792,
      "learning_rate": 0.00015147058823529412,
      "loss": 0.4103,
      "step": 731
    },
    {
      "epoch": 0.7322059329186333,
      "grad_norm": 0.19946269690990448,
      "learning_rate": 0.000151403743315508,
      "loss": 0.4172,
      "step": 732
    },
    {
      "epoch": 0.7332062142477572,
      "grad_norm": 0.19974975287914276,
      "learning_rate": 0.00015133689839572193,
      "loss": 0.4233,
      "step": 733
    },
    {
      "epoch": 0.734206495576881,
      "grad_norm": 0.21595142781734467,
      "learning_rate": 0.00015127005347593584,
      "loss": 0.3985,
      "step": 734
    },
    {
      "epoch": 0.7352067769060048,
      "grad_norm": 0.19416721165180206,
      "learning_rate": 0.00015120320855614974,
      "loss": 0.421,
      "step": 735
    },
    {
      "epoch": 0.7362070582351287,
      "grad_norm": 0.1955777257680893,
      "learning_rate": 0.00015113636363636365,
      "loss": 0.4113,
      "step": 736
    },
    {
      "epoch": 0.7372073395642524,
      "grad_norm": 0.20378634333610535,
      "learning_rate": 0.00015106951871657754,
      "loss": 0.3981,
      "step": 737
    },
    {
      "epoch": 0.7382076208933762,
      "grad_norm": 0.2140418440103531,
      "learning_rate": 0.00015100267379679146,
      "loss": 0.408,
      "step": 738
    },
    {
      "epoch": 0.7392079022225001,
      "grad_norm": 0.20906782150268555,
      "learning_rate": 0.00015093582887700535,
      "loss": 0.4229,
      "step": 739
    },
    {
      "epoch": 0.7402081835516239,
      "grad_norm": 0.18470560014247894,
      "learning_rate": 0.00015086898395721927,
      "loss": 0.4081,
      "step": 740
    },
    {
      "epoch": 0.7412084648807478,
      "grad_norm": 0.2016621083021164,
      "learning_rate": 0.00015080213903743316,
      "loss": 0.4322,
      "step": 741
    },
    {
      "epoch": 0.7422087462098715,
      "grad_norm": 0.19706487655639648,
      "learning_rate": 0.00015073529411764705,
      "loss": 0.3831,
      "step": 742
    },
    {
      "epoch": 0.7432090275389953,
      "grad_norm": 0.1912582516670227,
      "learning_rate": 0.00015066844919786097,
      "loss": 0.4026,
      "step": 743
    },
    {
      "epoch": 0.7442093088681192,
      "grad_norm": 0.18984350562095642,
      "learning_rate": 0.0001506016042780749,
      "loss": 0.4241,
      "step": 744
    },
    {
      "epoch": 0.745209590197243,
      "grad_norm": 0.198713019490242,
      "learning_rate": 0.00015053475935828878,
      "loss": 0.398,
      "step": 745
    },
    {
      "epoch": 0.7462098715263668,
      "grad_norm": 0.20366474986076355,
      "learning_rate": 0.00015046791443850267,
      "loss": 0.4345,
      "step": 746
    },
    {
      "epoch": 0.7472101528554906,
      "grad_norm": 0.1894349753856659,
      "learning_rate": 0.0001504010695187166,
      "loss": 0.4107,
      "step": 747
    },
    {
      "epoch": 0.7482104341846144,
      "grad_norm": 0.23197326064109802,
      "learning_rate": 0.0001503342245989305,
      "loss": 0.4047,
      "step": 748
    },
    {
      "epoch": 0.7492107155137382,
      "grad_norm": 0.1987650841474533,
      "learning_rate": 0.0001502673796791444,
      "loss": 0.4227,
      "step": 749
    },
    {
      "epoch": 0.7502109968428621,
      "grad_norm": 0.19031840562820435,
      "learning_rate": 0.0001502005347593583,
      "loss": 0.3873,
      "step": 750
    },
    {
      "epoch": 0.7512112781719859,
      "grad_norm": 0.21255357563495636,
      "learning_rate": 0.00015013368983957218,
      "loss": 0.4128,
      "step": 751
    },
    {
      "epoch": 0.7522115595011097,
      "grad_norm": 0.1933545023202896,
      "learning_rate": 0.0001500668449197861,
      "loss": 0.4146,
      "step": 752
    },
    {
      "epoch": 0.7532118408302335,
      "grad_norm": 0.19557367265224457,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.421,
      "step": 753
    },
    {
      "epoch": 0.7542121221593573,
      "grad_norm": 0.19831734895706177,
      "learning_rate": 0.0001499331550802139,
      "loss": 0.4075,
      "step": 754
    },
    {
      "epoch": 0.7552124034884812,
      "grad_norm": 0.19866791367530823,
      "learning_rate": 0.00014986631016042782,
      "loss": 0.3993,
      "step": 755
    },
    {
      "epoch": 0.756212684817605,
      "grad_norm": 0.1984596997499466,
      "learning_rate": 0.0001497994652406417,
      "loss": 0.4249,
      "step": 756
    },
    {
      "epoch": 0.7572129661467287,
      "grad_norm": 0.24051056802272797,
      "learning_rate": 0.00014973262032085563,
      "loss": 0.4178,
      "step": 757
    },
    {
      "epoch": 0.7582132474758526,
      "grad_norm": 0.20931924879550934,
      "learning_rate": 0.00014966577540106952,
      "loss": 0.4361,
      "step": 758
    },
    {
      "epoch": 0.7592135288049764,
      "grad_norm": 0.19387286901474,
      "learning_rate": 0.00014959893048128344,
      "loss": 0.4251,
      "step": 759
    },
    {
      "epoch": 0.7602138101341002,
      "grad_norm": 0.20487485826015472,
      "learning_rate": 0.00014953208556149733,
      "loss": 0.4252,
      "step": 760
    },
    {
      "epoch": 0.761214091463224,
      "grad_norm": 0.20621798932552338,
      "learning_rate": 0.00014946524064171122,
      "loss": 0.4211,
      "step": 761
    },
    {
      "epoch": 0.7622143727923478,
      "grad_norm": 0.19528158009052277,
      "learning_rate": 0.00014939839572192514,
      "loss": 0.4267,
      "step": 762
    },
    {
      "epoch": 0.7632146541214717,
      "grad_norm": 0.1847756803035736,
      "learning_rate": 0.00014933155080213906,
      "loss": 0.4113,
      "step": 763
    },
    {
      "epoch": 0.7642149354505955,
      "grad_norm": 0.20398756861686707,
      "learning_rate": 0.00014926470588235295,
      "loss": 0.4291,
      "step": 764
    },
    {
      "epoch": 0.7652152167797193,
      "grad_norm": 0.19679030776023865,
      "learning_rate": 0.00014919786096256684,
      "loss": 0.4124,
      "step": 765
    },
    {
      "epoch": 0.7662154981088432,
      "grad_norm": 0.18626010417938232,
      "learning_rate": 0.00014913101604278076,
      "loss": 0.3909,
      "step": 766
    },
    {
      "epoch": 0.7672157794379669,
      "grad_norm": 0.19373048841953278,
      "learning_rate": 0.00014906417112299468,
      "loss": 0.4093,
      "step": 767
    },
    {
      "epoch": 0.7682160607670907,
      "grad_norm": 0.20928546786308289,
      "learning_rate": 0.00014899732620320857,
      "loss": 0.41,
      "step": 768
    },
    {
      "epoch": 0.7692163420962146,
      "grad_norm": 0.18646028637886047,
      "learning_rate": 0.00014893048128342246,
      "loss": 0.4079,
      "step": 769
    },
    {
      "epoch": 0.7702166234253384,
      "grad_norm": 0.19709910452365875,
      "learning_rate": 0.00014886363636363635,
      "loss": 0.4068,
      "step": 770
    },
    {
      "epoch": 0.7712169047544621,
      "grad_norm": 0.19466939568519592,
      "learning_rate": 0.0001487967914438503,
      "loss": 0.4153,
      "step": 771
    },
    {
      "epoch": 0.772217186083586,
      "grad_norm": 0.19923321902751923,
      "learning_rate": 0.00014872994652406418,
      "loss": 0.4351,
      "step": 772
    },
    {
      "epoch": 0.7732174674127098,
      "grad_norm": 0.1893264651298523,
      "learning_rate": 0.00014866310160427807,
      "loss": 0.3978,
      "step": 773
    },
    {
      "epoch": 0.7742177487418337,
      "grad_norm": 0.2007315307855606,
      "learning_rate": 0.000148596256684492,
      "loss": 0.406,
      "step": 774
    },
    {
      "epoch": 0.7752180300709575,
      "grad_norm": 0.18538321554660797,
      "learning_rate": 0.00014852941176470588,
      "loss": 0.4136,
      "step": 775
    },
    {
      "epoch": 0.7762183114000812,
      "grad_norm": 0.2008058875799179,
      "learning_rate": 0.0001484625668449198,
      "loss": 0.405,
      "step": 776
    },
    {
      "epoch": 0.7772185927292051,
      "grad_norm": 0.18931308388710022,
      "learning_rate": 0.0001483957219251337,
      "loss": 0.3626,
      "step": 777
    },
    {
      "epoch": 0.7782188740583289,
      "grad_norm": 0.19763785600662231,
      "learning_rate": 0.0001483288770053476,
      "loss": 0.3876,
      "step": 778
    },
    {
      "epoch": 0.7792191553874527,
      "grad_norm": 0.19422905147075653,
      "learning_rate": 0.0001482620320855615,
      "loss": 0.4207,
      "step": 779
    },
    {
      "epoch": 0.7802194367165766,
      "grad_norm": 0.19686779379844666,
      "learning_rate": 0.00014819518716577542,
      "loss": 0.4094,
      "step": 780
    },
    {
      "epoch": 0.7812197180457003,
      "grad_norm": 0.19326677918434143,
      "learning_rate": 0.0001481283422459893,
      "loss": 0.4104,
      "step": 781
    },
    {
      "epoch": 0.7822199993748241,
      "grad_norm": 0.20089313387870789,
      "learning_rate": 0.00014806149732620323,
      "loss": 0.4242,
      "step": 782
    },
    {
      "epoch": 0.783220280703948,
      "grad_norm": 0.21526865661144257,
      "learning_rate": 0.00014799465240641712,
      "loss": 0.3968,
      "step": 783
    },
    {
      "epoch": 0.7842205620330718,
      "grad_norm": 0.19246849417686462,
      "learning_rate": 0.000147927807486631,
      "loss": 0.4362,
      "step": 784
    },
    {
      "epoch": 0.7852208433621957,
      "grad_norm": 0.18495364487171173,
      "learning_rate": 0.00014786096256684493,
      "loss": 0.3996,
      "step": 785
    },
    {
      "epoch": 0.7862211246913194,
      "grad_norm": 0.20154619216918945,
      "learning_rate": 0.00014779411764705884,
      "loss": 0.412,
      "step": 786
    },
    {
      "epoch": 0.7872214060204432,
      "grad_norm": 0.18654684722423553,
      "learning_rate": 0.00014772727272727274,
      "loss": 0.3822,
      "step": 787
    },
    {
      "epoch": 0.7882216873495671,
      "grad_norm": 0.19422447681427002,
      "learning_rate": 0.00014766042780748663,
      "loss": 0.4149,
      "step": 788
    },
    {
      "epoch": 0.7892219686786909,
      "grad_norm": 0.18254871666431427,
      "learning_rate": 0.00014759358288770054,
      "loss": 0.4055,
      "step": 789
    },
    {
      "epoch": 0.7902222500078147,
      "grad_norm": 0.19582059979438782,
      "learning_rate": 0.00014752673796791446,
      "loss": 0.4321,
      "step": 790
    },
    {
      "epoch": 0.7912225313369385,
      "grad_norm": 0.19865649938583374,
      "learning_rate": 0.00014745989304812835,
      "loss": 0.3921,
      "step": 791
    },
    {
      "epoch": 0.7922228126660623,
      "grad_norm": 0.19461636245250702,
      "learning_rate": 0.00014739304812834224,
      "loss": 0.3978,
      "step": 792
    },
    {
      "epoch": 0.7932230939951862,
      "grad_norm": 0.19305653870105743,
      "learning_rate": 0.00014732620320855613,
      "loss": 0.4194,
      "step": 793
    },
    {
      "epoch": 0.79422337532431,
      "grad_norm": 0.19069482386112213,
      "learning_rate": 0.00014725935828877008,
      "loss": 0.3992,
      "step": 794
    },
    {
      "epoch": 0.7952236566534338,
      "grad_norm": 0.1960972100496292,
      "learning_rate": 0.00014719251336898397,
      "loss": 0.4195,
      "step": 795
    },
    {
      "epoch": 0.7962239379825576,
      "grad_norm": 0.19313237071037292,
      "learning_rate": 0.00014712566844919786,
      "loss": 0.3921,
      "step": 796
    },
    {
      "epoch": 0.7972242193116814,
      "grad_norm": 0.19083590805530548,
      "learning_rate": 0.00014705882352941178,
      "loss": 0.4348,
      "step": 797
    },
    {
      "epoch": 0.7982245006408052,
      "grad_norm": 0.19219085574150085,
      "learning_rate": 0.00014699197860962567,
      "loss": 0.3964,
      "step": 798
    },
    {
      "epoch": 0.7992247819699291,
      "grad_norm": 0.18544498085975647,
      "learning_rate": 0.0001469251336898396,
      "loss": 0.3758,
      "step": 799
    },
    {
      "epoch": 0.8002250632990529,
      "grad_norm": 0.18522986769676208,
      "learning_rate": 0.00014685828877005348,
      "loss": 0.4049,
      "step": 800
    },
    {
      "epoch": 0.8012253446281766,
      "grad_norm": 0.18968360126018524,
      "learning_rate": 0.0001467914438502674,
      "loss": 0.401,
      "step": 801
    },
    {
      "epoch": 0.8022256259573005,
      "grad_norm": 0.18599694967269897,
      "learning_rate": 0.0001467245989304813,
      "loss": 0.3816,
      "step": 802
    },
    {
      "epoch": 0.8032259072864243,
      "grad_norm": 0.19700609147548676,
      "learning_rate": 0.0001466577540106952,
      "loss": 0.4032,
      "step": 803
    },
    {
      "epoch": 0.8042261886155482,
      "grad_norm": 0.19293420016765594,
      "learning_rate": 0.0001465909090909091,
      "loss": 0.4081,
      "step": 804
    },
    {
      "epoch": 0.805226469944672,
      "grad_norm": 0.189544215798378,
      "learning_rate": 0.00014652406417112301,
      "loss": 0.4097,
      "step": 805
    },
    {
      "epoch": 0.8062267512737957,
      "grad_norm": 0.1902182549238205,
      "learning_rate": 0.0001464572192513369,
      "loss": 0.4132,
      "step": 806
    },
    {
      "epoch": 0.8072270326029196,
      "grad_norm": 0.19499337673187256,
      "learning_rate": 0.0001463903743315508,
      "loss": 0.4177,
      "step": 807
    },
    {
      "epoch": 0.8082273139320434,
      "grad_norm": 0.19247886538505554,
      "learning_rate": 0.0001463235294117647,
      "loss": 0.4056,
      "step": 808
    },
    {
      "epoch": 0.8092275952611672,
      "grad_norm": 0.19226518273353577,
      "learning_rate": 0.00014625668449197863,
      "loss": 0.3919,
      "step": 809
    },
    {
      "epoch": 0.810227876590291,
      "grad_norm": 0.19893218576908112,
      "learning_rate": 0.00014618983957219252,
      "loss": 0.3915,
      "step": 810
    },
    {
      "epoch": 0.8112281579194148,
      "grad_norm": 0.18768532574176788,
      "learning_rate": 0.0001461229946524064,
      "loss": 0.3935,
      "step": 811
    },
    {
      "epoch": 0.8122284392485386,
      "grad_norm": 0.19249343872070312,
      "learning_rate": 0.00014605614973262033,
      "loss": 0.4218,
      "step": 812
    },
    {
      "epoch": 0.8132287205776625,
      "grad_norm": 0.26103681325912476,
      "learning_rate": 0.00014598930481283425,
      "loss": 0.4061,
      "step": 813
    },
    {
      "epoch": 0.8142290019067863,
      "grad_norm": 0.21007131040096283,
      "learning_rate": 0.00014592245989304814,
      "loss": 0.4116,
      "step": 814
    },
    {
      "epoch": 0.8152292832359102,
      "grad_norm": 0.1864834874868393,
      "learning_rate": 0.00014585561497326203,
      "loss": 0.4016,
      "step": 815
    },
    {
      "epoch": 0.8162295645650339,
      "grad_norm": 0.20848610997200012,
      "learning_rate": 0.00014578877005347595,
      "loss": 0.4393,
      "step": 816
    },
    {
      "epoch": 0.8172298458941577,
      "grad_norm": 0.22143127024173737,
      "learning_rate": 0.00014572192513368984,
      "loss": 0.4265,
      "step": 817
    },
    {
      "epoch": 0.8182301272232816,
      "grad_norm": 0.19629213213920593,
      "learning_rate": 0.00014565508021390376,
      "loss": 0.4302,
      "step": 818
    },
    {
      "epoch": 0.8192304085524054,
      "grad_norm": 0.19536511600017548,
      "learning_rate": 0.00014558823529411765,
      "loss": 0.4124,
      "step": 819
    },
    {
      "epoch": 0.8202306898815291,
      "grad_norm": 0.18831172585487366,
      "learning_rate": 0.00014552139037433157,
      "loss": 0.4133,
      "step": 820
    },
    {
      "epoch": 0.821230971210653,
      "grad_norm": 0.21315617859363556,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.4034,
      "step": 821
    },
    {
      "epoch": 0.8222312525397768,
      "grad_norm": 0.22125715017318726,
      "learning_rate": 0.00014538770053475937,
      "loss": 0.4272,
      "step": 822
    },
    {
      "epoch": 0.8232315338689006,
      "grad_norm": 0.1944158673286438,
      "learning_rate": 0.00014532085561497327,
      "loss": 0.4036,
      "step": 823
    },
    {
      "epoch": 0.8242318151980245,
      "grad_norm": 0.19563493132591248,
      "learning_rate": 0.00014525401069518718,
      "loss": 0.4137,
      "step": 824
    },
    {
      "epoch": 0.8252320965271482,
      "grad_norm": 0.19111137092113495,
      "learning_rate": 0.00014518716577540107,
      "loss": 0.3807,
      "step": 825
    },
    {
      "epoch": 0.8262323778562721,
      "grad_norm": 0.20833520591259003,
      "learning_rate": 0.00014512032085561496,
      "loss": 0.4162,
      "step": 826
    },
    {
      "epoch": 0.8272326591853959,
      "grad_norm": 0.19991528987884521,
      "learning_rate": 0.00014505347593582888,
      "loss": 0.4138,
      "step": 827
    },
    {
      "epoch": 0.8282329405145197,
      "grad_norm": 0.18485002219676971,
      "learning_rate": 0.0001449866310160428,
      "loss": 0.394,
      "step": 828
    },
    {
      "epoch": 0.8292332218436436,
      "grad_norm": 0.21205921471118927,
      "learning_rate": 0.0001449197860962567,
      "loss": 0.4111,
      "step": 829
    },
    {
      "epoch": 0.8302335031727673,
      "grad_norm": 0.201129749417305,
      "learning_rate": 0.00014485294117647058,
      "loss": 0.433,
      "step": 830
    },
    {
      "epoch": 0.8312337845018911,
      "grad_norm": 0.1909693330526352,
      "learning_rate": 0.0001447860962566845,
      "loss": 0.3912,
      "step": 831
    },
    {
      "epoch": 0.832234065831015,
      "grad_norm": 0.19338278472423553,
      "learning_rate": 0.00014471925133689842,
      "loss": 0.3838,
      "step": 832
    },
    {
      "epoch": 0.8332343471601388,
      "grad_norm": 0.21037954092025757,
      "learning_rate": 0.0001446524064171123,
      "loss": 0.3972,
      "step": 833
    },
    {
      "epoch": 0.8342346284892626,
      "grad_norm": 0.20426346361637115,
      "learning_rate": 0.0001445855614973262,
      "loss": 0.4192,
      "step": 834
    },
    {
      "epoch": 0.8352349098183864,
      "grad_norm": 0.19156718254089355,
      "learning_rate": 0.0001445187165775401,
      "loss": 0.4063,
      "step": 835
    },
    {
      "epoch": 0.8362351911475102,
      "grad_norm": 0.19791381061077118,
      "learning_rate": 0.00014445187165775404,
      "loss": 0.3998,
      "step": 836
    },
    {
      "epoch": 0.8372354724766341,
      "grad_norm": 0.19495005905628204,
      "learning_rate": 0.00014438502673796793,
      "loss": 0.4109,
      "step": 837
    },
    {
      "epoch": 0.8382357538057579,
      "grad_norm": 0.20204126834869385,
      "learning_rate": 0.00014431818181818182,
      "loss": 0.4349,
      "step": 838
    },
    {
      "epoch": 0.8392360351348817,
      "grad_norm": 0.18330642580986023,
      "learning_rate": 0.00014425133689839574,
      "loss": 0.3767,
      "step": 839
    },
    {
      "epoch": 0.8402363164640055,
      "grad_norm": 0.19165022671222687,
      "learning_rate": 0.00014418449197860963,
      "loss": 0.3895,
      "step": 840
    },
    {
      "epoch": 0.8412365977931293,
      "grad_norm": 0.21169708669185638,
      "learning_rate": 0.00014411764705882354,
      "loss": 0.4302,
      "step": 841
    },
    {
      "epoch": 0.8422368791222531,
      "grad_norm": 0.19759634137153625,
      "learning_rate": 0.00014405080213903743,
      "loss": 0.4145,
      "step": 842
    },
    {
      "epoch": 0.843237160451377,
      "grad_norm": 0.19510769844055176,
      "learning_rate": 0.00014398395721925135,
      "loss": 0.412,
      "step": 843
    },
    {
      "epoch": 0.8442374417805008,
      "grad_norm": 0.18549752235412598,
      "learning_rate": 0.00014391711229946524,
      "loss": 0.3985,
      "step": 844
    },
    {
      "epoch": 0.8452377231096245,
      "grad_norm": 0.19543305039405823,
      "learning_rate": 0.00014385026737967916,
      "loss": 0.3958,
      "step": 845
    },
    {
      "epoch": 0.8462380044387484,
      "grad_norm": 0.21237945556640625,
      "learning_rate": 0.00014378342245989305,
      "loss": 0.4358,
      "step": 846
    },
    {
      "epoch": 0.8472382857678722,
      "grad_norm": 0.2078273743391037,
      "learning_rate": 0.00014371657754010697,
      "loss": 0.4052,
      "step": 847
    },
    {
      "epoch": 0.8482385670969961,
      "grad_norm": 0.19445757567882538,
      "learning_rate": 0.00014364973262032086,
      "loss": 0.3894,
      "step": 848
    },
    {
      "epoch": 0.8492388484261199,
      "grad_norm": 0.19637370109558105,
      "learning_rate": 0.00014358288770053475,
      "loss": 0.4182,
      "step": 849
    },
    {
      "epoch": 0.8502391297552436,
      "grad_norm": 0.18749427795410156,
      "learning_rate": 0.00014351604278074867,
      "loss": 0.4133,
      "step": 850
    },
    {
      "epoch": 0.8512394110843675,
      "grad_norm": 0.1948145627975464,
      "learning_rate": 0.0001434491978609626,
      "loss": 0.4073,
      "step": 851
    },
    {
      "epoch": 0.8522396924134913,
      "grad_norm": 0.1908993422985077,
      "learning_rate": 0.00014338235294117648,
      "loss": 0.4159,
      "step": 852
    },
    {
      "epoch": 0.8532399737426151,
      "grad_norm": 0.19122084975242615,
      "learning_rate": 0.00014331550802139037,
      "loss": 0.389,
      "step": 853
    },
    {
      "epoch": 0.854240255071739,
      "grad_norm": 0.1932574212551117,
      "learning_rate": 0.0001432486631016043,
      "loss": 0.3855,
      "step": 854
    },
    {
      "epoch": 0.8552405364008627,
      "grad_norm": 0.19349347054958344,
      "learning_rate": 0.0001431818181818182,
      "loss": 0.4059,
      "step": 855
    },
    {
      "epoch": 0.8562408177299866,
      "grad_norm": 0.18627986311912537,
      "learning_rate": 0.0001431149732620321,
      "loss": 0.3821,
      "step": 856
    },
    {
      "epoch": 0.8572410990591104,
      "grad_norm": 0.19790273904800415,
      "learning_rate": 0.000143048128342246,
      "loss": 0.4068,
      "step": 857
    },
    {
      "epoch": 0.8582413803882342,
      "grad_norm": 0.1822570115327835,
      "learning_rate": 0.0001429812834224599,
      "loss": 0.3733,
      "step": 858
    },
    {
      "epoch": 0.859241661717358,
      "grad_norm": 0.18301276862621307,
      "learning_rate": 0.0001429144385026738,
      "loss": 0.4247,
      "step": 859
    },
    {
      "epoch": 0.8602419430464818,
      "grad_norm": 0.19230306148529053,
      "learning_rate": 0.0001428475935828877,
      "loss": 0.3773,
      "step": 860
    },
    {
      "epoch": 0.8612422243756056,
      "grad_norm": 0.18965975940227509,
      "learning_rate": 0.0001427807486631016,
      "loss": 0.3945,
      "step": 861
    },
    {
      "epoch": 0.8622425057047295,
      "grad_norm": 0.19626930356025696,
      "learning_rate": 0.00014271390374331552,
      "loss": 0.3895,
      "step": 862
    },
    {
      "epoch": 0.8632427870338533,
      "grad_norm": 0.1954018473625183,
      "learning_rate": 0.0001426470588235294,
      "loss": 0.4196,
      "step": 863
    },
    {
      "epoch": 0.864243068362977,
      "grad_norm": 0.1949518918991089,
      "learning_rate": 0.00014258021390374333,
      "loss": 0.4153,
      "step": 864
    },
    {
      "epoch": 0.8652433496921009,
      "grad_norm": 0.18893876671791077,
      "learning_rate": 0.00014251336898395722,
      "loss": 0.3873,
      "step": 865
    },
    {
      "epoch": 0.8662436310212247,
      "grad_norm": 0.18110498785972595,
      "learning_rate": 0.00014244652406417114,
      "loss": 0.3784,
      "step": 866
    },
    {
      "epoch": 0.8672439123503486,
      "grad_norm": 0.19815553724765778,
      "learning_rate": 0.00014237967914438503,
      "loss": 0.4201,
      "step": 867
    },
    {
      "epoch": 0.8682441936794724,
      "grad_norm": 0.19284170866012573,
      "learning_rate": 0.00014231283422459892,
      "loss": 0.4379,
      "step": 868
    },
    {
      "epoch": 0.8692444750085961,
      "grad_norm": 0.1822151243686676,
      "learning_rate": 0.00014224598930481284,
      "loss": 0.4033,
      "step": 869
    },
    {
      "epoch": 0.87024475633772,
      "grad_norm": 0.18983180820941925,
      "learning_rate": 0.00014217914438502676,
      "loss": 0.3911,
      "step": 870
    },
    {
      "epoch": 0.8712450376668438,
      "grad_norm": 0.19837361574172974,
      "learning_rate": 0.00014211229946524065,
      "loss": 0.4106,
      "step": 871
    },
    {
      "epoch": 0.8722453189959676,
      "grad_norm": 0.1911575049161911,
      "learning_rate": 0.00014204545454545454,
      "loss": 0.4282,
      "step": 872
    },
    {
      "epoch": 0.8732456003250915,
      "grad_norm": 0.19261616468429565,
      "learning_rate": 0.00014197860962566846,
      "loss": 0.4085,
      "step": 873
    },
    {
      "epoch": 0.8742458816542152,
      "grad_norm": 0.19099479913711548,
      "learning_rate": 0.00014191176470588237,
      "loss": 0.4055,
      "step": 874
    },
    {
      "epoch": 0.875246162983339,
      "grad_norm": 0.1838652789592743,
      "learning_rate": 0.00014184491978609627,
      "loss": 0.4093,
      "step": 875
    },
    {
      "epoch": 0.8762464443124629,
      "grad_norm": 0.19491593539714813,
      "learning_rate": 0.00014177807486631016,
      "loss": 0.4038,
      "step": 876
    },
    {
      "epoch": 0.8772467256415867,
      "grad_norm": 0.1958649605512619,
      "learning_rate": 0.00014171122994652405,
      "loss": 0.4033,
      "step": 877
    },
    {
      "epoch": 0.8782470069707106,
      "grad_norm": 0.20690329372882843,
      "learning_rate": 0.000141644385026738,
      "loss": 0.4028,
      "step": 878
    },
    {
      "epoch": 0.8792472882998343,
      "grad_norm": 0.1854771077632904,
      "learning_rate": 0.00014157754010695188,
      "loss": 0.3845,
      "step": 879
    },
    {
      "epoch": 0.8802475696289581,
      "grad_norm": 0.18194234371185303,
      "learning_rate": 0.00014151069518716577,
      "loss": 0.3828,
      "step": 880
    },
    {
      "epoch": 0.881247850958082,
      "grad_norm": 0.2217295914888382,
      "learning_rate": 0.0001414438502673797,
      "loss": 0.3996,
      "step": 881
    },
    {
      "epoch": 0.8822481322872058,
      "grad_norm": 0.2215280830860138,
      "learning_rate": 0.00014137700534759358,
      "loss": 0.4146,
      "step": 882
    },
    {
      "epoch": 0.8832484136163296,
      "grad_norm": 0.18286478519439697,
      "learning_rate": 0.0001413101604278075,
      "loss": 0.4079,
      "step": 883
    },
    {
      "epoch": 0.8842486949454534,
      "grad_norm": 0.1921008825302124,
      "learning_rate": 0.0001412433155080214,
      "loss": 0.3982,
      "step": 884
    },
    {
      "epoch": 0.8852489762745772,
      "grad_norm": 0.23457936942577362,
      "learning_rate": 0.0001411764705882353,
      "loss": 0.4247,
      "step": 885
    },
    {
      "epoch": 0.886249257603701,
      "grad_norm": 0.19752724468708038,
      "learning_rate": 0.0001411096256684492,
      "loss": 0.4032,
      "step": 886
    },
    {
      "epoch": 0.8872495389328249,
      "grad_norm": 0.19050294160842896,
      "learning_rate": 0.00014104278074866312,
      "loss": 0.3852,
      "step": 887
    },
    {
      "epoch": 0.8882498202619487,
      "grad_norm": 0.19361421465873718,
      "learning_rate": 0.000140975935828877,
      "loss": 0.411,
      "step": 888
    },
    {
      "epoch": 0.8892501015910725,
      "grad_norm": 0.19875557720661163,
      "learning_rate": 0.00014090909090909093,
      "loss": 0.3992,
      "step": 889
    },
    {
      "epoch": 0.8902503829201963,
      "grad_norm": 0.19662436842918396,
      "learning_rate": 0.00014084224598930482,
      "loss": 0.402,
      "step": 890
    },
    {
      "epoch": 0.8912506642493201,
      "grad_norm": 0.19621172547340393,
      "learning_rate": 0.0001407754010695187,
      "loss": 0.4035,
      "step": 891
    },
    {
      "epoch": 0.892250945578444,
      "grad_norm": 0.19263717532157898,
      "learning_rate": 0.00014070855614973263,
      "loss": 0.4006,
      "step": 892
    },
    {
      "epoch": 0.8932512269075678,
      "grad_norm": 0.205947607755661,
      "learning_rate": 0.00014064171122994654,
      "loss": 0.3843,
      "step": 893
    },
    {
      "epoch": 0.8942515082366915,
      "grad_norm": 0.20859695971012115,
      "learning_rate": 0.00014057486631016043,
      "loss": 0.4166,
      "step": 894
    },
    {
      "epoch": 0.8952517895658154,
      "grad_norm": 0.1934015452861786,
      "learning_rate": 0.00014050802139037433,
      "loss": 0.4036,
      "step": 895
    },
    {
      "epoch": 0.8962520708949392,
      "grad_norm": 0.1981888711452484,
      "learning_rate": 0.00014044117647058824,
      "loss": 0.4273,
      "step": 896
    },
    {
      "epoch": 0.897252352224063,
      "grad_norm": 0.18072594702243805,
      "learning_rate": 0.00014037433155080216,
      "loss": 0.4082,
      "step": 897
    },
    {
      "epoch": 0.8982526335531869,
      "grad_norm": 0.194056436419487,
      "learning_rate": 0.00014030748663101605,
      "loss": 0.4265,
      "step": 898
    },
    {
      "epoch": 0.8992529148823106,
      "grad_norm": 0.2134423702955246,
      "learning_rate": 0.00014024064171122994,
      "loss": 0.448,
      "step": 899
    },
    {
      "epoch": 0.9002531962114345,
      "grad_norm": 0.1929604560136795,
      "learning_rate": 0.00014017379679144386,
      "loss": 0.4071,
      "step": 900
    },
    {
      "epoch": 0.9012534775405583,
      "grad_norm": 0.1836298108100891,
      "learning_rate": 0.00014010695187165778,
      "loss": 0.4155,
      "step": 901
    },
    {
      "epoch": 0.9022537588696821,
      "grad_norm": 0.1737600564956665,
      "learning_rate": 0.00014004010695187167,
      "loss": 0.3779,
      "step": 902
    },
    {
      "epoch": 0.903254040198806,
      "grad_norm": 0.18683408200740814,
      "learning_rate": 0.00013997326203208556,
      "loss": 0.3882,
      "step": 903
    },
    {
      "epoch": 0.9042543215279297,
      "grad_norm": 0.19765792787075043,
      "learning_rate": 0.00013990641711229948,
      "loss": 0.4063,
      "step": 904
    },
    {
      "epoch": 0.9052546028570535,
      "grad_norm": 0.1815849095582962,
      "learning_rate": 0.00013983957219251337,
      "loss": 0.3943,
      "step": 905
    },
    {
      "epoch": 0.9062548841861774,
      "grad_norm": 0.18166109919548035,
      "learning_rate": 0.0001397727272727273,
      "loss": 0.4197,
      "step": 906
    },
    {
      "epoch": 0.9072551655153012,
      "grad_norm": 0.1938782036304474,
      "learning_rate": 0.00013970588235294118,
      "loss": 0.4222,
      "step": 907
    },
    {
      "epoch": 0.9082554468444249,
      "grad_norm": 0.1908324807882309,
      "learning_rate": 0.0001396390374331551,
      "loss": 0.421,
      "step": 908
    },
    {
      "epoch": 0.9092557281735488,
      "grad_norm": 0.19173042476177216,
      "learning_rate": 0.000139572192513369,
      "loss": 0.4287,
      "step": 909
    },
    {
      "epoch": 0.9102560095026726,
      "grad_norm": 0.1848210245370865,
      "learning_rate": 0.0001395053475935829,
      "loss": 0.3878,
      "step": 910
    },
    {
      "epoch": 0.9112562908317965,
      "grad_norm": 0.18545983731746674,
      "learning_rate": 0.0001394385026737968,
      "loss": 0.3787,
      "step": 911
    },
    {
      "epoch": 0.9122565721609203,
      "grad_norm": 0.18859964609146118,
      "learning_rate": 0.0001393716577540107,
      "loss": 0.4035,
      "step": 912
    },
    {
      "epoch": 0.913256853490044,
      "grad_norm": 0.19999009370803833,
      "learning_rate": 0.0001393048128342246,
      "loss": 0.4201,
      "step": 913
    },
    {
      "epoch": 0.9142571348191679,
      "grad_norm": 0.18937164545059204,
      "learning_rate": 0.0001392379679144385,
      "loss": 0.4067,
      "step": 914
    },
    {
      "epoch": 0.9152574161482917,
      "grad_norm": 0.1955537647008896,
      "learning_rate": 0.0001391711229946524,
      "loss": 0.3907,
      "step": 915
    },
    {
      "epoch": 0.9162576974774155,
      "grad_norm": 0.19052347540855408,
      "learning_rate": 0.00013910427807486633,
      "loss": 0.377,
      "step": 916
    },
    {
      "epoch": 0.9172579788065394,
      "grad_norm": 0.20451219379901886,
      "learning_rate": 0.00013903743315508022,
      "loss": 0.4162,
      "step": 917
    },
    {
      "epoch": 0.9182582601356631,
      "grad_norm": 0.18245601654052734,
      "learning_rate": 0.0001389705882352941,
      "loss": 0.4064,
      "step": 918
    },
    {
      "epoch": 0.919258541464787,
      "grad_norm": 0.18855002522468567,
      "learning_rate": 0.00013890374331550803,
      "loss": 0.3851,
      "step": 919
    },
    {
      "epoch": 0.9202588227939108,
      "grad_norm": 0.18447360396385193,
      "learning_rate": 0.00013883689839572195,
      "loss": 0.418,
      "step": 920
    },
    {
      "epoch": 0.9212591041230346,
      "grad_norm": 0.20271486043930054,
      "learning_rate": 0.00013877005347593584,
      "loss": 0.4582,
      "step": 921
    },
    {
      "epoch": 0.9222593854521585,
      "grad_norm": 0.182247593998909,
      "learning_rate": 0.00013870320855614973,
      "loss": 0.4142,
      "step": 922
    },
    {
      "epoch": 0.9232596667812822,
      "grad_norm": 0.18392527103424072,
      "learning_rate": 0.00013863636363636365,
      "loss": 0.4052,
      "step": 923
    },
    {
      "epoch": 0.924259948110406,
      "grad_norm": 0.18088680505752563,
      "learning_rate": 0.00013856951871657754,
      "loss": 0.3854,
      "step": 924
    },
    {
      "epoch": 0.9252602294395299,
      "grad_norm": 0.20581799745559692,
      "learning_rate": 0.00013850267379679146,
      "loss": 0.4241,
      "step": 925
    },
    {
      "epoch": 0.9262605107686537,
      "grad_norm": 0.18553832173347473,
      "learning_rate": 0.00013843582887700535,
      "loss": 0.3987,
      "step": 926
    },
    {
      "epoch": 0.9272607920977775,
      "grad_norm": 0.18916752934455872,
      "learning_rate": 0.00013836898395721927,
      "loss": 0.3837,
      "step": 927
    },
    {
      "epoch": 0.9282610734269013,
      "grad_norm": 0.19002124667167664,
      "learning_rate": 0.00013830213903743316,
      "loss": 0.397,
      "step": 928
    },
    {
      "epoch": 0.9292613547560251,
      "grad_norm": 0.19399455189704895,
      "learning_rate": 0.00013823529411764707,
      "loss": 0.3983,
      "step": 929
    },
    {
      "epoch": 0.930261636085149,
      "grad_norm": 0.1906272917985916,
      "learning_rate": 0.00013816844919786096,
      "loss": 0.4185,
      "step": 930
    },
    {
      "epoch": 0.9312619174142728,
      "grad_norm": 0.19948695600032806,
      "learning_rate": 0.00013810160427807488,
      "loss": 0.3916,
      "step": 931
    },
    {
      "epoch": 0.9322621987433966,
      "grad_norm": 0.1945783495903015,
      "learning_rate": 0.00013803475935828877,
      "loss": 0.4098,
      "step": 932
    },
    {
      "epoch": 0.9332624800725204,
      "grad_norm": 0.2003854513168335,
      "learning_rate": 0.00013796791443850266,
      "loss": 0.4151,
      "step": 933
    },
    {
      "epoch": 0.9342627614016442,
      "grad_norm": 0.19745071232318878,
      "learning_rate": 0.00013790106951871658,
      "loss": 0.3925,
      "step": 934
    },
    {
      "epoch": 0.935263042730768,
      "grad_norm": 0.19453400373458862,
      "learning_rate": 0.0001378342245989305,
      "loss": 0.4049,
      "step": 935
    },
    {
      "epoch": 0.9362633240598919,
      "grad_norm": 0.18442165851593018,
      "learning_rate": 0.0001377673796791444,
      "loss": 0.3962,
      "step": 936
    },
    {
      "epoch": 0.9372636053890157,
      "grad_norm": 0.21205684542655945,
      "learning_rate": 0.00013770053475935828,
      "loss": 0.3961,
      "step": 937
    },
    {
      "epoch": 0.9382638867181394,
      "grad_norm": 0.19430594146251678,
      "learning_rate": 0.0001376336898395722,
      "loss": 0.4279,
      "step": 938
    },
    {
      "epoch": 0.9392641680472633,
      "grad_norm": 0.19078563153743744,
      "learning_rate": 0.00013756684491978612,
      "loss": 0.4081,
      "step": 939
    },
    {
      "epoch": 0.9402644493763871,
      "grad_norm": 0.19051305949687958,
      "learning_rate": 0.0001375,
      "loss": 0.4075,
      "step": 940
    },
    {
      "epoch": 0.941264730705511,
      "grad_norm": 0.19989381730556488,
      "learning_rate": 0.0001374331550802139,
      "loss": 0.4026,
      "step": 941
    },
    {
      "epoch": 0.9422650120346348,
      "grad_norm": 0.20693150162696838,
      "learning_rate": 0.00013736631016042782,
      "loss": 0.3989,
      "step": 942
    },
    {
      "epoch": 0.9432652933637585,
      "grad_norm": 0.20523861050605774,
      "learning_rate": 0.00013729946524064173,
      "loss": 0.3831,
      "step": 943
    },
    {
      "epoch": 0.9442655746928824,
      "grad_norm": 0.19736282527446747,
      "learning_rate": 0.00013723262032085563,
      "loss": 0.4122,
      "step": 944
    },
    {
      "epoch": 0.9452658560220062,
      "grad_norm": 0.2001694142818451,
      "learning_rate": 0.00013716577540106952,
      "loss": 0.4116,
      "step": 945
    },
    {
      "epoch": 0.94626613735113,
      "grad_norm": 0.19313780963420868,
      "learning_rate": 0.00013709893048128343,
      "loss": 0.3868,
      "step": 946
    },
    {
      "epoch": 0.9472664186802539,
      "grad_norm": 0.17902351915836334,
      "learning_rate": 0.00013703208556149733,
      "loss": 0.3907,
      "step": 947
    },
    {
      "epoch": 0.9482667000093776,
      "grad_norm": 0.21178662776947021,
      "learning_rate": 0.00013696524064171124,
      "loss": 0.4067,
      "step": 948
    },
    {
      "epoch": 0.9492669813385014,
      "grad_norm": 0.1930374801158905,
      "learning_rate": 0.00013689839572192513,
      "loss": 0.4017,
      "step": 949
    },
    {
      "epoch": 0.9502672626676253,
      "grad_norm": 0.18677884340286255,
      "learning_rate": 0.00013683155080213905,
      "loss": 0.3947,
      "step": 950
    },
    {
      "epoch": 0.9512675439967491,
      "grad_norm": 0.1805962175130844,
      "learning_rate": 0.00013676470588235294,
      "loss": 0.3873,
      "step": 951
    },
    {
      "epoch": 0.952267825325873,
      "grad_norm": 0.19080987572669983,
      "learning_rate": 0.00013669786096256686,
      "loss": 0.4044,
      "step": 952
    },
    {
      "epoch": 0.9532681066549967,
      "grad_norm": 0.19088923931121826,
      "learning_rate": 0.00013663101604278075,
      "loss": 0.3871,
      "step": 953
    },
    {
      "epoch": 0.9542683879841205,
      "grad_norm": 0.19883207976818085,
      "learning_rate": 0.00013656417112299467,
      "loss": 0.4135,
      "step": 954
    },
    {
      "epoch": 0.9552686693132444,
      "grad_norm": 0.1914903074502945,
      "learning_rate": 0.00013649732620320856,
      "loss": 0.4015,
      "step": 955
    },
    {
      "epoch": 0.9562689506423682,
      "grad_norm": 0.18231062591075897,
      "learning_rate": 0.00013643048128342245,
      "loss": 0.4047,
      "step": 956
    },
    {
      "epoch": 0.9572692319714919,
      "grad_norm": 0.18952369689941406,
      "learning_rate": 0.00013636363636363637,
      "loss": 0.3996,
      "step": 957
    },
    {
      "epoch": 0.9582695133006158,
      "grad_norm": 0.1904633492231369,
      "learning_rate": 0.0001362967914438503,
      "loss": 0.4056,
      "step": 958
    },
    {
      "epoch": 0.9592697946297396,
      "grad_norm": 0.20127776265144348,
      "learning_rate": 0.00013622994652406418,
      "loss": 0.4077,
      "step": 959
    },
    {
      "epoch": 0.9602700759588634,
      "grad_norm": 0.19195671379566193,
      "learning_rate": 0.00013616310160427807,
      "loss": 0.4047,
      "step": 960
    },
    {
      "epoch": 0.9612703572879873,
      "grad_norm": 0.20003171265125275,
      "learning_rate": 0.00013609625668449199,
      "loss": 0.4066,
      "step": 961
    },
    {
      "epoch": 0.962270638617111,
      "grad_norm": 0.19859673082828522,
      "learning_rate": 0.0001360294117647059,
      "loss": 0.4277,
      "step": 962
    },
    {
      "epoch": 0.9632709199462349,
      "grad_norm": 0.1955680102109909,
      "learning_rate": 0.0001359625668449198,
      "loss": 0.4011,
      "step": 963
    },
    {
      "epoch": 0.9642712012753587,
      "grad_norm": 0.20077423751354218,
      "learning_rate": 0.00013589572192513369,
      "loss": 0.3947,
      "step": 964
    },
    {
      "epoch": 0.9652714826044825,
      "grad_norm": 0.17562292516231537,
      "learning_rate": 0.0001358288770053476,
      "loss": 0.3796,
      "step": 965
    },
    {
      "epoch": 0.9662717639336064,
      "grad_norm": 0.1909385472536087,
      "learning_rate": 0.0001357620320855615,
      "loss": 0.399,
      "step": 966
    },
    {
      "epoch": 0.9672720452627301,
      "grad_norm": 0.19191795587539673,
      "learning_rate": 0.0001356951871657754,
      "loss": 0.4139,
      "step": 967
    },
    {
      "epoch": 0.9682723265918539,
      "grad_norm": 0.19651272892951965,
      "learning_rate": 0.0001356283422459893,
      "loss": 0.4189,
      "step": 968
    },
    {
      "epoch": 0.9692726079209778,
      "grad_norm": 0.17839667201042175,
      "learning_rate": 0.00013556149732620322,
      "loss": 0.3686,
      "step": 969
    },
    {
      "epoch": 0.9702728892501016,
      "grad_norm": 0.19457711279392242,
      "learning_rate": 0.0001354946524064171,
      "loss": 0.3994,
      "step": 970
    },
    {
      "epoch": 0.9712731705792254,
      "grad_norm": 0.19300119578838348,
      "learning_rate": 0.00013542780748663103,
      "loss": 0.395,
      "step": 971
    },
    {
      "epoch": 0.9722734519083492,
      "grad_norm": 0.1862468272447586,
      "learning_rate": 0.00013536096256684492,
      "loss": 0.4153,
      "step": 972
    },
    {
      "epoch": 0.973273733237473,
      "grad_norm": 0.21518896520137787,
      "learning_rate": 0.00013529411764705884,
      "loss": 0.3851,
      "step": 973
    },
    {
      "epoch": 0.9742740145665969,
      "grad_norm": 0.18828287720680237,
      "learning_rate": 0.00013522727272727273,
      "loss": 0.3897,
      "step": 974
    },
    {
      "epoch": 0.9752742958957207,
      "grad_norm": 0.19021959602832794,
      "learning_rate": 0.00013516042780748662,
      "loss": 0.3956,
      "step": 975
    },
    {
      "epoch": 0.9762745772248445,
      "grad_norm": 0.20354677736759186,
      "learning_rate": 0.00013509358288770054,
      "loss": 0.4137,
      "step": 976
    },
    {
      "epoch": 0.9772748585539683,
      "grad_norm": 0.19351476430892944,
      "learning_rate": 0.00013502673796791446,
      "loss": 0.4189,
      "step": 977
    },
    {
      "epoch": 0.9782751398830921,
      "grad_norm": 0.19193604588508606,
      "learning_rate": 0.00013495989304812835,
      "loss": 0.4058,
      "step": 978
    },
    {
      "epoch": 0.9792754212122159,
      "grad_norm": 0.18845269083976746,
      "learning_rate": 0.00013489304812834224,
      "loss": 0.3894,
      "step": 979
    },
    {
      "epoch": 0.9802757025413398,
      "grad_norm": 0.18949660658836365,
      "learning_rate": 0.00013482620320855616,
      "loss": 0.3894,
      "step": 980
    },
    {
      "epoch": 0.9812759838704636,
      "grad_norm": 0.1983581930398941,
      "learning_rate": 0.00013475935828877007,
      "loss": 0.417,
      "step": 981
    },
    {
      "epoch": 0.9822762651995874,
      "grad_norm": 0.20402638614177704,
      "learning_rate": 0.00013469251336898396,
      "loss": 0.4113,
      "step": 982
    },
    {
      "epoch": 0.9832765465287112,
      "grad_norm": 0.206806480884552,
      "learning_rate": 0.00013462566844919786,
      "loss": 0.4182,
      "step": 983
    },
    {
      "epoch": 0.984276827857835,
      "grad_norm": 0.1953524798154831,
      "learning_rate": 0.00013455882352941177,
      "loss": 0.3933,
      "step": 984
    },
    {
      "epoch": 0.9852771091869589,
      "grad_norm": 0.1953764259815216,
      "learning_rate": 0.0001344919786096257,
      "loss": 0.4116,
      "step": 985
    },
    {
      "epoch": 0.9862773905160827,
      "grad_norm": 0.18486852943897247,
      "learning_rate": 0.00013442513368983958,
      "loss": 0.373,
      "step": 986
    },
    {
      "epoch": 0.9872776718452064,
      "grad_norm": 0.17973078787326813,
      "learning_rate": 0.00013435828877005347,
      "loss": 0.3833,
      "step": 987
    },
    {
      "epoch": 0.9882779531743303,
      "grad_norm": 0.2015920728445053,
      "learning_rate": 0.0001342914438502674,
      "loss": 0.4022,
      "step": 988
    },
    {
      "epoch": 0.9892782345034541,
      "grad_norm": 0.19203631579875946,
      "learning_rate": 0.00013422459893048128,
      "loss": 0.401,
      "step": 989
    },
    {
      "epoch": 0.9902785158325779,
      "grad_norm": 0.2003282606601715,
      "learning_rate": 0.0001341577540106952,
      "loss": 0.4055,
      "step": 990
    },
    {
      "epoch": 0.9912787971617018,
      "grad_norm": 0.19373619556427002,
      "learning_rate": 0.0001340909090909091,
      "loss": 0.3996,
      "step": 991
    },
    {
      "epoch": 0.9922790784908255,
      "grad_norm": 0.18733693659305573,
      "learning_rate": 0.000134024064171123,
      "loss": 0.3901,
      "step": 992
    },
    {
      "epoch": 0.9932793598199494,
      "grad_norm": 0.2048783153295517,
      "learning_rate": 0.0001339572192513369,
      "loss": 0.4096,
      "step": 993
    },
    {
      "epoch": 0.9942796411490732,
      "grad_norm": 0.19704581797122955,
      "learning_rate": 0.00013389037433155082,
      "loss": 0.4078,
      "step": 994
    },
    {
      "epoch": 0.995279922478197,
      "grad_norm": 0.20748738944530487,
      "learning_rate": 0.0001338235294117647,
      "loss": 0.3992,
      "step": 995
    },
    {
      "epoch": 0.9962802038073209,
      "grad_norm": 0.19509883224964142,
      "learning_rate": 0.00013375668449197863,
      "loss": 0.3688,
      "step": 996
    },
    {
      "epoch": 0.9972804851364446,
      "grad_norm": 0.21353912353515625,
      "learning_rate": 0.00013368983957219252,
      "loss": 0.3854,
      "step": 997
    },
    {
      "epoch": 0.9982807664655684,
      "grad_norm": 0.18891485035419464,
      "learning_rate": 0.0001336229946524064,
      "loss": 0.406,
      "step": 998
    },
    {
      "epoch": 0.9992810477946923,
      "grad_norm": 0.1948714405298233,
      "learning_rate": 0.00013355614973262033,
      "loss": 0.416,
      "step": 999
    },
    {
      "epoch": 1.0002813291238162,
      "grad_norm": 0.20808909833431244,
      "learning_rate": 0.00013348930481283424,
      "loss": 0.406,
      "step": 1000
    }
  ],
  "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": 6.935654442872832e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}