{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9988751406074241,
  "eval_steps": 500,
  "global_step": 777,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012855535915153463,
      "grad_norm": 0.020836442708969116,
      "learning_rate": 0.0,
      "loss": 0.6262,
      "step": 1
    },
    {
      "epoch": 0.0025711071830306926,
      "grad_norm": 0.022134091705083847,
      "learning_rate": 4.075900941810124e-06,
      "loss": 0.8688,
      "step": 2
    },
    {
      "epoch": 0.003856660774546039,
      "grad_norm": 0.023200005292892456,
      "learning_rate": 6.46015014942309e-06,
      "loss": 0.7864,
      "step": 3
    },
    {
      "epoch": 0.005142214366061385,
      "grad_norm": 0.02313530258834362,
      "learning_rate": 8.151801883620247e-06,
      "loss": 0.8897,
      "step": 4
    },
    {
      "epoch": 0.0064277679575767315,
      "grad_norm": 0.020561356097459793,
      "learning_rate": 9.463948908766788e-06,
      "loss": 0.6479,
      "step": 5
    },
    {
      "epoch": 0.007713321549092078,
      "grad_norm": 0.021870166063308716,
      "learning_rate": 1.0536051091233212e-05,
      "loss": 0.7501,
      "step": 6
    },
    {
      "epoch": 0.008998875140607425,
      "grad_norm": 0.023460067808628082,
      "learning_rate": 1.1442500570809876e-05,
      "loss": 0.8672,
      "step": 7
    },
    {
      "epoch": 0.01028442873212277,
      "grad_norm": 0.02368471957743168,
      "learning_rate": 1.222770282543037e-05,
      "loss": 0.8984,
      "step": 8
    },
    {
      "epoch": 0.011569982323638118,
      "grad_norm": 0.020765064284205437,
      "learning_rate": 1.292030029884618e-05,
      "loss": 0.6547,
      "step": 9
    },
    {
      "epoch": 0.012855535915153463,
      "grad_norm": 0.023947741836309433,
      "learning_rate": 1.3539849850576912e-05,
      "loss": 0.8205,
      "step": 10
    },
    {
      "epoch": 0.01414108950666881,
      "grad_norm": 0.028013406321406364,
      "learning_rate": 1.4100300592531481e-05,
      "loss": 0.7891,
      "step": 11
    },
    {
      "epoch": 0.015426643098184156,
      "grad_norm": 0.027111703529953957,
      "learning_rate": 1.4611952033043337e-05,
      "loss": 0.7678,
      "step": 12
    },
    {
      "epoch": 0.0167121966896995,
      "grad_norm": 0.028518904000520706,
      "learning_rate": 1.5082625732282867e-05,
      "loss": 0.8091,
      "step": 13
    },
    {
      "epoch": 0.01799775028121485,
      "grad_norm": 0.022600186988711357,
      "learning_rate": 1.551840151262e-05,
      "loss": 0.5875,
      "step": 14
    },
    {
      "epoch": 0.019283303872730195,
      "grad_norm": 0.021580247208476067,
      "learning_rate": 1.5924099058189875e-05,
      "loss": 0.6714,
      "step": 15
    },
    {
      "epoch": 0.02056885746424554,
      "grad_norm": 0.02505405619740486,
      "learning_rate": 1.6303603767240495e-05,
      "loss": 0.7534,
      "step": 16
    },
    {
      "epoch": 0.021854411055760886,
      "grad_norm": 0.024437466636300087,
      "learning_rate": 1.6660093644266146e-05,
      "loss": 0.6945,
      "step": 17
    },
    {
      "epoch": 0.023139964647276235,
      "grad_norm": 0.028052283450961113,
      "learning_rate": 1.6996201240656302e-05,
      "loss": 0.7076,
      "step": 18
    },
    {
      "epoch": 0.02442551823879158,
      "grad_norm": 0.03632762283086777,
      "learning_rate": 1.7314131752785847e-05,
      "loss": 0.769,
      "step": 19
    },
    {
      "epoch": 0.025711071830306926,
      "grad_norm": 0.02896072156727314,
      "learning_rate": 1.7615750792387035e-05,
      "loss": 0.8087,
      "step": 20
    },
    {
      "epoch": 0.02699662542182227,
      "grad_norm": 0.034198954701423645,
      "learning_rate": 1.7902650720232966e-05,
      "loss": 0.8161,
      "step": 21
    },
    {
      "epoch": 0.02828217901333762,
      "grad_norm": 0.03110469877719879,
      "learning_rate": 1.8176201534341607e-05,
      "loss": 0.8253,
      "step": 22
    },
    {
      "epoch": 0.029567732604852966,
      "grad_norm": 0.039295781403779984,
      "learning_rate": 1.8437590437029225e-05,
      "loss": 0.9744,
      "step": 23
    },
    {
      "epoch": 0.03085328619636831,
      "grad_norm": 0.03249296918511391,
      "learning_rate": 1.868785297485346e-05,
      "loss": 0.6455,
      "step": 24
    },
    {
      "epoch": 0.032138839787883657,
      "grad_norm": 0.03106599487364292,
      "learning_rate": 1.8927897817533575e-05,
      "loss": 0.7005,
      "step": 25
    },
    {
      "epoch": 0.033424393379399,
      "grad_norm": 0.03536655381321907,
      "learning_rate": 1.915852667409299e-05,
      "loss": 0.8004,
      "step": 26
    },
    {
      "epoch": 0.03470994697091435,
      "grad_norm": 0.035472676157951355,
      "learning_rate": 1.9380450448269272e-05,
      "loss": 0.675,
      "step": 27
    },
    {
      "epoch": 0.0359955005624297,
      "grad_norm": 0.03877939283847809,
      "learning_rate": 1.9594302454430122e-05,
      "loss": 0.6278,
      "step": 28
    },
    {
      "epoch": 0.037281054153945045,
      "grad_norm": 0.041341230273246765,
      "learning_rate": 1.9800649313336155e-05,
      "loss": 0.914,
      "step": 29
    },
    {
      "epoch": 0.03856660774546039,
      "grad_norm": 0.042063791304826736,
      "learning_rate": 2e-05,
      "loss": 0.7664,
      "step": 30
    },
    {
      "epoch": 0.039852161336975736,
      "grad_norm": 0.04166961461305618,
      "learning_rate": 2e-05,
      "loss": 0.6324,
      "step": 31
    },
    {
      "epoch": 0.04113771492849108,
      "grad_norm": 0.04256080463528633,
      "learning_rate": 2e-05,
      "loss": 0.6771,
      "step": 32
    },
    {
      "epoch": 0.04242326852000643,
      "grad_norm": 0.042959265410900116,
      "learning_rate": 2e-05,
      "loss": 0.6018,
      "step": 33
    },
    {
      "epoch": 0.04370882211152177,
      "grad_norm": 0.03880544751882553,
      "learning_rate": 2e-05,
      "loss": 0.5819,
      "step": 34
    },
    {
      "epoch": 0.04499437570303712,
      "grad_norm": 0.0412827730178833,
      "learning_rate": 2e-05,
      "loss": 0.8133,
      "step": 35
    },
    {
      "epoch": 0.04627992929455247,
      "grad_norm": 0.04274650663137436,
      "learning_rate": 2e-05,
      "loss": 0.6237,
      "step": 36
    },
    {
      "epoch": 0.047565482886067816,
      "grad_norm": 0.04136871546506882,
      "learning_rate": 2e-05,
      "loss": 0.5851,
      "step": 37
    },
    {
      "epoch": 0.04885103647758316,
      "grad_norm": 0.04220248758792877,
      "learning_rate": 2e-05,
      "loss": 0.7603,
      "step": 38
    },
    {
      "epoch": 0.050136590069098506,
      "grad_norm": 0.039129678159952164,
      "learning_rate": 2e-05,
      "loss": 0.5206,
      "step": 39
    },
    {
      "epoch": 0.05142214366061385,
      "grad_norm": 0.04173429682850838,
      "learning_rate": 2e-05,
      "loss": 0.6602,
      "step": 40
    },
    {
      "epoch": 0.0527076972521292,
      "grad_norm": 0.040010105818510056,
      "learning_rate": 2e-05,
      "loss": 0.5964,
      "step": 41
    },
    {
      "epoch": 0.05399325084364454,
      "grad_norm": 0.03841459006071091,
      "learning_rate": 2e-05,
      "loss": 0.6162,
      "step": 42
    },
    {
      "epoch": 0.05527880443515989,
      "grad_norm": 0.04042840003967285,
      "learning_rate": 2e-05,
      "loss": 0.535,
      "step": 43
    },
    {
      "epoch": 0.05656435802667524,
      "grad_norm": 0.040401577949523926,
      "learning_rate": 2e-05,
      "loss": 0.5685,
      "step": 44
    },
    {
      "epoch": 0.057849911618190586,
      "grad_norm": 0.06742753833532333,
      "learning_rate": 2e-05,
      "loss": 0.8276,
      "step": 45
    },
    {
      "epoch": 0.05913546520970593,
      "grad_norm": 0.040345244109630585,
      "learning_rate": 2e-05,
      "loss": 0.5988,
      "step": 46
    },
    {
      "epoch": 0.06042101880122128,
      "grad_norm": 0.0415828563272953,
      "learning_rate": 2e-05,
      "loss": 0.6151,
      "step": 47
    },
    {
      "epoch": 0.06170657239273662,
      "grad_norm": 0.041223231703042984,
      "learning_rate": 2e-05,
      "loss": 0.638,
      "step": 48
    },
    {
      "epoch": 0.06299212598425197,
      "grad_norm": 0.03628067672252655,
      "learning_rate": 2e-05,
      "loss": 0.5031,
      "step": 49
    },
    {
      "epoch": 0.06427767957576731,
      "grad_norm": 0.04399935156106949,
      "learning_rate": 2e-05,
      "loss": 0.6615,
      "step": 50
    },
    {
      "epoch": 0.06556323316728266,
      "grad_norm": 0.04084352031350136,
      "learning_rate": 2e-05,
      "loss": 0.5703,
      "step": 51
    },
    {
      "epoch": 0.066848786758798,
      "grad_norm": 0.039231687784194946,
      "learning_rate": 2e-05,
      "loss": 0.5325,
      "step": 52
    },
    {
      "epoch": 0.06813434035031335,
      "grad_norm": 0.04078860580921173,
      "learning_rate": 2e-05,
      "loss": 0.5959,
      "step": 53
    },
    {
      "epoch": 0.0694198939418287,
      "grad_norm": 0.03753922879695892,
      "learning_rate": 2e-05,
      "loss": 0.5652,
      "step": 54
    },
    {
      "epoch": 0.07070544753334404,
      "grad_norm": 0.041337307542562485,
      "learning_rate": 2e-05,
      "loss": 0.5579,
      "step": 55
    },
    {
      "epoch": 0.0719910011248594,
      "grad_norm": 0.03940434008836746,
      "learning_rate": 2e-05,
      "loss": 0.4821,
      "step": 56
    },
    {
      "epoch": 0.07327655471637474,
      "grad_norm": 0.03760010376572609,
      "learning_rate": 2e-05,
      "loss": 0.4442,
      "step": 57
    },
    {
      "epoch": 0.07456210830789009,
      "grad_norm": 0.042540181428194046,
      "learning_rate": 2e-05,
      "loss": 0.5285,
      "step": 58
    },
    {
      "epoch": 0.07584766189940544,
      "grad_norm": 0.0457993820309639,
      "learning_rate": 2e-05,
      "loss": 0.7136,
      "step": 59
    },
    {
      "epoch": 0.07713321549092078,
      "grad_norm": 0.033564481884241104,
      "learning_rate": 2e-05,
      "loss": 0.4617,
      "step": 60
    },
    {
      "epoch": 0.07841876908243613,
      "grad_norm": 0.041546691209077835,
      "learning_rate": 2e-05,
      "loss": 0.6912,
      "step": 61
    },
    {
      "epoch": 0.07970432267395147,
      "grad_norm": 0.03729071840643883,
      "learning_rate": 2e-05,
      "loss": 0.4584,
      "step": 62
    },
    {
      "epoch": 0.08098987626546682,
      "grad_norm": 0.04159967973828316,
      "learning_rate": 2e-05,
      "loss": 0.5392,
      "step": 63
    },
    {
      "epoch": 0.08227542985698216,
      "grad_norm": 0.03827968239784241,
      "learning_rate": 2e-05,
      "loss": 0.5548,
      "step": 64
    },
    {
      "epoch": 0.08356098344849751,
      "grad_norm": 0.04405729100108147,
      "learning_rate": 2e-05,
      "loss": 0.6239,
      "step": 65
    },
    {
      "epoch": 0.08484653704001285,
      "grad_norm": 0.03460558503866196,
      "learning_rate": 2e-05,
      "loss": 0.4405,
      "step": 66
    },
    {
      "epoch": 0.0861320906315282,
      "grad_norm": 0.030664170160889626,
      "learning_rate": 2e-05,
      "loss": 0.3396,
      "step": 67
    },
    {
      "epoch": 0.08741764422304354,
      "grad_norm": 0.0376565083861351,
      "learning_rate": 2e-05,
      "loss": 0.5822,
      "step": 68
    },
    {
      "epoch": 0.08870319781455889,
      "grad_norm": 0.0384797677397728,
      "learning_rate": 2e-05,
      "loss": 0.5402,
      "step": 69
    },
    {
      "epoch": 0.08998875140607424,
      "grad_norm": 0.030342888087034225,
      "learning_rate": 2e-05,
      "loss": 0.371,
      "step": 70
    },
    {
      "epoch": 0.09127430499758958,
      "grad_norm": 0.0449620746076107,
      "learning_rate": 2e-05,
      "loss": 0.5723,
      "step": 71
    },
    {
      "epoch": 0.09255985858910494,
      "grad_norm": 0.03808669000864029,
      "learning_rate": 2e-05,
      "loss": 0.4842,
      "step": 72
    },
    {
      "epoch": 0.09384541218062029,
      "grad_norm": 0.03985065966844559,
      "learning_rate": 2e-05,
      "loss": 0.4957,
      "step": 73
    },
    {
      "epoch": 0.09513096577213563,
      "grad_norm": 0.030943365767598152,
      "learning_rate": 2e-05,
      "loss": 0.4595,
      "step": 74
    },
    {
      "epoch": 0.09641651936365098,
      "grad_norm": 0.03418966010212898,
      "learning_rate": 2e-05,
      "loss": 0.3757,
      "step": 75
    },
    {
      "epoch": 0.09770207295516632,
      "grad_norm": 0.033448606729507446,
      "learning_rate": 2e-05,
      "loss": 0.4325,
      "step": 76
    },
    {
      "epoch": 0.09898762654668167,
      "grad_norm": 0.039748664945364,
      "learning_rate": 2e-05,
      "loss": 0.507,
      "step": 77
    },
    {
      "epoch": 0.10027318013819701,
      "grad_norm": 0.04277816414833069,
      "learning_rate": 2e-05,
      "loss": 0.6296,
      "step": 78
    },
    {
      "epoch": 0.10155873372971236,
      "grad_norm": 0.029562752693891525,
      "learning_rate": 2e-05,
      "loss": 0.395,
      "step": 79
    },
    {
      "epoch": 0.1028442873212277,
      "grad_norm": 0.029590601101517677,
      "learning_rate": 2e-05,
      "loss": 0.3807,
      "step": 80
    },
    {
      "epoch": 0.10412984091274305,
      "grad_norm": 0.031173471361398697,
      "learning_rate": 2e-05,
      "loss": 0.4175,
      "step": 81
    },
    {
      "epoch": 0.1054153945042584,
      "grad_norm": 0.03821694105863571,
      "learning_rate": 2e-05,
      "loss": 0.5547,
      "step": 82
    },
    {
      "epoch": 0.10670094809577374,
      "grad_norm": 0.02932704985141754,
      "learning_rate": 2e-05,
      "loss": 0.3954,
      "step": 83
    },
    {
      "epoch": 0.10798650168728909,
      "grad_norm": 0.030441921204328537,
      "learning_rate": 2e-05,
      "loss": 0.4564,
      "step": 84
    },
    {
      "epoch": 0.10927205527880443,
      "grad_norm": 0.03350207954645157,
      "learning_rate": 2e-05,
      "loss": 0.4477,
      "step": 85
    },
    {
      "epoch": 0.11055760887031978,
      "grad_norm": 0.030435308814048767,
      "learning_rate": 2e-05,
      "loss": 0.4292,
      "step": 86
    },
    {
      "epoch": 0.11184316246183512,
      "grad_norm": 0.03452485054731369,
      "learning_rate": 2e-05,
      "loss": 0.4572,
      "step": 87
    },
    {
      "epoch": 0.11312871605335048,
      "grad_norm": 0.029849708080291748,
      "learning_rate": 2e-05,
      "loss": 0.3826,
      "step": 88
    },
    {
      "epoch": 0.11441426964486583,
      "grad_norm": 0.026589911431074142,
      "learning_rate": 2e-05,
      "loss": 0.3335,
      "step": 89
    },
    {
      "epoch": 0.11569982323638117,
      "grad_norm": 0.03767862543463707,
      "learning_rate": 2e-05,
      "loss": 0.5377,
      "step": 90
    },
    {
      "epoch": 0.11698537682789652,
      "grad_norm": 0.030503496527671814,
      "learning_rate": 2e-05,
      "loss": 0.4019,
      "step": 91
    },
    {
      "epoch": 0.11827093041941186,
      "grad_norm": 0.02843611314892769,
      "learning_rate": 2e-05,
      "loss": 0.378,
      "step": 92
    },
    {
      "epoch": 0.11955648401092721,
      "grad_norm": 0.02735988050699234,
      "learning_rate": 2e-05,
      "loss": 0.3842,
      "step": 93
    },
    {
      "epoch": 0.12084203760244255,
      "grad_norm": 0.03628378361463547,
      "learning_rate": 2e-05,
      "loss": 0.502,
      "step": 94
    },
    {
      "epoch": 0.1221275911939579,
      "grad_norm": 0.029980337247252464,
      "learning_rate": 2e-05,
      "loss": 0.4177,
      "step": 95
    },
    {
      "epoch": 0.12341314478547324,
      "grad_norm": 0.03486626222729683,
      "learning_rate": 2e-05,
      "loss": 0.495,
      "step": 96
    },
    {
      "epoch": 0.12469869837698859,
      "grad_norm": 0.03005075454711914,
      "learning_rate": 2e-05,
      "loss": 0.3618,
      "step": 97
    },
    {
      "epoch": 0.12598425196850394,
      "grad_norm": 0.03018985688686371,
      "learning_rate": 2e-05,
      "loss": 0.4078,
      "step": 98
    },
    {
      "epoch": 0.1272698055600193,
      "grad_norm": 0.03108677826821804,
      "learning_rate": 2e-05,
      "loss": 0.4583,
      "step": 99
    },
    {
      "epoch": 0.12855535915153463,
      "grad_norm": 0.029582438990473747,
      "learning_rate": 2e-05,
      "loss": 0.4142,
      "step": 100
    },
    {
      "epoch": 0.12984091274304999,
      "grad_norm": 0.02979620173573494,
      "learning_rate": 2e-05,
      "loss": 0.4535,
      "step": 101
    },
    {
      "epoch": 0.13112646633456532,
      "grad_norm": 0.032250065356492996,
      "learning_rate": 2e-05,
      "loss": 0.3805,
      "step": 102
    },
    {
      "epoch": 0.13241201992608068,
      "grad_norm": 0.03306899964809418,
      "learning_rate": 2e-05,
      "loss": 0.4351,
      "step": 103
    },
    {
      "epoch": 0.133697573517596,
      "grad_norm": 0.023130670189857483,
      "learning_rate": 2e-05,
      "loss": 0.2417,
      "step": 104
    },
    {
      "epoch": 0.13498312710911137,
      "grad_norm": 0.03372225537896156,
      "learning_rate": 2e-05,
      "loss": 0.4703,
      "step": 105
    },
    {
      "epoch": 0.1362686807006267,
      "grad_norm": 0.02907857671380043,
      "learning_rate": 2e-05,
      "loss": 0.3437,
      "step": 106
    },
    {
      "epoch": 0.13755423429214206,
      "grad_norm": 0.03021407686173916,
      "learning_rate": 2e-05,
      "loss": 0.4327,
      "step": 107
    },
    {
      "epoch": 0.1388397878836574,
      "grad_norm": 0.027038615196943283,
      "learning_rate": 2e-05,
      "loss": 0.3652,
      "step": 108
    },
    {
      "epoch": 0.14012534147517275,
      "grad_norm": 0.02982942759990692,
      "learning_rate": 2e-05,
      "loss": 0.345,
      "step": 109
    },
    {
      "epoch": 0.14141089506668808,
      "grad_norm": 0.0561259388923645,
      "learning_rate": 2e-05,
      "loss": 0.5073,
      "step": 110
    },
    {
      "epoch": 0.14269644865820344,
      "grad_norm": 0.024736687541007996,
      "learning_rate": 2e-05,
      "loss": 0.3149,
      "step": 111
    },
    {
      "epoch": 0.1439820022497188,
      "grad_norm": 0.02275976352393627,
      "learning_rate": 2e-05,
      "loss": 0.3147,
      "step": 112
    },
    {
      "epoch": 0.14526755584123413,
      "grad_norm": 0.030464742332696915,
      "learning_rate": 2e-05,
      "loss": 0.4512,
      "step": 113
    },
    {
      "epoch": 0.1465531094327495,
      "grad_norm": 0.026887530460953712,
      "learning_rate": 2e-05,
      "loss": 0.3679,
      "step": 114
    },
    {
      "epoch": 0.14783866302426482,
      "grad_norm": 0.03605503961443901,
      "learning_rate": 2e-05,
      "loss": 0.4392,
      "step": 115
    },
    {
      "epoch": 0.14912421661578018,
      "grad_norm": 0.02638978883624077,
      "learning_rate": 2e-05,
      "loss": 0.3484,
      "step": 116
    },
    {
      "epoch": 0.1504097702072955,
      "grad_norm": 0.03650350496172905,
      "learning_rate": 2e-05,
      "loss": 0.3978,
      "step": 117
    },
    {
      "epoch": 0.15169532379881087,
      "grad_norm": 0.022277837619185448,
      "learning_rate": 2e-05,
      "loss": 0.2525,
      "step": 118
    },
    {
      "epoch": 0.1529808773903262,
      "grad_norm": 0.021412434056401253,
      "learning_rate": 2e-05,
      "loss": 0.2922,
      "step": 119
    },
    {
      "epoch": 0.15426643098184156,
      "grad_norm": 0.029154105111956596,
      "learning_rate": 2e-05,
      "loss": 0.3864,
      "step": 120
    },
    {
      "epoch": 0.1555519845733569,
      "grad_norm": 0.024072440341114998,
      "learning_rate": 2e-05,
      "loss": 0.2467,
      "step": 121
    },
    {
      "epoch": 0.15683753816487225,
      "grad_norm": 0.019447140395641327,
      "learning_rate": 2e-05,
      "loss": 0.2086,
      "step": 122
    },
    {
      "epoch": 0.15812309175638758,
      "grad_norm": 0.035536400973796844,
      "learning_rate": 2e-05,
      "loss": 0.489,
      "step": 123
    },
    {
      "epoch": 0.15940864534790294,
      "grad_norm": 0.026226134970784187,
      "learning_rate": 2e-05,
      "loss": 0.3502,
      "step": 124
    },
    {
      "epoch": 0.16069419893941828,
      "grad_norm": 0.029284900054335594,
      "learning_rate": 2e-05,
      "loss": 0.3683,
      "step": 125
    },
    {
      "epoch": 0.16197975253093364,
      "grad_norm": 0.026484966278076172,
      "learning_rate": 2e-05,
      "loss": 0.3686,
      "step": 126
    },
    {
      "epoch": 0.16326530612244897,
      "grad_norm": 0.03296555206179619,
      "learning_rate": 2e-05,
      "loss": 0.4598,
      "step": 127
    },
    {
      "epoch": 0.16455085971396433,
      "grad_norm": 0.03217398375272751,
      "learning_rate": 2e-05,
      "loss": 0.4292,
      "step": 128
    },
    {
      "epoch": 0.16583641330547969,
      "grad_norm": 0.02639828808605671,
      "learning_rate": 2e-05,
      "loss": 0.324,
      "step": 129
    },
    {
      "epoch": 0.16712196689699502,
      "grad_norm": 0.025398138910531998,
      "learning_rate": 2e-05,
      "loss": 0.3565,
      "step": 130
    },
    {
      "epoch": 0.16840752048851038,
      "grad_norm": 0.026609797030687332,
      "learning_rate": 2e-05,
      "loss": 0.326,
      "step": 131
    },
    {
      "epoch": 0.1696930740800257,
      "grad_norm": 0.029938040301203728,
      "learning_rate": 2e-05,
      "loss": 0.4149,
      "step": 132
    },
    {
      "epoch": 0.17097862767154107,
      "grad_norm": 0.02608969807624817,
      "learning_rate": 2e-05,
      "loss": 0.3774,
      "step": 133
    },
    {
      "epoch": 0.1722641812630564,
      "grad_norm": 0.02580363303422928,
      "learning_rate": 2e-05,
      "loss": 0.2944,
      "step": 134
    },
    {
      "epoch": 0.17354973485457176,
      "grad_norm": 0.029851458966732025,
      "learning_rate": 2e-05,
      "loss": 0.3316,
      "step": 135
    },
    {
      "epoch": 0.1748352884460871,
      "grad_norm": 0.02928406558930874,
      "learning_rate": 2e-05,
      "loss": 0.3548,
      "step": 136
    },
    {
      "epoch": 0.17612084203760245,
      "grad_norm": 0.030875032767653465,
      "learning_rate": 2e-05,
      "loss": 0.3617,
      "step": 137
    },
    {
      "epoch": 0.17740639562911778,
      "grad_norm": 0.026721350848674774,
      "learning_rate": 2e-05,
      "loss": 0.3799,
      "step": 138
    },
    {
      "epoch": 0.17869194922063314,
      "grad_norm": 0.03269115090370178,
      "learning_rate": 2e-05,
      "loss": 0.4324,
      "step": 139
    },
    {
      "epoch": 0.17997750281214847,
      "grad_norm": 0.022154508158564568,
      "learning_rate": 2e-05,
      "loss": 0.2744,
      "step": 140
    },
    {
      "epoch": 0.18126305640366383,
      "grad_norm": 0.022251179441809654,
      "learning_rate": 2e-05,
      "loss": 0.2886,
      "step": 141
    },
    {
      "epoch": 0.18254860999517916,
      "grad_norm": 0.03386593237519264,
      "learning_rate": 2e-05,
      "loss": 0.473,
      "step": 142
    },
    {
      "epoch": 0.18383416358669452,
      "grad_norm": 0.02578306384384632,
      "learning_rate": 2e-05,
      "loss": 0.3224,
      "step": 143
    },
    {
      "epoch": 0.18511971717820988,
      "grad_norm": 0.027509864419698715,
      "learning_rate": 2e-05,
      "loss": 0.3224,
      "step": 144
    },
    {
      "epoch": 0.1864052707697252,
      "grad_norm": 0.02819378860294819,
      "learning_rate": 2e-05,
      "loss": 0.3176,
      "step": 145
    },
    {
      "epoch": 0.18769082436124057,
      "grad_norm": 0.028061147779226303,
      "learning_rate": 2e-05,
      "loss": 0.3494,
      "step": 146
    },
    {
      "epoch": 0.1889763779527559,
      "grad_norm": 0.032399386167526245,
      "learning_rate": 2e-05,
      "loss": 0.3647,
      "step": 147
    },
    {
      "epoch": 0.19026193154427126,
      "grad_norm": 0.028246790170669556,
      "learning_rate": 2e-05,
      "loss": 0.3366,
      "step": 148
    },
    {
      "epoch": 0.1915474851357866,
      "grad_norm": 0.03099609911441803,
      "learning_rate": 2e-05,
      "loss": 0.4034,
      "step": 149
    },
    {
      "epoch": 0.19283303872730195,
      "grad_norm": 0.03750993683934212,
      "learning_rate": 2e-05,
      "loss": 0.3395,
      "step": 150
    },
    {
      "epoch": 0.19411859231881728,
      "grad_norm": 0.0326780304312706,
      "learning_rate": 2e-05,
      "loss": 0.4482,
      "step": 151
    },
    {
      "epoch": 0.19540414591033264,
      "grad_norm": 0.033816393464803696,
      "learning_rate": 2e-05,
      "loss": 0.4504,
      "step": 152
    },
    {
      "epoch": 0.19668969950184798,
      "grad_norm": 0.026754887774586678,
      "learning_rate": 2e-05,
      "loss": 0.3334,
      "step": 153
    },
    {
      "epoch": 0.19797525309336333,
      "grad_norm": 0.02957574650645256,
      "learning_rate": 2e-05,
      "loss": 0.3698,
      "step": 154
    },
    {
      "epoch": 0.19926080668487867,
      "grad_norm": 0.02848845347762108,
      "learning_rate": 2e-05,
      "loss": 0.3001,
      "step": 155
    },
    {
      "epoch": 0.20054636027639403,
      "grad_norm": 0.03636415675282478,
      "learning_rate": 2e-05,
      "loss": 0.4872,
      "step": 156
    },
    {
      "epoch": 0.20183191386790936,
      "grad_norm": 0.018864037469029427,
      "learning_rate": 2e-05,
      "loss": 0.2086,
      "step": 157
    },
    {
      "epoch": 0.20311746745942472,
      "grad_norm": 0.027126725763082504,
      "learning_rate": 2e-05,
      "loss": 0.3181,
      "step": 158
    },
    {
      "epoch": 0.20440302105094005,
      "grad_norm": 0.025296056643128395,
      "learning_rate": 2e-05,
      "loss": 0.3169,
      "step": 159
    },
    {
      "epoch": 0.2056885746424554,
      "grad_norm": 0.035376112908124924,
      "learning_rate": 2e-05,
      "loss": 0.4219,
      "step": 160
    },
    {
      "epoch": 0.20697412823397077,
      "grad_norm": 0.030744420364499092,
      "learning_rate": 2e-05,
      "loss": 0.3818,
      "step": 161
    },
    {
      "epoch": 0.2082596818254861,
      "grad_norm": 0.03273791819810867,
      "learning_rate": 2e-05,
      "loss": 0.3823,
      "step": 162
    },
    {
      "epoch": 0.20954523541700146,
      "grad_norm": 0.030423806980252266,
      "learning_rate": 2e-05,
      "loss": 0.3451,
      "step": 163
    },
    {
      "epoch": 0.2108307890085168,
      "grad_norm": 0.029618561267852783,
      "learning_rate": 2e-05,
      "loss": 0.3604,
      "step": 164
    },
    {
      "epoch": 0.21211634260003215,
      "grad_norm": 0.030883729457855225,
      "learning_rate": 2e-05,
      "loss": 0.401,
      "step": 165
    },
    {
      "epoch": 0.21340189619154748,
      "grad_norm": 0.028922105208039284,
      "learning_rate": 2e-05,
      "loss": 0.3305,
      "step": 166
    },
    {
      "epoch": 0.21468744978306284,
      "grad_norm": 0.033665966242551804,
      "learning_rate": 2e-05,
      "loss": 0.3175,
      "step": 167
    },
    {
      "epoch": 0.21597300337457817,
      "grad_norm": 0.035460278391838074,
      "learning_rate": 2e-05,
      "loss": 0.4509,
      "step": 168
    },
    {
      "epoch": 0.21725855696609353,
      "grad_norm": 0.026533829048275948,
      "learning_rate": 2e-05,
      "loss": 0.2403,
      "step": 169
    },
    {
      "epoch": 0.21854411055760886,
      "grad_norm": 0.029200293123722076,
      "learning_rate": 2e-05,
      "loss": 0.2794,
      "step": 170
    },
    {
      "epoch": 0.21982966414912422,
      "grad_norm": 0.027879290282726288,
      "learning_rate": 2e-05,
      "loss": 0.2995,
      "step": 171
    },
    {
      "epoch": 0.22111521774063955,
      "grad_norm": 0.027549387887120247,
      "learning_rate": 2e-05,
      "loss": 0.2803,
      "step": 172
    },
    {
      "epoch": 0.2224007713321549,
      "grad_norm": 0.03113819658756256,
      "learning_rate": 2e-05,
      "loss": 0.2479,
      "step": 173
    },
    {
      "epoch": 0.22368632492367024,
      "grad_norm": 0.024273231625556946,
      "learning_rate": 2e-05,
      "loss": 0.2705,
      "step": 174
    },
    {
      "epoch": 0.2249718785151856,
      "grad_norm": 0.02970244735479355,
      "learning_rate": 2e-05,
      "loss": 0.3266,
      "step": 175
    },
    {
      "epoch": 0.22625743210670096,
      "grad_norm": 0.028792355209589005,
      "learning_rate": 2e-05,
      "loss": 0.3311,
      "step": 176
    },
    {
      "epoch": 0.2275429856982163,
      "grad_norm": 0.029121607542037964,
      "learning_rate": 2e-05,
      "loss": 0.2814,
      "step": 177
    },
    {
      "epoch": 0.22882853928973165,
      "grad_norm": 0.029099591076374054,
      "learning_rate": 2e-05,
      "loss": 0.3065,
      "step": 178
    },
    {
      "epoch": 0.23011409288124698,
      "grad_norm": 0.02833685837686062,
      "learning_rate": 2e-05,
      "loss": 0.3459,
      "step": 179
    },
    {
      "epoch": 0.23139964647276234,
      "grad_norm": 0.03676662966609001,
      "learning_rate": 2e-05,
      "loss": 0.4179,
      "step": 180
    },
    {
      "epoch": 0.23268520006427768,
      "grad_norm": 0.02846740558743477,
      "learning_rate": 2e-05,
      "loss": 0.2879,
      "step": 181
    },
    {
      "epoch": 0.23397075365579303,
      "grad_norm": 0.030531803146004677,
      "learning_rate": 2e-05,
      "loss": 0.362,
      "step": 182
    },
    {
      "epoch": 0.23525630724730837,
      "grad_norm": 0.034853462129831314,
      "learning_rate": 2e-05,
      "loss": 0.3814,
      "step": 183
    },
    {
      "epoch": 0.23654186083882373,
      "grad_norm": 0.03336189687252045,
      "learning_rate": 2e-05,
      "loss": 0.4272,
      "step": 184
    },
    {
      "epoch": 0.23782741443033906,
      "grad_norm": 0.03514046594500542,
      "learning_rate": 2e-05,
      "loss": 0.3432,
      "step": 185
    },
    {
      "epoch": 0.23911296802185442,
      "grad_norm": 0.032468028366565704,
      "learning_rate": 2e-05,
      "loss": 0.405,
      "step": 186
    },
    {
      "epoch": 0.24039852161336975,
      "grad_norm": 0.026813151314854622,
      "learning_rate": 2e-05,
      "loss": 0.2746,
      "step": 187
    },
    {
      "epoch": 0.2416840752048851,
      "grad_norm": 0.03329463675618172,
      "learning_rate": 2e-05,
      "loss": 0.3566,
      "step": 188
    },
    {
      "epoch": 0.24296962879640044,
      "grad_norm": 0.03253549337387085,
      "learning_rate": 2e-05,
      "loss": 0.3951,
      "step": 189
    },
    {
      "epoch": 0.2442551823879158,
      "grad_norm": 0.03337908163666725,
      "learning_rate": 2e-05,
      "loss": 0.4022,
      "step": 190
    },
    {
      "epoch": 0.24554073597943113,
      "grad_norm": 0.029503121972084045,
      "learning_rate": 2e-05,
      "loss": 0.3154,
      "step": 191
    },
    {
      "epoch": 0.2468262895709465,
      "grad_norm": 0.03800208494067192,
      "learning_rate": 2e-05,
      "loss": 0.3716,
      "step": 192
    },
    {
      "epoch": 0.24811184316246185,
      "grad_norm": 0.04471494257450104,
      "learning_rate": 2e-05,
      "loss": 0.3618,
      "step": 193
    },
    {
      "epoch": 0.24939739675397718,
      "grad_norm": 0.03158828616142273,
      "learning_rate": 2e-05,
      "loss": 0.3035,
      "step": 194
    },
    {
      "epoch": 0.25068295034549254,
      "grad_norm": 0.030343275517225266,
      "learning_rate": 2e-05,
      "loss": 0.3177,
      "step": 195
    },
    {
      "epoch": 0.25196850393700787,
      "grad_norm": 0.027333417907357216,
      "learning_rate": 2e-05,
      "loss": 0.2688,
      "step": 196
    },
    {
      "epoch": 0.2532540575285232,
      "grad_norm": 0.034231096506118774,
      "learning_rate": 2e-05,
      "loss": 0.2827,
      "step": 197
    },
    {
      "epoch": 0.2545396111200386,
      "grad_norm": 0.042767249047756195,
      "learning_rate": 2e-05,
      "loss": 0.3617,
      "step": 198
    },
    {
      "epoch": 0.2558251647115539,
      "grad_norm": 0.04363776370882988,
      "learning_rate": 2e-05,
      "loss": 0.428,
      "step": 199
    },
    {
      "epoch": 0.25711071830306925,
      "grad_norm": 0.03701059892773628,
      "learning_rate": 2e-05,
      "loss": 0.4258,
      "step": 200
    },
    {
      "epoch": 0.2583962718945846,
      "grad_norm": 0.03248538821935654,
      "learning_rate": 2e-05,
      "loss": 0.3127,
      "step": 201
    },
    {
      "epoch": 0.25968182548609997,
      "grad_norm": 0.02792442962527275,
      "learning_rate": 2e-05,
      "loss": 0.2616,
      "step": 202
    },
    {
      "epoch": 0.2609673790776153,
      "grad_norm": 0.02882961928844452,
      "learning_rate": 2e-05,
      "loss": 0.2822,
      "step": 203
    },
    {
      "epoch": 0.26225293266913063,
      "grad_norm": 0.02498476952314377,
      "learning_rate": 2e-05,
      "loss": 0.2291,
      "step": 204
    },
    {
      "epoch": 0.26353848626064597,
      "grad_norm": 0.0262466911226511,
      "learning_rate": 2e-05,
      "loss": 0.2084,
      "step": 205
    },
    {
      "epoch": 0.26482403985216135,
      "grad_norm": 0.031161930412054062,
      "learning_rate": 2e-05,
      "loss": 0.2977,
      "step": 206
    },
    {
      "epoch": 0.2661095934436767,
      "grad_norm": 0.03852604702115059,
      "learning_rate": 2e-05,
      "loss": 0.3606,
      "step": 207
    },
    {
      "epoch": 0.267395147035192,
      "grad_norm": 0.03641024976968765,
      "learning_rate": 2e-05,
      "loss": 0.3855,
      "step": 208
    },
    {
      "epoch": 0.2686807006267074,
      "grad_norm": 0.03774799406528473,
      "learning_rate": 2e-05,
      "loss": 0.3458,
      "step": 209
    },
    {
      "epoch": 0.26996625421822273,
      "grad_norm": 0.04067372530698776,
      "learning_rate": 2e-05,
      "loss": 0.4515,
      "step": 210
    },
    {
      "epoch": 0.27125180780973807,
      "grad_norm": 0.03964482620358467,
      "learning_rate": 2e-05,
      "loss": 0.4272,
      "step": 211
    },
    {
      "epoch": 0.2725373614012534,
      "grad_norm": 0.02894040197134018,
      "learning_rate": 2e-05,
      "loss": 0.256,
      "step": 212
    },
    {
      "epoch": 0.2738229149927688,
      "grad_norm": 0.036077771335840225,
      "learning_rate": 2e-05,
      "loss": 0.3755,
      "step": 213
    },
    {
      "epoch": 0.2751084685842841,
      "grad_norm": 0.032988108694553375,
      "learning_rate": 2e-05,
      "loss": 0.3135,
      "step": 214
    },
    {
      "epoch": 0.27639402217579945,
      "grad_norm": 0.02877802960574627,
      "learning_rate": 2e-05,
      "loss": 0.2762,
      "step": 215
    },
    {
      "epoch": 0.2776795757673148,
      "grad_norm": 0.03700711205601692,
      "learning_rate": 2e-05,
      "loss": 0.3022,
      "step": 216
    },
    {
      "epoch": 0.27896512935883017,
      "grad_norm": 0.03660174459218979,
      "learning_rate": 2e-05,
      "loss": 0.3265,
      "step": 217
    },
    {
      "epoch": 0.2802506829503455,
      "grad_norm": 0.034895338118076324,
      "learning_rate": 2e-05,
      "loss": 0.3337,
      "step": 218
    },
    {
      "epoch": 0.28153623654186083,
      "grad_norm": 0.029524167999625206,
      "learning_rate": 2e-05,
      "loss": 0.2872,
      "step": 219
    },
    {
      "epoch": 0.28282179013337616,
      "grad_norm": 0.037102892994880676,
      "learning_rate": 2e-05,
      "loss": 0.3484,
      "step": 220
    },
    {
      "epoch": 0.28410734372489155,
      "grad_norm": 0.02568918839097023,
      "learning_rate": 2e-05,
      "loss": 0.2352,
      "step": 221
    },
    {
      "epoch": 0.2853928973164069,
      "grad_norm": 0.03680694103240967,
      "learning_rate": 2e-05,
      "loss": 0.3156,
      "step": 222
    },
    {
      "epoch": 0.2866784509079222,
      "grad_norm": 0.03616785258054733,
      "learning_rate": 2e-05,
      "loss": 0.3435,
      "step": 223
    },
    {
      "epoch": 0.2879640044994376,
      "grad_norm": 0.03019794449210167,
      "learning_rate": 2e-05,
      "loss": 0.2342,
      "step": 224
    },
    {
      "epoch": 0.28924955809095293,
      "grad_norm": 0.029189620167016983,
      "learning_rate": 2e-05,
      "loss": 0.2622,
      "step": 225
    },
    {
      "epoch": 0.29053511168246826,
      "grad_norm": 0.03722851350903511,
      "learning_rate": 2e-05,
      "loss": 0.3245,
      "step": 226
    },
    {
      "epoch": 0.2918206652739836,
      "grad_norm": 0.028928019106388092,
      "learning_rate": 2e-05,
      "loss": 0.2444,
      "step": 227
    },
    {
      "epoch": 0.293106218865499,
      "grad_norm": 0.03965122997760773,
      "learning_rate": 2e-05,
      "loss": 0.2914,
      "step": 228
    },
    {
      "epoch": 0.2943917724570143,
      "grad_norm": 0.03618443012237549,
      "learning_rate": 2e-05,
      "loss": 0.2944,
      "step": 229
    },
    {
      "epoch": 0.29567732604852964,
      "grad_norm": 0.04255329445004463,
      "learning_rate": 2e-05,
      "loss": 0.3803,
      "step": 230
    },
    {
      "epoch": 0.296962879640045,
      "grad_norm": 0.03631114959716797,
      "learning_rate": 2e-05,
      "loss": 0.3529,
      "step": 231
    },
    {
      "epoch": 0.29824843323156036,
      "grad_norm": 0.0347764790058136,
      "learning_rate": 2e-05,
      "loss": 0.2967,
      "step": 232
    },
    {
      "epoch": 0.2995339868230757,
      "grad_norm": 0.03510100021958351,
      "learning_rate": 2e-05,
      "loss": 0.3316,
      "step": 233
    },
    {
      "epoch": 0.300819540414591,
      "grad_norm": 0.03378084674477577,
      "learning_rate": 2e-05,
      "loss": 0.3318,
      "step": 234
    },
    {
      "epoch": 0.30210509400610636,
      "grad_norm": 0.035719968378543854,
      "learning_rate": 2e-05,
      "loss": 0.2408,
      "step": 235
    },
    {
      "epoch": 0.30339064759762174,
      "grad_norm": 0.03345809876918793,
      "learning_rate": 2e-05,
      "loss": 0.2553,
      "step": 236
    },
    {
      "epoch": 0.3046762011891371,
      "grad_norm": 0.03555387631058693,
      "learning_rate": 2e-05,
      "loss": 0.2032,
      "step": 237
    },
    {
      "epoch": 0.3059617547806524,
      "grad_norm": 0.037534430623054504,
      "learning_rate": 2e-05,
      "loss": 0.3482,
      "step": 238
    },
    {
      "epoch": 0.30724730837216774,
      "grad_norm": 0.03810921311378479,
      "learning_rate": 2e-05,
      "loss": 0.2931,
      "step": 239
    },
    {
      "epoch": 0.3085328619636831,
      "grad_norm": 0.03767091780900955,
      "learning_rate": 2e-05,
      "loss": 0.3031,
      "step": 240
    },
    {
      "epoch": 0.30981841555519846,
      "grad_norm": 0.04636585712432861,
      "learning_rate": 2e-05,
      "loss": 0.3323,
      "step": 241
    },
    {
      "epoch": 0.3111039691467138,
      "grad_norm": 0.02405642159283161,
      "learning_rate": 2e-05,
      "loss": 0.1964,
      "step": 242
    },
    {
      "epoch": 0.3123895227382292,
      "grad_norm": 0.03820343688130379,
      "learning_rate": 2e-05,
      "loss": 0.265,
      "step": 243
    },
    {
      "epoch": 0.3136750763297445,
      "grad_norm": 0.04235352948307991,
      "learning_rate": 2e-05,
      "loss": 0.3761,
      "step": 244
    },
    {
      "epoch": 0.31496062992125984,
      "grad_norm": 0.02953983098268509,
      "learning_rate": 2e-05,
      "loss": 0.2458,
      "step": 245
    },
    {
      "epoch": 0.31624618351277517,
      "grad_norm": 0.031593743711709976,
      "learning_rate": 2e-05,
      "loss": 0.2278,
      "step": 246
    },
    {
      "epoch": 0.31753173710429056,
      "grad_norm": 0.033025920391082764,
      "learning_rate": 2e-05,
      "loss": 0.2967,
      "step": 247
    },
    {
      "epoch": 0.3188172906958059,
      "grad_norm": 0.03608924522995949,
      "learning_rate": 2e-05,
      "loss": 0.3211,
      "step": 248
    },
    {
      "epoch": 0.3201028442873212,
      "grad_norm": 0.029520737007260323,
      "learning_rate": 2e-05,
      "loss": 0.2659,
      "step": 249
    },
    {
      "epoch": 0.32138839787883655,
      "grad_norm": 0.043838564306497574,
      "learning_rate": 2e-05,
      "loss": 0.4001,
      "step": 250
    },
    {
      "epoch": 0.32267395147035194,
      "grad_norm": 0.03314085677266121,
      "learning_rate": 2e-05,
      "loss": 0.2669,
      "step": 251
    },
    {
      "epoch": 0.32395950506186727,
      "grad_norm": 0.03647439181804657,
      "learning_rate": 2e-05,
      "loss": 0.3063,
      "step": 252
    },
    {
      "epoch": 0.3252450586533826,
      "grad_norm": 0.03778000921010971,
      "learning_rate": 2e-05,
      "loss": 0.3437,
      "step": 253
    },
    {
      "epoch": 0.32653061224489793,
      "grad_norm": 0.035549599677324295,
      "learning_rate": 2e-05,
      "loss": 0.3332,
      "step": 254
    },
    {
      "epoch": 0.3278161658364133,
      "grad_norm": 0.033758629113435745,
      "learning_rate": 2e-05,
      "loss": 0.2372,
      "step": 255
    },
    {
      "epoch": 0.32910171942792865,
      "grad_norm": 0.04042687267065048,
      "learning_rate": 2e-05,
      "loss": 0.2862,
      "step": 256
    },
    {
      "epoch": 0.330387273019444,
      "grad_norm": 0.032794684171676636,
      "learning_rate": 2e-05,
      "loss": 0.2631,
      "step": 257
    },
    {
      "epoch": 0.33167282661095937,
      "grad_norm": 0.03374920412898064,
      "learning_rate": 2e-05,
      "loss": 0.2703,
      "step": 258
    },
    {
      "epoch": 0.3329583802024747,
      "grad_norm": 0.03981158137321472,
      "learning_rate": 2e-05,
      "loss": 0.3021,
      "step": 259
    },
    {
      "epoch": 0.33424393379399003,
      "grad_norm": 0.034164056181907654,
      "learning_rate": 2e-05,
      "loss": 0.3245,
      "step": 260
    },
    {
      "epoch": 0.33552948738550537,
      "grad_norm": 0.03673673793673515,
      "learning_rate": 2e-05,
      "loss": 0.3044,
      "step": 261
    },
    {
      "epoch": 0.33681504097702075,
      "grad_norm": 0.04251427203416824,
      "learning_rate": 2e-05,
      "loss": 0.3132,
      "step": 262
    },
    {
      "epoch": 0.3381005945685361,
      "grad_norm": 0.055292125791311264,
      "learning_rate": 2e-05,
      "loss": 0.3668,
      "step": 263
    },
    {
      "epoch": 0.3393861481600514,
      "grad_norm": 0.03982202708721161,
      "learning_rate": 2e-05,
      "loss": 0.3389,
      "step": 264
    },
    {
      "epoch": 0.34067170175156675,
      "grad_norm": 0.03548764809966087,
      "learning_rate": 2e-05,
      "loss": 0.2439,
      "step": 265
    },
    {
      "epoch": 0.34195725534308213,
      "grad_norm": 0.04806696996092796,
      "learning_rate": 2e-05,
      "loss": 0.3923,
      "step": 266
    },
    {
      "epoch": 0.34324280893459747,
      "grad_norm": 0.036050595343112946,
      "learning_rate": 2e-05,
      "loss": 0.2605,
      "step": 267
    },
    {
      "epoch": 0.3445283625261128,
      "grad_norm": 0.032735515385866165,
      "learning_rate": 2e-05,
      "loss": 0.2451,
      "step": 268
    },
    {
      "epoch": 0.34581391611762813,
      "grad_norm": 0.039695464074611664,
      "learning_rate": 2e-05,
      "loss": 0.3072,
      "step": 269
    },
    {
      "epoch": 0.3470994697091435,
      "grad_norm": 0.027333933860063553,
      "learning_rate": 2e-05,
      "loss": 0.2099,
      "step": 270
    },
    {
      "epoch": 0.34838502330065885,
      "grad_norm": 0.03149592876434326,
      "learning_rate": 2e-05,
      "loss": 0.2613,
      "step": 271
    },
    {
      "epoch": 0.3496705768921742,
      "grad_norm": 0.031215226277709007,
      "learning_rate": 2e-05,
      "loss": 0.2833,
      "step": 272
    },
    {
      "epoch": 0.35095613048368957,
      "grad_norm": 0.04059711471199989,
      "learning_rate": 2e-05,
      "loss": 0.3666,
      "step": 273
    },
    {
      "epoch": 0.3522416840752049,
      "grad_norm": 0.04247285798192024,
      "learning_rate": 2e-05,
      "loss": 0.3758,
      "step": 274
    },
    {
      "epoch": 0.35352723766672023,
      "grad_norm": 0.034378454089164734,
      "learning_rate": 2e-05,
      "loss": 0.2519,
      "step": 275
    },
    {
      "epoch": 0.35481279125823556,
      "grad_norm": 0.037096619606018066,
      "learning_rate": 2e-05,
      "loss": 0.3256,
      "step": 276
    },
    {
      "epoch": 0.35609834484975095,
      "grad_norm": 0.03536511957645416,
      "learning_rate": 2e-05,
      "loss": 0.2596,
      "step": 277
    },
    {
      "epoch": 0.3573838984412663,
      "grad_norm": 0.046086303889751434,
      "learning_rate": 2e-05,
      "loss": 0.3132,
      "step": 278
    },
    {
      "epoch": 0.3586694520327816,
      "grad_norm": 0.03302552178502083,
      "learning_rate": 2e-05,
      "loss": 0.2839,
      "step": 279
    },
    {
      "epoch": 0.35995500562429694,
      "grad_norm": 0.03423115238547325,
      "learning_rate": 2e-05,
      "loss": 0.2678,
      "step": 280
    },
    {
      "epoch": 0.36124055921581233,
      "grad_norm": 0.03363805264234543,
      "learning_rate": 2e-05,
      "loss": 0.2243,
      "step": 281
    },
    {
      "epoch": 0.36252611280732766,
      "grad_norm": 0.03901209309697151,
      "learning_rate": 2e-05,
      "loss": 0.2956,
      "step": 282
    },
    {
      "epoch": 0.363811666398843,
      "grad_norm": 0.03081115335226059,
      "learning_rate": 2e-05,
      "loss": 0.213,
      "step": 283
    },
    {
      "epoch": 0.3650972199903583,
      "grad_norm": 0.04130322486162186,
      "learning_rate": 2e-05,
      "loss": 0.3161,
      "step": 284
    },
    {
      "epoch": 0.3663827735818737,
      "grad_norm": 0.03694218024611473,
      "learning_rate": 2e-05,
      "loss": 0.3228,
      "step": 285
    },
    {
      "epoch": 0.36766832717338904,
      "grad_norm": 0.048961639404296875,
      "learning_rate": 2e-05,
      "loss": 0.3688,
      "step": 286
    },
    {
      "epoch": 0.3689538807649044,
      "grad_norm": 0.03482965752482414,
      "learning_rate": 2e-05,
      "loss": 0.2797,
      "step": 287
    },
    {
      "epoch": 0.37023943435641976,
      "grad_norm": 0.043517641723155975,
      "learning_rate": 2e-05,
      "loss": 0.3395,
      "step": 288
    },
    {
      "epoch": 0.3715249879479351,
      "grad_norm": 0.03916122019290924,
      "learning_rate": 2e-05,
      "loss": 0.3168,
      "step": 289
    },
    {
      "epoch": 0.3728105415394504,
      "grad_norm": 0.03970535099506378,
      "learning_rate": 2e-05,
      "loss": 0.3523,
      "step": 290
    },
    {
      "epoch": 0.37409609513096576,
      "grad_norm": 0.043576546013355255,
      "learning_rate": 2e-05,
      "loss": 0.3974,
      "step": 291
    },
    {
      "epoch": 0.37538164872248114,
      "grad_norm": 0.03478504344820976,
      "learning_rate": 2e-05,
      "loss": 0.2663,
      "step": 292
    },
    {
      "epoch": 0.3766672023139965,
      "grad_norm": 0.0442640446126461,
      "learning_rate": 2e-05,
      "loss": 0.2685,
      "step": 293
    },
    {
      "epoch": 0.3779527559055118,
      "grad_norm": 0.04135148599743843,
      "learning_rate": 2e-05,
      "loss": 0.3765,
      "step": 294
    },
    {
      "epoch": 0.37923830949702714,
      "grad_norm": 0.03744332864880562,
      "learning_rate": 2e-05,
      "loss": 0.3693,
      "step": 295
    },
    {
      "epoch": 0.3805238630885425,
      "grad_norm": 0.038954440504312515,
      "learning_rate": 2e-05,
      "loss": 0.289,
      "step": 296
    },
    {
      "epoch": 0.38180941668005786,
      "grad_norm": 0.031730618327856064,
      "learning_rate": 2e-05,
      "loss": 0.2271,
      "step": 297
    },
    {
      "epoch": 0.3830949702715732,
      "grad_norm": 0.04433518648147583,
      "learning_rate": 2e-05,
      "loss": 0.4079,
      "step": 298
    },
    {
      "epoch": 0.3843805238630885,
      "grad_norm": 0.04384070262312889,
      "learning_rate": 2e-05,
      "loss": 0.3005,
      "step": 299
    },
    {
      "epoch": 0.3856660774546039,
      "grad_norm": 0.03004288114607334,
      "learning_rate": 2e-05,
      "loss": 0.2113,
      "step": 300
    },
    {
      "epoch": 0.38695163104611924,
      "grad_norm": 0.0353570394217968,
      "learning_rate": 2e-05,
      "loss": 0.2198,
      "step": 301
    },
    {
      "epoch": 0.38823718463763457,
      "grad_norm": 0.04267432913184166,
      "learning_rate": 2e-05,
      "loss": 0.3431,
      "step": 302
    },
    {
      "epoch": 0.3895227382291499,
      "grad_norm": 0.04084617272019386,
      "learning_rate": 2e-05,
      "loss": 0.3099,
      "step": 303
    },
    {
      "epoch": 0.3908082918206653,
      "grad_norm": 0.059954188764095306,
      "learning_rate": 2e-05,
      "loss": 0.3891,
      "step": 304
    },
    {
      "epoch": 0.3920938454121806,
      "grad_norm": 0.03467090055346489,
      "learning_rate": 2e-05,
      "loss": 0.2383,
      "step": 305
    },
    {
      "epoch": 0.39337939900369595,
      "grad_norm": 0.03164566680788994,
      "learning_rate": 2e-05,
      "loss": 0.2079,
      "step": 306
    },
    {
      "epoch": 0.39466495259521134,
      "grad_norm": 0.048123132437467575,
      "learning_rate": 2e-05,
      "loss": 0.3726,
      "step": 307
    },
    {
      "epoch": 0.39595050618672667,
      "grad_norm": 0.03534458950161934,
      "learning_rate": 2e-05,
      "loss": 0.2651,
      "step": 308
    },
    {
      "epoch": 0.397236059778242,
      "grad_norm": 0.03836483508348465,
      "learning_rate": 2e-05,
      "loss": 0.3101,
      "step": 309
    },
    {
      "epoch": 0.39852161336975733,
      "grad_norm": 0.047910891473293304,
      "learning_rate": 2e-05,
      "loss": 0.3234,
      "step": 310
    },
    {
      "epoch": 0.3998071669612727,
      "grad_norm": 0.027741173282265663,
      "learning_rate": 2e-05,
      "loss": 0.1632,
      "step": 311
    },
    {
      "epoch": 0.40109272055278805,
      "grad_norm": 0.0344574935734272,
      "learning_rate": 2e-05,
      "loss": 0.2463,
      "step": 312
    },
    {
      "epoch": 0.4023782741443034,
      "grad_norm": 0.032118018716573715,
      "learning_rate": 2e-05,
      "loss": 0.2298,
      "step": 313
    },
    {
      "epoch": 0.4036638277358187,
      "grad_norm": 0.040490612387657166,
      "learning_rate": 2e-05,
      "loss": 0.3247,
      "step": 314
    },
    {
      "epoch": 0.4049493813273341,
      "grad_norm": 0.03369493409991264,
      "learning_rate": 2e-05,
      "loss": 0.2088,
      "step": 315
    },
    {
      "epoch": 0.40623493491884943,
      "grad_norm": 0.04419386386871338,
      "learning_rate": 2e-05,
      "loss": 0.3354,
      "step": 316
    },
    {
      "epoch": 0.40752048851036476,
      "grad_norm": 0.04048989340662956,
      "learning_rate": 2e-05,
      "loss": 0.2988,
      "step": 317
    },
    {
      "epoch": 0.4088060421018801,
      "grad_norm": 0.040915414690971375,
      "learning_rate": 2e-05,
      "loss": 0.2315,
      "step": 318
    },
    {
      "epoch": 0.4100915956933955,
      "grad_norm": 0.03020886704325676,
      "learning_rate": 2e-05,
      "loss": 0.2137,
      "step": 319
    },
    {
      "epoch": 0.4113771492849108,
      "grad_norm": 0.0413849912583828,
      "learning_rate": 2e-05,
      "loss": 0.3479,
      "step": 320
    },
    {
      "epoch": 0.41266270287642615,
      "grad_norm": 0.04639044404029846,
      "learning_rate": 2e-05,
      "loss": 0.3689,
      "step": 321
    },
    {
      "epoch": 0.41394825646794153,
      "grad_norm": 0.044351786375045776,
      "learning_rate": 2e-05,
      "loss": 0.3488,
      "step": 322
    },
    {
      "epoch": 0.41523381005945686,
      "grad_norm": 0.030558589845895767,
      "learning_rate": 2e-05,
      "loss": 0.2211,
      "step": 323
    },
    {
      "epoch": 0.4165193636509722,
      "grad_norm": 0.03329205513000488,
      "learning_rate": 2e-05,
      "loss": 0.2282,
      "step": 324
    },
    {
      "epoch": 0.41780491724248753,
      "grad_norm": 0.04240158200263977,
      "learning_rate": 2e-05,
      "loss": 0.2571,
      "step": 325
    },
    {
      "epoch": 0.4190904708340029,
      "grad_norm": 0.040866266936063766,
      "learning_rate": 2e-05,
      "loss": 0.289,
      "step": 326
    },
    {
      "epoch": 0.42037602442551825,
      "grad_norm": 0.04475086182355881,
      "learning_rate": 2e-05,
      "loss": 0.2889,
      "step": 327
    },
    {
      "epoch": 0.4216615780170336,
      "grad_norm": 0.03587472438812256,
      "learning_rate": 2e-05,
      "loss": 0.2452,
      "step": 328
    },
    {
      "epoch": 0.4229471316085489,
      "grad_norm": 0.04346352815628052,
      "learning_rate": 2e-05,
      "loss": 0.3751,
      "step": 329
    },
    {
      "epoch": 0.4242326852000643,
      "grad_norm": 0.03417763113975525,
      "learning_rate": 2e-05,
      "loss": 0.2825,
      "step": 330
    },
    {
      "epoch": 0.42551823879157963,
      "grad_norm": 0.030223989859223366,
      "learning_rate": 2e-05,
      "loss": 0.2339,
      "step": 331
    },
    {
      "epoch": 0.42680379238309496,
      "grad_norm": 0.0342961922287941,
      "learning_rate": 2e-05,
      "loss": 0.2616,
      "step": 332
    },
    {
      "epoch": 0.4280893459746103,
      "grad_norm": 0.04207473620772362,
      "learning_rate": 2e-05,
      "loss": 0.265,
      "step": 333
    },
    {
      "epoch": 0.4293748995661257,
      "grad_norm": 0.03148888424038887,
      "learning_rate": 2e-05,
      "loss": 0.1792,
      "step": 334
    },
    {
      "epoch": 0.430660453157641,
      "grad_norm": 0.039937492460012436,
      "learning_rate": 2e-05,
      "loss": 0.2502,
      "step": 335
    },
    {
      "epoch": 0.43194600674915634,
      "grad_norm": 0.03943054750561714,
      "learning_rate": 2e-05,
      "loss": 0.2733,
      "step": 336
    },
    {
      "epoch": 0.43323156034067173,
      "grad_norm": 0.03569771721959114,
      "learning_rate": 2e-05,
      "loss": 0.2099,
      "step": 337
    },
    {
      "epoch": 0.43451711393218706,
      "grad_norm": 0.036599624902009964,
      "learning_rate": 2e-05,
      "loss": 0.2478,
      "step": 338
    },
    {
      "epoch": 0.4358026675237024,
      "grad_norm": 0.054707758128643036,
      "learning_rate": 2e-05,
      "loss": 0.4257,
      "step": 339
    },
    {
      "epoch": 0.4370882211152177,
      "grad_norm": 0.0450870580971241,
      "learning_rate": 2e-05,
      "loss": 0.3091,
      "step": 340
    },
    {
      "epoch": 0.4383737747067331,
      "grad_norm": 0.03818565234541893,
      "learning_rate": 2e-05,
      "loss": 0.2781,
      "step": 341
    },
    {
      "epoch": 0.43965932829824844,
      "grad_norm": 0.03722561523318291,
      "learning_rate": 2e-05,
      "loss": 0.2602,
      "step": 342
    },
    {
      "epoch": 0.4409448818897638,
      "grad_norm": 0.038348764181137085,
      "learning_rate": 2e-05,
      "loss": 0.286,
      "step": 343
    },
    {
      "epoch": 0.4422304354812791,
      "grad_norm": 0.02572775073349476,
      "learning_rate": 2e-05,
      "loss": 0.1886,
      "step": 344
    },
    {
      "epoch": 0.4435159890727945,
      "grad_norm": 0.03972122073173523,
      "learning_rate": 2e-05,
      "loss": 0.2756,
      "step": 345
    },
    {
      "epoch": 0.4448015426643098,
      "grad_norm": 0.03696167469024658,
      "learning_rate": 2e-05,
      "loss": 0.2526,
      "step": 346
    },
    {
      "epoch": 0.44608709625582516,
      "grad_norm": 0.03587668761610985,
      "learning_rate": 2e-05,
      "loss": 0.2044,
      "step": 347
    },
    {
      "epoch": 0.4473726498473405,
      "grad_norm": 0.03959975019097328,
      "learning_rate": 2e-05,
      "loss": 0.3007,
      "step": 348
    },
    {
      "epoch": 0.4486582034388559,
      "grad_norm": 0.03879138454794884,
      "learning_rate": 2e-05,
      "loss": 0.2382,
      "step": 349
    },
    {
      "epoch": 0.4499437570303712,
      "grad_norm": 0.05302846059203148,
      "learning_rate": 2e-05,
      "loss": 0.3375,
      "step": 350
    },
    {
      "epoch": 0.45122931062188654,
      "grad_norm": 0.039411693811416626,
      "learning_rate": 2e-05,
      "loss": 0.2662,
      "step": 351
    },
    {
      "epoch": 0.4525148642134019,
      "grad_norm": 0.03571093827486038,
      "learning_rate": 2e-05,
      "loss": 0.2054,
      "step": 352
    },
    {
      "epoch": 0.45380041780491726,
      "grad_norm": 0.0486789233982563,
      "learning_rate": 2e-05,
      "loss": 0.3314,
      "step": 353
    },
    {
      "epoch": 0.4550859713964326,
      "grad_norm": 0.037670183926820755,
      "learning_rate": 2e-05,
      "loss": 0.2484,
      "step": 354
    },
    {
      "epoch": 0.4563715249879479,
      "grad_norm": 0.056887123733758926,
      "learning_rate": 2e-05,
      "loss": 0.3562,
      "step": 355
    },
    {
      "epoch": 0.4576570785794633,
      "grad_norm": 0.04562405124306679,
      "learning_rate": 2e-05,
      "loss": 0.2869,
      "step": 356
    },
    {
      "epoch": 0.45894263217097864,
      "grad_norm": 0.040491264313459396,
      "learning_rate": 2e-05,
      "loss": 0.3541,
      "step": 357
    },
    {
      "epoch": 0.46022818576249397,
      "grad_norm": 0.04283326864242554,
      "learning_rate": 2e-05,
      "loss": 0.2674,
      "step": 358
    },
    {
      "epoch": 0.4615137393540093,
      "grad_norm": 0.05063975229859352,
      "learning_rate": 2e-05,
      "loss": 0.4013,
      "step": 359
    },
    {
      "epoch": 0.4627992929455247,
      "grad_norm": 0.037555571645498276,
      "learning_rate": 2e-05,
      "loss": 0.2419,
      "step": 360
    },
    {
      "epoch": 0.46408484653704,
      "grad_norm": 0.036944594234228134,
      "learning_rate": 2e-05,
      "loss": 0.2426,
      "step": 361
    },
    {
      "epoch": 0.46537040012855535,
      "grad_norm": 0.05010130628943443,
      "learning_rate": 2e-05,
      "loss": 0.2996,
      "step": 362
    },
    {
      "epoch": 0.4666559537200707,
      "grad_norm": 0.0335206501185894,
      "learning_rate": 2e-05,
      "loss": 0.2451,
      "step": 363
    },
    {
      "epoch": 0.46794150731158607,
      "grad_norm": 0.052481383085250854,
      "learning_rate": 2e-05,
      "loss": 0.3812,
      "step": 364
    },
    {
      "epoch": 0.4692270609031014,
      "grad_norm": 0.04185234755277634,
      "learning_rate": 2e-05,
      "loss": 0.274,
      "step": 365
    },
    {
      "epoch": 0.47051261449461673,
      "grad_norm": 0.03707558289170265,
      "learning_rate": 2e-05,
      "loss": 0.2505,
      "step": 366
    },
    {
      "epoch": 0.47179816808613206,
      "grad_norm": 0.060728251934051514,
      "learning_rate": 2e-05,
      "loss": 0.3279,
      "step": 367
    },
    {
      "epoch": 0.47308372167764745,
      "grad_norm": 0.031999371945858,
      "learning_rate": 2e-05,
      "loss": 0.1866,
      "step": 368
    },
    {
      "epoch": 0.4743692752691628,
      "grad_norm": 0.044399287551641464,
      "learning_rate": 2e-05,
      "loss": 0.249,
      "step": 369
    },
    {
      "epoch": 0.4756548288606781,
      "grad_norm": 0.05057983100414276,
      "learning_rate": 2e-05,
      "loss": 0.3612,
      "step": 370
    },
    {
      "epoch": 0.4769403824521935,
      "grad_norm": 0.039979059249162674,
      "learning_rate": 2e-05,
      "loss": 0.2684,
      "step": 371
    },
    {
      "epoch": 0.47822593604370883,
      "grad_norm": 0.03305087611079216,
      "learning_rate": 2e-05,
      "loss": 0.2164,
      "step": 372
    },
    {
      "epoch": 0.47951148963522416,
      "grad_norm": 0.045574892312288284,
      "learning_rate": 2e-05,
      "loss": 0.3127,
      "step": 373
    },
    {
      "epoch": 0.4807970432267395,
      "grad_norm": 0.05269627645611763,
      "learning_rate": 2e-05,
      "loss": 0.3315,
      "step": 374
    },
    {
      "epoch": 0.4820825968182549,
      "grad_norm": 0.06162478029727936,
      "learning_rate": 2e-05,
      "loss": 0.3347,
      "step": 375
    },
    {
      "epoch": 0.4833681504097702,
      "grad_norm": 0.04428340122103691,
      "learning_rate": 2e-05,
      "loss": 0.2794,
      "step": 376
    },
    {
      "epoch": 0.48465370400128555,
      "grad_norm": 0.04249970242381096,
      "learning_rate": 2e-05,
      "loss": 0.2781,
      "step": 377
    },
    {
      "epoch": 0.4859392575928009,
      "grad_norm": 0.04270468279719353,
      "learning_rate": 2e-05,
      "loss": 0.2878,
      "step": 378
    },
    {
      "epoch": 0.48722481118431626,
      "grad_norm": 0.036853183060884476,
      "learning_rate": 2e-05,
      "loss": 0.2548,
      "step": 379
    },
    {
      "epoch": 0.4885103647758316,
      "grad_norm": 0.03981437534093857,
      "learning_rate": 2e-05,
      "loss": 0.2743,
      "step": 380
    },
    {
      "epoch": 0.4897959183673469,
      "grad_norm": 0.04621482267975807,
      "learning_rate": 2e-05,
      "loss": 0.3524,
      "step": 381
    },
    {
      "epoch": 0.49108147195886226,
      "grad_norm": 0.04479382932186127,
      "learning_rate": 2e-05,
      "loss": 0.3013,
      "step": 382
    },
    {
      "epoch": 0.49236702555037765,
      "grad_norm": 0.0524832084774971,
      "learning_rate": 2e-05,
      "loss": 0.4674,
      "step": 383
    },
    {
      "epoch": 0.493652579141893,
      "grad_norm": 0.05657699331641197,
      "learning_rate": 2e-05,
      "loss": 0.3734,
      "step": 384
    },
    {
      "epoch": 0.4949381327334083,
      "grad_norm": 0.05035189166665077,
      "learning_rate": 2e-05,
      "loss": 0.2522,
      "step": 385
    },
    {
      "epoch": 0.4962236863249237,
      "grad_norm": 0.045344091951847076,
      "learning_rate": 2e-05,
      "loss": 0.3121,
      "step": 386
    },
    {
      "epoch": 0.49750923991643903,
      "grad_norm": 0.038680486381053925,
      "learning_rate": 2e-05,
      "loss": 0.2999,
      "step": 387
    },
    {
      "epoch": 0.49879479350795436,
      "grad_norm": 0.03980954363942146,
      "learning_rate": 2e-05,
      "loss": 0.2476,
      "step": 388
    },
    {
      "epoch": 0.5000803470994697,
      "grad_norm": 0.04812563210725784,
      "learning_rate": 2e-05,
      "loss": 0.3218,
      "step": 389
    },
    {
      "epoch": 0.5013659006909851,
      "grad_norm": 0.04132760316133499,
      "learning_rate": 2e-05,
      "loss": 0.2344,
      "step": 390
    },
    {
      "epoch": 0.5026514542825004,
      "grad_norm": 0.03867589682340622,
      "learning_rate": 2e-05,
      "loss": 0.2172,
      "step": 391
    },
    {
      "epoch": 0.5039370078740157,
      "grad_norm": 0.05404170975089073,
      "learning_rate": 2e-05,
      "loss": 0.3489,
      "step": 392
    },
    {
      "epoch": 0.5052225614655311,
      "grad_norm": 0.05424851179122925,
      "learning_rate": 2e-05,
      "loss": 0.3908,
      "step": 393
    },
    {
      "epoch": 0.5065081150570464,
      "grad_norm": 0.046993743628263474,
      "learning_rate": 2e-05,
      "loss": 0.3133,
      "step": 394
    },
    {
      "epoch": 0.5077936686485618,
      "grad_norm": 0.038952894508838654,
      "learning_rate": 2e-05,
      "loss": 0.273,
      "step": 395
    },
    {
      "epoch": 0.5090792222400772,
      "grad_norm": 0.039642345160245895,
      "learning_rate": 2e-05,
      "loss": 0.2163,
      "step": 396
    },
    {
      "epoch": 0.5103647758315925,
      "grad_norm": 0.05045924335718155,
      "learning_rate": 2e-05,
      "loss": 0.3934,
      "step": 397
    },
    {
      "epoch": 0.5116503294231078,
      "grad_norm": 0.03384791314601898,
      "learning_rate": 2e-05,
      "loss": 0.2427,
      "step": 398
    },
    {
      "epoch": 0.5129358830146231,
      "grad_norm": 0.04521351680159569,
      "learning_rate": 2e-05,
      "loss": 0.3329,
      "step": 399
    },
    {
      "epoch": 0.5142214366061385,
      "grad_norm": 0.044563427567481995,
      "learning_rate": 2e-05,
      "loss": 0.327,
      "step": 400
    },
    {
      "epoch": 0.5155069901976539,
      "grad_norm": 0.027659917250275612,
      "learning_rate": 2e-05,
      "loss": 0.1984,
      "step": 401
    },
    {
      "epoch": 0.5167925437891692,
      "grad_norm": 0.047275714576244354,
      "learning_rate": 2e-05,
      "loss": 0.2867,
      "step": 402
    },
    {
      "epoch": 0.5180780973806846,
      "grad_norm": 0.04775230586528778,
      "learning_rate": 2e-05,
      "loss": 0.355,
      "step": 403
    },
    {
      "epoch": 0.5193636509721999,
      "grad_norm": 0.04720161855220795,
      "learning_rate": 2e-05,
      "loss": 0.2423,
      "step": 404
    },
    {
      "epoch": 0.5206492045637152,
      "grad_norm": 0.04180417209863663,
      "learning_rate": 2e-05,
      "loss": 0.2688,
      "step": 405
    },
    {
      "epoch": 0.5219347581552306,
      "grad_norm": 0.05189646780490875,
      "learning_rate": 2e-05,
      "loss": 0.3736,
      "step": 406
    },
    {
      "epoch": 0.523220311746746,
      "grad_norm": 0.04067251831293106,
      "learning_rate": 2e-05,
      "loss": 0.3039,
      "step": 407
    },
    {
      "epoch": 0.5245058653382613,
      "grad_norm": 0.05931917205452919,
      "learning_rate": 2e-05,
      "loss": 0.3374,
      "step": 408
    },
    {
      "epoch": 0.5257914189297767,
      "grad_norm": 0.04547608271241188,
      "learning_rate": 2e-05,
      "loss": 0.2968,
      "step": 409
    },
    {
      "epoch": 0.5270769725212919,
      "grad_norm": 0.04650389403104782,
      "learning_rate": 2e-05,
      "loss": 0.2854,
      "step": 410
    },
    {
      "epoch": 0.5283625261128073,
      "grad_norm": 0.05240015685558319,
      "learning_rate": 2e-05,
      "loss": 0.2837,
      "step": 411
    },
    {
      "epoch": 0.5296480797043227,
      "grad_norm": 0.05040004476904869,
      "learning_rate": 2e-05,
      "loss": 0.2923,
      "step": 412
    },
    {
      "epoch": 0.530933633295838,
      "grad_norm": 0.04871930554509163,
      "learning_rate": 2e-05,
      "loss": 0.2414,
      "step": 413
    },
    {
      "epoch": 0.5322191868873534,
      "grad_norm": 0.04192574322223663,
      "learning_rate": 2e-05,
      "loss": 0.2764,
      "step": 414
    },
    {
      "epoch": 0.5335047404788688,
      "grad_norm": 0.05296563729643822,
      "learning_rate": 2e-05,
      "loss": 0.2723,
      "step": 415
    },
    {
      "epoch": 0.534790294070384,
      "grad_norm": 0.03959592431783676,
      "learning_rate": 2e-05,
      "loss": 0.2204,
      "step": 416
    },
    {
      "epoch": 0.5360758476618994,
      "grad_norm": 0.03962741047143936,
      "learning_rate": 2e-05,
      "loss": 0.2518,
      "step": 417
    },
    {
      "epoch": 0.5373614012534148,
      "grad_norm": 0.040081944316625595,
      "learning_rate": 2e-05,
      "loss": 0.2573,
      "step": 418
    },
    {
      "epoch": 0.5386469548449301,
      "grad_norm": 0.04713954031467438,
      "learning_rate": 2e-05,
      "loss": 0.2925,
      "step": 419
    },
    {
      "epoch": 0.5399325084364455,
      "grad_norm": 0.05657007545232773,
      "learning_rate": 2e-05,
      "loss": 0.4272,
      "step": 420
    },
    {
      "epoch": 0.5412180620279607,
      "grad_norm": 0.05307560786604881,
      "learning_rate": 2e-05,
      "loss": 0.316,
      "step": 421
    },
    {
      "epoch": 0.5425036156194761,
      "grad_norm": 0.04280155152082443,
      "learning_rate": 2e-05,
      "loss": 0.2614,
      "step": 422
    },
    {
      "epoch": 0.5437891692109915,
      "grad_norm": 0.03501439467072487,
      "learning_rate": 2e-05,
      "loss": 0.2318,
      "step": 423
    },
    {
      "epoch": 0.5450747228025068,
      "grad_norm": 0.05088590830564499,
      "learning_rate": 2e-05,
      "loss": 0.3533,
      "step": 424
    },
    {
      "epoch": 0.5463602763940222,
      "grad_norm": 0.03503134846687317,
      "learning_rate": 2e-05,
      "loss": 0.2079,
      "step": 425
    },
    {
      "epoch": 0.5476458299855376,
      "grad_norm": 0.043812718242406845,
      "learning_rate": 2e-05,
      "loss": 0.3205,
      "step": 426
    },
    {
      "epoch": 0.5489313835770528,
      "grad_norm": 0.05358745902776718,
      "learning_rate": 2e-05,
      "loss": 0.3713,
      "step": 427
    },
    {
      "epoch": 0.5502169371685682,
      "grad_norm": 0.042078517377376556,
      "learning_rate": 2e-05,
      "loss": 0.2371,
      "step": 428
    },
    {
      "epoch": 0.5515024907600835,
      "grad_norm": 0.04489399120211601,
      "learning_rate": 2e-05,
      "loss": 0.2832,
      "step": 429
    },
    {
      "epoch": 0.5527880443515989,
      "grad_norm": 0.04766567423939705,
      "learning_rate": 2e-05,
      "loss": 0.2151,
      "step": 430
    },
    {
      "epoch": 0.5540735979431143,
      "grad_norm": 0.04447382688522339,
      "learning_rate": 2e-05,
      "loss": 0.2317,
      "step": 431
    },
    {
      "epoch": 0.5553591515346296,
      "grad_norm": 0.04144001007080078,
      "learning_rate": 2e-05,
      "loss": 0.2667,
      "step": 432
    },
    {
      "epoch": 0.556644705126145,
      "grad_norm": 0.04112810641527176,
      "learning_rate": 2e-05,
      "loss": 0.2758,
      "step": 433
    },
    {
      "epoch": 0.5579302587176603,
      "grad_norm": 0.032402511686086655,
      "learning_rate": 2e-05,
      "loss": 0.2047,
      "step": 434
    },
    {
      "epoch": 0.5592158123091756,
      "grad_norm": 0.04352883994579315,
      "learning_rate": 2e-05,
      "loss": 0.323,
      "step": 435
    },
    {
      "epoch": 0.560501365900691,
      "grad_norm": 0.0496109239757061,
      "learning_rate": 2e-05,
      "loss": 0.2962,
      "step": 436
    },
    {
      "epoch": 0.5617869194922064,
      "grad_norm": 0.04593720659613609,
      "learning_rate": 2e-05,
      "loss": 0.3705,
      "step": 437
    },
    {
      "epoch": 0.5630724730837217,
      "grad_norm": 0.040998801589012146,
      "learning_rate": 2e-05,
      "loss": 0.2219,
      "step": 438
    },
    {
      "epoch": 0.564358026675237,
      "grad_norm": 0.04891293868422508,
      "learning_rate": 2e-05,
      "loss": 0.2539,
      "step": 439
    },
    {
      "epoch": 0.5656435802667523,
      "grad_norm": 0.04628092423081398,
      "learning_rate": 2e-05,
      "loss": 0.2521,
      "step": 440
    },
    {
      "epoch": 0.5669291338582677,
      "grad_norm": 0.03929414600133896,
      "learning_rate": 2e-05,
      "loss": 0.1931,
      "step": 441
    },
    {
      "epoch": 0.5682146874497831,
      "grad_norm": 0.03937762975692749,
      "learning_rate": 2e-05,
      "loss": 0.2225,
      "step": 442
    },
    {
      "epoch": 0.5695002410412984,
      "grad_norm": 0.057498469948768616,
      "learning_rate": 2e-05,
      "loss": 0.4021,
      "step": 443
    },
    {
      "epoch": 0.5707857946328138,
      "grad_norm": 0.04665215313434601,
      "learning_rate": 2e-05,
      "loss": 0.3026,
      "step": 444
    },
    {
      "epoch": 0.5720713482243291,
      "grad_norm": 0.04521113634109497,
      "learning_rate": 2e-05,
      "loss": 0.2592,
      "step": 445
    },
    {
      "epoch": 0.5733569018158444,
      "grad_norm": 0.038349051028490067,
      "learning_rate": 2e-05,
      "loss": 0.2501,
      "step": 446
    },
    {
      "epoch": 0.5746424554073598,
      "grad_norm": 0.04515808820724487,
      "learning_rate": 2e-05,
      "loss": 0.3092,
      "step": 447
    },
    {
      "epoch": 0.5759280089988752,
      "grad_norm": 0.047012921422719955,
      "learning_rate": 2e-05,
      "loss": 0.3338,
      "step": 448
    },
    {
      "epoch": 0.5772135625903905,
      "grad_norm": 0.0472906231880188,
      "learning_rate": 2e-05,
      "loss": 0.3139,
      "step": 449
    },
    {
      "epoch": 0.5784991161819059,
      "grad_norm": 0.04748733341693878,
      "learning_rate": 2e-05,
      "loss": 0.2414,
      "step": 450
    },
    {
      "epoch": 0.5797846697734211,
      "grad_norm": 0.03514058515429497,
      "learning_rate": 2e-05,
      "loss": 0.1946,
      "step": 451
    },
    {
      "epoch": 0.5810702233649365,
      "grad_norm": 0.050174906849861145,
      "learning_rate": 2e-05,
      "loss": 0.3284,
      "step": 452
    },
    {
      "epoch": 0.5823557769564519,
      "grad_norm": 0.05283737555146217,
      "learning_rate": 2e-05,
      "loss": 0.3073,
      "step": 453
    },
    {
      "epoch": 0.5836413305479672,
      "grad_norm": 0.04498602822422981,
      "learning_rate": 2e-05,
      "loss": 0.2604,
      "step": 454
    },
    {
      "epoch": 0.5849268841394826,
      "grad_norm": 0.042758163064718246,
      "learning_rate": 2e-05,
      "loss": 0.2221,
      "step": 455
    },
    {
      "epoch": 0.586212437730998,
      "grad_norm": 0.041656941175460815,
      "learning_rate": 2e-05,
      "loss": 0.2491,
      "step": 456
    },
    {
      "epoch": 0.5874979913225132,
      "grad_norm": 0.03713398054242134,
      "learning_rate": 2e-05,
      "loss": 0.1754,
      "step": 457
    },
    {
      "epoch": 0.5887835449140286,
      "grad_norm": 0.0447508729994297,
      "learning_rate": 2e-05,
      "loss": 0.2792,
      "step": 458
    },
    {
      "epoch": 0.5900690985055439,
      "grad_norm": 0.04686212167143822,
      "learning_rate": 2e-05,
      "loss": 0.2609,
      "step": 459
    },
    {
      "epoch": 0.5913546520970593,
      "grad_norm": 0.040732961148023605,
      "learning_rate": 2e-05,
      "loss": 0.2089,
      "step": 460
    },
    {
      "epoch": 0.5926402056885747,
      "grad_norm": 0.04114542156457901,
      "learning_rate": 2e-05,
      "loss": 0.2315,
      "step": 461
    },
    {
      "epoch": 0.59392575928009,
      "grad_norm": 0.040324702858924866,
      "learning_rate": 2e-05,
      "loss": 0.2778,
      "step": 462
    },
    {
      "epoch": 0.5952113128716053,
      "grad_norm": 0.0678023248910904,
      "learning_rate": 2e-05,
      "loss": 0.3029,
      "step": 463
    },
    {
      "epoch": 0.5964968664631207,
      "grad_norm": 0.04701264947652817,
      "learning_rate": 2e-05,
      "loss": 0.2829,
      "step": 464
    },
    {
      "epoch": 0.597782420054636,
      "grad_norm": 0.03481682017445564,
      "learning_rate": 2e-05,
      "loss": 0.2345,
      "step": 465
    },
    {
      "epoch": 0.5990679736461514,
      "grad_norm": 0.0509064756333828,
      "learning_rate": 2e-05,
      "loss": 0.303,
      "step": 466
    },
    {
      "epoch": 0.6003535272376668,
      "grad_norm": 0.052839163690805435,
      "learning_rate": 2e-05,
      "loss": 0.2798,
      "step": 467
    },
    {
      "epoch": 0.601639080829182,
      "grad_norm": 0.03605001047253609,
      "learning_rate": 2e-05,
      "loss": 0.1783,
      "step": 468
    },
    {
      "epoch": 0.6029246344206974,
      "grad_norm": 0.03640325739979744,
      "learning_rate": 2e-05,
      "loss": 0.2498,
      "step": 469
    },
    {
      "epoch": 0.6042101880122127,
      "grad_norm": 0.03874512016773224,
      "learning_rate": 2e-05,
      "loss": 0.1996,
      "step": 470
    },
    {
      "epoch": 0.6054957416037281,
      "grad_norm": 0.03477559611201286,
      "learning_rate": 2e-05,
      "loss": 0.2121,
      "step": 471
    },
    {
      "epoch": 0.6067812951952435,
      "grad_norm": 0.04953417927026749,
      "learning_rate": 2e-05,
      "loss": 0.2821,
      "step": 472
    },
    {
      "epoch": 0.6080668487867588,
      "grad_norm": 0.04992024600505829,
      "learning_rate": 2e-05,
      "loss": 0.362,
      "step": 473
    },
    {
      "epoch": 0.6093524023782741,
      "grad_norm": 0.048429060727357864,
      "learning_rate": 2e-05,
      "loss": 0.2217,
      "step": 474
    },
    {
      "epoch": 0.6106379559697895,
      "grad_norm": 0.05344587191939354,
      "learning_rate": 2e-05,
      "loss": 0.2989,
      "step": 475
    },
    {
      "epoch": 0.6119235095613048,
      "grad_norm": 0.04274825379252434,
      "learning_rate": 2e-05,
      "loss": 0.2424,
      "step": 476
    },
    {
      "epoch": 0.6132090631528202,
      "grad_norm": 0.04651128128170967,
      "learning_rate": 2e-05,
      "loss": 0.3412,
      "step": 477
    },
    {
      "epoch": 0.6144946167443355,
      "grad_norm": 0.05821945145726204,
      "learning_rate": 2e-05,
      "loss": 0.2726,
      "step": 478
    },
    {
      "epoch": 0.6157801703358509,
      "grad_norm": 0.0519278421998024,
      "learning_rate": 2e-05,
      "loss": 0.2927,
      "step": 479
    },
    {
      "epoch": 0.6170657239273662,
      "grad_norm": 0.03331352025270462,
      "learning_rate": 2e-05,
      "loss": 0.1688,
      "step": 480
    },
    {
      "epoch": 0.6183512775188815,
      "grad_norm": 0.04451346397399902,
      "learning_rate": 2e-05,
      "loss": 0.213,
      "step": 481
    },
    {
      "epoch": 0.6196368311103969,
      "grad_norm": 0.04776597023010254,
      "learning_rate": 2e-05,
      "loss": 0.2826,
      "step": 482
    },
    {
      "epoch": 0.6209223847019123,
      "grad_norm": 0.0488264262676239,
      "learning_rate": 2e-05,
      "loss": 0.2886,
      "step": 483
    },
    {
      "epoch": 0.6222079382934276,
      "grad_norm": 0.04393550381064415,
      "learning_rate": 2e-05,
      "loss": 0.1949,
      "step": 484
    },
    {
      "epoch": 0.623493491884943,
      "grad_norm": 0.050872016698122025,
      "learning_rate": 2e-05,
      "loss": 0.2201,
      "step": 485
    },
    {
      "epoch": 0.6247790454764584,
      "grad_norm": 0.06177595257759094,
      "learning_rate": 2e-05,
      "loss": 0.318,
      "step": 486
    },
    {
      "epoch": 0.6260645990679736,
      "grad_norm": 0.03842415288090706,
      "learning_rate": 2e-05,
      "loss": 0.1763,
      "step": 487
    },
    {
      "epoch": 0.627350152659489,
      "grad_norm": 0.04788699373602867,
      "learning_rate": 2e-05,
      "loss": 0.247,
      "step": 488
    },
    {
      "epoch": 0.6286357062510043,
      "grad_norm": 0.05789102241396904,
      "learning_rate": 2e-05,
      "loss": 0.3338,
      "step": 489
    },
    {
      "epoch": 0.6299212598425197,
      "grad_norm": 0.04298072308301926,
      "learning_rate": 2e-05,
      "loss": 0.2321,
      "step": 490
    },
    {
      "epoch": 0.6312068134340351,
      "grad_norm": 0.03914102911949158,
      "learning_rate": 2e-05,
      "loss": 0.2341,
      "step": 491
    },
    {
      "epoch": 0.6324923670255503,
      "grad_norm": 0.04699448123574257,
      "learning_rate": 2e-05,
      "loss": 0.2462,
      "step": 492
    },
    {
      "epoch": 0.6337779206170657,
      "grad_norm": 0.04092938452959061,
      "learning_rate": 2e-05,
      "loss": 0.2378,
      "step": 493
    },
    {
      "epoch": 0.6350634742085811,
      "grad_norm": 0.0463721826672554,
      "learning_rate": 2e-05,
      "loss": 0.225,
      "step": 494
    },
    {
      "epoch": 0.6363490278000964,
      "grad_norm": 0.0489421971142292,
      "learning_rate": 2e-05,
      "loss": 0.2341,
      "step": 495
    },
    {
      "epoch": 0.6376345813916118,
      "grad_norm": 0.04278067871928215,
      "learning_rate": 2e-05,
      "loss": 0.234,
      "step": 496
    },
    {
      "epoch": 0.6389201349831272,
      "grad_norm": 0.04674089327454567,
      "learning_rate": 2e-05,
      "loss": 0.2755,
      "step": 497
    },
    {
      "epoch": 0.6402056885746424,
      "grad_norm": 0.056766536086797714,
      "learning_rate": 2e-05,
      "loss": 0.3656,
      "step": 498
    },
    {
      "epoch": 0.6414912421661578,
      "grad_norm": 0.04216759279370308,
      "learning_rate": 2e-05,
      "loss": 0.2931,
      "step": 499
    },
    {
      "epoch": 0.6427767957576731,
      "grad_norm": 0.04742797464132309,
      "learning_rate": 2e-05,
      "loss": 0.3386,
      "step": 500
    },
    {
      "epoch": 0.6440623493491885,
      "grad_norm": 0.05907592922449112,
      "learning_rate": 2e-05,
      "loss": 0.3194,
      "step": 501
    },
    {
      "epoch": 0.6453479029407039,
      "grad_norm": 0.047280214726924896,
      "learning_rate": 2e-05,
      "loss": 0.2993,
      "step": 502
    },
    {
      "epoch": 0.6466334565322192,
      "grad_norm": 0.03869684040546417,
      "learning_rate": 2e-05,
      "loss": 0.158,
      "step": 503
    },
    {
      "epoch": 0.6479190101237345,
      "grad_norm": 0.04897621273994446,
      "learning_rate": 2e-05,
      "loss": 0.1948,
      "step": 504
    },
    {
      "epoch": 0.6492045637152499,
      "grad_norm": 0.055846258997917175,
      "learning_rate": 2e-05,
      "loss": 0.312,
      "step": 505
    },
    {
      "epoch": 0.6504901173067652,
      "grad_norm": 0.04266876354813576,
      "learning_rate": 2e-05,
      "loss": 0.2377,
      "step": 506
    },
    {
      "epoch": 0.6517756708982806,
      "grad_norm": 0.050029207020998,
      "learning_rate": 2e-05,
      "loss": 0.1797,
      "step": 507
    },
    {
      "epoch": 0.6530612244897959,
      "grad_norm": 0.035082824528217316,
      "learning_rate": 2e-05,
      "loss": 0.1799,
      "step": 508
    },
    {
      "epoch": 0.6543467780813113,
      "grad_norm": 0.04430130124092102,
      "learning_rate": 2e-05,
      "loss": 0.2327,
      "step": 509
    },
    {
      "epoch": 0.6556323316728266,
      "grad_norm": 0.03854670003056526,
      "learning_rate": 2e-05,
      "loss": 0.2235,
      "step": 510
    },
    {
      "epoch": 0.6569178852643419,
      "grad_norm": 0.04970936104655266,
      "learning_rate": 2e-05,
      "loss": 0.2818,
      "step": 511
    },
    {
      "epoch": 0.6582034388558573,
      "grad_norm": 0.04700899496674538,
      "learning_rate": 2e-05,
      "loss": 0.2417,
      "step": 512
    },
    {
      "epoch": 0.6594889924473727,
      "grad_norm": 0.04256317391991615,
      "learning_rate": 2e-05,
      "loss": 0.2703,
      "step": 513
    },
    {
      "epoch": 0.660774546038888,
      "grad_norm": 0.04744260385632515,
      "learning_rate": 2e-05,
      "loss": 0.2048,
      "step": 514
    },
    {
      "epoch": 0.6620600996304034,
      "grad_norm": 0.04310823976993561,
      "learning_rate": 2e-05,
      "loss": 0.1897,
      "step": 515
    },
    {
      "epoch": 0.6633456532219187,
      "grad_norm": 0.04300684109330177,
      "learning_rate": 2e-05,
      "loss": 0.2139,
      "step": 516
    },
    {
      "epoch": 0.664631206813434,
      "grad_norm": 0.05581510066986084,
      "learning_rate": 2e-05,
      "loss": 0.2616,
      "step": 517
    },
    {
      "epoch": 0.6659167604049494,
      "grad_norm": 0.055505942553281784,
      "learning_rate": 2e-05,
      "loss": 0.2915,
      "step": 518
    },
    {
      "epoch": 0.6672023139964647,
      "grad_norm": 0.040814101696014404,
      "learning_rate": 2e-05,
      "loss": 0.2187,
      "step": 519
    },
    {
      "epoch": 0.6684878675879801,
      "grad_norm": 0.05864616110920906,
      "learning_rate": 2e-05,
      "loss": 0.3499,
      "step": 520
    },
    {
      "epoch": 0.6697734211794955,
      "grad_norm": 0.057373858988285065,
      "learning_rate": 2e-05,
      "loss": 0.3538,
      "step": 521
    },
    {
      "epoch": 0.6710589747710107,
      "grad_norm": 0.041141483932733536,
      "learning_rate": 2e-05,
      "loss": 0.2711,
      "step": 522
    },
    {
      "epoch": 0.6723445283625261,
      "grad_norm": 0.03994324058294296,
      "learning_rate": 2e-05,
      "loss": 0.182,
      "step": 523
    },
    {
      "epoch": 0.6736300819540415,
      "grad_norm": 0.04982011020183563,
      "learning_rate": 2e-05,
      "loss": 0.2911,
      "step": 524
    },
    {
      "epoch": 0.6749156355455568,
      "grad_norm": 0.04852016270160675,
      "learning_rate": 2e-05,
      "loss": 0.254,
      "step": 525
    },
    {
      "epoch": 0.6762011891370722,
      "grad_norm": 0.05752996355295181,
      "learning_rate": 2e-05,
      "loss": 0.2969,
      "step": 526
    },
    {
      "epoch": 0.6774867427285874,
      "grad_norm": 0.04058138653635979,
      "learning_rate": 2e-05,
      "loss": 0.1861,
      "step": 527
    },
    {
      "epoch": 0.6787722963201028,
      "grad_norm": 0.05575535446405411,
      "learning_rate": 2e-05,
      "loss": 0.3174,
      "step": 528
    },
    {
      "epoch": 0.6800578499116182,
      "grad_norm": 0.0468176007270813,
      "learning_rate": 2e-05,
      "loss": 0.2699,
      "step": 529
    },
    {
      "epoch": 0.6813434035031335,
      "grad_norm": 0.054678115993738174,
      "learning_rate": 2e-05,
      "loss": 0.3051,
      "step": 530
    },
    {
      "epoch": 0.6826289570946489,
      "grad_norm": 0.055189572274684906,
      "learning_rate": 2e-05,
      "loss": 0.2397,
      "step": 531
    },
    {
      "epoch": 0.6839145106861643,
      "grad_norm": 0.048087868839502335,
      "learning_rate": 2e-05,
      "loss": 0.2302,
      "step": 532
    },
    {
      "epoch": 0.6852000642776795,
      "grad_norm": 0.057727813720703125,
      "learning_rate": 2e-05,
      "loss": 0.2457,
      "step": 533
    },
    {
      "epoch": 0.6864856178691949,
      "grad_norm": 0.04846923425793648,
      "learning_rate": 2e-05,
      "loss": 0.2506,
      "step": 534
    },
    {
      "epoch": 0.6877711714607103,
      "grad_norm": 0.0410042330622673,
      "learning_rate": 2e-05,
      "loss": 0.198,
      "step": 535
    },
    {
      "epoch": 0.6890567250522256,
      "grad_norm": 0.05333555117249489,
      "learning_rate": 2e-05,
      "loss": 0.283,
      "step": 536
    },
    {
      "epoch": 0.690342278643741,
      "grad_norm": 0.05376364290714264,
      "learning_rate": 2e-05,
      "loss": 0.3337,
      "step": 537
    },
    {
      "epoch": 0.6916278322352563,
      "grad_norm": 0.04879291355609894,
      "learning_rate": 2e-05,
      "loss": 0.3075,
      "step": 538
    },
    {
      "epoch": 0.6929133858267716,
      "grad_norm": 0.0375969335436821,
      "learning_rate": 2e-05,
      "loss": 0.1652,
      "step": 539
    },
    {
      "epoch": 0.694198939418287,
      "grad_norm": 0.042424045503139496,
      "learning_rate": 2e-05,
      "loss": 0.2398,
      "step": 540
    },
    {
      "epoch": 0.6954844930098023,
      "grad_norm": 0.048496536910533905,
      "learning_rate": 2e-05,
      "loss": 0.239,
      "step": 541
    },
    {
      "epoch": 0.6967700466013177,
      "grad_norm": 0.04180686175823212,
      "learning_rate": 2e-05,
      "loss": 0.2521,
      "step": 542
    },
    {
      "epoch": 0.6980556001928331,
      "grad_norm": 0.046767883002758026,
      "learning_rate": 2e-05,
      "loss": 0.2113,
      "step": 543
    },
    {
      "epoch": 0.6993411537843484,
      "grad_norm": 0.05949412286281586,
      "learning_rate": 2e-05,
      "loss": 0.3443,
      "step": 544
    },
    {
      "epoch": 0.7006267073758637,
      "grad_norm": 0.04437008500099182,
      "learning_rate": 2e-05,
      "loss": 0.2244,
      "step": 545
    },
    {
      "epoch": 0.7019122609673791,
      "grad_norm": 0.04240270331501961,
      "learning_rate": 2e-05,
      "loss": 0.2239,
      "step": 546
    },
    {
      "epoch": 0.7031978145588944,
      "grad_norm": 0.04866647720336914,
      "learning_rate": 2e-05,
      "loss": 0.2846,
      "step": 547
    },
    {
      "epoch": 0.7044833681504098,
      "grad_norm": 0.04255237057805061,
      "learning_rate": 2e-05,
      "loss": 0.1759,
      "step": 548
    },
    {
      "epoch": 0.7057689217419251,
      "grad_norm": 0.04113907366991043,
      "learning_rate": 2e-05,
      "loss": 0.2481,
      "step": 549
    },
    {
      "epoch": 0.7070544753334405,
      "grad_norm": 0.04230246692895889,
      "learning_rate": 2e-05,
      "loss": 0.1963,
      "step": 550
    },
    {
      "epoch": 0.7083400289249558,
      "grad_norm": 0.05263131856918335,
      "learning_rate": 2e-05,
      "loss": 0.2355,
      "step": 551
    },
    {
      "epoch": 0.7096255825164711,
      "grad_norm": 0.041025299578905106,
      "learning_rate": 2e-05,
      "loss": 0.193,
      "step": 552
    },
    {
      "epoch": 0.7109111361079865,
      "grad_norm": 0.048196010291576385,
      "learning_rate": 2e-05,
      "loss": 0.2183,
      "step": 553
    },
    {
      "epoch": 0.7121966896995019,
      "grad_norm": 0.05287821963429451,
      "learning_rate": 2e-05,
      "loss": 0.2969,
      "step": 554
    },
    {
      "epoch": 0.7134822432910172,
      "grad_norm": 0.04392276331782341,
      "learning_rate": 2e-05,
      "loss": 0.2029,
      "step": 555
    },
    {
      "epoch": 0.7147677968825326,
      "grad_norm": 0.05237026512622833,
      "learning_rate": 2e-05,
      "loss": 0.2653,
      "step": 556
    },
    {
      "epoch": 0.7160533504740478,
      "grad_norm": 0.05913091078400612,
      "learning_rate": 2e-05,
      "loss": 0.2944,
      "step": 557
    },
    {
      "epoch": 0.7173389040655632,
      "grad_norm": 0.04113471135497093,
      "learning_rate": 2e-05,
      "loss": 0.2411,
      "step": 558
    },
    {
      "epoch": 0.7186244576570786,
      "grad_norm": 0.040105462074279785,
      "learning_rate": 2e-05,
      "loss": 0.1857,
      "step": 559
    },
    {
      "epoch": 0.7199100112485939,
      "grad_norm": 0.058607831597328186,
      "learning_rate": 2e-05,
      "loss": 0.1984,
      "step": 560
    },
    {
      "epoch": 0.7211955648401093,
      "grad_norm": 0.043256357312202454,
      "learning_rate": 2e-05,
      "loss": 0.2584,
      "step": 561
    },
    {
      "epoch": 0.7224811184316247,
      "grad_norm": 0.05908385291695595,
      "learning_rate": 2e-05,
      "loss": 0.33,
      "step": 562
    },
    {
      "epoch": 0.7237666720231399,
      "grad_norm": 0.050697483122348785,
      "learning_rate": 2e-05,
      "loss": 0.242,
      "step": 563
    },
    {
      "epoch": 0.7250522256146553,
      "grad_norm": 0.05611984431743622,
      "learning_rate": 2e-05,
      "loss": 0.3334,
      "step": 564
    },
    {
      "epoch": 0.7263377792061707,
      "grad_norm": 0.05749541521072388,
      "learning_rate": 2e-05,
      "loss": 0.2454,
      "step": 565
    },
    {
      "epoch": 0.727623332797686,
      "grad_norm": 0.05453288555145264,
      "learning_rate": 2e-05,
      "loss": 0.249,
      "step": 566
    },
    {
      "epoch": 0.7289088863892014,
      "grad_norm": 0.061655569821596146,
      "learning_rate": 2e-05,
      "loss": 0.2954,
      "step": 567
    },
    {
      "epoch": 0.7301944399807166,
      "grad_norm": 0.051404744386672974,
      "learning_rate": 2e-05,
      "loss": 0.2356,
      "step": 568
    },
    {
      "epoch": 0.731479993572232,
      "grad_norm": 0.04265725240111351,
      "learning_rate": 2e-05,
      "loss": 0.1842,
      "step": 569
    },
    {
      "epoch": 0.7327655471637474,
      "grad_norm": 0.06363217532634735,
      "learning_rate": 2e-05,
      "loss": 0.3187,
      "step": 570
    },
    {
      "epoch": 0.7340511007552627,
      "grad_norm": 0.04742373526096344,
      "learning_rate": 2e-05,
      "loss": 0.2286,
      "step": 571
    },
    {
      "epoch": 0.7353366543467781,
      "grad_norm": 0.05723915994167328,
      "learning_rate": 2e-05,
      "loss": 0.3183,
      "step": 572
    },
    {
      "epoch": 0.7366222079382935,
      "grad_norm": 0.04636276140809059,
      "learning_rate": 2e-05,
      "loss": 0.2172,
      "step": 573
    },
    {
      "epoch": 0.7379077615298087,
      "grad_norm": 0.041882552206516266,
      "learning_rate": 2e-05,
      "loss": 0.195,
      "step": 574
    },
    {
      "epoch": 0.7391933151213241,
      "grad_norm": 0.05022399127483368,
      "learning_rate": 2e-05,
      "loss": 0.2564,
      "step": 575
    },
    {
      "epoch": 0.7404788687128395,
      "grad_norm": 0.058215439319610596,
      "learning_rate": 2e-05,
      "loss": 0.3047,
      "step": 576
    },
    {
      "epoch": 0.7417644223043548,
      "grad_norm": 0.04993325099349022,
      "learning_rate": 2e-05,
      "loss": 0.1955,
      "step": 577
    },
    {
      "epoch": 0.7430499758958702,
      "grad_norm": 0.05288231745362282,
      "learning_rate": 2e-05,
      "loss": 0.3005,
      "step": 578
    },
    {
      "epoch": 0.7443355294873855,
      "grad_norm": 0.055686481297016144,
      "learning_rate": 2e-05,
      "loss": 0.3304,
      "step": 579
    },
    {
      "epoch": 0.7456210830789008,
      "grad_norm": 0.06084279343485832,
      "learning_rate": 2e-05,
      "loss": 0.3377,
      "step": 580
    },
    {
      "epoch": 0.7469066366704162,
      "grad_norm": 0.041104961186647415,
      "learning_rate": 2e-05,
      "loss": 0.2019,
      "step": 581
    },
    {
      "epoch": 0.7481921902619315,
      "grad_norm": 0.04409842938184738,
      "learning_rate": 2e-05,
      "loss": 0.2383,
      "step": 582
    },
    {
      "epoch": 0.7494777438534469,
      "grad_norm": 0.050962381064891815,
      "learning_rate": 2e-05,
      "loss": 0.2439,
      "step": 583
    },
    {
      "epoch": 0.7507632974449623,
      "grad_norm": 0.05231870710849762,
      "learning_rate": 2e-05,
      "loss": 0.2337,
      "step": 584
    },
    {
      "epoch": 0.7520488510364776,
      "grad_norm": 0.04085131362080574,
      "learning_rate": 2e-05,
      "loss": 0.1451,
      "step": 585
    },
    {
      "epoch": 0.753334404627993,
      "grad_norm": 0.04120944067835808,
      "learning_rate": 2e-05,
      "loss": 0.2029,
      "step": 586
    },
    {
      "epoch": 0.7546199582195082,
      "grad_norm": 0.0363801047205925,
      "learning_rate": 2e-05,
      "loss": 0.1393,
      "step": 587
    },
    {
      "epoch": 0.7559055118110236,
      "grad_norm": 0.04919865354895592,
      "learning_rate": 2e-05,
      "loss": 0.2308,
      "step": 588
    },
    {
      "epoch": 0.757191065402539,
      "grad_norm": 0.0516657792031765,
      "learning_rate": 2e-05,
      "loss": 0.3006,
      "step": 589
    },
    {
      "epoch": 0.7584766189940543,
      "grad_norm": 0.07350458204746246,
      "learning_rate": 2e-05,
      "loss": 0.3796,
      "step": 590
    },
    {
      "epoch": 0.7597621725855697,
      "grad_norm": 0.05353572219610214,
      "learning_rate": 2e-05,
      "loss": 0.2548,
      "step": 591
    },
    {
      "epoch": 0.761047726177085,
      "grad_norm": 0.04492725431919098,
      "learning_rate": 2e-05,
      "loss": 0.199,
      "step": 592
    },
    {
      "epoch": 0.7623332797686003,
      "grad_norm": 0.04892539232969284,
      "learning_rate": 2e-05,
      "loss": 0.2108,
      "step": 593
    },
    {
      "epoch": 0.7636188333601157,
      "grad_norm": 0.03860924020409584,
      "learning_rate": 2e-05,
      "loss": 0.1896,
      "step": 594
    },
    {
      "epoch": 0.7649043869516311,
      "grad_norm": 0.052807312458753586,
      "learning_rate": 2e-05,
      "loss": 0.2709,
      "step": 595
    },
    {
      "epoch": 0.7661899405431464,
      "grad_norm": 0.04871145263314247,
      "learning_rate": 2e-05,
      "loss": 0.2779,
      "step": 596
    },
    {
      "epoch": 0.7674754941346618,
      "grad_norm": 0.04021324962377548,
      "learning_rate": 2e-05,
      "loss": 0.2136,
      "step": 597
    },
    {
      "epoch": 0.768761047726177,
      "grad_norm": 0.050265613943338394,
      "learning_rate": 2e-05,
      "loss": 0.2601,
      "step": 598
    },
    {
      "epoch": 0.7700466013176924,
      "grad_norm": 0.03576774150133133,
      "learning_rate": 2e-05,
      "loss": 0.2114,
      "step": 599
    },
    {
      "epoch": 0.7713321549092078,
      "grad_norm": 0.055398743599653244,
      "learning_rate": 2e-05,
      "loss": 0.2701,
      "step": 600
    },
    {
      "epoch": 0.7726177085007231,
      "grad_norm": 0.06506812572479248,
      "learning_rate": 2e-05,
      "loss": 0.3518,
      "step": 601
    },
    {
      "epoch": 0.7739032620922385,
      "grad_norm": 0.037148088216781616,
      "learning_rate": 2e-05,
      "loss": 0.1438,
      "step": 602
    },
    {
      "epoch": 0.7751888156837539,
      "grad_norm": 0.046173613518476486,
      "learning_rate": 2e-05,
      "loss": 0.2294,
      "step": 603
    },
    {
      "epoch": 0.7764743692752691,
      "grad_norm": 0.06617863476276398,
      "learning_rate": 2e-05,
      "loss": 0.2888,
      "step": 604
    },
    {
      "epoch": 0.7777599228667845,
      "grad_norm": 0.051207173615694046,
      "learning_rate": 2e-05,
      "loss": 0.2624,
      "step": 605
    },
    {
      "epoch": 0.7790454764582998,
      "grad_norm": 0.041766516864299774,
      "learning_rate": 2e-05,
      "loss": 0.1881,
      "step": 606
    },
    {
      "epoch": 0.7803310300498152,
      "grad_norm": 0.05160610005259514,
      "learning_rate": 2e-05,
      "loss": 0.258,
      "step": 607
    },
    {
      "epoch": 0.7816165836413306,
      "grad_norm": 0.04584109038114548,
      "learning_rate": 2e-05,
      "loss": 0.2087,
      "step": 608
    },
    {
      "epoch": 0.7829021372328459,
      "grad_norm": 0.04200456291437149,
      "learning_rate": 2e-05,
      "loss": 0.2036,
      "step": 609
    },
    {
      "epoch": 0.7841876908243612,
      "grad_norm": 0.039162181317806244,
      "learning_rate": 2e-05,
      "loss": 0.1833,
      "step": 610
    },
    {
      "epoch": 0.7854732444158766,
      "grad_norm": 0.041861940175294876,
      "learning_rate": 2e-05,
      "loss": 0.1623,
      "step": 611
    },
    {
      "epoch": 0.7867587980073919,
      "grad_norm": 0.05622352659702301,
      "learning_rate": 2e-05,
      "loss": 0.3556,
      "step": 612
    },
    {
      "epoch": 0.7880443515989073,
      "grad_norm": 0.048621952533721924,
      "learning_rate": 2e-05,
      "loss": 0.2211,
      "step": 613
    },
    {
      "epoch": 0.7893299051904227,
      "grad_norm": 0.0437590628862381,
      "learning_rate": 2e-05,
      "loss": 0.2015,
      "step": 614
    },
    {
      "epoch": 0.790615458781938,
      "grad_norm": 0.05675414949655533,
      "learning_rate": 2e-05,
      "loss": 0.2416,
      "step": 615
    },
    {
      "epoch": 0.7919010123734533,
      "grad_norm": 0.03869640827178955,
      "learning_rate": 2e-05,
      "loss": 0.1655,
      "step": 616
    },
    {
      "epoch": 0.7931865659649686,
      "grad_norm": 0.04821722209453583,
      "learning_rate": 2e-05,
      "loss": 0.1902,
      "step": 617
    },
    {
      "epoch": 0.794472119556484,
      "grad_norm": 0.04423803463578224,
      "learning_rate": 2e-05,
      "loss": 0.157,
      "step": 618
    },
    {
      "epoch": 0.7957576731479994,
      "grad_norm": 0.04364867880940437,
      "learning_rate": 2e-05,
      "loss": 0.2406,
      "step": 619
    },
    {
      "epoch": 0.7970432267395147,
      "grad_norm": 0.059711892157793045,
      "learning_rate": 2e-05,
      "loss": 0.2981,
      "step": 620
    },
    {
      "epoch": 0.79832878033103,
      "grad_norm": 0.046063173562288284,
      "learning_rate": 2e-05,
      "loss": 0.2184,
      "step": 621
    },
    {
      "epoch": 0.7996143339225454,
      "grad_norm": 0.06073896959424019,
      "learning_rate": 2e-05,
      "loss": 0.2351,
      "step": 622
    },
    {
      "epoch": 0.8008998875140607,
      "grad_norm": 0.039248064160346985,
      "learning_rate": 2e-05,
      "loss": 0.1888,
      "step": 623
    },
    {
      "epoch": 0.8021854411055761,
      "grad_norm": 0.05402129143476486,
      "learning_rate": 2e-05,
      "loss": 0.3368,
      "step": 624
    },
    {
      "epoch": 0.8034709946970915,
      "grad_norm": 0.04230786859989166,
      "learning_rate": 2e-05,
      "loss": 0.1748,
      "step": 625
    },
    {
      "epoch": 0.8047565482886068,
      "grad_norm": 0.06045274809002876,
      "learning_rate": 2e-05,
      "loss": 0.3958,
      "step": 626
    },
    {
      "epoch": 0.8060421018801222,
      "grad_norm": 0.04717743769288063,
      "learning_rate": 2e-05,
      "loss": 0.2704,
      "step": 627
    },
    {
      "epoch": 0.8073276554716374,
      "grad_norm": 0.04878292232751846,
      "learning_rate": 2e-05,
      "loss": 0.2412,
      "step": 628
    },
    {
      "epoch": 0.8086132090631528,
      "grad_norm": 0.038947124034166336,
      "learning_rate": 2e-05,
      "loss": 0.2169,
      "step": 629
    },
    {
      "epoch": 0.8098987626546682,
      "grad_norm": 0.0614759586751461,
      "learning_rate": 2e-05,
      "loss": 0.3013,
      "step": 630
    },
    {
      "epoch": 0.8111843162461835,
      "grad_norm": 0.06246621906757355,
      "learning_rate": 2e-05,
      "loss": 0.2947,
      "step": 631
    },
    {
      "epoch": 0.8124698698376989,
      "grad_norm": 0.06976212561130524,
      "learning_rate": 2e-05,
      "loss": 0.297,
      "step": 632
    },
    {
      "epoch": 0.8137554234292143,
      "grad_norm": 0.03317941352725029,
      "learning_rate": 2e-05,
      "loss": 0.1375,
      "step": 633
    },
    {
      "epoch": 0.8150409770207295,
      "grad_norm": 0.06765579432249069,
      "learning_rate": 2e-05,
      "loss": 0.258,
      "step": 634
    },
    {
      "epoch": 0.8163265306122449,
      "grad_norm": 0.06797792762517929,
      "learning_rate": 2e-05,
      "loss": 0.256,
      "step": 635
    },
    {
      "epoch": 0.8176120842037602,
      "grad_norm": 0.059785496443510056,
      "learning_rate": 2e-05,
      "loss": 0.3343,
      "step": 636
    },
    {
      "epoch": 0.8188976377952756,
      "grad_norm": 0.059780728071928024,
      "learning_rate": 2e-05,
      "loss": 0.3634,
      "step": 637
    },
    {
      "epoch": 0.820183191386791,
      "grad_norm": 0.04111599549651146,
      "learning_rate": 2e-05,
      "loss": 0.2011,
      "step": 638
    },
    {
      "epoch": 0.8214687449783062,
      "grad_norm": 0.04656028002500534,
      "learning_rate": 2e-05,
      "loss": 0.2214,
      "step": 639
    },
    {
      "epoch": 0.8227542985698216,
      "grad_norm": 0.054362326860427856,
      "learning_rate": 2e-05,
      "loss": 0.2928,
      "step": 640
    },
    {
      "epoch": 0.824039852161337,
      "grad_norm": 0.04594152048230171,
      "learning_rate": 2e-05,
      "loss": 0.2285,
      "step": 641
    },
    {
      "epoch": 0.8253254057528523,
      "grad_norm": 0.056715745478868484,
      "learning_rate": 2e-05,
      "loss": 0.2531,
      "step": 642
    },
    {
      "epoch": 0.8266109593443677,
      "grad_norm": 0.049057237803936005,
      "learning_rate": 2e-05,
      "loss": 0.1749,
      "step": 643
    },
    {
      "epoch": 0.8278965129358831,
      "grad_norm": 0.05435045436024666,
      "learning_rate": 2e-05,
      "loss": 0.2796,
      "step": 644
    },
    {
      "epoch": 0.8291820665273983,
      "grad_norm": 0.049284275621175766,
      "learning_rate": 2e-05,
      "loss": 0.2381,
      "step": 645
    },
    {
      "epoch": 0.8304676201189137,
      "grad_norm": 0.044050633907318115,
      "learning_rate": 2e-05,
      "loss": 0.2804,
      "step": 646
    },
    {
      "epoch": 0.831753173710429,
      "grad_norm": 0.054185982793569565,
      "learning_rate": 2e-05,
      "loss": 0.2617,
      "step": 647
    },
    {
      "epoch": 0.8330387273019444,
      "grad_norm": 0.0534062534570694,
      "learning_rate": 2e-05,
      "loss": 0.2502,
      "step": 648
    },
    {
      "epoch": 0.8343242808934598,
      "grad_norm": 0.06242300197482109,
      "learning_rate": 2e-05,
      "loss": 0.2662,
      "step": 649
    },
    {
      "epoch": 0.8356098344849751,
      "grad_norm": 0.0385594442486763,
      "learning_rate": 2e-05,
      "loss": 0.1897,
      "step": 650
    },
    {
      "epoch": 0.8368953880764904,
      "grad_norm": 0.065641388297081,
      "learning_rate": 2e-05,
      "loss": 0.3179,
      "step": 651
    },
    {
      "epoch": 0.8381809416680058,
      "grad_norm": 0.054985061287879944,
      "learning_rate": 2e-05,
      "loss": 0.222,
      "step": 652
    },
    {
      "epoch": 0.8394664952595211,
      "grad_norm": 0.05766449496150017,
      "learning_rate": 2e-05,
      "loss": 0.289,
      "step": 653
    },
    {
      "epoch": 0.8407520488510365,
      "grad_norm": 0.04635515809059143,
      "learning_rate": 2e-05,
      "loss": 0.2464,
      "step": 654
    },
    {
      "epoch": 0.8420376024425518,
      "grad_norm": 0.0583229660987854,
      "learning_rate": 2e-05,
      "loss": 0.2436,
      "step": 655
    },
    {
      "epoch": 0.8433231560340672,
      "grad_norm": 0.04983345419168472,
      "learning_rate": 2e-05,
      "loss": 0.2534,
      "step": 656
    },
    {
      "epoch": 0.8446087096255825,
      "grad_norm": 0.04292474314570427,
      "learning_rate": 2e-05,
      "loss": 0.1772,
      "step": 657
    },
    {
      "epoch": 0.8458942632170978,
      "grad_norm": 0.05735989660024643,
      "learning_rate": 2e-05,
      "loss": 0.267,
      "step": 658
    },
    {
      "epoch": 0.8471798168086132,
      "grad_norm": 0.055415477603673935,
      "learning_rate": 2e-05,
      "loss": 0.2651,
      "step": 659
    },
    {
      "epoch": 0.8484653704001286,
      "grad_norm": 0.052020199596881866,
      "learning_rate": 2e-05,
      "loss": 0.2177,
      "step": 660
    },
    {
      "epoch": 0.8497509239916439,
      "grad_norm": 0.05934329703450203,
      "learning_rate": 2e-05,
      "loss": 0.2665,
      "step": 661
    },
    {
      "epoch": 0.8510364775831593,
      "grad_norm": 0.06611707806587219,
      "learning_rate": 2e-05,
      "loss": 0.3774,
      "step": 662
    },
    {
      "epoch": 0.8523220311746746,
      "grad_norm": 0.05337178707122803,
      "learning_rate": 2e-05,
      "loss": 0.2699,
      "step": 663
    },
    {
      "epoch": 0.8536075847661899,
      "grad_norm": 0.05552757531404495,
      "learning_rate": 2e-05,
      "loss": 0.2204,
      "step": 664
    },
    {
      "epoch": 0.8548931383577053,
      "grad_norm": 0.051326069980859756,
      "learning_rate": 2e-05,
      "loss": 0.1791,
      "step": 665
    },
    {
      "epoch": 0.8561786919492206,
      "grad_norm": 0.04780028760433197,
      "learning_rate": 2e-05,
      "loss": 0.1959,
      "step": 666
    },
    {
      "epoch": 0.857464245540736,
      "grad_norm": 0.06344909965991974,
      "learning_rate": 2e-05,
      "loss": 0.2809,
      "step": 667
    },
    {
      "epoch": 0.8587497991322514,
      "grad_norm": 0.0526767373085022,
      "learning_rate": 2e-05,
      "loss": 0.2547,
      "step": 668
    },
    {
      "epoch": 0.8600353527237666,
      "grad_norm": 0.04369194433093071,
      "learning_rate": 2e-05,
      "loss": 0.233,
      "step": 669
    },
    {
      "epoch": 0.861320906315282,
      "grad_norm": 0.05023709312081337,
      "learning_rate": 2e-05,
      "loss": 0.2576,
      "step": 670
    },
    {
      "epoch": 0.8626064599067974,
      "grad_norm": 0.06402754783630371,
      "learning_rate": 2e-05,
      "loss": 0.2579,
      "step": 671
    },
    {
      "epoch": 0.8638920134983127,
      "grad_norm": 0.06747744977474213,
      "learning_rate": 2e-05,
      "loss": 0.393,
      "step": 672
    },
    {
      "epoch": 0.8651775670898281,
      "grad_norm": 0.06799997389316559,
      "learning_rate": 2e-05,
      "loss": 0.3114,
      "step": 673
    },
    {
      "epoch": 0.8664631206813435,
      "grad_norm": 0.044738415628671646,
      "learning_rate": 2e-05,
      "loss": 0.222,
      "step": 674
    },
    {
      "epoch": 0.8677486742728587,
      "grad_norm": 0.05913526564836502,
      "learning_rate": 2e-05,
      "loss": 0.2701,
      "step": 675
    },
    {
      "epoch": 0.8690342278643741,
      "grad_norm": 0.052639495581388474,
      "learning_rate": 2e-05,
      "loss": 0.2279,
      "step": 676
    },
    {
      "epoch": 0.8703197814558894,
      "grad_norm": 0.0436641164124012,
      "learning_rate": 2e-05,
      "loss": 0.1722,
      "step": 677
    },
    {
      "epoch": 0.8716053350474048,
      "grad_norm": 0.06275106966495514,
      "learning_rate": 2e-05,
      "loss": 0.3289,
      "step": 678
    },
    {
      "epoch": 0.8728908886389202,
      "grad_norm": 0.034002162516117096,
      "learning_rate": 2e-05,
      "loss": 0.1262,
      "step": 679
    },
    {
      "epoch": 0.8741764422304354,
      "grad_norm": 0.04524555802345276,
      "learning_rate": 2e-05,
      "loss": 0.1765,
      "step": 680
    },
    {
      "epoch": 0.8754619958219508,
      "grad_norm": 0.04776989668607712,
      "learning_rate": 2e-05,
      "loss": 0.242,
      "step": 681
    },
    {
      "epoch": 0.8767475494134662,
      "grad_norm": 0.060143712908029556,
      "learning_rate": 2e-05,
      "loss": 0.24,
      "step": 682
    },
    {
      "epoch": 0.8780331030049815,
      "grad_norm": 0.06363454461097717,
      "learning_rate": 2e-05,
      "loss": 0.3104,
      "step": 683
    },
    {
      "epoch": 0.8793186565964969,
      "grad_norm": 0.05736486613750458,
      "learning_rate": 2e-05,
      "loss": 0.3299,
      "step": 684
    },
    {
      "epoch": 0.8806042101880122,
      "grad_norm": 0.048391181975603104,
      "learning_rate": 2e-05,
      "loss": 0.1937,
      "step": 685
    },
    {
      "epoch": 0.8818897637795275,
      "grad_norm": 0.047165125608444214,
      "learning_rate": 2e-05,
      "loss": 0.2608,
      "step": 686
    },
    {
      "epoch": 0.8831753173710429,
      "grad_norm": 0.061681345105171204,
      "learning_rate": 2e-05,
      "loss": 0.2948,
      "step": 687
    },
    {
      "epoch": 0.8844608709625582,
      "grad_norm": 0.060136910527944565,
      "learning_rate": 2e-05,
      "loss": 0.2272,
      "step": 688
    },
    {
      "epoch": 0.8857464245540736,
      "grad_norm": 0.047498807311058044,
      "learning_rate": 2e-05,
      "loss": 0.1813,
      "step": 689
    },
    {
      "epoch": 0.887031978145589,
      "grad_norm": 0.06447866559028625,
      "learning_rate": 2e-05,
      "loss": 0.2808,
      "step": 690
    },
    {
      "epoch": 0.8883175317371043,
      "grad_norm": 0.05992686748504639,
      "learning_rate": 2e-05,
      "loss": 0.262,
      "step": 691
    },
    {
      "epoch": 0.8896030853286196,
      "grad_norm": 0.048196423798799515,
      "learning_rate": 2e-05,
      "loss": 0.2238,
      "step": 692
    },
    {
      "epoch": 0.890888638920135,
      "grad_norm": 0.06860709935426712,
      "learning_rate": 2e-05,
      "loss": 0.2679,
      "step": 693
    },
    {
      "epoch": 0.8921741925116503,
      "grad_norm": 0.05085690692067146,
      "learning_rate": 2e-05,
      "loss": 0.2948,
      "step": 694
    },
    {
      "epoch": 0.8934597461031657,
      "grad_norm": 0.06869999319314957,
      "learning_rate": 2e-05,
      "loss": 0.2961,
      "step": 695
    },
    {
      "epoch": 0.894745299694681,
      "grad_norm": 0.04691535234451294,
      "learning_rate": 2e-05,
      "loss": 0.2019,
      "step": 696
    },
    {
      "epoch": 0.8960308532861964,
      "grad_norm": 0.04785510525107384,
      "learning_rate": 2e-05,
      "loss": 0.147,
      "step": 697
    },
    {
      "epoch": 0.8973164068777117,
      "grad_norm": 0.06156083196401596,
      "learning_rate": 2e-05,
      "loss": 0.2215,
      "step": 698
    },
    {
      "epoch": 0.898601960469227,
      "grad_norm": 0.051647745072841644,
      "learning_rate": 2e-05,
      "loss": 0.2252,
      "step": 699
    },
    {
      "epoch": 0.8998875140607424,
      "grad_norm": 0.04751814156770706,
      "learning_rate": 2e-05,
      "loss": 0.2482,
      "step": 700
    },
    {
      "epoch": 0.9011730676522578,
      "grad_norm": 0.05452054366469383,
      "learning_rate": 2e-05,
      "loss": 0.2138,
      "step": 701
    },
    {
      "epoch": 0.9024586212437731,
      "grad_norm": 0.045277033001184464,
      "learning_rate": 2e-05,
      "loss": 0.2148,
      "step": 702
    },
    {
      "epoch": 0.9037441748352885,
      "grad_norm": 0.045462466776371,
      "learning_rate": 2e-05,
      "loss": 0.1711,
      "step": 703
    },
    {
      "epoch": 0.9050297284268038,
      "grad_norm": 0.06722573935985565,
      "learning_rate": 2e-05,
      "loss": 0.3205,
      "step": 704
    },
    {
      "epoch": 0.9063152820183191,
      "grad_norm": 0.05163208395242691,
      "learning_rate": 2e-05,
      "loss": 0.247,
      "step": 705
    },
    {
      "epoch": 0.9076008356098345,
      "grad_norm": 0.052614837884902954,
      "learning_rate": 2e-05,
      "loss": 0.2002,
      "step": 706
    },
    {
      "epoch": 0.9088863892013498,
      "grad_norm": 0.03826769068837166,
      "learning_rate": 2e-05,
      "loss": 0.1744,
      "step": 707
    },
    {
      "epoch": 0.9101719427928652,
      "grad_norm": 0.04780410975217819,
      "learning_rate": 2e-05,
      "loss": 0.2524,
      "step": 708
    },
    {
      "epoch": 0.9114574963843806,
      "grad_norm": 0.03547963872551918,
      "learning_rate": 2e-05,
      "loss": 0.1674,
      "step": 709
    },
    {
      "epoch": 0.9127430499758958,
      "grad_norm": 0.0573282465338707,
      "learning_rate": 2e-05,
      "loss": 0.2749,
      "step": 710
    },
    {
      "epoch": 0.9140286035674112,
      "grad_norm": 0.0570538304746151,
      "learning_rate": 2e-05,
      "loss": 0.2412,
      "step": 711
    },
    {
      "epoch": 0.9153141571589266,
      "grad_norm": 0.054683949798345566,
      "learning_rate": 2e-05,
      "loss": 0.2537,
      "step": 712
    },
    {
      "epoch": 0.9165997107504419,
      "grad_norm": 0.05413772165775299,
      "learning_rate": 2e-05,
      "loss": 0.2314,
      "step": 713
    },
    {
      "epoch": 0.9178852643419573,
      "grad_norm": 0.05124877020716667,
      "learning_rate": 2e-05,
      "loss": 0.2645,
      "step": 714
    },
    {
      "epoch": 0.9191708179334726,
      "grad_norm": 0.06577921658754349,
      "learning_rate": 2e-05,
      "loss": 0.314,
      "step": 715
    },
    {
      "epoch": 0.9204563715249879,
      "grad_norm": 0.05663186311721802,
      "learning_rate": 2e-05,
      "loss": 0.2422,
      "step": 716
    },
    {
      "epoch": 0.9217419251165033,
      "grad_norm": 0.05851929262280464,
      "learning_rate": 2e-05,
      "loss": 0.2845,
      "step": 717
    },
    {
      "epoch": 0.9230274787080186,
      "grad_norm": 0.06582541763782501,
      "learning_rate": 2e-05,
      "loss": 0.2487,
      "step": 718
    },
    {
      "epoch": 0.924313032299534,
      "grad_norm": 0.0434844084084034,
      "learning_rate": 2e-05,
      "loss": 0.191,
      "step": 719
    },
    {
      "epoch": 0.9255985858910494,
      "grad_norm": 0.056996386498212814,
      "learning_rate": 2e-05,
      "loss": 0.2733,
      "step": 720
    },
    {
      "epoch": 0.9268841394825647,
      "grad_norm": 0.04399803280830383,
      "learning_rate": 2e-05,
      "loss": 0.1991,
      "step": 721
    },
    {
      "epoch": 0.92816969307408,
      "grad_norm": 0.047656819224357605,
      "learning_rate": 2e-05,
      "loss": 0.2274,
      "step": 722
    },
    {
      "epoch": 0.9294552466655954,
      "grad_norm": 0.0753135085105896,
      "learning_rate": 2e-05,
      "loss": 0.3748,
      "step": 723
    },
    {
      "epoch": 0.9307408002571107,
      "grad_norm": 0.07544931024312973,
      "learning_rate": 2e-05,
      "loss": 0.282,
      "step": 724
    },
    {
      "epoch": 0.9320263538486261,
      "grad_norm": 0.05577397346496582,
      "learning_rate": 2e-05,
      "loss": 0.273,
      "step": 725
    },
    {
      "epoch": 0.9333119074401414,
      "grad_norm": 0.039960604161024094,
      "learning_rate": 2e-05,
      "loss": 0.1423,
      "step": 726
    },
    {
      "epoch": 0.9345974610316568,
      "grad_norm": 0.0625922679901123,
      "learning_rate": 2e-05,
      "loss": 0.2504,
      "step": 727
    },
    {
      "epoch": 0.9358830146231721,
      "grad_norm": 0.060125015676021576,
      "learning_rate": 2e-05,
      "loss": 0.2061,
      "step": 728
    },
    {
      "epoch": 0.9371685682146874,
      "grad_norm": 0.06697895377874374,
      "learning_rate": 2e-05,
      "loss": 0.2672,
      "step": 729
    },
    {
      "epoch": 0.9384541218062028,
      "grad_norm": 0.09079831093549728,
      "learning_rate": 2e-05,
      "loss": 0.3944,
      "step": 730
    },
    {
      "epoch": 0.9397396753977182,
      "grad_norm": 0.05246804282069206,
      "learning_rate": 2e-05,
      "loss": 0.2153,
      "step": 731
    },
    {
      "epoch": 0.9410252289892335,
      "grad_norm": 0.03938793018460274,
      "learning_rate": 2e-05,
      "loss": 0.1496,
      "step": 732
    },
    {
      "epoch": 0.9423107825807489,
      "grad_norm": 0.05081872642040253,
      "learning_rate": 2e-05,
      "loss": 0.1939,
      "step": 733
    },
    {
      "epoch": 0.9435963361722641,
      "grad_norm": 0.055075064301490784,
      "learning_rate": 2e-05,
      "loss": 0.2314,
      "step": 734
    },
    {
      "epoch": 0.9448818897637795,
      "grad_norm": 0.057048946619033813,
      "learning_rate": 2e-05,
      "loss": 0.2258,
      "step": 735
    },
    {
      "epoch": 0.9461674433552949,
      "grad_norm": 0.0564640611410141,
      "learning_rate": 2e-05,
      "loss": 0.221,
      "step": 736
    },
    {
      "epoch": 0.9474529969468102,
      "grad_norm": 0.06246118247509003,
      "learning_rate": 2e-05,
      "loss": 0.2655,
      "step": 737
    },
    {
      "epoch": 0.9487385505383256,
      "grad_norm": 0.06543996930122375,
      "learning_rate": 2e-05,
      "loss": 0.3487,
      "step": 738
    },
    {
      "epoch": 0.950024104129841,
      "grad_norm": 0.05123418942093849,
      "learning_rate": 2e-05,
      "loss": 0.2593,
      "step": 739
    },
    {
      "epoch": 0.9513096577213562,
      "grad_norm": 0.04761409014463425,
      "learning_rate": 2e-05,
      "loss": 0.1717,
      "step": 740
    },
    {
      "epoch": 0.9525952113128716,
      "grad_norm": 0.05747079476714134,
      "learning_rate": 2e-05,
      "loss": 0.2239,
      "step": 741
    },
    {
      "epoch": 0.953880764904387,
      "grad_norm": 0.04854227229952812,
      "learning_rate": 2e-05,
      "loss": 0.1742,
      "step": 742
    },
    {
      "epoch": 0.9551663184959023,
      "grad_norm": 0.05784037709236145,
      "learning_rate": 2e-05,
      "loss": 0.203,
      "step": 743
    },
    {
      "epoch": 0.9564518720874177,
      "grad_norm": 0.05370228737592697,
      "learning_rate": 2e-05,
      "loss": 0.255,
      "step": 744
    },
    {
      "epoch": 0.9577374256789329,
      "grad_norm": 0.04535800218582153,
      "learning_rate": 2e-05,
      "loss": 0.1951,
      "step": 745
    },
    {
      "epoch": 0.9590229792704483,
      "grad_norm": 0.044412512332201004,
      "learning_rate": 2e-05,
      "loss": 0.2087,
      "step": 746
    },
    {
      "epoch": 0.9603085328619637,
      "grad_norm": 0.05077359825372696,
      "learning_rate": 2e-05,
      "loss": 0.19,
      "step": 747
    },
    {
      "epoch": 0.961594086453479,
      "grad_norm": 0.056578539311885834,
      "learning_rate": 2e-05,
      "loss": 0.2784,
      "step": 748
    },
    {
      "epoch": 0.9628796400449944,
      "grad_norm": 0.04252656549215317,
      "learning_rate": 2e-05,
      "loss": 0.239,
      "step": 749
    },
    {
      "epoch": 0.9641651936365098,
      "grad_norm": 0.04754233360290527,
      "learning_rate": 2e-05,
      "loss": 0.1871,
      "step": 750
    },
    {
      "epoch": 0.965450747228025,
      "grad_norm": 0.04948977380990982,
      "learning_rate": 2e-05,
      "loss": 0.2095,
      "step": 751
    },
    {
      "epoch": 0.9667363008195404,
      "grad_norm": 0.056569986045360565,
      "learning_rate": 2e-05,
      "loss": 0.1627,
      "step": 752
    },
    {
      "epoch": 0.9680218544110558,
      "grad_norm": 0.058012060821056366,
      "learning_rate": 2e-05,
      "loss": 0.277,
      "step": 753
    },
    {
      "epoch": 0.9693074080025711,
      "grad_norm": 0.06445303559303284,
      "learning_rate": 2e-05,
      "loss": 0.3453,
      "step": 754
    },
    {
      "epoch": 0.9705929615940865,
      "grad_norm": 0.04822942987084389,
      "learning_rate": 2e-05,
      "loss": 0.1958,
      "step": 755
    },
    {
      "epoch": 0.9718785151856018,
      "grad_norm": 0.04951447993516922,
      "learning_rate": 2e-05,
      "loss": 0.2342,
      "step": 756
    },
    {
      "epoch": 0.9731640687771171,
      "grad_norm": 0.04779404401779175,
      "learning_rate": 2e-05,
      "loss": 0.2277,
      "step": 757
    },
    {
      "epoch": 0.9744496223686325,
      "grad_norm": 0.047998420894145966,
      "learning_rate": 2e-05,
      "loss": 0.1817,
      "step": 758
    },
    {
      "epoch": 0.9757351759601478,
      "grad_norm": 0.050718434154987335,
      "learning_rate": 2e-05,
      "loss": 0.2289,
      "step": 759
    },
    {
      "epoch": 0.9770207295516632,
      "grad_norm": 0.05427386984229088,
      "learning_rate": 2e-05,
      "loss": 0.2597,
      "step": 760
    },
    {
      "epoch": 0.9783062831431786,
      "grad_norm": 0.06047537922859192,
      "learning_rate": 2e-05,
      "loss": 0.2597,
      "step": 761
    },
    {
      "epoch": 0.9795918367346939,
      "grad_norm": 0.048412878066301346,
      "learning_rate": 2e-05,
      "loss": 0.2386,
      "step": 762
    },
    {
      "epoch": 0.9808773903262092,
      "grad_norm": 0.04905233159661293,
      "learning_rate": 2e-05,
      "loss": 0.2239,
      "step": 763
    },
    {
      "epoch": 0.9821629439177245,
      "grad_norm": 0.052379023283720016,
      "learning_rate": 2e-05,
      "loss": 0.263,
      "step": 764
    },
    {
      "epoch": 0.9834484975092399,
      "grad_norm": 0.0489642396569252,
      "learning_rate": 2e-05,
      "loss": 0.225,
      "step": 765
    },
    {
      "epoch": 0.9847340511007553,
      "grad_norm": 0.050984520465135574,
      "learning_rate": 2e-05,
      "loss": 0.219,
      "step": 766
    },
    {
      "epoch": 0.9860196046922706,
      "grad_norm": 0.05487053468823433,
      "learning_rate": 2e-05,
      "loss": 0.1788,
      "step": 767
    },
    {
      "epoch": 0.987305158283786,
      "grad_norm": 0.06488880515098572,
      "learning_rate": 2e-05,
      "loss": 0.2994,
      "step": 768
    },
    {
      "epoch": 0.9885907118753013,
      "grad_norm": 0.057233408093452454,
      "learning_rate": 2e-05,
      "loss": 0.3028,
      "step": 769
    },
    {
      "epoch": 0.9898762654668166,
      "grad_norm": 0.03885122016072273,
      "learning_rate": 2e-05,
      "loss": 0.1704,
      "step": 770
    },
    {
      "epoch": 0.991161819058332,
      "grad_norm": 0.04395405203104019,
      "learning_rate": 2e-05,
      "loss": 0.168,
      "step": 771
    },
    {
      "epoch": 0.9924473726498474,
      "grad_norm": 0.07156252861022949,
      "learning_rate": 2e-05,
      "loss": 0.3431,
      "step": 772
    },
    {
      "epoch": 0.9937329262413627,
      "grad_norm": 0.05737178027629852,
      "learning_rate": 2e-05,
      "loss": 0.2595,
      "step": 773
    },
    {
      "epoch": 0.9950184798328781,
      "grad_norm": 0.0596122108399868,
      "learning_rate": 2e-05,
      "loss": 0.2177,
      "step": 774
    },
    {
      "epoch": 0.9963040334243933,
      "grad_norm": 0.0480956956744194,
      "learning_rate": 2e-05,
      "loss": 0.2008,
      "step": 775
    },
    {
      "epoch": 0.9975895870159087,
      "grad_norm": 0.045857105404138565,
      "learning_rate": 2e-05,
      "loss": 0.2093,
      "step": 776
    },
    {
      "epoch": 0.9988751406074241,
      "grad_norm": 0.05208531767129898,
      "learning_rate": 2e-05,
      "loss": 0.1512,
      "step": 777
    },
    {
      "epoch": 0.9988751406074241,
      "step": 777,
      "total_flos": 525522702336000.0,
      "train_loss": 0.3197911096739186,
      "train_runtime": 4432.7229,
      "train_samples_per_second": 5.616,
      "train_steps_per_second": 0.175
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 777,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100.0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 525522702336000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}