{
  "best_metric": 0.3638736605644226,
  "best_model_checkpoint": "miner_id_24/checkpoint-650",
  "epoch": 1.3579461065138978,
  "eval_steps": 50,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001697432633142372,
      "grad_norm": 0.22029195725917816,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 1.2479,
      "step": 1
    },
    {
      "epoch": 0.001697432633142372,
      "eval_loss": 0.6322442293167114,
      "eval_runtime": 65.6226,
      "eval_samples_per_second": 2.941,
      "eval_steps_per_second": 2.941,
      "step": 1
    },
    {
      "epoch": 0.003394865266284744,
      "grad_norm": 0.24590638279914856,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 1.2438,
      "step": 2
    },
    {
      "epoch": 0.005092297899427116,
      "grad_norm": 0.23055589199066162,
      "learning_rate": 8.999999999999999e-05,
      "loss": 1.0916,
      "step": 3
    },
    {
      "epoch": 0.006789730532569488,
      "grad_norm": 0.21309782564640045,
      "learning_rate": 0.00011999999999999999,
      "loss": 1.0918,
      "step": 4
    },
    {
      "epoch": 0.008487163165711862,
      "grad_norm": 0.21661481261253357,
      "learning_rate": 0.00015,
      "loss": 0.8365,
      "step": 5
    },
    {
      "epoch": 0.010184595798854232,
      "grad_norm": 0.2395806461572647,
      "learning_rate": 0.00017999999999999998,
      "loss": 1.0087,
      "step": 6
    },
    {
      "epoch": 0.011882028431996604,
      "grad_norm": 0.25481849908828735,
      "learning_rate": 0.00020999999999999998,
      "loss": 0.9591,
      "step": 7
    },
    {
      "epoch": 0.013579461065138977,
      "grad_norm": 0.22890186309814453,
      "learning_rate": 0.00023999999999999998,
      "loss": 0.6067,
      "step": 8
    },
    {
      "epoch": 0.015276893698281349,
      "grad_norm": 0.2807515263557434,
      "learning_rate": 0.00027,
      "loss": 0.6593,
      "step": 9
    },
    {
      "epoch": 0.016974326331423723,
      "grad_norm": 0.3522188067436218,
      "learning_rate": 0.0003,
      "loss": 0.847,
      "step": 10
    },
    {
      "epoch": 0.018671758964566094,
      "grad_norm": 0.31385794281959534,
      "learning_rate": 0.0002999992447508326,
      "loss": 0.7329,
      "step": 11
    },
    {
      "epoch": 0.020369191597708464,
      "grad_norm": 0.5269914269447327,
      "learning_rate": 0.0002999969790109359,
      "loss": 0.8751,
      "step": 12
    },
    {
      "epoch": 0.02206662423085084,
      "grad_norm": 0.2571907341480255,
      "learning_rate": 0.0002999932028031259,
      "loss": 0.6175,
      "step": 13
    },
    {
      "epoch": 0.02376405686399321,
      "grad_norm": 0.2777341306209564,
      "learning_rate": 0.0002999879161654289,
      "loss": 0.7442,
      "step": 14
    },
    {
      "epoch": 0.025461489497135583,
      "grad_norm": 0.19830763339996338,
      "learning_rate": 0.00029998111915108125,
      "loss": 0.4802,
      "step": 15
    },
    {
      "epoch": 0.027158922130277954,
      "grad_norm": 0.21772292256355286,
      "learning_rate": 0.00029997281182852885,
      "loss": 0.527,
      "step": 16
    },
    {
      "epoch": 0.028856354763420328,
      "grad_norm": 0.18149510025978088,
      "learning_rate": 0.00029996299428142637,
      "loss": 0.4808,
      "step": 17
    },
    {
      "epoch": 0.030553787396562698,
      "grad_norm": 0.22295671701431274,
      "learning_rate": 0.00029995166660863636,
      "loss": 0.5326,
      "step": 18
    },
    {
      "epoch": 0.03225122002970507,
      "grad_norm": 0.24240700900554657,
      "learning_rate": 0.0002999388289242284,
      "loss": 0.5986,
      "step": 19
    },
    {
      "epoch": 0.033948652662847446,
      "grad_norm": 0.21365882456302643,
      "learning_rate": 0.00029992448135747777,
      "loss": 0.4533,
      "step": 20
    },
    {
      "epoch": 0.03564608529598982,
      "grad_norm": 0.13466337323188782,
      "learning_rate": 0.00029990862405286433,
      "loss": 0.2177,
      "step": 21
    },
    {
      "epoch": 0.03734351792913219,
      "grad_norm": 0.2027832567691803,
      "learning_rate": 0.00029989125717007104,
      "loss": 0.4166,
      "step": 22
    },
    {
      "epoch": 0.03904095056227456,
      "grad_norm": 0.14215879142284393,
      "learning_rate": 0.0002998723808839821,
      "loss": 0.2648,
      "step": 23
    },
    {
      "epoch": 0.04073838319541693,
      "grad_norm": 0.10996250063180923,
      "learning_rate": 0.00029985199538468154,
      "loss": 0.1554,
      "step": 24
    },
    {
      "epoch": 0.042435815828559306,
      "grad_norm": 0.10510318726301193,
      "learning_rate": 0.0002998301008774512,
      "loss": 0.0231,
      "step": 25
    },
    {
      "epoch": 0.04413324846170168,
      "grad_norm": 0.10925798863172531,
      "learning_rate": 0.00029980669758276836,
      "loss": 0.1159,
      "step": 26
    },
    {
      "epoch": 0.04583068109484405,
      "grad_norm": 0.06849532574415207,
      "learning_rate": 0.0002997817857363041,
      "loss": 0.039,
      "step": 27
    },
    {
      "epoch": 0.04752811372798642,
      "grad_norm": 0.0729198008775711,
      "learning_rate": 0.0002997553655889203,
      "loss": 0.0084,
      "step": 28
    },
    {
      "epoch": 0.049225546361128796,
      "grad_norm": 0.10013315826654434,
      "learning_rate": 0.00029972743740666765,
      "loss": 0.0985,
      "step": 29
    },
    {
      "epoch": 0.050922978994271166,
      "grad_norm": 0.047209128737449646,
      "learning_rate": 0.00029969800147078263,
      "loss": 0.0234,
      "step": 30
    },
    {
      "epoch": 0.05262041162741354,
      "grad_norm": 0.015719635412096977,
      "learning_rate": 0.00029966705807768474,
      "loss": 0.0014,
      "step": 31
    },
    {
      "epoch": 0.05431784426055591,
      "grad_norm": 0.032827939838171005,
      "learning_rate": 0.0002996346075389736,
      "loss": 0.005,
      "step": 32
    },
    {
      "epoch": 0.056015276893698285,
      "grad_norm": 0.021124735474586487,
      "learning_rate": 0.0002996006501814258,
      "loss": 0.0012,
      "step": 33
    },
    {
      "epoch": 0.057712709526840655,
      "grad_norm": 0.014757171273231506,
      "learning_rate": 0.0002995651863469916,
      "loss": 0.0019,
      "step": 34
    },
    {
      "epoch": 0.059410142159983026,
      "grad_norm": 0.013099136762320995,
      "learning_rate": 0.00029952821639279135,
      "loss": 0.0012,
      "step": 35
    },
    {
      "epoch": 0.061107574793125397,
      "grad_norm": 0.02350614406168461,
      "learning_rate": 0.0002994897406911121,
      "loss": 0.0032,
      "step": 36
    },
    {
      "epoch": 0.06280500742626777,
      "grad_norm": 0.01101439818739891,
      "learning_rate": 0.0002994497596294037,
      "loss": 0.0006,
      "step": 37
    },
    {
      "epoch": 0.06450244005941014,
      "grad_norm": 0.08192350715398788,
      "learning_rate": 0.00029940827361027504,
      "loss": 0.0046,
      "step": 38
    },
    {
      "epoch": 0.06619987269255251,
      "grad_norm": 0.03598169609904289,
      "learning_rate": 0.0002993652830514899,
      "loss": 0.0027,
      "step": 39
    },
    {
      "epoch": 0.06789730532569489,
      "grad_norm": 0.045441944152116776,
      "learning_rate": 0.0002993207883859627,
      "loss": 0.0076,
      "step": 40
    },
    {
      "epoch": 0.06959473795883726,
      "grad_norm": 0.048115745186805725,
      "learning_rate": 0.00029927479006175417,
      "loss": 0.0028,
      "step": 41
    },
    {
      "epoch": 0.07129217059197963,
      "grad_norm": 0.027597462758421898,
      "learning_rate": 0.00029922728854206703,
      "loss": 0.002,
      "step": 42
    },
    {
      "epoch": 0.072989603225122,
      "grad_norm": 0.0355045348405838,
      "learning_rate": 0.00029917828430524096,
      "loss": 0.0013,
      "step": 43
    },
    {
      "epoch": 0.07468703585826438,
      "grad_norm": 0.0412307046353817,
      "learning_rate": 0.00029912777784474814,
      "loss": 0.003,
      "step": 44
    },
    {
      "epoch": 0.07638446849140675,
      "grad_norm": 0.051867593079805374,
      "learning_rate": 0.0002990757696691881,
      "loss": 0.0039,
      "step": 45
    },
    {
      "epoch": 0.07808190112454912,
      "grad_norm": 0.06054271385073662,
      "learning_rate": 0.00029902226030228247,
      "loss": 0.0019,
      "step": 46
    },
    {
      "epoch": 0.07977933375769149,
      "grad_norm": 0.05313190817832947,
      "learning_rate": 0.00029896725028287014,
      "loss": 0.0041,
      "step": 47
    },
    {
      "epoch": 0.08147676639083386,
      "grad_norm": 0.18755203485488892,
      "learning_rate": 0.00029891074016490126,
      "loss": 0.0036,
      "step": 48
    },
    {
      "epoch": 0.08317419902397624,
      "grad_norm": 0.05305561423301697,
      "learning_rate": 0.00029885273051743214,
      "loss": 0.0051,
      "step": 49
    },
    {
      "epoch": 0.08487163165711861,
      "grad_norm": 0.08674199134111404,
      "learning_rate": 0.00029879322192461925,
      "loss": 0.012,
      "step": 50
    },
    {
      "epoch": 0.08487163165711861,
      "eval_loss": 0.4556533694267273,
      "eval_runtime": 65.6522,
      "eval_samples_per_second": 2.94,
      "eval_steps_per_second": 2.94,
      "step": 50
    },
    {
      "epoch": 0.08656906429026098,
      "grad_norm": 0.5487300753593445,
      "learning_rate": 0.00029873221498571354,
      "loss": 1.0487,
      "step": 51
    },
    {
      "epoch": 0.08826649692340335,
      "grad_norm": 0.27697888016700745,
      "learning_rate": 0.00029866971031505417,
      "loss": 0.7504,
      "step": 52
    },
    {
      "epoch": 0.08996392955654572,
      "grad_norm": 0.2856276035308838,
      "learning_rate": 0.00029860570854206244,
      "loss": 1.0179,
      "step": 53
    },
    {
      "epoch": 0.0916613621896881,
      "grad_norm": 0.43166583776474,
      "learning_rate": 0.0002985402103112355,
      "loss": 0.7947,
      "step": 54
    },
    {
      "epoch": 0.09335879482283047,
      "grad_norm": 0.26107504963874817,
      "learning_rate": 0.0002984732162821399,
      "loss": 0.9617,
      "step": 55
    },
    {
      "epoch": 0.09505622745597284,
      "grad_norm": 0.20953023433685303,
      "learning_rate": 0.00029840472712940465,
      "loss": 0.7355,
      "step": 56
    },
    {
      "epoch": 0.0967536600891152,
      "grad_norm": 0.22740969061851501,
      "learning_rate": 0.0002983347435427148,
      "loss": 0.839,
      "step": 57
    },
    {
      "epoch": 0.09845109272225759,
      "grad_norm": 0.24932198226451874,
      "learning_rate": 0.00029826326622680433,
      "loss": 0.775,
      "step": 58
    },
    {
      "epoch": 0.10014852535539996,
      "grad_norm": 0.260080486536026,
      "learning_rate": 0.000298190295901449,
      "loss": 0.9275,
      "step": 59
    },
    {
      "epoch": 0.10184595798854233,
      "grad_norm": 0.22443322837352753,
      "learning_rate": 0.00029811583330145914,
      "loss": 0.796,
      "step": 60
    },
    {
      "epoch": 0.1035433906216847,
      "grad_norm": 0.2286413460969925,
      "learning_rate": 0.0002980398791766723,
      "loss": 0.6944,
      "step": 61
    },
    {
      "epoch": 0.10524082325482707,
      "grad_norm": 0.18511152267456055,
      "learning_rate": 0.00029796243429194575,
      "loss": 0.4977,
      "step": 62
    },
    {
      "epoch": 0.10693825588796944,
      "grad_norm": 0.745172917842865,
      "learning_rate": 0.00029788349942714854,
      "loss": 0.4391,
      "step": 63
    },
    {
      "epoch": 0.10863568852111181,
      "grad_norm": 0.27929672598838806,
      "learning_rate": 0.0002978030753771539,
      "loss": 0.8052,
      "step": 64
    },
    {
      "epoch": 0.11033312115425419,
      "grad_norm": 0.3147849440574646,
      "learning_rate": 0.0002977211629518312,
      "loss": 1.0817,
      "step": 65
    },
    {
      "epoch": 0.11203055378739657,
      "grad_norm": 0.22278442978858948,
      "learning_rate": 0.00029763776297603756,
      "loss": 0.5924,
      "step": 66
    },
    {
      "epoch": 0.11372798642053894,
      "grad_norm": 0.1911861002445221,
      "learning_rate": 0.0002975528762896098,
      "loss": 0.3729,
      "step": 67
    },
    {
      "epoch": 0.11542541905368131,
      "grad_norm": 0.21224386990070343,
      "learning_rate": 0.000297466503747356,
      "loss": 0.569,
      "step": 68
    },
    {
      "epoch": 0.11712285168682368,
      "grad_norm": 0.25374075770378113,
      "learning_rate": 0.0002973786462190466,
      "loss": 0.8077,
      "step": 69
    },
    {
      "epoch": 0.11882028431996605,
      "grad_norm": 0.16218560934066772,
      "learning_rate": 0.00029728930458940595,
      "loss": 0.3303,
      "step": 70
    },
    {
      "epoch": 0.12051771695310842,
      "grad_norm": 0.18142607808113098,
      "learning_rate": 0.0002971984797581034,
      "loss": 0.4428,
      "step": 71
    },
    {
      "epoch": 0.12221514958625079,
      "grad_norm": 0.22838933765888214,
      "learning_rate": 0.0002971061726397438,
      "loss": 0.6141,
      "step": 72
    },
    {
      "epoch": 0.12391258221939316,
      "grad_norm": 0.16390271484851837,
      "learning_rate": 0.00029701238416385896,
      "loss": 0.3882,
      "step": 73
    },
    {
      "epoch": 0.12561001485253553,
      "grad_norm": 0.07758953422307968,
      "learning_rate": 0.00029691711527489776,
      "loss": 0.0949,
      "step": 74
    },
    {
      "epoch": 0.1273074474856779,
      "grad_norm": 0.10925949364900589,
      "learning_rate": 0.0002968203669322168,
      "loss": 0.1791,
      "step": 75
    },
    {
      "epoch": 0.12900488011882028,
      "grad_norm": 0.021430950611829758,
      "learning_rate": 0.0002967221401100708,
      "loss": 0.003,
      "step": 76
    },
    {
      "epoch": 0.13070231275196265,
      "grad_norm": 0.02433953993022442,
      "learning_rate": 0.0002966224357976029,
      "loss": 0.0021,
      "step": 77
    },
    {
      "epoch": 0.13239974538510502,
      "grad_norm": 0.11294607818126678,
      "learning_rate": 0.0002965212549988342,
      "loss": 0.0765,
      "step": 78
    },
    {
      "epoch": 0.1340971780182474,
      "grad_norm": 0.026264643296599388,
      "learning_rate": 0.0002964185987326545,
      "loss": 0.0026,
      "step": 79
    },
    {
      "epoch": 0.13579461065138979,
      "grad_norm": 0.0762176588177681,
      "learning_rate": 0.00029631446803281107,
      "loss": 0.0394,
      "step": 80
    },
    {
      "epoch": 0.13749204328453216,
      "grad_norm": 0.03476507589221001,
      "learning_rate": 0.00029620886394789885,
      "loss": 0.005,
      "step": 81
    },
    {
      "epoch": 0.13918947591767453,
      "grad_norm": 0.03176519274711609,
      "learning_rate": 0.00029610178754135,
      "loss": 0.0038,
      "step": 82
    },
    {
      "epoch": 0.1408869085508169,
      "grad_norm": 0.006855768151581287,
      "learning_rate": 0.00029599323989142263,
      "loss": 0.0004,
      "step": 83
    },
    {
      "epoch": 0.14258434118395927,
      "grad_norm": 0.013548546470701694,
      "learning_rate": 0.00029588322209119037,
      "loss": 0.0007,
      "step": 84
    },
    {
      "epoch": 0.14428177381710164,
      "grad_norm": 0.032073307782411575,
      "learning_rate": 0.00029577173524853123,
      "loss": 0.0023,
      "step": 85
    },
    {
      "epoch": 0.145979206450244,
      "grad_norm": 0.06568052619695663,
      "learning_rate": 0.0002956587804861165,
      "loss": 0.003,
      "step": 86
    },
    {
      "epoch": 0.14767663908338638,
      "grad_norm": 0.017053432762622833,
      "learning_rate": 0.0002955443589413994,
      "loss": 0.0011,
      "step": 87
    },
    {
      "epoch": 0.14937407171652875,
      "grad_norm": 0.027703823521733284,
      "learning_rate": 0.0002954284717666036,
      "loss": 0.0011,
      "step": 88
    },
    {
      "epoch": 0.15107150434967112,
      "grad_norm": 0.028447195887565613,
      "learning_rate": 0.00029531112012871175,
      "loss": 0.002,
      "step": 89
    },
    {
      "epoch": 0.1527689369828135,
      "grad_norm": 0.051351480185985565,
      "learning_rate": 0.0002951923052094534,
      "loss": 0.0023,
      "step": 90
    },
    {
      "epoch": 0.15446636961595586,
      "grad_norm": 0.04188869521021843,
      "learning_rate": 0.0002950720282052936,
      "loss": 0.0022,
      "step": 91
    },
    {
      "epoch": 0.15616380224909823,
      "grad_norm": 0.03857725113630295,
      "learning_rate": 0.00029495029032742024,
      "loss": 0.0013,
      "step": 92
    },
    {
      "epoch": 0.1578612348822406,
      "grad_norm": 0.030291402712464333,
      "learning_rate": 0.0002948270928017326,
      "loss": 0.0015,
      "step": 93
    },
    {
      "epoch": 0.15955866751538297,
      "grad_norm": 0.05515044555068016,
      "learning_rate": 0.00029470243686882837,
      "loss": 0.0008,
      "step": 94
    },
    {
      "epoch": 0.16125610014852534,
      "grad_norm": 0.0681704506278038,
      "learning_rate": 0.00029457632378399127,
      "loss": 0.0016,
      "step": 95
    },
    {
      "epoch": 0.16295353278166771,
      "grad_norm": 0.17659763991832733,
      "learning_rate": 0.0002944487548171788,
      "loss": 0.0015,
      "step": 96
    },
    {
      "epoch": 0.1646509654148101,
      "grad_norm": 0.01778286136686802,
      "learning_rate": 0.00029431973125300907,
      "loss": 0.0003,
      "step": 97
    },
    {
      "epoch": 0.16634839804795248,
      "grad_norm": 0.052063290029764175,
      "learning_rate": 0.0002941892543907478,
      "loss": 0.0042,
      "step": 98
    },
    {
      "epoch": 0.16804583068109485,
      "grad_norm": 0.08560975641012192,
      "learning_rate": 0.00029405732554429564,
      "loss": 0.003,
      "step": 99
    },
    {
      "epoch": 0.16974326331423722,
      "grad_norm": 0.07182486355304718,
      "learning_rate": 0.0002939239460421746,
      "loss": 0.0091,
      "step": 100
    },
    {
      "epoch": 0.16974326331423722,
      "eval_loss": 0.4275517165660858,
      "eval_runtime": 65.6527,
      "eval_samples_per_second": 2.94,
      "eval_steps_per_second": 2.94,
      "step": 100
    },
    {
      "epoch": 0.1714406959473796,
      "grad_norm": 0.33816632628440857,
      "learning_rate": 0.0002937891172275147,
      "loss": 0.6861,
      "step": 101
    },
    {
      "epoch": 0.17313812858052197,
      "grad_norm": 0.24974839389324188,
      "learning_rate": 0.00029365284045804077,
      "loss": 0.7581,
      "step": 102
    },
    {
      "epoch": 0.17483556121366434,
      "grad_norm": 0.389892041683197,
      "learning_rate": 0.00029351511710605825,
      "loss": 0.8517,
      "step": 103
    },
    {
      "epoch": 0.1765329938468067,
      "grad_norm": 0.21865390241146088,
      "learning_rate": 0.0002933759485584397,
      "loss": 0.7927,
      "step": 104
    },
    {
      "epoch": 0.17823042647994908,
      "grad_norm": 0.2867435812950134,
      "learning_rate": 0.00029323533621661106,
      "loss": 0.8931,
      "step": 105
    },
    {
      "epoch": 0.17992785911309145,
      "grad_norm": 0.19504129886627197,
      "learning_rate": 0.0002930932814965369,
      "loss": 0.5056,
      "step": 106
    },
    {
      "epoch": 0.18162529174623382,
      "grad_norm": 0.2704707980155945,
      "learning_rate": 0.00029294978582870666,
      "loss": 0.7927,
      "step": 107
    },
    {
      "epoch": 0.1833227243793762,
      "grad_norm": 0.20052890479564667,
      "learning_rate": 0.0002928048506581202,
      "loss": 0.6507,
      "step": 108
    },
    {
      "epoch": 0.18502015701251856,
      "grad_norm": 0.20652854442596436,
      "learning_rate": 0.00029265847744427303,
      "loss": 0.6928,
      "step": 109
    },
    {
      "epoch": 0.18671758964566093,
      "grad_norm": 0.2864634096622467,
      "learning_rate": 0.00029251066766114176,
      "loss": 1.0405,
      "step": 110
    },
    {
      "epoch": 0.1884150222788033,
      "grad_norm": 0.2000068873167038,
      "learning_rate": 0.0002923614227971694,
      "loss": 0.5787,
      "step": 111
    },
    {
      "epoch": 0.19011245491194567,
      "grad_norm": 0.16141685843467712,
      "learning_rate": 0.0002922107443552499,
      "loss": 0.4154,
      "step": 112
    },
    {
      "epoch": 0.19180988754508804,
      "grad_norm": 0.2669724225997925,
      "learning_rate": 0.00029205863385271363,
      "loss": 0.9767,
      "step": 113
    },
    {
      "epoch": 0.1935073201782304,
      "grad_norm": 0.7105275988578796,
      "learning_rate": 0.00029190509282131153,
      "loss": 0.6763,
      "step": 114
    },
    {
      "epoch": 0.1952047528113728,
      "grad_norm": 0.23595799505710602,
      "learning_rate": 0.00029175012280720024,
      "loss": 0.6856,
      "step": 115
    },
    {
      "epoch": 0.19690218544451518,
      "grad_norm": 0.23921440541744232,
      "learning_rate": 0.00029159372537092596,
      "loss": 0.7075,
      "step": 116
    },
    {
      "epoch": 0.19859961807765755,
      "grad_norm": 0.21551960706710815,
      "learning_rate": 0.0002914359020874092,
      "loss": 0.6004,
      "step": 117
    },
    {
      "epoch": 0.20029705071079992,
      "grad_norm": 0.20390333235263824,
      "learning_rate": 0.0002912766545459287,
      "loss": 0.57,
      "step": 118
    },
    {
      "epoch": 0.2019944833439423,
      "grad_norm": 0.15612931549549103,
      "learning_rate": 0.0002911159843501053,
      "loss": 0.2055,
      "step": 119
    },
    {
      "epoch": 0.20369191597708466,
      "grad_norm": 0.17460142076015472,
      "learning_rate": 0.0002909538931178862,
      "loss": 0.371,
      "step": 120
    },
    {
      "epoch": 0.20538934861022703,
      "grad_norm": 0.18853937089443207,
      "learning_rate": 0.00029079038248152835,
      "loss": 0.4252,
      "step": 121
    },
    {
      "epoch": 0.2070867812433694,
      "grad_norm": 0.14426594972610474,
      "learning_rate": 0.0002906254540875819,
      "loss": 0.2658,
      "step": 122
    },
    {
      "epoch": 0.20878421387651178,
      "grad_norm": 0.16134832799434662,
      "learning_rate": 0.0002904591095968741,
      "loss": 0.297,
      "step": 123
    },
    {
      "epoch": 0.21048164650965415,
      "grad_norm": 0.3797933757305145,
      "learning_rate": 0.00029029135068449195,
      "loss": 0.2837,
      "step": 124
    },
    {
      "epoch": 0.21217907914279652,
      "grad_norm": 0.038109440356492996,
      "learning_rate": 0.000290122179039766,
      "loss": 0.0149,
      "step": 125
    },
    {
      "epoch": 0.2138765117759389,
      "grad_norm": 0.11762002855539322,
      "learning_rate": 0.00028995159636625276,
      "loss": 0.0684,
      "step": 126
    },
    {
      "epoch": 0.21557394440908126,
      "grad_norm": 0.02665620669722557,
      "learning_rate": 0.00028977960438171784,
      "loss": 0.0044,
      "step": 127
    },
    {
      "epoch": 0.21727137704222363,
      "grad_norm": 0.03071051463484764,
      "learning_rate": 0.0002896062048181186,
      "loss": 0.0018,
      "step": 128
    },
    {
      "epoch": 0.218968809675366,
      "grad_norm": 0.009578248485922813,
      "learning_rate": 0.00028943139942158683,
      "loss": 0.0004,
      "step": 129
    },
    {
      "epoch": 0.22066624230850837,
      "grad_norm": 0.0018459237180650234,
      "learning_rate": 0.0002892551899524109,
      "loss": 0.0001,
      "step": 130
    },
    {
      "epoch": 0.22236367494165074,
      "grad_norm": 0.09641125798225403,
      "learning_rate": 0.0002890775781850181,
      "loss": 0.0588,
      "step": 131
    },
    {
      "epoch": 0.22406110757479314,
      "grad_norm": 0.008955306373536587,
      "learning_rate": 0.000288898565907957,
      "loss": 0.0002,
      "step": 132
    },
    {
      "epoch": 0.2257585402079355,
      "grad_norm": 0.4112979471683502,
      "learning_rate": 0.0002887181549238793,
      "loss": 0.0037,
      "step": 133
    },
    {
      "epoch": 0.22745597284107788,
      "grad_norm": 0.0008860170491971076,
      "learning_rate": 0.00028853634704952165,
      "loss": 0.0001,
      "step": 134
    },
    {
      "epoch": 0.22915340547422025,
      "grad_norm": 0.03983623534440994,
      "learning_rate": 0.0002883531441156872,
      "loss": 0.0014,
      "step": 135
    },
    {
      "epoch": 0.23085083810736262,
      "grad_norm": 0.13147315382957458,
      "learning_rate": 0.00028816854796722747,
      "loss": 0.0039,
      "step": 136
    },
    {
      "epoch": 0.232548270740505,
      "grad_norm": 0.027041589841246605,
      "learning_rate": 0.00028798256046302375,
      "loss": 0.003,
      "step": 137
    },
    {
      "epoch": 0.23424570337364736,
      "grad_norm": 0.012492002919316292,
      "learning_rate": 0.000287795183475968,
      "loss": 0.0006,
      "step": 138
    },
    {
      "epoch": 0.23594313600678973,
      "grad_norm": 0.004202733281999826,
      "learning_rate": 0.00028760641889294446,
      "loss": 0.0002,
      "step": 139
    },
    {
      "epoch": 0.2376405686399321,
      "grad_norm": 0.004685190040618181,
      "learning_rate": 0.0002874162686148104,
      "loss": 0.0003,
      "step": 140
    },
    {
      "epoch": 0.23933800127307447,
      "grad_norm": 0.009362437762320042,
      "learning_rate": 0.000287224734556377,
      "loss": 0.0007,
      "step": 141
    },
    {
      "epoch": 0.24103543390621684,
      "grad_norm": 0.0981183648109436,
      "learning_rate": 0.0002870318186463901,
      "loss": 0.0042,
      "step": 142
    },
    {
      "epoch": 0.24273286653935922,
      "grad_norm": 0.015274147503077984,
      "learning_rate": 0.00028683752282751074,
      "loss": 0.0007,
      "step": 143
    },
    {
      "epoch": 0.24443029917250159,
      "grad_norm": 0.00900458823889494,
      "learning_rate": 0.0002866418490562957,
      "loss": 0.0007,
      "step": 144
    },
    {
      "epoch": 0.24612773180564396,
      "grad_norm": 0.01067203190177679,
      "learning_rate": 0.00028644479930317775,
      "loss": 0.0006,
      "step": 145
    },
    {
      "epoch": 0.24782516443878633,
      "grad_norm": 0.022083261981606483,
      "learning_rate": 0.0002862463755524455,
      "loss": 0.0006,
      "step": 146
    },
    {
      "epoch": 0.2495225970719287,
      "grad_norm": 0.003914229571819305,
      "learning_rate": 0.00028604657980222417,
      "loss": 0.0003,
      "step": 147
    },
    {
      "epoch": 0.25122002970507107,
      "grad_norm": 0.005544353276491165,
      "learning_rate": 0.0002858454140644546,
      "loss": 0.0004,
      "step": 148
    },
    {
      "epoch": 0.25291746233821344,
      "grad_norm": 0.006152280140668154,
      "learning_rate": 0.00028564288036487357,
      "loss": 0.0005,
      "step": 149
    },
    {
      "epoch": 0.2546148949713558,
      "grad_norm": 0.04355669021606445,
      "learning_rate": 0.00028543898074299317,
      "loss": 0.0053,
      "step": 150
    },
    {
      "epoch": 0.2546148949713558,
      "eval_loss": 0.42699772119522095,
      "eval_runtime": 65.6214,
      "eval_samples_per_second": 2.941,
      "eval_steps_per_second": 2.941,
      "step": 150
    },
    {
      "epoch": 0.2563123276044982,
      "grad_norm": 0.33021700382232666,
      "learning_rate": 0.00028523371725208035,
      "loss": 0.7046,
      "step": 151
    },
    {
      "epoch": 0.25800976023764055,
      "grad_norm": 0.29715627431869507,
      "learning_rate": 0.00028502709195913614,
      "loss": 0.8173,
      "step": 152
    },
    {
      "epoch": 0.2597071928707829,
      "grad_norm": 0.23798537254333496,
      "learning_rate": 0.000284819106944875,
      "loss": 0.8376,
      "step": 153
    },
    {
      "epoch": 0.2614046255039253,
      "grad_norm": 0.24740736186504364,
      "learning_rate": 0.0002846097643037037,
      "loss": 0.8829,
      "step": 154
    },
    {
      "epoch": 0.26310205813706766,
      "grad_norm": 0.8396446704864502,
      "learning_rate": 0.00028439906614370034,
      "loss": 0.8286,
      "step": 155
    },
    {
      "epoch": 0.26479949077021003,
      "grad_norm": 0.271604061126709,
      "learning_rate": 0.00028418701458659304,
      "loss": 0.8996,
      "step": 156
    },
    {
      "epoch": 0.2664969234033524,
      "grad_norm": 0.2267700582742691,
      "learning_rate": 0.00028397361176773855,
      "loss": 0.6639,
      "step": 157
    },
    {
      "epoch": 0.2681943560364948,
      "grad_norm": 0.19427096843719482,
      "learning_rate": 0.000283758859836101,
      "loss": 0.4771,
      "step": 158
    },
    {
      "epoch": 0.2698917886696372,
      "grad_norm": 0.1682572066783905,
      "learning_rate": 0.0002835427609542298,
      "loss": 0.407,
      "step": 159
    },
    {
      "epoch": 0.27158922130277957,
      "grad_norm": 0.22453951835632324,
      "learning_rate": 0.0002833253172982385,
      "loss": 0.6087,
      "step": 160
    },
    {
      "epoch": 0.27328665393592194,
      "grad_norm": 0.2826938331127167,
      "learning_rate": 0.00028310653105778215,
      "loss": 0.8161,
      "step": 161
    },
    {
      "epoch": 0.2749840865690643,
      "grad_norm": 0.26969850063323975,
      "learning_rate": 0.0002828864044360358,
      "loss": 0.9043,
      "step": 162
    },
    {
      "epoch": 0.2766815192022067,
      "grad_norm": 0.2145734280347824,
      "learning_rate": 0.0002826649396496721,
      "loss": 0.5051,
      "step": 163
    },
    {
      "epoch": 0.27837895183534905,
      "grad_norm": 0.22222040593624115,
      "learning_rate": 0.000282442138928839,
      "loss": 0.6356,
      "step": 164
    },
    {
      "epoch": 0.2800763844684914,
      "grad_norm": 0.1878889799118042,
      "learning_rate": 0.0002822180045171373,
      "loss": 0.4778,
      "step": 165
    },
    {
      "epoch": 0.2817738171016338,
      "grad_norm": 0.1969398856163025,
      "learning_rate": 0.00028199253867159795,
      "loss": 0.4855,
      "step": 166
    },
    {
      "epoch": 0.28347124973477617,
      "grad_norm": 0.11540260910987854,
      "learning_rate": 0.0002817657436626596,
      "loss": 0.1777,
      "step": 167
    },
    {
      "epoch": 0.28516868236791854,
      "grad_norm": 0.14375105500221252,
      "learning_rate": 0.0002815376217741454,
      "loss": 0.3379,
      "step": 168
    },
    {
      "epoch": 0.2868661150010609,
      "grad_norm": 0.4472449719905853,
      "learning_rate": 0.0002813081753032403,
      "loss": 0.5727,
      "step": 169
    },
    {
      "epoch": 0.2885635476342033,
      "grad_norm": 0.24242308735847473,
      "learning_rate": 0.0002810774065604677,
      "loss": 0.3351,
      "step": 170
    },
    {
      "epoch": 0.29026098026734565,
      "grad_norm": 0.13647812604904175,
      "learning_rate": 0.0002808453178696663,
      "loss": 0.2388,
      "step": 171
    },
    {
      "epoch": 0.291958412900488,
      "grad_norm": 0.13304531574249268,
      "learning_rate": 0.00028061191156796656,
      "loss": 0.2208,
      "step": 172
    },
    {
      "epoch": 0.2936558455336304,
      "grad_norm": 0.13337798416614532,
      "learning_rate": 0.0002803771900057674,
      "loss": 0.1881,
      "step": 173
    },
    {
      "epoch": 0.29535327816677276,
      "grad_norm": 0.12482510507106781,
      "learning_rate": 0.00028014115554671236,
      "loss": 0.1659,
      "step": 174
    },
    {
      "epoch": 0.29705071079991513,
      "grad_norm": 0.05092178285121918,
      "learning_rate": 0.0002799038105676658,
      "loss": 0.0022,
      "step": 175
    },
    {
      "epoch": 0.2987481434330575,
      "grad_norm": 0.03115926869213581,
      "learning_rate": 0.000279665157458689,
      "loss": 0.007,
      "step": 176
    },
    {
      "epoch": 0.30044557606619987,
      "grad_norm": 0.048752959817647934,
      "learning_rate": 0.0002794251986230161,
      "loss": 0.0231,
      "step": 177
    },
    {
      "epoch": 0.30214300869934224,
      "grad_norm": 0.049951329827308655,
      "learning_rate": 0.0002791839364770301,
      "loss": 0.024,
      "step": 178
    },
    {
      "epoch": 0.3038404413324846,
      "grad_norm": 0.019635546952486038,
      "learning_rate": 0.00027894137345023785,
      "loss": 0.0009,
      "step": 179
    },
    {
      "epoch": 0.305537873965627,
      "grad_norm": 0.008390502072870731,
      "learning_rate": 0.0002786975119852465,
      "loss": 0.0002,
      "step": 180
    },
    {
      "epoch": 0.30723530659876935,
      "grad_norm": 0.030752401798963547,
      "learning_rate": 0.00027845235453773836,
      "loss": 0.0012,
      "step": 181
    },
    {
      "epoch": 0.3089327392319117,
      "grad_norm": 0.004207144025713205,
      "learning_rate": 0.000278205903576446,
      "loss": 0.0001,
      "step": 182
    },
    {
      "epoch": 0.3106301718650541,
      "grad_norm": 0.012170841917395592,
      "learning_rate": 0.00027795816158312803,
      "loss": 0.0004,
      "step": 183
    },
    {
      "epoch": 0.31232760449819646,
      "grad_norm": 0.004860470537096262,
      "learning_rate": 0.0002777091310525435,
      "loss": 0.0002,
      "step": 184
    },
    {
      "epoch": 0.31402503713133884,
      "grad_norm": 0.004869968164712191,
      "learning_rate": 0.00027745881449242713,
      "loss": 0.0002,
      "step": 185
    },
    {
      "epoch": 0.3157224697644812,
      "grad_norm": 0.011595932766795158,
      "learning_rate": 0.00027720721442346387,
      "loss": 0.0003,
      "step": 186
    },
    {
      "epoch": 0.3174199023976236,
      "grad_norm": 0.02118592895567417,
      "learning_rate": 0.0002769543333792636,
      "loss": 0.0012,
      "step": 187
    },
    {
      "epoch": 0.31911733503076595,
      "grad_norm": 0.03935430571436882,
      "learning_rate": 0.00027670017390633573,
      "loss": 0.0003,
      "step": 188
    },
    {
      "epoch": 0.3208147676639083,
      "grad_norm": 0.0356944277882576,
      "learning_rate": 0.0002764447385640632,
      "loss": 0.0008,
      "step": 189
    },
    {
      "epoch": 0.3225122002970507,
      "grad_norm": 0.05277875065803528,
      "learning_rate": 0.0002761880299246772,
      "loss": 0.0007,
      "step": 190
    },
    {
      "epoch": 0.32420963293019306,
      "grad_norm": 0.0025087774265557528,
      "learning_rate": 0.0002759300505732307,
      "loss": 0.0001,
      "step": 191
    },
    {
      "epoch": 0.32590706556333543,
      "grad_norm": 0.002132557798177004,
      "learning_rate": 0.00027567080310757306,
      "loss": 0.0001,
      "step": 192
    },
    {
      "epoch": 0.3276044981964778,
      "grad_norm": 0.0010882457718253136,
      "learning_rate": 0.0002754102901383233,
      "loss": 0.0001,
      "step": 193
    },
    {
      "epoch": 0.3293019308296202,
      "grad_norm": 0.02085525542497635,
      "learning_rate": 0.0002751485142888443,
      "loss": 0.0004,
      "step": 194
    },
    {
      "epoch": 0.3309993634627626,
      "grad_norm": 0.003921423573046923,
      "learning_rate": 0.0002748854781952157,
      "loss": 0.0001,
      "step": 195
    },
    {
      "epoch": 0.33269679609590497,
      "grad_norm": 0.05576641112565994,
      "learning_rate": 0.0002746211845062082,
      "loss": 0.0027,
      "step": 196
    },
    {
      "epoch": 0.33439422872904734,
      "grad_norm": 0.025059282779693604,
      "learning_rate": 0.0002743556358832562,
      "loss": 0.0009,
      "step": 197
    },
    {
      "epoch": 0.3360916613621897,
      "grad_norm": 0.14736546576023102,
      "learning_rate": 0.00027408883500043156,
      "loss": 0.0117,
      "step": 198
    },
    {
      "epoch": 0.3377890939953321,
      "grad_norm": 0.022192303091287613,
      "learning_rate": 0.00027382078454441606,
      "loss": 0.0005,
      "step": 199
    },
    {
      "epoch": 0.33948652662847445,
      "grad_norm": 0.005171961151063442,
      "learning_rate": 0.0002735514872144749,
      "loss": 0.0002,
      "step": 200
    },
    {
      "epoch": 0.33948652662847445,
      "eval_loss": 0.42559075355529785,
      "eval_runtime": 65.6151,
      "eval_samples_per_second": 2.941,
      "eval_steps_per_second": 2.941,
      "step": 200
    },
    {
      "epoch": 0.3411839592616168,
      "grad_norm": 0.5887985825538635,
      "learning_rate": 0.0002732809457224292,
      "loss": 0.9434,
      "step": 201
    },
    {
      "epoch": 0.3428813918947592,
      "grad_norm": 0.38302966952323914,
      "learning_rate": 0.00027300916279262866,
      "loss": 1.0988,
      "step": 202
    },
    {
      "epoch": 0.34457882452790156,
      "grad_norm": 0.2614414095878601,
      "learning_rate": 0.0002727361411619245,
      "loss": 0.6772,
      "step": 203
    },
    {
      "epoch": 0.34627625716104393,
      "grad_norm": 0.3063081204891205,
      "learning_rate": 0.0002724618835796414,
      "loss": 0.7314,
      "step": 204
    },
    {
      "epoch": 0.3479736897941863,
      "grad_norm": 0.18658895790576935,
      "learning_rate": 0.0002721863928075503,
      "loss": 0.514,
      "step": 205
    },
    {
      "epoch": 0.3496711224273287,
      "grad_norm": 0.282010018825531,
      "learning_rate": 0.0002719096716198402,
      "loss": 0.892,
      "step": 206
    },
    {
      "epoch": 0.35136855506047104,
      "grad_norm": 0.17541489005088806,
      "learning_rate": 0.00027163172280309026,
      "loss": 0.5047,
      "step": 207
    },
    {
      "epoch": 0.3530659876936134,
      "grad_norm": 0.21916832029819489,
      "learning_rate": 0.0002713525491562421,
      "loss": 0.7146,
      "step": 208
    },
    {
      "epoch": 0.3547634203267558,
      "grad_norm": 0.20561501383781433,
      "learning_rate": 0.0002710721534905712,
      "loss": 0.6104,
      "step": 209
    },
    {
      "epoch": 0.35646085295989816,
      "grad_norm": 0.1947142332792282,
      "learning_rate": 0.00027079053862965875,
      "loss": 0.4924,
      "step": 210
    },
    {
      "epoch": 0.3581582855930405,
      "grad_norm": 0.23798146843910217,
      "learning_rate": 0.00027050770740936336,
      "loss": 0.6153,
      "step": 211
    },
    {
      "epoch": 0.3598557182261829,
      "grad_norm": 0.21775560081005096,
      "learning_rate": 0.00027022366267779224,
      "loss": 0.4658,
      "step": 212
    },
    {
      "epoch": 0.36155315085932527,
      "grad_norm": 0.24994409084320068,
      "learning_rate": 0.0002699384072952727,
      "loss": 0.5979,
      "step": 213
    },
    {
      "epoch": 0.36325058349246764,
      "grad_norm": 0.28469640016555786,
      "learning_rate": 0.0002696519441343233,
      "loss": 0.8796,
      "step": 214
    },
    {
      "epoch": 0.36494801612561,
      "grad_norm": 0.2747570276260376,
      "learning_rate": 0.0002693642760796248,
      "loss": 0.8625,
      "step": 215
    },
    {
      "epoch": 0.3666454487587524,
      "grad_norm": 0.2469591647386551,
      "learning_rate": 0.00026907540602799136,
      "loss": 0.6991,
      "step": 216
    },
    {
      "epoch": 0.36834288139189475,
      "grad_norm": 0.20425763726234436,
      "learning_rate": 0.00026878533688834123,
      "loss": 0.5774,
      "step": 217
    },
    {
      "epoch": 0.3700403140250371,
      "grad_norm": 0.2737872898578644,
      "learning_rate": 0.0002684940715816674,
      "loss": 0.9062,
      "step": 218
    },
    {
      "epoch": 0.3717377466581795,
      "grad_norm": 0.2064121514558792,
      "learning_rate": 0.00026820161304100823,
      "loss": 0.5054,
      "step": 219
    },
    {
      "epoch": 0.37343517929132186,
      "grad_norm": 0.14863868057727814,
      "learning_rate": 0.00026790796421141813,
      "loss": 0.285,
      "step": 220
    },
    {
      "epoch": 0.37513261192446423,
      "grad_norm": 0.12498918920755386,
      "learning_rate": 0.00026761312804993734,
      "loss": 0.1999,
      "step": 221
    },
    {
      "epoch": 0.3768300445576066,
      "grad_norm": 0.1726280152797699,
      "learning_rate": 0.0002673171075255629,
      "loss": 0.2852,
      "step": 222
    },
    {
      "epoch": 0.378527477190749,
      "grad_norm": 0.1533537358045578,
      "learning_rate": 0.0002670199056192181,
      "loss": 0.3106,
      "step": 223
    },
    {
      "epoch": 0.38022490982389134,
      "grad_norm": 0.125217467546463,
      "learning_rate": 0.00026672152532372287,
      "loss": 0.1804,
      "step": 224
    },
    {
      "epoch": 0.3819223424570337,
      "grad_norm": 0.05522383376955986,
      "learning_rate": 0.0002664219696437635,
      "loss": 0.0442,
      "step": 225
    },
    {
      "epoch": 0.3836197750901761,
      "grad_norm": 0.04138198867440224,
      "learning_rate": 0.00026612124159586237,
      "loss": 0.023,
      "step": 226
    },
    {
      "epoch": 0.38531720772331846,
      "grad_norm": 0.05575822666287422,
      "learning_rate": 0.0002658193442083475,
      "loss": 0.0024,
      "step": 227
    },
    {
      "epoch": 0.3870146403564608,
      "grad_norm": 0.12629126012325287,
      "learning_rate": 0.0002655162805213223,
      "loss": 0.1524,
      "step": 228
    },
    {
      "epoch": 0.38871207298960325,
      "grad_norm": 0.02942221239209175,
      "learning_rate": 0.00026521205358663477,
      "loss": 0.0096,
      "step": 229
    },
    {
      "epoch": 0.3904095056227456,
      "grad_norm": 0.0953650251030922,
      "learning_rate": 0.00026490666646784665,
      "loss": 0.0043,
      "step": 230
    },
    {
      "epoch": 0.392106938255888,
      "grad_norm": 0.005734459031373262,
      "learning_rate": 0.00026460012224020297,
      "loss": 0.0003,
      "step": 231
    },
    {
      "epoch": 0.39380437088903036,
      "grad_norm": 0.010758363641798496,
      "learning_rate": 0.0002642924239906006,
      "loss": 0.0003,
      "step": 232
    },
    {
      "epoch": 0.39550180352217273,
      "grad_norm": 0.01772010512650013,
      "learning_rate": 0.0002639835748175575,
      "loss": 0.0007,
      "step": 233
    },
    {
      "epoch": 0.3971992361553151,
      "grad_norm": 0.005056055262684822,
      "learning_rate": 0.0002636735778311815,
      "loss": 0.0002,
      "step": 234
    },
    {
      "epoch": 0.3988966687884575,
      "grad_norm": 0.24263891577720642,
      "learning_rate": 0.00026336243615313873,
      "loss": 0.0008,
      "step": 235
    },
    {
      "epoch": 0.40059410142159985,
      "grad_norm": 0.0014849180588498712,
      "learning_rate": 0.0002630501529166224,
      "loss": 0.0001,
      "step": 236
    },
    {
      "epoch": 0.4022915340547422,
      "grad_norm": 0.0037826071493327618,
      "learning_rate": 0.00026273673126632133,
      "loss": 0.0002,
      "step": 237
    },
    {
      "epoch": 0.4039889666878846,
      "grad_norm": 0.08331254124641418,
      "learning_rate": 0.0002624221743583881,
      "loss": 0.0016,
      "step": 238
    },
    {
      "epoch": 0.40568639932102696,
      "grad_norm": 0.002364553976804018,
      "learning_rate": 0.0002621064853604071,
      "loss": 0.0001,
      "step": 239
    },
    {
      "epoch": 0.40738383195416933,
      "grad_norm": 0.014542756602168083,
      "learning_rate": 0.0002617896674513632,
      "loss": 0.0002,
      "step": 240
    },
    {
      "epoch": 0.4090812645873117,
      "grad_norm": 0.0031418628059327602,
      "learning_rate": 0.00026147172382160914,
      "loss": 0.0001,
      "step": 241
    },
    {
      "epoch": 0.41077869722045407,
      "grad_norm": 0.11094752699136734,
      "learning_rate": 0.00026115265767283374,
      "loss": 0.0031,
      "step": 242
    },
    {
      "epoch": 0.41247612985359644,
      "grad_norm": 0.012769564054906368,
      "learning_rate": 0.0002608324722180296,
      "loss": 0.0005,
      "step": 243
    },
    {
      "epoch": 0.4141735624867388,
      "grad_norm": 0.055052801966667175,
      "learning_rate": 0.0002605111706814607,
      "loss": 0.0023,
      "step": 244
    },
    {
      "epoch": 0.4158709951198812,
      "grad_norm": 0.003668338293209672,
      "learning_rate": 0.00026018875629862996,
      "loss": 0.0002,
      "step": 245
    },
    {
      "epoch": 0.41756842775302355,
      "grad_norm": 0.009973675012588501,
      "learning_rate": 0.0002598652323162466,
      "loss": 0.0003,
      "step": 246
    },
    {
      "epoch": 0.4192658603861659,
      "grad_norm": 0.02005830593407154,
      "learning_rate": 0.0002595406019921936,
      "loss": 0.0008,
      "step": 247
    },
    {
      "epoch": 0.4209632930193083,
      "grad_norm": 0.02860446274280548,
      "learning_rate": 0.0002592148685954946,
      "loss": 0.0024,
      "step": 248
    },
    {
      "epoch": 0.42266072565245066,
      "grad_norm": 0.03582284599542618,
      "learning_rate": 0.0002588880354062814,
      "loss": 0.0014,
      "step": 249
    },
    {
      "epoch": 0.42435815828559303,
      "grad_norm": 0.03657930716872215,
      "learning_rate": 0.0002585601057157605,
      "loss": 0.0023,
      "step": 250
    },
    {
      "epoch": 0.42435815828559303,
      "eval_loss": 0.39342138171195984,
      "eval_runtime": 65.6277,
      "eval_samples_per_second": 2.941,
      "eval_steps_per_second": 2.941,
      "step": 250
    },
    {
      "epoch": 0.4260555909187354,
      "grad_norm": 0.3402771055698395,
      "learning_rate": 0.0002582310828261803,
      "loss": 0.955,
      "step": 251
    },
    {
      "epoch": 0.4277530235518778,
      "grad_norm": 0.2694092392921448,
      "learning_rate": 0.00025790097005079764,
      "loss": 0.7843,
      "step": 252
    },
    {
      "epoch": 0.42945045618502015,
      "grad_norm": 0.22484031319618225,
      "learning_rate": 0.00025756977071384455,
      "loss": 0.6626,
      "step": 253
    },
    {
      "epoch": 0.4311478888181625,
      "grad_norm": 0.25034627318382263,
      "learning_rate": 0.0002572374881504945,
      "loss": 0.8865,
      "step": 254
    },
    {
      "epoch": 0.4328453214513049,
      "grad_norm": 0.25369909405708313,
      "learning_rate": 0.00025690412570682946,
      "loss": 0.7099,
      "step": 255
    },
    {
      "epoch": 0.43454275408444726,
      "grad_norm": 0.22795934975147247,
      "learning_rate": 0.0002565696867398053,
      "loss": 0.7818,
      "step": 256
    },
    {
      "epoch": 0.43624018671758963,
      "grad_norm": 0.2158069759607315,
      "learning_rate": 0.00025623417461721884,
      "loss": 0.6434,
      "step": 257
    },
    {
      "epoch": 0.437937619350732,
      "grad_norm": 0.2332068681716919,
      "learning_rate": 0.00025589759271767344,
      "loss": 0.8126,
      "step": 258
    },
    {
      "epoch": 0.43963505198387437,
      "grad_norm": 0.21993213891983032,
      "learning_rate": 0.00025555994443054504,
      "loss": 0.6689,
      "step": 259
    },
    {
      "epoch": 0.44133248461701674,
      "grad_norm": 0.26037323474884033,
      "learning_rate": 0.0002552212331559482,
      "loss": 0.992,
      "step": 260
    },
    {
      "epoch": 0.4430299172501591,
      "grad_norm": 0.2357717603445053,
      "learning_rate": 0.00025488146230470156,
      "loss": 0.7212,
      "step": 261
    },
    {
      "epoch": 0.4447273498833015,
      "grad_norm": 0.22752051055431366,
      "learning_rate": 0.00025454063529829405,
      "loss": 0.7759,
      "step": 262
    },
    {
      "epoch": 0.44642478251644385,
      "grad_norm": 0.20641978085041046,
      "learning_rate": 0.0002541987555688496,
      "loss": 0.6029,
      "step": 263
    },
    {
      "epoch": 0.4481222151495863,
      "grad_norm": 1.728589415550232,
      "learning_rate": 0.0002538558265590934,
      "loss": 0.8527,
      "step": 264
    },
    {
      "epoch": 0.44981964778272865,
      "grad_norm": 0.3176920711994171,
      "learning_rate": 0.0002535118517223168,
      "loss": 1.0045,
      "step": 265
    },
    {
      "epoch": 0.451517080415871,
      "grad_norm": 0.22813205420970917,
      "learning_rate": 0.00025316683452234254,
      "loss": 0.5755,
      "step": 266
    },
    {
      "epoch": 0.4532145130490134,
      "grad_norm": 0.27417638897895813,
      "learning_rate": 0.00025282077843349,
      "loss": 0.6442,
      "step": 267
    },
    {
      "epoch": 0.45491194568215576,
      "grad_norm": 0.23180553317070007,
      "learning_rate": 0.00025247368694054017,
      "loss": 0.3961,
      "step": 268
    },
    {
      "epoch": 0.45660937831529813,
      "grad_norm": 0.21716707944869995,
      "learning_rate": 0.0002521255635387005,
      "loss": 0.5498,
      "step": 269
    },
    {
      "epoch": 0.4583068109484405,
      "grad_norm": 0.1608789563179016,
      "learning_rate": 0.0002517764117335698,
      "loss": 0.3229,
      "step": 270
    },
    {
      "epoch": 0.4600042435815829,
      "grad_norm": 0.06968680769205093,
      "learning_rate": 0.00025142623504110286,
      "loss": 0.0545,
      "step": 271
    },
    {
      "epoch": 0.46170167621472524,
      "grad_norm": 0.17753787338733673,
      "learning_rate": 0.0002510750369875752,
      "loss": 0.3944,
      "step": 272
    },
    {
      "epoch": 0.4633991088478676,
      "grad_norm": 0.1846492886543274,
      "learning_rate": 0.0002507228211095471,
      "loss": 0.4219,
      "step": 273
    },
    {
      "epoch": 0.46509654148101,
      "grad_norm": 0.12200163304805756,
      "learning_rate": 0.0002503695909538287,
      "loss": 0.1832,
      "step": 274
    },
    {
      "epoch": 0.46679397411415235,
      "grad_norm": 0.08617426455020905,
      "learning_rate": 0.00025001535007744373,
      "loss": 0.0833,
      "step": 275
    },
    {
      "epoch": 0.4684914067472947,
      "grad_norm": 0.10826346278190613,
      "learning_rate": 0.0002496601020475938,
      "loss": 0.1379,
      "step": 276
    },
    {
      "epoch": 0.4701888393804371,
      "grad_norm": 0.09130895137786865,
      "learning_rate": 0.00024930385044162276,
      "loss": 0.0909,
      "step": 277
    },
    {
      "epoch": 0.47188627201357947,
      "grad_norm": 0.01284122746437788,
      "learning_rate": 0.0002489465988469802,
      "loss": 0.0011,
      "step": 278
    },
    {
      "epoch": 0.47358370464672184,
      "grad_norm": 0.03364328294992447,
      "learning_rate": 0.0002485883508611858,
      "loss": 0.0151,
      "step": 279
    },
    {
      "epoch": 0.4752811372798642,
      "grad_norm": 0.005700011737644672,
      "learning_rate": 0.00024822911009179276,
      "loss": 0.0004,
      "step": 280
    },
    {
      "epoch": 0.4769785699130066,
      "grad_norm": 0.026785628870129585,
      "learning_rate": 0.0002478688801563516,
      "loss": 0.0022,
      "step": 281
    },
    {
      "epoch": 0.47867600254614895,
      "grad_norm": 0.014533424749970436,
      "learning_rate": 0.00024750766468237387,
      "loss": 0.0009,
      "step": 282
    },
    {
      "epoch": 0.4803734351792913,
      "grad_norm": 0.02565724588930607,
      "learning_rate": 0.0002471454673072953,
      "loss": 0.0015,
      "step": 283
    },
    {
      "epoch": 0.4820708678124337,
      "grad_norm": 0.01476586889475584,
      "learning_rate": 0.0002467822916784394,
      "loss": 0.0007,
      "step": 284
    },
    {
      "epoch": 0.48376830044557606,
      "grad_norm": 0.0030139784794300795,
      "learning_rate": 0.0002464181414529809,
      "loss": 0.0001,
      "step": 285
    },
    {
      "epoch": 0.48546573307871843,
      "grad_norm": 0.013711950741708279,
      "learning_rate": 0.00024605302029790836,
      "loss": 0.0002,
      "step": 286
    },
    {
      "epoch": 0.4871631657118608,
      "grad_norm": 0.0045742918737232685,
      "learning_rate": 0.00024568693188998776,
      "loss": 0.0002,
      "step": 287
    },
    {
      "epoch": 0.48886059834500317,
      "grad_norm": 0.01617550477385521,
      "learning_rate": 0.00024531987991572543,
      "loss": 0.0008,
      "step": 288
    },
    {
      "epoch": 0.49055803097814554,
      "grad_norm": 0.0015017741825431585,
      "learning_rate": 0.00024495186807133056,
      "loss": 0.0001,
      "step": 289
    },
    {
      "epoch": 0.4922554636112879,
      "grad_norm": 0.04141293093562126,
      "learning_rate": 0.00024458290006267833,
      "loss": 0.0021,
      "step": 290
    },
    {
      "epoch": 0.4939528962444303,
      "grad_norm": 0.03005625680088997,
      "learning_rate": 0.0002442129796052726,
      "loss": 0.0015,
      "step": 291
    },
    {
      "epoch": 0.49565032887757265,
      "grad_norm": 0.0004941977094858885,
      "learning_rate": 0.00024384211042420822,
      "loss": 0.0,
      "step": 292
    },
    {
      "epoch": 0.497347761510715,
      "grad_norm": 0.0018400073749944568,
      "learning_rate": 0.00024347029625413364,
      "loss": 0.0001,
      "step": 293
    },
    {
      "epoch": 0.4990451941438574,
      "grad_norm": 0.023964567109942436,
      "learning_rate": 0.00024309754083921354,
      "loss": 0.0008,
      "step": 294
    },
    {
      "epoch": 0.5007426267769998,
      "grad_norm": 0.00808011181652546,
      "learning_rate": 0.00024272384793309077,
      "loss": 0.0003,
      "step": 295
    },
    {
      "epoch": 0.5024400594101421,
      "grad_norm": 0.026506319642066956,
      "learning_rate": 0.0002423492212988487,
      "loss": 0.0011,
      "step": 296
    },
    {
      "epoch": 0.5041374920432845,
      "grad_norm": 0.0033183887135237455,
      "learning_rate": 0.0002419736647089735,
      "loss": 0.0001,
      "step": 297
    },
    {
      "epoch": 0.5058349246764269,
      "grad_norm": 0.0012288711732253432,
      "learning_rate": 0.00024159718194531572,
      "loss": 0.0001,
      "step": 298
    },
    {
      "epoch": 0.5075323573095692,
      "grad_norm": 0.001825229381211102,
      "learning_rate": 0.00024121977679905266,
      "loss": 0.0001,
      "step": 299
    },
    {
      "epoch": 0.5092297899427116,
      "grad_norm": 0.0013848728267475963,
      "learning_rate": 0.00024084145307064997,
      "loss": 0.0001,
      "step": 300
    },
    {
      "epoch": 0.5092297899427116,
      "eval_loss": 0.408105731010437,
      "eval_runtime": 65.5854,
      "eval_samples_per_second": 2.943,
      "eval_steps_per_second": 2.943,
      "step": 300
    },
    {
      "epoch": 0.510927222575854,
      "grad_norm": 0.6500065922737122,
      "learning_rate": 0.0002404622145698234,
      "loss": 1.2109,
      "step": 301
    },
    {
      "epoch": 0.5126246552089964,
      "grad_norm": 0.2953287661075592,
      "learning_rate": 0.00024008206511550044,
      "loss": 0.8961,
      "step": 302
    },
    {
      "epoch": 0.5143220878421387,
      "grad_norm": 0.2599642276763916,
      "learning_rate": 0.00023970100853578185,
      "loss": 0.822,
      "step": 303
    },
    {
      "epoch": 0.5160195204752811,
      "grad_norm": 0.22075462341308594,
      "learning_rate": 0.00023931904866790317,
      "loss": 0.7042,
      "step": 304
    },
    {
      "epoch": 0.5177169531084235,
      "grad_norm": 0.1947249174118042,
      "learning_rate": 0.00023893618935819607,
      "loss": 0.6038,
      "step": 305
    },
    {
      "epoch": 0.5194143857415658,
      "grad_norm": 0.1981605589389801,
      "learning_rate": 0.00023855243446204946,
      "loss": 0.5842,
      "step": 306
    },
    {
      "epoch": 0.5211118183747082,
      "grad_norm": 0.25752243399620056,
      "learning_rate": 0.00023816778784387094,
      "loss": 0.7636,
      "step": 307
    },
    {
      "epoch": 0.5228092510078506,
      "grad_norm": 0.20701764523983002,
      "learning_rate": 0.00023778225337704772,
      "loss": 0.5711,
      "step": 308
    },
    {
      "epoch": 0.524506683640993,
      "grad_norm": 0.1890690177679062,
      "learning_rate": 0.00023739583494390752,
      "loss": 0.5323,
      "step": 309
    },
    {
      "epoch": 0.5262041162741353,
      "grad_norm": 0.2634682059288025,
      "learning_rate": 0.0002370085364356797,
      "loss": 0.8929,
      "step": 310
    },
    {
      "epoch": 0.5279015489072777,
      "grad_norm": 0.21140585839748383,
      "learning_rate": 0.00023662036175245595,
      "loss": 0.6722,
      "step": 311
    },
    {
      "epoch": 0.5295989815404201,
      "grad_norm": 0.1461462825536728,
      "learning_rate": 0.00023623131480315107,
      "loss": 0.3355,
      "step": 312
    },
    {
      "epoch": 0.5312964141735624,
      "grad_norm": 0.25913017988204956,
      "learning_rate": 0.00023584139950546344,
      "loss": 0.809,
      "step": 313
    },
    {
      "epoch": 0.5329938468067048,
      "grad_norm": 0.20216749608516693,
      "learning_rate": 0.0002354506197858358,
      "loss": 0.522,
      "step": 314
    },
    {
      "epoch": 0.5346912794398472,
      "grad_norm": 0.19447529315948486,
      "learning_rate": 0.00023505897957941556,
      "loss": 0.4756,
      "step": 315
    },
    {
      "epoch": 0.5363887120729895,
      "grad_norm": 0.20887967944145203,
      "learning_rate": 0.00023466648283001538,
      "loss": 0.5348,
      "step": 316
    },
    {
      "epoch": 0.538086144706132,
      "grad_norm": 0.2380082756280899,
      "learning_rate": 0.000234273133490073,
      "loss": 0.6786,
      "step": 317
    },
    {
      "epoch": 0.5397835773392744,
      "grad_norm": 0.13057811558246613,
      "learning_rate": 0.00023387893552061199,
      "loss": 0.2262,
      "step": 318
    },
    {
      "epoch": 0.5414810099724168,
      "grad_norm": 0.19371569156646729,
      "learning_rate": 0.00023348389289120158,
      "loss": 0.4282,
      "step": 319
    },
    {
      "epoch": 0.5431784426055591,
      "grad_norm": 0.20126739144325256,
      "learning_rate": 0.00023308800957991653,
      "loss": 0.4524,
      "step": 320
    },
    {
      "epoch": 0.5448758752387015,
      "grad_norm": 0.1577330082654953,
      "learning_rate": 0.00023269128957329748,
      "loss": 0.2979,
      "step": 321
    },
    {
      "epoch": 0.5465733078718439,
      "grad_norm": 0.1581580936908722,
      "learning_rate": 0.0002322937368663105,
      "loss": 0.2393,
      "step": 322
    },
    {
      "epoch": 0.5482707405049863,
      "grad_norm": 0.0836775079369545,
      "learning_rate": 0.00023189535546230683,
      "loss": 0.0756,
      "step": 323
    },
    {
      "epoch": 0.5499681731381286,
      "grad_norm": 0.13577239215373993,
      "learning_rate": 0.00023149614937298296,
      "loss": 0.204,
      "step": 324
    },
    {
      "epoch": 0.551665605771271,
      "grad_norm": 0.003654525149613619,
      "learning_rate": 0.00023109612261833963,
      "loss": 0.0001,
      "step": 325
    },
    {
      "epoch": 0.5533630384044134,
      "grad_norm": 0.0016976917395368218,
      "learning_rate": 0.00023069527922664186,
      "loss": 0.0001,
      "step": 326
    },
    {
      "epoch": 0.5550604710375557,
      "grad_norm": 0.006387701723724604,
      "learning_rate": 0.00023029362323437818,
      "loss": 0.0002,
      "step": 327
    },
    {
      "epoch": 0.5567579036706981,
      "grad_norm": 0.0010255499510094523,
      "learning_rate": 0.00022989115868621995,
      "loss": 0.0001,
      "step": 328
    },
    {
      "epoch": 0.5584553363038405,
      "grad_norm": 0.002511462429538369,
      "learning_rate": 0.0002294878896349807,
      "loss": 0.0001,
      "step": 329
    },
    {
      "epoch": 0.5601527689369828,
      "grad_norm": 0.002243687631562352,
      "learning_rate": 0.00022908382014157533,
      "loss": 0.0001,
      "step": 330
    },
    {
      "epoch": 0.5618502015701252,
      "grad_norm": 0.0010394121054559946,
      "learning_rate": 0.00022867895427497914,
      "loss": 0.0,
      "step": 331
    },
    {
      "epoch": 0.5635476342032676,
      "grad_norm": 0.004921845626085997,
      "learning_rate": 0.00022827329611218688,
      "loss": 0.0002,
      "step": 332
    },
    {
      "epoch": 0.56524506683641,
      "grad_norm": 0.006571977864950895,
      "learning_rate": 0.0002278668497381718,
      "loss": 0.0003,
      "step": 333
    },
    {
      "epoch": 0.5669424994695523,
      "grad_norm": 0.06410548835992813,
      "learning_rate": 0.00022745961924584428,
      "loss": 0.0393,
      "step": 334
    },
    {
      "epoch": 0.5686399321026947,
      "grad_norm": 0.0016587848076596856,
      "learning_rate": 0.00022705160873601096,
      "loss": 0.0001,
      "step": 335
    },
    {
      "epoch": 0.5703373647358371,
      "grad_norm": 0.002642609179019928,
      "learning_rate": 0.00022664282231733309,
      "loss": 0.0001,
      "step": 336
    },
    {
      "epoch": 0.5720347973689794,
      "grad_norm": 0.09959813952445984,
      "learning_rate": 0.00022623326410628534,
      "loss": 0.0009,
      "step": 337
    },
    {
      "epoch": 0.5737322300021218,
      "grad_norm": 0.0017017674399539828,
      "learning_rate": 0.00022582293822711444,
      "loss": 0.0001,
      "step": 338
    },
    {
      "epoch": 0.5754296626352642,
      "grad_norm": 0.0015052666421979666,
      "learning_rate": 0.00022541184881179737,
      "loss": 0.0001,
      "step": 339
    },
    {
      "epoch": 0.5771270952684066,
      "grad_norm": 0.0034250568132847548,
      "learning_rate": 0.000225,
      "loss": 0.0001,
      "step": 340
    },
    {
      "epoch": 0.5788245279015489,
      "grad_norm": 0.004533613566309214,
      "learning_rate": 0.0002245873959390353,
      "loss": 0.0001,
      "step": 341
    },
    {
      "epoch": 0.5805219605346913,
      "grad_norm": 0.0014232480898499489,
      "learning_rate": 0.00022417404078382152,
      "loss": 0.0001,
      "step": 342
    },
    {
      "epoch": 0.5822193931678337,
      "grad_norm": 0.0018840961856767535,
      "learning_rate": 0.00022375993869684058,
      "loss": 0.0,
      "step": 343
    },
    {
      "epoch": 0.583916825800976,
      "grad_norm": 0.0005610976368188858,
      "learning_rate": 0.00022334509384809584,
      "loss": 0.0,
      "step": 344
    },
    {
      "epoch": 0.5856142584341184,
      "grad_norm": 0.011308716610074043,
      "learning_rate": 0.00022292951041507028,
      "loss": 0.0003,
      "step": 345
    },
    {
      "epoch": 0.5873116910672608,
      "grad_norm": 0.008396640419960022,
      "learning_rate": 0.00022251319258268453,
      "loss": 0.0001,
      "step": 346
    },
    {
      "epoch": 0.5890091237004031,
      "grad_norm": 0.016598394140601158,
      "learning_rate": 0.00022209614454325459,
      "loss": 0.0002,
      "step": 347
    },
    {
      "epoch": 0.5907065563335455,
      "grad_norm": 0.0011634851107373834,
      "learning_rate": 0.00022167837049644947,
      "loss": 0.0,
      "step": 348
    },
    {
      "epoch": 0.5924039889666879,
      "grad_norm": 0.05063653737306595,
      "learning_rate": 0.00022125987464924926,
      "loss": 0.0006,
      "step": 349
    },
    {
      "epoch": 0.5941014215998303,
      "grad_norm": 0.030548613518476486,
      "learning_rate": 0.0002208406612159024,
      "loss": 0.0005,
      "step": 350
    },
    {
      "epoch": 0.5941014215998303,
      "eval_loss": 0.403373122215271,
      "eval_runtime": 65.5747,
      "eval_samples_per_second": 2.943,
      "eval_steps_per_second": 2.943,
      "step": 350
    },
    {
      "epoch": 0.5957988542329726,
      "grad_norm": 0.4255245625972748,
      "learning_rate": 0.00022042073441788358,
      "loss": 1.1602,
      "step": 351
    },
    {
      "epoch": 0.597496286866115,
      "grad_norm": 1.3056901693344116,
      "learning_rate": 0.00022000009848385105,
      "loss": 0.9796,
      "step": 352
    },
    {
      "epoch": 0.5991937194992574,
      "grad_norm": 0.21184608340263367,
      "learning_rate": 0.0002195787576496039,
      "loss": 0.6262,
      "step": 353
    },
    {
      "epoch": 0.6008911521323997,
      "grad_norm": 0.24157075583934784,
      "learning_rate": 0.00021915671615803966,
      "loss": 0.8544,
      "step": 354
    },
    {
      "epoch": 0.6025885847655421,
      "grad_norm": 0.20036348700523376,
      "learning_rate": 0.00021873397825911153,
      "loss": 0.6267,
      "step": 355
    },
    {
      "epoch": 0.6042860173986845,
      "grad_norm": 0.20190277695655823,
      "learning_rate": 0.00021831054820978544,
      "loss": 0.6421,
      "step": 356
    },
    {
      "epoch": 0.6059834500318269,
      "grad_norm": 0.2218364179134369,
      "learning_rate": 0.00021788643027399724,
      "loss": 0.7318,
      "step": 357
    },
    {
      "epoch": 0.6076808826649692,
      "grad_norm": 0.2376060038805008,
      "learning_rate": 0.00021746162872260985,
      "loss": 0.8077,
      "step": 358
    },
    {
      "epoch": 0.6093783152981116,
      "grad_norm": 0.19997930526733398,
      "learning_rate": 0.0002170361478333702,
      "loss": 0.6109,
      "step": 359
    },
    {
      "epoch": 0.611075747931254,
      "grad_norm": 0.25473812222480774,
      "learning_rate": 0.0002166099918908661,
      "loss": 0.7628,
      "step": 360
    },
    {
      "epoch": 0.6127731805643963,
      "grad_norm": 0.16967284679412842,
      "learning_rate": 0.00021618316518648317,
      "loss": 0.3639,
      "step": 361
    },
    {
      "epoch": 0.6144706131975387,
      "grad_norm": 0.2045927196741104,
      "learning_rate": 0.0002157556720183616,
      "loss": 0.5688,
      "step": 362
    },
    {
      "epoch": 0.6161680458306811,
      "grad_norm": 0.30063769221305847,
      "learning_rate": 0.00021532751669135284,
      "loss": 0.8787,
      "step": 363
    },
    {
      "epoch": 0.6178654784638234,
      "grad_norm": 0.22912342846393585,
      "learning_rate": 0.00021489870351697622,
      "loss": 0.5724,
      "step": 364
    },
    {
      "epoch": 0.6195629110969658,
      "grad_norm": 0.1712283343076706,
      "learning_rate": 0.00021446923681337575,
      "loss": 0.3771,
      "step": 365
    },
    {
      "epoch": 0.6212603437301082,
      "grad_norm": 0.22983159124851227,
      "learning_rate": 0.00021403912090527623,
      "loss": 0.6274,
      "step": 366
    },
    {
      "epoch": 0.6229577763632506,
      "grad_norm": 0.2075144350528717,
      "learning_rate": 0.00021360836012394025,
      "loss": 0.5276,
      "step": 367
    },
    {
      "epoch": 0.6246552089963929,
      "grad_norm": 0.1731417328119278,
      "learning_rate": 0.00021317695880712398,
      "loss": 0.314,
      "step": 368
    },
    {
      "epoch": 0.6263526416295353,
      "grad_norm": 0.1949385702610016,
      "learning_rate": 0.0002127449212990339,
      "loss": 0.4633,
      "step": 369
    },
    {
      "epoch": 0.6280500742626777,
      "grad_norm": 0.20679379999637604,
      "learning_rate": 0.00021231225195028297,
      "loss": 0.4547,
      "step": 370
    },
    {
      "epoch": 0.62974750689582,
      "grad_norm": 0.1853644698858261,
      "learning_rate": 0.00021187895511784666,
      "loss": 0.3758,
      "step": 371
    },
    {
      "epoch": 0.6314449395289624,
      "grad_norm": 0.2339005470275879,
      "learning_rate": 0.00021144503516501927,
      "loss": 0.4251,
      "step": 372
    },
    {
      "epoch": 0.6331423721621048,
      "grad_norm": 0.12531976401805878,
      "learning_rate": 0.00021101049646137003,
      "loss": 0.1716,
      "step": 373
    },
    {
      "epoch": 0.6348398047952472,
      "grad_norm": 0.12999360263347626,
      "learning_rate": 0.00021057534338269872,
      "loss": 0.2032,
      "step": 374
    },
    {
      "epoch": 0.6365372374283895,
      "grad_norm": 0.1318761557340622,
      "learning_rate": 0.00021013958031099205,
      "loss": 0.1968,
      "step": 375
    },
    {
      "epoch": 0.6382346700615319,
      "grad_norm": 0.06346186250448227,
      "learning_rate": 0.00020970321163437934,
      "loss": 0.05,
      "step": 376
    },
    {
      "epoch": 0.6399321026946743,
      "grad_norm": 0.12222940474748611,
      "learning_rate": 0.00020926624174708827,
      "loss": 0.1675,
      "step": 377
    },
    {
      "epoch": 0.6416295353278166,
      "grad_norm": 0.12370602786540985,
      "learning_rate": 0.0002088286750494008,
      "loss": 0.0724,
      "step": 378
    },
    {
      "epoch": 0.643326967960959,
      "grad_norm": 0.0037796611431986094,
      "learning_rate": 0.00020839051594760872,
      "loss": 0.0002,
      "step": 379
    },
    {
      "epoch": 0.6450244005941014,
      "grad_norm": 0.08905645459890366,
      "learning_rate": 0.00020795176885396926,
      "loss": 0.0305,
      "step": 380
    },
    {
      "epoch": 0.6467218332272437,
      "grad_norm": 0.11877533793449402,
      "learning_rate": 0.00020751243818666087,
      "loss": 0.1818,
      "step": 381
    },
    {
      "epoch": 0.6484192658603861,
      "grad_norm": 0.0044077117927372456,
      "learning_rate": 0.00020707252836973844,
      "loss": 0.0001,
      "step": 382
    },
    {
      "epoch": 0.6501166984935285,
      "grad_norm": 0.0014336027670651674,
      "learning_rate": 0.00020663204383308898,
      "loss": 0.0001,
      "step": 383
    },
    {
      "epoch": 0.6518141311266709,
      "grad_norm": 0.025872627273201942,
      "learning_rate": 0.0002061909890123868,
      "loss": 0.0031,
      "step": 384
    },
    {
      "epoch": 0.6535115637598132,
      "grad_norm": 0.007007645908743143,
      "learning_rate": 0.0002057493683490491,
      "loss": 0.0002,
      "step": 385
    },
    {
      "epoch": 0.6552089963929556,
      "grad_norm": 0.01107161957770586,
      "learning_rate": 0.0002053071862901911,
      "loss": 0.0003,
      "step": 386
    },
    {
      "epoch": 0.6569064290260981,
      "grad_norm": 0.014977892860770226,
      "learning_rate": 0.00020486444728858117,
      "loss": 0.0003,
      "step": 387
    },
    {
      "epoch": 0.6586038616592405,
      "grad_norm": 0.011495725251734257,
      "learning_rate": 0.00020442115580259613,
      "loss": 0.0002,
      "step": 388
    },
    {
      "epoch": 0.6603012942923828,
      "grad_norm": 0.0011856303317472339,
      "learning_rate": 0.00020397731629617636,
      "loss": 0.0001,
      "step": 389
    },
    {
      "epoch": 0.6619987269255252,
      "grad_norm": 0.000914178614038974,
      "learning_rate": 0.00020353293323878074,
      "loss": 0.0,
      "step": 390
    },
    {
      "epoch": 0.6636961595586676,
      "grad_norm": 0.01322512049227953,
      "learning_rate": 0.00020308801110534178,
      "loss": 0.0003,
      "step": 391
    },
    {
      "epoch": 0.6653935921918099,
      "grad_norm": 0.07302884012460709,
      "learning_rate": 0.00020264255437622036,
      "loss": 0.0008,
      "step": 392
    },
    {
      "epoch": 0.6670910248249523,
      "grad_norm": 0.002658440498635173,
      "learning_rate": 0.00020219656753716074,
      "loss": 0.0001,
      "step": 393
    },
    {
      "epoch": 0.6687884574580947,
      "grad_norm": 0.0038816186133772135,
      "learning_rate": 0.00020175005507924558,
      "loss": 0.0001,
      "step": 394
    },
    {
      "epoch": 0.670485890091237,
      "grad_norm": 0.0019201135728508234,
      "learning_rate": 0.00020130302149885031,
      "loss": 0.0,
      "step": 395
    },
    {
      "epoch": 0.6721833227243794,
      "grad_norm": 0.005636914633214474,
      "learning_rate": 0.00020085547129759806,
      "loss": 0.0002,
      "step": 396
    },
    {
      "epoch": 0.6738807553575218,
      "grad_norm": 0.003746110713109374,
      "learning_rate": 0.00020040740898231448,
      "loss": 0.0001,
      "step": 397
    },
    {
      "epoch": 0.6755781879906642,
      "grad_norm": 0.004497275687754154,
      "learning_rate": 0.0001999588390649821,
      "loss": 0.0001,
      "step": 398
    },
    {
      "epoch": 0.6772756206238065,
      "grad_norm": 0.004322202410548925,
      "learning_rate": 0.00019950976606269497,
      "loss": 0.0001,
      "step": 399
    },
    {
      "epoch": 0.6789730532569489,
      "grad_norm": 0.025630857795476913,
      "learning_rate": 0.00019906019449761325,
      "loss": 0.0003,
      "step": 400
    },
    {
      "epoch": 0.6789730532569489,
      "eval_loss": 0.3837679922580719,
      "eval_runtime": 65.6798,
      "eval_samples_per_second": 2.938,
      "eval_steps_per_second": 2.938,
      "step": 400
    },
    {
      "epoch": 0.6806704858900913,
      "grad_norm": 0.23363079130649567,
      "learning_rate": 0.00019861012889691755,
      "loss": 0.6918,
      "step": 401
    },
    {
      "epoch": 0.6823679185232336,
      "grad_norm": 0.2805746793746948,
      "learning_rate": 0.0001981595737927636,
      "loss": 0.8612,
      "step": 402
    },
    {
      "epoch": 0.684065351156376,
      "grad_norm": 0.2095121443271637,
      "learning_rate": 0.00019770853372223625,
      "loss": 0.5805,
      "step": 403
    },
    {
      "epoch": 0.6857627837895184,
      "grad_norm": 0.23234990239143372,
      "learning_rate": 0.0001972570132273039,
      "loss": 0.7755,
      "step": 404
    },
    {
      "epoch": 0.6874602164226608,
      "grad_norm": 0.23639503121376038,
      "learning_rate": 0.00019680501685477304,
      "loss": 0.8386,
      "step": 405
    },
    {
      "epoch": 0.6891576490558031,
      "grad_norm": 0.21290989220142365,
      "learning_rate": 0.0001963525491562421,
      "loss": 0.6506,
      "step": 406
    },
    {
      "epoch": 0.6908550816889455,
      "grad_norm": 0.19381728768348694,
      "learning_rate": 0.00019589961468805578,
      "loss": 0.5448,
      "step": 407
    },
    {
      "epoch": 0.6925525143220879,
      "grad_norm": 0.3582805395126343,
      "learning_rate": 0.00019544621801125908,
      "loss": 1.0269,
      "step": 408
    },
    {
      "epoch": 0.6942499469552302,
      "grad_norm": 0.24776633083820343,
      "learning_rate": 0.00019499236369155157,
      "loss": 0.8699,
      "step": 409
    },
    {
      "epoch": 0.6959473795883726,
      "grad_norm": 0.24224227666854858,
      "learning_rate": 0.00019453805629924124,
      "loss": 0.8062,
      "step": 410
    },
    {
      "epoch": 0.697644812221515,
      "grad_norm": 0.20559021830558777,
      "learning_rate": 0.0001940833004091984,
      "loss": 0.5474,
      "step": 411
    },
    {
      "epoch": 0.6993422448546573,
      "grad_norm": 0.27351394295692444,
      "learning_rate": 0.00019362810060080985,
      "loss": 0.7381,
      "step": 412
    },
    {
      "epoch": 0.7010396774877997,
      "grad_norm": 0.22222575545310974,
      "learning_rate": 0.00019317246145793263,
      "loss": 0.6845,
      "step": 413
    },
    {
      "epoch": 0.7027371101209421,
      "grad_norm": 0.24615706503391266,
      "learning_rate": 0.00019271638756884784,
      "loss": 0.8067,
      "step": 414
    },
    {
      "epoch": 0.7044345427540845,
      "grad_norm": 0.18379613757133484,
      "learning_rate": 0.00019225988352621445,
      "loss": 0.4555,
      "step": 415
    },
    {
      "epoch": 0.7061319753872268,
      "grad_norm": 0.22946029901504517,
      "learning_rate": 0.00019180295392702315,
      "loss": 0.6708,
      "step": 416
    },
    {
      "epoch": 0.7078294080203692,
      "grad_norm": 0.2477787286043167,
      "learning_rate": 0.00019134560337254986,
      "loss": 0.749,
      "step": 417
    },
    {
      "epoch": 0.7095268406535116,
      "grad_norm": 0.15241138637065887,
      "learning_rate": 0.00019088783646830967,
      "loss": 0.2924,
      "step": 418
    },
    {
      "epoch": 0.7112242732866539,
      "grad_norm": 0.12446551769971848,
      "learning_rate": 0.00019042965782401018,
      "loss": 0.1693,
      "step": 419
    },
    {
      "epoch": 0.7129217059197963,
      "grad_norm": 0.18220585584640503,
      "learning_rate": 0.0001899710720535052,
      "loss": 0.4431,
      "step": 420
    },
    {
      "epoch": 0.7146191385529387,
      "grad_norm": 0.17593543231487274,
      "learning_rate": 0.00018951208377474847,
      "loss": 0.3987,
      "step": 421
    },
    {
      "epoch": 0.716316571186081,
      "grad_norm": 0.1010337546467781,
      "learning_rate": 0.0001890526976097468,
      "loss": 0.1318,
      "step": 422
    },
    {
      "epoch": 0.7180140038192234,
      "grad_norm": 0.13775108754634857,
      "learning_rate": 0.00018859291818451373,
      "loss": 0.2565,
      "step": 423
    },
    {
      "epoch": 0.7197114364523658,
      "grad_norm": 0.23579080402851105,
      "learning_rate": 0.00018813275012902306,
      "loss": 0.5919,
      "step": 424
    },
    {
      "epoch": 0.7214088690855082,
      "grad_norm": 0.13805098831653595,
      "learning_rate": 0.00018767219807716185,
      "loss": 0.2562,
      "step": 425
    },
    {
      "epoch": 0.7231063017186505,
      "grad_norm": 0.11531147360801697,
      "learning_rate": 0.00018721126666668432,
      "loss": 0.1649,
      "step": 426
    },
    {
      "epoch": 0.7248037343517929,
      "grad_norm": 0.09808983653783798,
      "learning_rate": 0.00018674996053916456,
      "loss": 0.1384,
      "step": 427
    },
    {
      "epoch": 0.7265011669849353,
      "grad_norm": 0.004477047827094793,
      "learning_rate": 0.00018628828433995013,
      "loss": 0.0002,
      "step": 428
    },
    {
      "epoch": 0.7281985996180776,
      "grad_norm": 0.11150182038545609,
      "learning_rate": 0.00018582624271811532,
      "loss": 0.0681,
      "step": 429
    },
    {
      "epoch": 0.72989603225122,
      "grad_norm": 0.005313314031809568,
      "learning_rate": 0.0001853638403264141,
      "loss": 0.0002,
      "step": 430
    },
    {
      "epoch": 0.7315934648843624,
      "grad_norm": 0.05417265370488167,
      "learning_rate": 0.00018490108182123334,
      "loss": 0.0018,
      "step": 431
    },
    {
      "epoch": 0.7332908975175048,
      "grad_norm": 0.03447933495044708,
      "learning_rate": 0.00018443797186254614,
      "loss": 0.0021,
      "step": 432
    },
    {
      "epoch": 0.7349883301506471,
      "grad_norm": 0.0018511873204261065,
      "learning_rate": 0.00018397451511386467,
      "loss": 0.0001,
      "step": 433
    },
    {
      "epoch": 0.7366857627837895,
      "grad_norm": 0.0019058893667533994,
      "learning_rate": 0.00018351071624219311,
      "loss": 0.0001,
      "step": 434
    },
    {
      "epoch": 0.7383831954169319,
      "grad_norm": 0.006601972505450249,
      "learning_rate": 0.0001830465799179811,
      "loss": 0.0003,
      "step": 435
    },
    {
      "epoch": 0.7400806280500742,
      "grad_norm": 0.011643564328551292,
      "learning_rate": 0.00018258211081507614,
      "loss": 0.0004,
      "step": 436
    },
    {
      "epoch": 0.7417780606832166,
      "grad_norm": 0.004530356731265783,
      "learning_rate": 0.00018211731361067706,
      "loss": 0.0002,
      "step": 437
    },
    {
      "epoch": 0.743475493316359,
      "grad_norm": 0.0015783226117491722,
      "learning_rate": 0.00018165219298528647,
      "loss": 0.0001,
      "step": 438
    },
    {
      "epoch": 0.7451729259495014,
      "grad_norm": 0.03880147635936737,
      "learning_rate": 0.00018118675362266385,
      "loss": 0.0011,
      "step": 439
    },
    {
      "epoch": 0.7468703585826437,
      "grad_norm": 0.04943560063838959,
      "learning_rate": 0.0001807210002097786,
      "loss": 0.0045,
      "step": 440
    },
    {
      "epoch": 0.7485677912157861,
      "grad_norm": 0.009896587580442429,
      "learning_rate": 0.0001802549374367623,
      "loss": 0.0005,
      "step": 441
    },
    {
      "epoch": 0.7502652238489285,
      "grad_norm": 0.009237539954483509,
      "learning_rate": 0.0001797885699968618,
      "loss": 0.0004,
      "step": 442
    },
    {
      "epoch": 0.7519626564820708,
      "grad_norm": 0.005970139987766743,
      "learning_rate": 0.0001793219025863922,
      "loss": 0.0001,
      "step": 443
    },
    {
      "epoch": 0.7536600891152132,
      "grad_norm": 0.0007102653034962714,
      "learning_rate": 0.00017885493990468915,
      "loss": 0.0,
      "step": 444
    },
    {
      "epoch": 0.7553575217483556,
      "grad_norm": 0.0005071276100352407,
      "learning_rate": 0.0001783876866540615,
      "loss": 0.0,
      "step": 445
    },
    {
      "epoch": 0.757054954381498,
      "grad_norm": 0.0011907740263268352,
      "learning_rate": 0.0001779201475397445,
      "loss": 0.0001,
      "step": 446
    },
    {
      "epoch": 0.7587523870146403,
      "grad_norm": 0.0038478299975395203,
      "learning_rate": 0.00017745232726985166,
      "loss": 0.0002,
      "step": 447
    },
    {
      "epoch": 0.7604498196477827,
      "grad_norm": 0.008054184727370739,
      "learning_rate": 0.00017698423055532807,
      "loss": 0.0002,
      "step": 448
    },
    {
      "epoch": 0.7621472522809251,
      "grad_norm": 0.0007232764619402587,
      "learning_rate": 0.00017651586210990232,
      "loss": 0.0,
      "step": 449
    },
    {
      "epoch": 0.7638446849140674,
      "grad_norm": 0.0009626049431972206,
      "learning_rate": 0.00017604722665003956,
      "loss": 0.0001,
      "step": 450
    },
    {
      "epoch": 0.7638446849140674,
      "eval_loss": 0.38282719254493713,
      "eval_runtime": 65.9216,
      "eval_samples_per_second": 2.928,
      "eval_steps_per_second": 2.928,
      "step": 450
    },
    {
      "epoch": 0.7655421175472098,
      "grad_norm": 0.35101303458213806,
      "learning_rate": 0.00017557832889489357,
      "loss": 1.093,
      "step": 451
    },
    {
      "epoch": 0.7672395501803522,
      "grad_norm": 0.23341582715511322,
      "learning_rate": 0.0001751091735662596,
      "loss": 0.7267,
      "step": 452
    },
    {
      "epoch": 0.7689369828134945,
      "grad_norm": 0.25353920459747314,
      "learning_rate": 0.00017463976538852654,
      "loss": 0.8581,
      "step": 453
    },
    {
      "epoch": 0.7706344154466369,
      "grad_norm": 0.21722197532653809,
      "learning_rate": 0.00017417010908862962,
      "loss": 0.7378,
      "step": 454
    },
    {
      "epoch": 0.7723318480797793,
      "grad_norm": 0.22062261402606964,
      "learning_rate": 0.00017370020939600248,
      "loss": 0.7099,
      "step": 455
    },
    {
      "epoch": 0.7740292807129217,
      "grad_norm": 0.1780662089586258,
      "learning_rate": 0.00017323007104252984,
      "loss": 0.4919,
      "step": 456
    },
    {
      "epoch": 0.775726713346064,
      "grad_norm": 0.20236726105213165,
      "learning_rate": 0.00017275969876249974,
      "loss": 0.5919,
      "step": 457
    },
    {
      "epoch": 0.7774241459792065,
      "grad_norm": 0.22523203492164612,
      "learning_rate": 0.00017228909729255574,
      "loss": 0.7686,
      "step": 458
    },
    {
      "epoch": 0.7791215786123489,
      "grad_norm": 0.23676562309265137,
      "learning_rate": 0.00017181827137164953,
      "loss": 0.8026,
      "step": 459
    },
    {
      "epoch": 0.7808190112454912,
      "grad_norm": 0.21583965420722961,
      "learning_rate": 0.00017134722574099276,
      "loss": 0.7097,
      "step": 460
    },
    {
      "epoch": 0.7825164438786336,
      "grad_norm": 0.2776244282722473,
      "learning_rate": 0.0001708759651440098,
      "loss": 0.9476,
      "step": 461
    },
    {
      "epoch": 0.784213876511776,
      "grad_norm": 0.2028312236070633,
      "learning_rate": 0.00017040449432628962,
      "loss": 0.6013,
      "step": 462
    },
    {
      "epoch": 0.7859113091449184,
      "grad_norm": 0.2275046855211258,
      "learning_rate": 0.0001699328180355381,
      "loss": 0.7551,
      "step": 463
    },
    {
      "epoch": 0.7876087417780607,
      "grad_norm": 0.20202623307704926,
      "learning_rate": 0.00016946094102153025,
      "loss": 0.4759,
      "step": 464
    },
    {
      "epoch": 0.7893061744112031,
      "grad_norm": 0.17477299273014069,
      "learning_rate": 0.00016898886803606237,
      "loss": 0.4537,
      "step": 465
    },
    {
      "epoch": 0.7910036070443455,
      "grad_norm": 0.08333531022071838,
      "learning_rate": 0.0001685166038329042,
      "loss": 0.1224,
      "step": 466
    },
    {
      "epoch": 0.7927010396774878,
      "grad_norm": 0.21820639073848724,
      "learning_rate": 0.000168044153167751,
      "loss": 0.5658,
      "step": 467
    },
    {
      "epoch": 0.7943984723106302,
      "grad_norm": 0.14012931287288666,
      "learning_rate": 0.00016757152079817573,
      "loss": 0.2818,
      "step": 468
    },
    {
      "epoch": 0.7960959049437726,
      "grad_norm": 0.1741451919078827,
      "learning_rate": 0.00016709871148358108,
      "loss": 0.3492,
      "step": 469
    },
    {
      "epoch": 0.797793337576915,
      "grad_norm": 0.1527792066335678,
      "learning_rate": 0.00016662572998515164,
      "loss": 0.2187,
      "step": 470
    },
    {
      "epoch": 0.7994907702100573,
      "grad_norm": 0.1383330523967743,
      "learning_rate": 0.00016615258106580585,
      "loss": 0.2405,
      "step": 471
    },
    {
      "epoch": 0.8011882028431997,
      "grad_norm": 0.13245010375976562,
      "learning_rate": 0.000165679269490148,
      "loss": 0.2295,
      "step": 472
    },
    {
      "epoch": 0.8028856354763421,
      "grad_norm": 0.13676372170448303,
      "learning_rate": 0.0001652058000244205,
      "loss": 0.2516,
      "step": 473
    },
    {
      "epoch": 0.8045830681094844,
      "grad_norm": 0.07976588606834412,
      "learning_rate": 0.00016473217743645556,
      "loss": 0.0916,
      "step": 474
    },
    {
      "epoch": 0.8062805007426268,
      "grad_norm": 0.11341172456741333,
      "learning_rate": 0.00016425840649562736,
      "loss": 0.152,
      "step": 475
    },
    {
      "epoch": 0.8079779333757692,
      "grad_norm": 0.12954847514629364,
      "learning_rate": 0.00016378449197280412,
      "loss": 0.1525,
      "step": 476
    },
    {
      "epoch": 0.8096753660089115,
      "grad_norm": 0.08243954181671143,
      "learning_rate": 0.0001633104386402997,
      "loss": 0.0708,
      "step": 477
    },
    {
      "epoch": 0.8113727986420539,
      "grad_norm": 0.0030563257168978453,
      "learning_rate": 0.00016283625127182596,
      "loss": 0.0001,
      "step": 478
    },
    {
      "epoch": 0.8130702312751963,
      "grad_norm": 0.0008315025479532778,
      "learning_rate": 0.00016236193464244444,
      "loss": 0.0,
      "step": 479
    },
    {
      "epoch": 0.8147676639083387,
      "grad_norm": 0.006789859849959612,
      "learning_rate": 0.00016188749352851825,
      "loss": 0.0002,
      "step": 480
    },
    {
      "epoch": 0.816465096541481,
      "grad_norm": 0.009863720275461674,
      "learning_rate": 0.00016141293270766424,
      "loss": 0.0002,
      "step": 481
    },
    {
      "epoch": 0.8181625291746234,
      "grad_norm": 0.059226732701063156,
      "learning_rate": 0.00016093825695870462,
      "loss": 0.0008,
      "step": 482
    },
    {
      "epoch": 0.8198599618077658,
      "grad_norm": 0.0056890202686190605,
      "learning_rate": 0.00016046347106161876,
      "loss": 0.0003,
      "step": 483
    },
    {
      "epoch": 0.8215573944409081,
      "grad_norm": 0.0004136976203881204,
      "learning_rate": 0.0001599885797974956,
      "loss": 0.0,
      "step": 484
    },
    {
      "epoch": 0.8232548270740505,
      "grad_norm": 0.016998767852783203,
      "learning_rate": 0.00015951358794848465,
      "loss": 0.0004,
      "step": 485
    },
    {
      "epoch": 0.8249522597071929,
      "grad_norm": 0.0017255417769774795,
      "learning_rate": 0.00015903850029774878,
      "loss": 0.0001,
      "step": 486
    },
    {
      "epoch": 0.8266496923403353,
      "grad_norm": 0.0012270875740796328,
      "learning_rate": 0.0001585633216294152,
      "loss": 0.0001,
      "step": 487
    },
    {
      "epoch": 0.8283471249734776,
      "grad_norm": 0.0009051132365129888,
      "learning_rate": 0.0001580880567285279,
      "loss": 0.0,
      "step": 488
    },
    {
      "epoch": 0.83004455760662,
      "grad_norm": 0.0009166182717308402,
      "learning_rate": 0.00015761271038099912,
      "loss": 0.0001,
      "step": 489
    },
    {
      "epoch": 0.8317419902397624,
      "grad_norm": 0.002149962354451418,
      "learning_rate": 0.00015713728737356137,
      "loss": 0.0001,
      "step": 490
    },
    {
      "epoch": 0.8334394228729047,
      "grad_norm": 0.008419407531619072,
      "learning_rate": 0.00015666179249371892,
      "loss": 0.0004,
      "step": 491
    },
    {
      "epoch": 0.8351368555060471,
      "grad_norm": 0.0006536226137541234,
      "learning_rate": 0.00015618623052970006,
      "loss": 0.0,
      "step": 492
    },
    {
      "epoch": 0.8368342881391895,
      "grad_norm": 0.035275768488645554,
      "learning_rate": 0.0001557106062704085,
      "loss": 0.0064,
      "step": 493
    },
    {
      "epoch": 0.8385317207723318,
      "grad_norm": 0.002518226159736514,
      "learning_rate": 0.00015523492450537517,
      "loss": 0.0001,
      "step": 494
    },
    {
      "epoch": 0.8402291534054742,
      "grad_norm": 0.00048825182602740824,
      "learning_rate": 0.00015475919002471016,
      "loss": 0.0,
      "step": 495
    },
    {
      "epoch": 0.8419265860386166,
      "grad_norm": 0.007141390815377235,
      "learning_rate": 0.0001542834076190544,
      "loss": 0.0001,
      "step": 496
    },
    {
      "epoch": 0.843624018671759,
      "grad_norm": 0.048018842935562134,
      "learning_rate": 0.00015380758207953155,
      "loss": 0.0004,
      "step": 497
    },
    {
      "epoch": 0.8453214513049013,
      "grad_norm": 0.0009412519866600633,
      "learning_rate": 0.0001533317181976994,
      "loss": 0.0,
      "step": 498
    },
    {
      "epoch": 0.8470188839380437,
      "grad_norm": 0.031883303076028824,
      "learning_rate": 0.00015285582076550198,
      "loss": 0.0037,
      "step": 499
    },
    {
      "epoch": 0.8487163165711861,
      "grad_norm": 0.016174526885151863,
      "learning_rate": 0.00015237989457522118,
      "loss": 0.0007,
      "step": 500
    },
    {
      "epoch": 0.8487163165711861,
      "eval_loss": 0.372147798538208,
      "eval_runtime": 65.9897,
      "eval_samples_per_second": 2.925,
      "eval_steps_per_second": 2.925,
      "step": 500
    },
    {
      "epoch": 0.8504137492043284,
      "grad_norm": 0.23917846381664276,
      "learning_rate": 0.00015190394441942843,
      "loss": 0.8684,
      "step": 501
    },
    {
      "epoch": 0.8521111818374708,
      "grad_norm": 0.27708154916763306,
      "learning_rate": 0.0001514279750909365,
      "loss": 1.0004,
      "step": 502
    },
    {
      "epoch": 0.8538086144706132,
      "grad_norm": 0.25657930970191956,
      "learning_rate": 0.00015095199138275128,
      "loss": 0.7568,
      "step": 503
    },
    {
      "epoch": 0.8555060471037556,
      "grad_norm": 0.2313452512025833,
      "learning_rate": 0.00015047599808802332,
      "loss": 0.8288,
      "step": 504
    },
    {
      "epoch": 0.8572034797368979,
      "grad_norm": 0.2528156042098999,
      "learning_rate": 0.00015,
      "loss": 1.011,
      "step": 505
    },
    {
      "epoch": 0.8589009123700403,
      "grad_norm": 0.1938907355070114,
      "learning_rate": 0.00014952400191197665,
      "loss": 0.5598,
      "step": 506
    },
    {
      "epoch": 0.8605983450031827,
      "grad_norm": 0.23120371997356415,
      "learning_rate": 0.00014904800861724872,
      "loss": 0.6959,
      "step": 507
    },
    {
      "epoch": 0.862295777636325,
      "grad_norm": 0.23072639107704163,
      "learning_rate": 0.00014857202490906347,
      "loss": 0.7868,
      "step": 508
    },
    {
      "epoch": 0.8639932102694674,
      "grad_norm": 0.21651454269886017,
      "learning_rate": 0.00014809605558057157,
      "loss": 0.6725,
      "step": 509
    },
    {
      "epoch": 0.8656906429026098,
      "grad_norm": 0.1905306875705719,
      "learning_rate": 0.0001476201054247788,
      "loss": 0.5756,
      "step": 510
    },
    {
      "epoch": 0.8673880755357521,
      "grad_norm": 0.35889434814453125,
      "learning_rate": 0.00014714417923449797,
      "loss": 0.6115,
      "step": 511
    },
    {
      "epoch": 0.8690855081688945,
      "grad_norm": 0.19174250960350037,
      "learning_rate": 0.00014666828180230057,
      "loss": 0.4859,
      "step": 512
    },
    {
      "epoch": 0.8707829408020369,
      "grad_norm": 0.2138870805501938,
      "learning_rate": 0.0001461924179204684,
      "loss": 0.6636,
      "step": 513
    },
    {
      "epoch": 0.8724803734351793,
      "grad_norm": 0.17262116074562073,
      "learning_rate": 0.00014571659238094556,
      "loss": 0.42,
      "step": 514
    },
    {
      "epoch": 0.8741778060683216,
      "grad_norm": 0.22339358925819397,
      "learning_rate": 0.00014524080997528987,
      "loss": 0.6612,
      "step": 515
    },
    {
      "epoch": 0.875875238701464,
      "grad_norm": 0.1979471892118454,
      "learning_rate": 0.0001447650754946249,
      "loss": 0.5441,
      "step": 516
    },
    {
      "epoch": 0.8775726713346064,
      "grad_norm": 0.20259279012680054,
      "learning_rate": 0.00014428939372959152,
      "loss": 0.5254,
      "step": 517
    },
    {
      "epoch": 0.8792701039677487,
      "grad_norm": 0.12251409888267517,
      "learning_rate": 0.0001438137694702999,
      "loss": 0.2171,
      "step": 518
    },
    {
      "epoch": 0.8809675366008911,
      "grad_norm": 0.16714578866958618,
      "learning_rate": 0.00014333820750628105,
      "loss": 0.311,
      "step": 519
    },
    {
      "epoch": 0.8826649692340335,
      "grad_norm": 0.24203087389469147,
      "learning_rate": 0.00014286271262643866,
      "loss": 0.6175,
      "step": 520
    },
    {
      "epoch": 0.8843624018671759,
      "grad_norm": 0.1858789026737213,
      "learning_rate": 0.00014238728961900088,
      "loss": 0.3565,
      "step": 521
    },
    {
      "epoch": 0.8860598345003182,
      "grad_norm": 0.09111540019512177,
      "learning_rate": 0.00014191194327147212,
      "loss": 0.1199,
      "step": 522
    },
    {
      "epoch": 0.8877572671334606,
      "grad_norm": 0.13533198833465576,
      "learning_rate": 0.00014143667837058477,
      "loss": 0.2471,
      "step": 523
    },
    {
      "epoch": 0.889454699766603,
      "grad_norm": 0.17338241636753082,
      "learning_rate": 0.00014096149970225122,
      "loss": 0.3255,
      "step": 524
    },
    {
      "epoch": 0.8911521323997453,
      "grad_norm": 0.05573137849569321,
      "learning_rate": 0.00014048641205151533,
      "loss": 0.0455,
      "step": 525
    },
    {
      "epoch": 0.8928495650328877,
      "grad_norm": 0.007357200141996145,
      "learning_rate": 0.0001400114202025044,
      "loss": 0.0004,
      "step": 526
    },
    {
      "epoch": 0.8945469976660301,
      "grad_norm": 0.00043303659185767174,
      "learning_rate": 0.00013953652893838119,
      "loss": 0.0,
      "step": 527
    },
    {
      "epoch": 0.8962444302991726,
      "grad_norm": 0.02541971206665039,
      "learning_rate": 0.0001390617430412954,
      "loss": 0.0028,
      "step": 528
    },
    {
      "epoch": 0.8979418629323149,
      "grad_norm": 0.010525004006922245,
      "learning_rate": 0.0001385870672923357,
      "loss": 0.0005,
      "step": 529
    },
    {
      "epoch": 0.8996392955654573,
      "grad_norm": 0.03903070092201233,
      "learning_rate": 0.0001381125064714817,
      "loss": 0.0003,
      "step": 530
    },
    {
      "epoch": 0.9013367281985997,
      "grad_norm": 0.010076366364955902,
      "learning_rate": 0.00013763806535755562,
      "loss": 0.0002,
      "step": 531
    },
    {
      "epoch": 0.903034160831742,
      "grad_norm": 0.0008758578333072364,
      "learning_rate": 0.00013716374872817407,
      "loss": 0.0,
      "step": 532
    },
    {
      "epoch": 0.9047315934648844,
      "grad_norm": 0.0009034467511810362,
      "learning_rate": 0.0001366895613597003,
      "loss": 0.0,
      "step": 533
    },
    {
      "epoch": 0.9064290260980268,
      "grad_norm": 0.0004988125874660909,
      "learning_rate": 0.00013621550802719588,
      "loss": 0.0,
      "step": 534
    },
    {
      "epoch": 0.9081264587311692,
      "grad_norm": 0.012061301618814468,
      "learning_rate": 0.00013574159350437261,
      "loss": 0.0006,
      "step": 535
    },
    {
      "epoch": 0.9098238913643115,
      "grad_norm": 0.0005069606122560799,
      "learning_rate": 0.0001352678225635444,
      "loss": 0.0,
      "step": 536
    },
    {
      "epoch": 0.9115213239974539,
      "grad_norm": 0.003097748151049018,
      "learning_rate": 0.00013479419997557948,
      "loss": 0.0001,
      "step": 537
    },
    {
      "epoch": 0.9132187566305963,
      "grad_norm": 0.010489325039088726,
      "learning_rate": 0.000134320730509852,
      "loss": 0.0002,
      "step": 538
    },
    {
      "epoch": 0.9149161892637386,
      "grad_norm": 0.00030282657826319337,
      "learning_rate": 0.00013384741893419415,
      "loss": 0.0,
      "step": 539
    },
    {
      "epoch": 0.916613621896881,
      "grad_norm": 0.0403389073908329,
      "learning_rate": 0.00013337427001484836,
      "loss": 0.0005,
      "step": 540
    },
    {
      "epoch": 0.9183110545300234,
      "grad_norm": 0.003200069535523653,
      "learning_rate": 0.0001329012885164189,
      "loss": 0.0001,
      "step": 541
    },
    {
      "epoch": 0.9200084871631657,
      "grad_norm": 0.007805091328918934,
      "learning_rate": 0.00013242847920182424,
      "loss": 0.0002,
      "step": 542
    },
    {
      "epoch": 0.9217059197963081,
      "grad_norm": 0.004255454055964947,
      "learning_rate": 0.000131955846832249,
      "loss": 0.0001,
      "step": 543
    },
    {
      "epoch": 0.9234033524294505,
      "grad_norm": 0.0008626742055639625,
      "learning_rate": 0.00013148339616709577,
      "loss": 0.0,
      "step": 544
    },
    {
      "epoch": 0.9251007850625929,
      "grad_norm": 0.005825830157846212,
      "learning_rate": 0.00013101113196393758,
      "loss": 0.0002,
      "step": 545
    },
    {
      "epoch": 0.9267982176957352,
      "grad_norm": 0.00038926751585677266,
      "learning_rate": 0.00013053905897846972,
      "loss": 0.0,
      "step": 546
    },
    {
      "epoch": 0.9284956503288776,
      "grad_norm": 0.025748664513230324,
      "learning_rate": 0.00013006718196446188,
      "loss": 0.0007,
      "step": 547
    },
    {
      "epoch": 0.93019308296202,
      "grad_norm": 0.000722411903552711,
      "learning_rate": 0.0001295955056737104,
      "loss": 0.0,
      "step": 548
    },
    {
      "epoch": 0.9318905155951623,
      "grad_norm": 0.013827555812895298,
      "learning_rate": 0.0001291240348559902,
      "loss": 0.0003,
      "step": 549
    },
    {
      "epoch": 0.9335879482283047,
      "grad_norm": 0.0006142717902548611,
      "learning_rate": 0.00012865277425900724,
      "loss": 0.0,
      "step": 550
    },
    {
      "epoch": 0.9335879482283047,
      "eval_loss": 0.37203362584114075,
      "eval_runtime": 65.9103,
      "eval_samples_per_second": 2.928,
      "eval_steps_per_second": 2.928,
      "step": 550
    },
    {
      "epoch": 0.9352853808614471,
      "grad_norm": 0.28680503368377686,
      "learning_rate": 0.0001281817286283505,
      "loss": 0.9974,
      "step": 551
    },
    {
      "epoch": 0.9369828134945895,
      "grad_norm": 0.21847711503505707,
      "learning_rate": 0.00012771090270744426,
      "loss": 0.5843,
      "step": 552
    },
    {
      "epoch": 0.9386802461277318,
      "grad_norm": 0.21124739944934845,
      "learning_rate": 0.00012724030123750026,
      "loss": 0.7508,
      "step": 553
    },
    {
      "epoch": 0.9403776787608742,
      "grad_norm": 0.26063379645347595,
      "learning_rate": 0.00012676992895747016,
      "loss": 1.0164,
      "step": 554
    },
    {
      "epoch": 0.9420751113940166,
      "grad_norm": 0.22532792389392853,
      "learning_rate": 0.0001262997906039975,
      "loss": 0.7664,
      "step": 555
    },
    {
      "epoch": 0.9437725440271589,
      "grad_norm": 0.233880877494812,
      "learning_rate": 0.00012582989091137038,
      "loss": 0.7483,
      "step": 556
    },
    {
      "epoch": 0.9454699766603013,
      "grad_norm": 0.20552365481853485,
      "learning_rate": 0.00012536023461147346,
      "loss": 0.6613,
      "step": 557
    },
    {
      "epoch": 0.9471674092934437,
      "grad_norm": 0.20067091286182404,
      "learning_rate": 0.0001248908264337404,
      "loss": 0.5999,
      "step": 558
    },
    {
      "epoch": 0.948864841926586,
      "grad_norm": 0.19979502260684967,
      "learning_rate": 0.00012442167110510643,
      "loss": 0.5804,
      "step": 559
    },
    {
      "epoch": 0.9505622745597284,
      "grad_norm": 1.8899680376052856,
      "learning_rate": 0.00012395277334996044,
      "loss": 1.2513,
      "step": 560
    },
    {
      "epoch": 0.9522597071928708,
      "grad_norm": 1.1816651821136475,
      "learning_rate": 0.0001234841378900976,
      "loss": 0.5431,
      "step": 561
    },
    {
      "epoch": 0.9539571398260132,
      "grad_norm": 0.7981509566307068,
      "learning_rate": 0.0001230157694446719,
      "loss": 0.4656,
      "step": 562
    },
    {
      "epoch": 0.9556545724591555,
      "grad_norm": 0.15804308652877808,
      "learning_rate": 0.00012254767273014828,
      "loss": 0.3057,
      "step": 563
    },
    {
      "epoch": 0.9573520050922979,
      "grad_norm": 0.25787147879600525,
      "learning_rate": 0.00012207985246025547,
      "loss": 0.5838,
      "step": 564
    },
    {
      "epoch": 0.9590494377254403,
      "grad_norm": 0.2439812868833542,
      "learning_rate": 0.00012161231334593851,
      "loss": 0.4171,
      "step": 565
    },
    {
      "epoch": 0.9607468703585826,
      "grad_norm": 0.2657896876335144,
      "learning_rate": 0.0001211450600953109,
      "loss": 0.4894,
      "step": 566
    },
    {
      "epoch": 0.962444302991725,
      "grad_norm": 0.19345270097255707,
      "learning_rate": 0.00012067809741360779,
      "loss": 0.4258,
      "step": 567
    },
    {
      "epoch": 0.9641417356248674,
      "grad_norm": 0.2370881736278534,
      "learning_rate": 0.0001202114300031382,
      "loss": 0.5128,
      "step": 568
    },
    {
      "epoch": 0.9658391682580098,
      "grad_norm": 0.15387995541095734,
      "learning_rate": 0.00011974506256323775,
      "loss": 0.3073,
      "step": 569
    },
    {
      "epoch": 0.9675366008911521,
      "grad_norm": 0.12014123052358627,
      "learning_rate": 0.0001192789997902214,
      "loss": 0.1645,
      "step": 570
    },
    {
      "epoch": 0.9692340335242945,
      "grad_norm": 0.07062285393476486,
      "learning_rate": 0.00011881324637733611,
      "loss": 0.057,
      "step": 571
    },
    {
      "epoch": 0.9709314661574369,
      "grad_norm": 0.017441993579268456,
      "learning_rate": 0.00011834780701471354,
      "loss": 0.0017,
      "step": 572
    },
    {
      "epoch": 0.9726288987905792,
      "grad_norm": 0.09837821871042252,
      "learning_rate": 0.00011788268638932295,
      "loss": 0.0769,
      "step": 573
    },
    {
      "epoch": 0.9743263314237216,
      "grad_norm": 0.006846334785223007,
      "learning_rate": 0.00011741788918492386,
      "loss": 0.0002,
      "step": 574
    },
    {
      "epoch": 0.976023764056864,
      "grad_norm": 0.07346488535404205,
      "learning_rate": 0.00011695342008201888,
      "loss": 0.0527,
      "step": 575
    },
    {
      "epoch": 0.9777211966900063,
      "grad_norm": 0.022366201505064964,
      "learning_rate": 0.00011648928375780686,
      "loss": 0.0002,
      "step": 576
    },
    {
      "epoch": 0.9794186293231487,
      "grad_norm": 0.02840852551162243,
      "learning_rate": 0.00011602548488613531,
      "loss": 0.0024,
      "step": 577
    },
    {
      "epoch": 0.9811160619562911,
      "grad_norm": 0.004534956067800522,
      "learning_rate": 0.00011556202813745382,
      "loss": 0.0002,
      "step": 578
    },
    {
      "epoch": 0.9828134945894335,
      "grad_norm": 0.023318735882639885,
      "learning_rate": 0.00011509891817876662,
      "loss": 0.0048,
      "step": 579
    },
    {
      "epoch": 0.9845109272225758,
      "grad_norm": 0.003532181493937969,
      "learning_rate": 0.00011463615967358588,
      "loss": 0.0002,
      "step": 580
    },
    {
      "epoch": 0.9862083598557182,
      "grad_norm": 0.004218058194965124,
      "learning_rate": 0.00011417375728188464,
      "loss": 0.0002,
      "step": 581
    },
    {
      "epoch": 0.9879057924888606,
      "grad_norm": 0.036903224885463715,
      "learning_rate": 0.00011371171566004985,
      "loss": 0.0045,
      "step": 582
    },
    {
      "epoch": 0.9896032251220029,
      "grad_norm": 0.0010676698293536901,
      "learning_rate": 0.00011325003946083548,
      "loss": 0.0001,
      "step": 583
    },
    {
      "epoch": 0.9913006577551453,
      "grad_norm": 0.0011252000695094466,
      "learning_rate": 0.00011278873333331572,
      "loss": 0.0001,
      "step": 584
    },
    {
      "epoch": 0.9929980903882877,
      "grad_norm": 0.015459141694009304,
      "learning_rate": 0.00011232780192283812,
      "loss": 0.0005,
      "step": 585
    },
    {
      "epoch": 0.99469552302143,
      "grad_norm": 0.0027658988256007433,
      "learning_rate": 0.00011186724987097698,
      "loss": 0.0002,
      "step": 586
    },
    {
      "epoch": 0.9963929556545724,
      "grad_norm": 0.0068977042101323605,
      "learning_rate": 0.00011140708181548628,
      "loss": 0.0003,
      "step": 587
    },
    {
      "epoch": 0.9980903882877148,
      "grad_norm": 0.024217281490564346,
      "learning_rate": 0.00011094730239025318,
      "loss": 0.0007,
      "step": 588
    },
    {
      "epoch": 0.9997878209208572,
      "grad_norm": 0.1039547249674797,
      "learning_rate": 0.0001104879162252515,
      "loss": 0.0096,
      "step": 589
    },
    {
      "epoch": 1.0014852535539995,
      "grad_norm": 0.5956621170043945,
      "learning_rate": 0.00011002892794649476,
      "loss": 0.918,
      "step": 590
    },
    {
      "epoch": 1.003182686187142,
      "grad_norm": 0.28132206201553345,
      "learning_rate": 0.00010957034217598982,
      "loss": 0.5421,
      "step": 591
    },
    {
      "epoch": 1.0048801188202843,
      "grad_norm": 0.29155442118644714,
      "learning_rate": 0.00010911216353169033,
      "loss": 0.7092,
      "step": 592
    },
    {
      "epoch": 1.0065775514534268,
      "grad_norm": 0.20578022301197052,
      "learning_rate": 0.00010865439662745013,
      "loss": 0.4683,
      "step": 593
    },
    {
      "epoch": 1.008274984086569,
      "grad_norm": 0.21167628467082977,
      "learning_rate": 0.00010819704607297685,
      "loss": 0.4827,
      "step": 594
    },
    {
      "epoch": 1.0099724167197115,
      "grad_norm": 0.23780500888824463,
      "learning_rate": 0.00010774011647378553,
      "loss": 0.506,
      "step": 595
    },
    {
      "epoch": 1.0116698493528538,
      "grad_norm": 0.34926292300224304,
      "learning_rate": 0.00010728361243115215,
      "loss": 0.654,
      "step": 596
    },
    {
      "epoch": 1.0133672819859962,
      "grad_norm": 0.29102039337158203,
      "learning_rate": 0.00010682753854206733,
      "loss": 0.5844,
      "step": 597
    },
    {
      "epoch": 1.0150647146191385,
      "grad_norm": 0.23482352495193481,
      "learning_rate": 0.00010637189939919014,
      "loss": 0.4841,
      "step": 598
    },
    {
      "epoch": 1.016762147252281,
      "grad_norm": 0.25120899081230164,
      "learning_rate": 0.00010591669959080162,
      "loss": 0.5328,
      "step": 599
    },
    {
      "epoch": 1.0184595798854232,
      "grad_norm": 0.26982659101486206,
      "learning_rate": 0.00010546194370075881,
      "loss": 0.6439,
      "step": 600
    },
    {
      "epoch": 1.0184595798854232,
      "eval_loss": 0.3681555986404419,
      "eval_runtime": 65.873,
      "eval_samples_per_second": 2.93,
      "eval_steps_per_second": 2.93,
      "step": 600
    },
    {
      "epoch": 1.0201570125185657,
      "grad_norm": 0.24521693587303162,
      "learning_rate": 0.00010500763630844842,
      "loss": 0.471,
      "step": 601
    },
    {
      "epoch": 1.021854445151708,
      "grad_norm": 0.24358759820461273,
      "learning_rate": 0.00010455378198874092,
      "loss": 0.5164,
      "step": 602
    },
    {
      "epoch": 1.0235518777848505,
      "grad_norm": 0.25223568081855774,
      "learning_rate": 0.00010410038531194427,
      "loss": 0.5172,
      "step": 603
    },
    {
      "epoch": 1.0252493104179927,
      "grad_norm": 0.2088579535484314,
      "learning_rate": 0.0001036474508437579,
      "loss": 0.3021,
      "step": 604
    },
    {
      "epoch": 1.0269467430511352,
      "grad_norm": 0.24515843391418457,
      "learning_rate": 0.00010319498314522693,
      "loss": 0.5318,
      "step": 605
    },
    {
      "epoch": 1.0286441756842775,
      "grad_norm": 0.21473954617977142,
      "learning_rate": 0.0001027429867726961,
      "loss": 0.3774,
      "step": 606
    },
    {
      "epoch": 1.03034160831742,
      "grad_norm": 0.15975739061832428,
      "learning_rate": 0.00010229146627776376,
      "loss": 0.2362,
      "step": 607
    },
    {
      "epoch": 1.0320390409505622,
      "grad_norm": 0.11923979967832565,
      "learning_rate": 0.00010184042620723637,
      "loss": 0.1048,
      "step": 608
    },
    {
      "epoch": 1.0337364735837047,
      "grad_norm": 0.28334590792655945,
      "learning_rate": 0.00010138987110308241,
      "loss": 0.5413,
      "step": 609
    },
    {
      "epoch": 1.035433906216847,
      "grad_norm": 0.15508587658405304,
      "learning_rate": 0.00010093980550238675,
      "loss": 0.1701,
      "step": 610
    },
    {
      "epoch": 1.0371313388499894,
      "grad_norm": 0.16336044669151306,
      "learning_rate": 0.00010049023393730502,
      "loss": 0.2,
      "step": 611
    },
    {
      "epoch": 1.0388287714831317,
      "grad_norm": 0.15937276184558868,
      "learning_rate": 0.00010004116093501789,
      "loss": 0.2001,
      "step": 612
    },
    {
      "epoch": 1.0405262041162742,
      "grad_norm": 0.16733552515506744,
      "learning_rate": 9.959259101768545e-05,
      "loss": 0.2056,
      "step": 613
    },
    {
      "epoch": 1.0422236367494164,
      "grad_norm": 0.16601236164569855,
      "learning_rate": 9.914452870240188e-05,
      "loss": 0.1972,
      "step": 614
    },
    {
      "epoch": 1.043921069382559,
      "grad_norm": 0.16554437577724457,
      "learning_rate": 9.869697850114969e-05,
      "loss": 0.1963,
      "step": 615
    },
    {
      "epoch": 1.0456185020157012,
      "grad_norm": 0.08596237003803253,
      "learning_rate": 9.824994492075444e-05,
      "loss": 0.0567,
      "step": 616
    },
    {
      "epoch": 1.0473159346488436,
      "grad_norm": 0.0006779459654353559,
      "learning_rate": 9.780343246283923e-05,
      "loss": 0.0,
      "step": 617
    },
    {
      "epoch": 1.049013367281986,
      "grad_norm": 0.00339099601842463,
      "learning_rate": 9.735744562377968e-05,
      "loss": 0.0001,
      "step": 618
    },
    {
      "epoch": 1.0507107999151284,
      "grad_norm": 0.09683417528867722,
      "learning_rate": 9.691198889465824e-05,
      "loss": 0.0579,
      "step": 619
    },
    {
      "epoch": 1.0524082325482707,
      "grad_norm": 0.003139798529446125,
      "learning_rate": 9.646706676121923e-05,
      "loss": 0.0001,
      "step": 620
    },
    {
      "epoch": 1.0541056651814131,
      "grad_norm": 0.01017076801508665,
      "learning_rate": 9.602268370382363e-05,
      "loss": 0.0004,
      "step": 621
    },
    {
      "epoch": 1.0558030978145554,
      "grad_norm": 0.0703444853425026,
      "learning_rate": 9.557884419740386e-05,
      "loss": 0.0398,
      "step": 622
    },
    {
      "epoch": 1.0575005304476979,
      "grad_norm": 0.002169876592233777,
      "learning_rate": 9.513555271141882e-05,
      "loss": 0.0001,
      "step": 623
    },
    {
      "epoch": 1.0591979630808401,
      "grad_norm": 0.00480187963694334,
      "learning_rate": 9.46928137098089e-05,
      "loss": 0.0001,
      "step": 624
    },
    {
      "epoch": 1.0608953957139826,
      "grad_norm": 0.0012345153372734785,
      "learning_rate": 9.425063165095088e-05,
      "loss": 0.0,
      "step": 625
    },
    {
      "epoch": 1.0625928283471249,
      "grad_norm": 0.0015107739018276334,
      "learning_rate": 9.380901098761319e-05,
      "loss": 0.0001,
      "step": 626
    },
    {
      "epoch": 1.0642902609802674,
      "grad_norm": 0.00046349604963324964,
      "learning_rate": 9.336795616691103e-05,
      "loss": 0.0,
      "step": 627
    },
    {
      "epoch": 1.0659876936134096,
      "grad_norm": 0.023465273901820183,
      "learning_rate": 9.292747163026154e-05,
      "loss": 0.0007,
      "step": 628
    },
    {
      "epoch": 1.067685126246552,
      "grad_norm": 0.0014659131411463022,
      "learning_rate": 9.24875618133391e-05,
      "loss": 0.0,
      "step": 629
    },
    {
      "epoch": 1.0693825588796946,
      "grad_norm": 0.0005259321187622845,
      "learning_rate": 9.204823114603068e-05,
      "loss": 0.0,
      "step": 630
    },
    {
      "epoch": 1.0710799915128368,
      "grad_norm": 0.018575303256511688,
      "learning_rate": 9.160948405239128e-05,
      "loss": 0.0007,
      "step": 631
    },
    {
      "epoch": 1.072777424145979,
      "grad_norm": 0.026870638132095337,
      "learning_rate": 9.117132495059916e-05,
      "loss": 0.0008,
      "step": 632
    },
    {
      "epoch": 1.0744748567791216,
      "grad_norm": 0.0007909996784292161,
      "learning_rate": 9.07337582529117e-05,
      "loss": 0.0,
      "step": 633
    },
    {
      "epoch": 1.076172289412264,
      "grad_norm": 0.000697901239618659,
      "learning_rate": 9.02967883656207e-05,
      "loss": 0.0,
      "step": 634
    },
    {
      "epoch": 1.0778697220454063,
      "grad_norm": 0.0005197379505261779,
      "learning_rate": 8.986041968900796e-05,
      "loss": 0.0,
      "step": 635
    },
    {
      "epoch": 1.0795671546785486,
      "grad_norm": 0.0005938683752901852,
      "learning_rate": 8.942465661730129e-05,
      "loss": 0.0,
      "step": 636
    },
    {
      "epoch": 1.081264587311691,
      "grad_norm": 0.006787140388041735,
      "learning_rate": 8.898950353862998e-05,
      "loss": 0.0002,
      "step": 637
    },
    {
      "epoch": 1.0829620199448335,
      "grad_norm": 0.008357354439795017,
      "learning_rate": 8.85549648349807e-05,
      "loss": 0.0002,
      "step": 638
    },
    {
      "epoch": 1.0846594525779758,
      "grad_norm": 0.018981877714395523,
      "learning_rate": 8.812104488215332e-05,
      "loss": 0.0005,
      "step": 639
    },
    {
      "epoch": 1.0863568852111183,
      "grad_norm": 0.2934776842594147,
      "learning_rate": 8.768774804971705e-05,
      "loss": 0.614,
      "step": 640
    },
    {
      "epoch": 1.0880543178442605,
      "grad_norm": 0.3190712034702301,
      "learning_rate": 8.725507870096609e-05,
      "loss": 0.7782,
      "step": 641
    },
    {
      "epoch": 1.089751750477403,
      "grad_norm": 0.27697721123695374,
      "learning_rate": 8.6823041192876e-05,
      "loss": 0.6048,
      "step": 642
    },
    {
      "epoch": 1.0914491831105453,
      "grad_norm": 0.28390857577323914,
      "learning_rate": 8.639163987605976e-05,
      "loss": 0.7607,
      "step": 643
    },
    {
      "epoch": 1.0931466157436878,
      "grad_norm": 0.2731177806854248,
      "learning_rate": 8.596087909472373e-05,
      "loss": 0.6359,
      "step": 644
    },
    {
      "epoch": 1.09484404837683,
      "grad_norm": 0.2403832972049713,
      "learning_rate": 8.553076318662425e-05,
      "loss": 0.549,
      "step": 645
    },
    {
      "epoch": 1.0965414810099725,
      "grad_norm": 0.2551855742931366,
      "learning_rate": 8.510129648302372e-05,
      "loss": 0.6247,
      "step": 646
    },
    {
      "epoch": 1.0982389136431148,
      "grad_norm": 0.25632765889167786,
      "learning_rate": 8.467248330864718e-05,
      "loss": 0.5901,
      "step": 647
    },
    {
      "epoch": 1.0999363462762572,
      "grad_norm": 0.22331362962722778,
      "learning_rate": 8.424432798163836e-05,
      "loss": 0.5206,
      "step": 648
    },
    {
      "epoch": 1.1016337789093995,
      "grad_norm": 0.20115035772323608,
      "learning_rate": 8.381683481351676e-05,
      "loss": 0.3558,
      "step": 649
    },
    {
      "epoch": 1.103331211542542,
      "grad_norm": 0.21585069596767426,
      "learning_rate": 8.339000810913386e-05,
      "loss": 0.479,
      "step": 650
    },
    {
      "epoch": 1.103331211542542,
      "eval_loss": 0.3638736605644226,
      "eval_runtime": 65.9097,
      "eval_samples_per_second": 2.928,
      "eval_steps_per_second": 2.928,
      "step": 650
    },
    {
      "epoch": 1.1050286441756842,
      "grad_norm": 1.5040993690490723,
      "learning_rate": 8.296385216662983e-05,
      "loss": 0.8622,
      "step": 651
    },
    {
      "epoch": 1.1067260768088267,
      "grad_norm": 0.20278804004192352,
      "learning_rate": 8.253837127739014e-05,
      "loss": 0.3313,
      "step": 652
    },
    {
      "epoch": 1.108423509441969,
      "grad_norm": 0.22194603085517883,
      "learning_rate": 8.21135697260028e-05,
      "loss": 0.436,
      "step": 653
    },
    {
      "epoch": 1.1101209420751115,
      "grad_norm": 0.26204535365104675,
      "learning_rate": 8.168945179021458e-05,
      "loss": 0.5942,
      "step": 654
    },
    {
      "epoch": 1.1118183747082537,
      "grad_norm": 0.2720772922039032,
      "learning_rate": 8.126602174088843e-05,
      "loss": 0.5629,
      "step": 655
    },
    {
      "epoch": 1.1135158073413962,
      "grad_norm": 0.3167116641998291,
      "learning_rate": 8.084328384196034e-05,
      "loss": 0.7216,
      "step": 656
    },
    {
      "epoch": 1.1152132399745385,
      "grad_norm": 0.1929994821548462,
      "learning_rate": 8.042124235039612e-05,
      "loss": 0.3211,
      "step": 657
    },
    {
      "epoch": 1.116910672607681,
      "grad_norm": 0.256496787071228,
      "learning_rate": 7.999990151614894e-05,
      "loss": 0.4641,
      "step": 658
    },
    {
      "epoch": 1.1186081052408232,
      "grad_norm": 0.18538035452365875,
      "learning_rate": 7.957926558211642e-05,
      "loss": 0.2509,
      "step": 659
    },
    {
      "epoch": 1.1203055378739657,
      "grad_norm": 0.16746576130390167,
      "learning_rate": 7.915933878409761e-05,
      "loss": 0.2268,
      "step": 660
    },
    {
      "epoch": 1.122002970507108,
      "grad_norm": 0.14101870357990265,
      "learning_rate": 7.874012535075076e-05,
      "loss": 0.1466,
      "step": 661
    },
    {
      "epoch": 1.1237004031402504,
      "grad_norm": 0.1386355608701706,
      "learning_rate": 7.832162950355055e-05,
      "loss": 0.1181,
      "step": 662
    },
    {
      "epoch": 1.1253978357733927,
      "grad_norm": 0.17996515333652496,
      "learning_rate": 7.79038554567454e-05,
      "loss": 0.2161,
      "step": 663
    },
    {
      "epoch": 1.1270952684065352,
      "grad_norm": 0.10335368663072586,
      "learning_rate": 7.74868074173154e-05,
      "loss": 0.0803,
      "step": 664
    },
    {
      "epoch": 1.1287927010396774,
      "grad_norm": 0.08208036422729492,
      "learning_rate": 7.707048958492972e-05,
      "loss": 0.0472,
      "step": 665
    },
    {
      "epoch": 1.13049013367282,
      "grad_norm": 0.0008246850338764489,
      "learning_rate": 7.665490615190418e-05,
      "loss": 0.0,
      "step": 666
    },
    {
      "epoch": 1.1321875663059622,
      "grad_norm": 0.10074999183416367,
      "learning_rate": 7.624006130315941e-05,
      "loss": 0.0596,
      "step": 667
    },
    {
      "epoch": 1.1338849989391047,
      "grad_norm": 0.005631667096167803,
      "learning_rate": 7.582595921617849e-05,
      "loss": 0.0001,
      "step": 668
    },
    {
      "epoch": 1.135582431572247,
      "grad_norm": 0.0009247282869182527,
      "learning_rate": 7.541260406096477e-05,
      "loss": 0.0,
      "step": 669
    },
    {
      "epoch": 1.1372798642053894,
      "grad_norm": 0.0009505698108114302,
      "learning_rate": 7.500000000000002e-05,
      "loss": 0.0,
      "step": 670
    },
    {
      "epoch": 1.1389772968385317,
      "grad_norm": 0.0032684446778148413,
      "learning_rate": 7.458815118820262e-05,
      "loss": 0.0001,
      "step": 671
    },
    {
      "epoch": 1.1406747294716741,
      "grad_norm": 0.0013583129039034247,
      "learning_rate": 7.417706177288559e-05,
      "loss": 0.0001,
      "step": 672
    },
    {
      "epoch": 1.1423721621048164,
      "grad_norm": 0.01342520397156477,
      "learning_rate": 7.376673589371466e-05,
      "loss": 0.0001,
      "step": 673
    },
    {
      "epoch": 1.1440695947379589,
      "grad_norm": 0.0014044721610844135,
      "learning_rate": 7.335717768266692e-05,
      "loss": 0.0001,
      "step": 674
    },
    {
      "epoch": 1.1457670273711011,
      "grad_norm": 0.00327441468834877,
      "learning_rate": 7.294839126398908e-05,
      "loss": 0.0001,
      "step": 675
    },
    {
      "epoch": 1.1474644600042436,
      "grad_norm": 0.0010030365083366632,
      "learning_rate": 7.254038075415572e-05,
      "loss": 0.0001,
      "step": 676
    },
    {
      "epoch": 1.1491618926373859,
      "grad_norm": 0.0014624049654230475,
      "learning_rate": 7.21331502618282e-05,
      "loss": 0.0001,
      "step": 677
    },
    {
      "epoch": 1.1508593252705284,
      "grad_norm": 0.0015749256126582623,
      "learning_rate": 7.172670388781313e-05,
      "loss": 0.0001,
      "step": 678
    },
    {
      "epoch": 1.1525567579036706,
      "grad_norm": 0.0019347285851836205,
      "learning_rate": 7.132104572502085e-05,
      "loss": 0.0001,
      "step": 679
    },
    {
      "epoch": 1.154254190536813,
      "grad_norm": 0.0021744261030107737,
      "learning_rate": 7.091617985842462e-05,
      "loss": 0.0001,
      "step": 680
    },
    {
      "epoch": 1.1559516231699554,
      "grad_norm": 0.001666248426772654,
      "learning_rate": 7.051211036501928e-05,
      "loss": 0.0001,
      "step": 681
    },
    {
      "epoch": 1.1576490558030978,
      "grad_norm": 0.0027833145577460527,
      "learning_rate": 7.010884131378001e-05,
      "loss": 0.0001,
      "step": 682
    },
    {
      "epoch": 1.15934648843624,
      "grad_norm": 0.0027128716465085745,
      "learning_rate": 6.970637676562177e-05,
      "loss": 0.0001,
      "step": 683
    },
    {
      "epoch": 1.1610439210693826,
      "grad_norm": 0.0008519128314219415,
      "learning_rate": 6.930472077335813e-05,
      "loss": 0.0,
      "step": 684
    },
    {
      "epoch": 1.1627413537025248,
      "grad_norm": 0.0009717077482491732,
      "learning_rate": 6.890387738166041e-05,
      "loss": 0.0,
      "step": 685
    },
    {
      "epoch": 1.1644387863356673,
      "grad_norm": 0.0008186842896975577,
      "learning_rate": 6.850385062701707e-05,
      "loss": 0.0,
      "step": 686
    },
    {
      "epoch": 1.1661362189688096,
      "grad_norm": 0.00198109308257699,
      "learning_rate": 6.810464453769313e-05,
      "loss": 0.0001,
      "step": 687
    },
    {
      "epoch": 1.167833651601952,
      "grad_norm": 0.0016451094998046756,
      "learning_rate": 6.770626313368954e-05,
      "loss": 0.0001,
      "step": 688
    },
    {
      "epoch": 1.1695310842350943,
      "grad_norm": 0.012841903604567051,
      "learning_rate": 6.730871042670253e-05,
      "loss": 0.0001,
      "step": 689
    },
    {
      "epoch": 1.1712285168682368,
      "grad_norm": 0.24701042473316193,
      "learning_rate": 6.691199042008345e-05,
      "loss": 0.5718,
      "step": 690
    },
    {
      "epoch": 1.172925949501379,
      "grad_norm": 0.2914482057094574,
      "learning_rate": 6.651610710879847e-05,
      "loss": 0.6846,
      "step": 691
    },
    {
      "epoch": 1.1746233821345216,
      "grad_norm": 0.2963961362838745,
      "learning_rate": 6.612106447938799e-05,
      "loss": 0.6591,
      "step": 692
    },
    {
      "epoch": 1.1763208147676638,
      "grad_norm": 0.29871684312820435,
      "learning_rate": 6.572686650992696e-05,
      "loss": 0.7258,
      "step": 693
    },
    {
      "epoch": 1.1780182474008063,
      "grad_norm": 0.29003167152404785,
      "learning_rate": 6.533351716998465e-05,
      "loss": 0.7024,
      "step": 694
    },
    {
      "epoch": 1.1797156800339486,
      "grad_norm": 0.21721364557743073,
      "learning_rate": 6.49410204205844e-05,
      "loss": 0.4072,
      "step": 695
    },
    {
      "epoch": 1.181413112667091,
      "grad_norm": 0.26777032017707825,
      "learning_rate": 6.454938021416417e-05,
      "loss": 0.6083,
      "step": 696
    },
    {
      "epoch": 1.1831105453002335,
      "grad_norm": 0.25797197222709656,
      "learning_rate": 6.415860049453657e-05,
      "loss": 0.5343,
      "step": 697
    },
    {
      "epoch": 1.1848079779333758,
      "grad_norm": 0.27494683861732483,
      "learning_rate": 6.376868519684892e-05,
      "loss": 0.6913,
      "step": 698
    },
    {
      "epoch": 1.186505410566518,
      "grad_norm": 0.22641535103321075,
      "learning_rate": 6.337963824754399e-05,
      "loss": 0.4186,
      "step": 699
    },
    {
      "epoch": 1.1882028431996605,
      "grad_norm": 0.21553833782672882,
      "learning_rate": 6.299146356432029e-05,
      "loss": 0.4194,
      "step": 700
    },
    {
      "epoch": 1.1882028431996605,
      "eval_loss": 0.36409613490104675,
      "eval_runtime": 65.9367,
      "eval_samples_per_second": 2.927,
      "eval_steps_per_second": 2.927,
      "step": 700
    },
    {
      "epoch": 1.189900275832803,
      "grad_norm": 0.23178090155124664,
      "learning_rate": 6.260416505609246e-05,
      "loss": 0.4426,
      "step": 701
    },
    {
      "epoch": 1.1915977084659453,
      "grad_norm": 0.3357522785663605,
      "learning_rate": 6.221774662295231e-05,
      "loss": 0.6644,
      "step": 702
    },
    {
      "epoch": 1.1932951410990875,
      "grad_norm": 0.22388817369937897,
      "learning_rate": 6.183221215612904e-05,
      "loss": 0.4101,
      "step": 703
    },
    {
      "epoch": 1.19499257373223,
      "grad_norm": 0.2008681744337082,
      "learning_rate": 6.144756553795056e-05,
      "loss": 0.3087,
      "step": 704
    },
    {
      "epoch": 1.1966900063653725,
      "grad_norm": 0.22424735128879547,
      "learning_rate": 6.106381064180395e-05,
      "loss": 0.4092,
      "step": 705
    },
    {
      "epoch": 1.1983874389985147,
      "grad_norm": 0.26054248213768005,
      "learning_rate": 6.068095133209681e-05,
      "loss": 0.498,
      "step": 706
    },
    {
      "epoch": 1.200084871631657,
      "grad_norm": 0.1590735763311386,
      "learning_rate": 6.0298991464218164e-05,
      "loss": 0.1884,
      "step": 707
    },
    {
      "epoch": 1.2017823042647995,
      "grad_norm": 0.20946505665779114,
      "learning_rate": 5.991793488449955e-05,
      "loss": 0.3051,
      "step": 708
    },
    {
      "epoch": 1.203479736897942,
      "grad_norm": 0.1654549539089203,
      "learning_rate": 5.953778543017656e-05,
      "loss": 0.2029,
      "step": 709
    },
    {
      "epoch": 1.2051771695310842,
      "grad_norm": 0.11620619148015976,
      "learning_rate": 5.915854692935002e-05,
      "loss": 0.0943,
      "step": 710
    },
    {
      "epoch": 1.2068746021642265,
      "grad_norm": 0.19273479282855988,
      "learning_rate": 5.8780223200947325e-05,
      "loss": 0.2541,
      "step": 711
    },
    {
      "epoch": 1.208572034797369,
      "grad_norm": 0.22115856409072876,
      "learning_rate": 5.840281805468426e-05,
      "loss": 0.335,
      "step": 712
    },
    {
      "epoch": 1.2102694674305114,
      "grad_norm": 0.17392244935035706,
      "learning_rate": 5.8026335291026534e-05,
      "loss": 0.1842,
      "step": 713
    },
    {
      "epoch": 1.2119669000636537,
      "grad_norm": 0.04149521142244339,
      "learning_rate": 5.765077870115125e-05,
      "loss": 0.0099,
      "step": 714
    },
    {
      "epoch": 1.2136643326967962,
      "grad_norm": 0.14882031083106995,
      "learning_rate": 5.72761520669092e-05,
      "loss": 0.1405,
      "step": 715
    },
    {
      "epoch": 1.2153617653299384,
      "grad_norm": 0.04529095068573952,
      "learning_rate": 5.6902459160786444e-05,
      "loss": 0.0137,
      "step": 716
    },
    {
      "epoch": 1.217059197963081,
      "grad_norm": 0.031042039394378662,
      "learning_rate": 5.6529703745866324e-05,
      "loss": 0.0031,
      "step": 717
    },
    {
      "epoch": 1.2187566305962232,
      "grad_norm": 0.00039801717502996325,
      "learning_rate": 5.6157889575791764e-05,
      "loss": 0.0,
      "step": 718
    },
    {
      "epoch": 1.2204540632293657,
      "grad_norm": 0.0020159813575446606,
      "learning_rate": 5.578702039472738e-05,
      "loss": 0.0001,
      "step": 719
    },
    {
      "epoch": 1.222151495862508,
      "grad_norm": 0.0011594186071306467,
      "learning_rate": 5.541709993732167e-05,
      "loss": 0.0,
      "step": 720
    },
    {
      "epoch": 1.2238489284956504,
      "grad_norm": 0.003208533627912402,
      "learning_rate": 5.504813192866945e-05,
      "loss": 0.0,
      "step": 721
    },
    {
      "epoch": 1.2255463611287927,
      "grad_norm": 0.001415073755197227,
      "learning_rate": 5.4680120084274574e-05,
      "loss": 0.0,
      "step": 722
    },
    {
      "epoch": 1.2272437937619352,
      "grad_norm": 0.0004124438273720443,
      "learning_rate": 5.4313068110012245e-05,
      "loss": 0.0,
      "step": 723
    },
    {
      "epoch": 1.2289412263950774,
      "grad_norm": 0.00023227222845889628,
      "learning_rate": 5.394697970209166e-05,
      "loss": 0.0,
      "step": 724
    },
    {
      "epoch": 1.23063865902822,
      "grad_norm": 0.0005153273814357817,
      "learning_rate": 5.358185854701909e-05,
      "loss": 0.0,
      "step": 725
    },
    {
      "epoch": 1.2323360916613622,
      "grad_norm": 0.03805829957127571,
      "learning_rate": 5.321770832156057e-05,
      "loss": 0.0003,
      "step": 726
    },
    {
      "epoch": 1.2340335242945046,
      "grad_norm": 0.00048098803381435573,
      "learning_rate": 5.285453269270471e-05,
      "loss": 0.0,
      "step": 727
    },
    {
      "epoch": 1.235730956927647,
      "grad_norm": 0.03290550410747528,
      "learning_rate": 5.249233531762612e-05,
      "loss": 0.0008,
      "step": 728
    },
    {
      "epoch": 1.2374283895607894,
      "grad_norm": 0.00626510102301836,
      "learning_rate": 5.213111984364839e-05,
      "loss": 0.0002,
      "step": 729
    },
    {
      "epoch": 1.2391258221939316,
      "grad_norm": 0.006389813032001257,
      "learning_rate": 5.1770889908207245e-05,
      "loss": 0.0001,
      "step": 730
    },
    {
      "epoch": 1.2408232548270741,
      "grad_norm": 0.0006512326071970165,
      "learning_rate": 5.141164913881417e-05,
      "loss": 0.0,
      "step": 731
    },
    {
      "epoch": 1.2425206874602164,
      "grad_norm": 0.0029449777211993933,
      "learning_rate": 5.105340115301977e-05,
      "loss": 0.0001,
      "step": 732
    },
    {
      "epoch": 1.2442181200933589,
      "grad_norm": 0.0047165704891085625,
      "learning_rate": 5.0696149558377215e-05,
      "loss": 0.0001,
      "step": 733
    },
    {
      "epoch": 1.2459155527265011,
      "grad_norm": 0.0005647541838698089,
      "learning_rate": 5.0339897952406123e-05,
      "loss": 0.0,
      "step": 734
    },
    {
      "epoch": 1.2476129853596436,
      "grad_norm": 0.001746086752973497,
      "learning_rate": 4.998464992255627e-05,
      "loss": 0.0001,
      "step": 735
    },
    {
      "epoch": 1.2493104179927859,
      "grad_norm": 0.00047052078298293054,
      "learning_rate": 4.963040904617131e-05,
      "loss": 0.0,
      "step": 736
    },
    {
      "epoch": 1.2510078506259283,
      "grad_norm": 0.0064684562385082245,
      "learning_rate": 4.9277178890452896e-05,
      "loss": 0.0002,
      "step": 737
    },
    {
      "epoch": 1.2527052832590706,
      "grad_norm": 0.0021551090758293867,
      "learning_rate": 4.892496301242482e-05,
      "loss": 0.0,
      "step": 738
    },
    {
      "epoch": 1.254402715892213,
      "grad_norm": 0.0014455855125561357,
      "learning_rate": 4.857376495889712e-05,
      "loss": 0.0001,
      "step": 739
    },
    {
      "epoch": 1.2561001485253553,
      "grad_norm": 0.23304064571857452,
      "learning_rate": 4.8223588266430186e-05,
      "loss": 0.4913,
      "step": 740
    },
    {
      "epoch": 1.2577975811584978,
      "grad_norm": 0.28668463230133057,
      "learning_rate": 4.787443646129948e-05,
      "loss": 0.6474,
      "step": 741
    },
    {
      "epoch": 1.25949501379164,
      "grad_norm": 0.334522545337677,
      "learning_rate": 4.752631305945985e-05,
      "loss": 0.7787,
      "step": 742
    },
    {
      "epoch": 1.2611924464247826,
      "grad_norm": 0.28749802708625793,
      "learning_rate": 4.717922156651001e-05,
      "loss": 0.6218,
      "step": 743
    },
    {
      "epoch": 1.2628898790579248,
      "grad_norm": 0.2978324890136719,
      "learning_rate": 4.6833165477657446e-05,
      "loss": 0.7438,
      "step": 744
    },
    {
      "epoch": 1.2645873116910673,
      "grad_norm": 0.2923458218574524,
      "learning_rate": 4.648814827768322e-05,
      "loss": 0.6148,
      "step": 745
    },
    {
      "epoch": 1.2662847443242096,
      "grad_norm": 0.26087573170661926,
      "learning_rate": 4.614417344090659e-05,
      "loss": 0.5136,
      "step": 746
    },
    {
      "epoch": 1.267982176957352,
      "grad_norm": 0.19124242663383484,
      "learning_rate": 4.5801244431150394e-05,
      "loss": 0.3201,
      "step": 747
    },
    {
      "epoch": 1.2696796095904943,
      "grad_norm": 0.28308284282684326,
      "learning_rate": 4.5459364701705995e-05,
      "loss": 0.684,
      "step": 748
    },
    {
      "epoch": 1.2713770422236368,
      "grad_norm": 0.2998988628387451,
      "learning_rate": 4.51185376952984e-05,
      "loss": 0.6558,
      "step": 749
    },
    {
      "epoch": 1.273074474856779,
      "grad_norm": 0.2379872053861618,
      "learning_rate": 4.477876684405179e-05,
      "loss": 0.4853,
      "step": 750
    },
    {
      "epoch": 1.273074474856779,
      "eval_loss": 0.3654167652130127,
      "eval_runtime": 65.9099,
      "eval_samples_per_second": 2.928,
      "eval_steps_per_second": 2.928,
      "step": 750
    },
    {
      "epoch": 1.2747719074899215,
      "grad_norm": 0.2629989981651306,
      "learning_rate": 4.4440055569454936e-05,
      "loss": 0.5687,
      "step": 751
    },
    {
      "epoch": 1.2764693401230638,
      "grad_norm": 0.29386061429977417,
      "learning_rate": 4.410240728232653e-05,
      "loss": 0.4559,
      "step": 752
    },
    {
      "epoch": 1.2781667727562063,
      "grad_norm": 0.32051095366477966,
      "learning_rate": 4.376582538278114e-05,
      "loss": 0.7155,
      "step": 753
    },
    {
      "epoch": 1.2798642053893485,
      "grad_norm": 0.2592981159687042,
      "learning_rate": 4.3430313260194697e-05,
      "loss": 0.4972,
      "step": 754
    },
    {
      "epoch": 1.281561638022491,
      "grad_norm": 0.23039335012435913,
      "learning_rate": 4.309587429317061e-05,
      "loss": 0.4049,
      "step": 755
    },
    {
      "epoch": 1.2832590706556333,
      "grad_norm": 0.2293672114610672,
      "learning_rate": 4.2762511849505476e-05,
      "loss": 0.4085,
      "step": 756
    },
    {
      "epoch": 1.2849565032887758,
      "grad_norm": 0.2180144041776657,
      "learning_rate": 4.2430229286155484e-05,
      "loss": 0.3829,
      "step": 757
    },
    {
      "epoch": 1.286653935921918,
      "grad_norm": 0.22328434884548187,
      "learning_rate": 4.209902994920235e-05,
      "loss": 0.381,
      "step": 758
    },
    {
      "epoch": 1.2883513685550605,
      "grad_norm": 0.19186857342720032,
      "learning_rate": 4.176891717381967e-05,
      "loss": 0.2676,
      "step": 759
    },
    {
      "epoch": 1.290048801188203,
      "grad_norm": 0.19644580781459808,
      "learning_rate": 4.143989428423947e-05,
      "loss": 0.2604,
      "step": 760
    },
    {
      "epoch": 1.2917462338213452,
      "grad_norm": 0.1470167487859726,
      "learning_rate": 4.111196459371862e-05,
      "loss": 0.1697,
      "step": 761
    },
    {
      "epoch": 1.2934436664544875,
      "grad_norm": 0.10344719886779785,
      "learning_rate": 4.0785131404505376e-05,
      "loss": 0.0742,
      "step": 762
    },
    {
      "epoch": 1.29514109908763,
      "grad_norm": 0.08508791774511337,
      "learning_rate": 4.045939800780639e-05,
      "loss": 0.0492,
      "step": 763
    },
    {
      "epoch": 1.2968385317207725,
      "grad_norm": 0.08410584181547165,
      "learning_rate": 4.0134767683753385e-05,
      "loss": 0.049,
      "step": 764
    },
    {
      "epoch": 1.2985359643539147,
      "grad_norm": 0.001906770863570273,
      "learning_rate": 3.981124370137001e-05,
      "loss": 0.0001,
      "step": 765
    },
    {
      "epoch": 1.300233396987057,
      "grad_norm": 0.14595600962638855,
      "learning_rate": 3.948882931853924e-05,
      "loss": 0.119,
      "step": 766
    },
    {
      "epoch": 1.3019308296201995,
      "grad_norm": 0.00104467140045017,
      "learning_rate": 3.916752778197039e-05,
      "loss": 0.0001,
      "step": 767
    },
    {
      "epoch": 1.303628262253342,
      "grad_norm": 0.00029723646002821624,
      "learning_rate": 3.8847342327166244e-05,
      "loss": 0.0,
      "step": 768
    },
    {
      "epoch": 1.3053256948864842,
      "grad_norm": 0.07592643052339554,
      "learning_rate": 3.852827617839084e-05,
      "loss": 0.026,
      "step": 769
    },
    {
      "epoch": 1.3070231275196265,
      "grad_norm": 0.00041246655746363103,
      "learning_rate": 3.8210332548636796e-05,
      "loss": 0.0,
      "step": 770
    },
    {
      "epoch": 1.308720560152769,
      "grad_norm": 0.002659448655322194,
      "learning_rate": 3.7893514639592895e-05,
      "loss": 0.0001,
      "step": 771
    },
    {
      "epoch": 1.3104179927859114,
      "grad_norm": 0.00021023498266004026,
      "learning_rate": 3.757782564161191e-05,
      "loss": 0.0,
      "step": 772
    },
    {
      "epoch": 1.3121154254190537,
      "grad_norm": 0.0010800276650115848,
      "learning_rate": 3.7263268733678606e-05,
      "loss": 0.0,
      "step": 773
    },
    {
      "epoch": 1.313812858052196,
      "grad_norm": 0.0006105787470005453,
      "learning_rate": 3.694984708337756e-05,
      "loss": 0.0,
      "step": 774
    },
    {
      "epoch": 1.3155102906853384,
      "grad_norm": 0.0007423445931635797,
      "learning_rate": 3.663756384686127e-05,
      "loss": 0.0,
      "step": 775
    },
    {
      "epoch": 1.317207723318481,
      "grad_norm": 0.0007892303401604295,
      "learning_rate": 3.632642216881847e-05,
      "loss": 0.0,
      "step": 776
    },
    {
      "epoch": 1.3189051559516232,
      "grad_norm": 0.0015005484456196427,
      "learning_rate": 3.601642518244247e-05,
      "loss": 0.0,
      "step": 777
    },
    {
      "epoch": 1.3206025885847654,
      "grad_norm": 0.0008817919879220426,
      "learning_rate": 3.570757600939939e-05,
      "loss": 0.0,
      "step": 778
    },
    {
      "epoch": 1.322300021217908,
      "grad_norm": 0.0003715140337590128,
      "learning_rate": 3.5399877759797e-05,
      "loss": 0.0,
      "step": 779
    },
    {
      "epoch": 1.3239974538510504,
      "grad_norm": 0.001832145731896162,
      "learning_rate": 3.509333353215331e-05,
      "loss": 0.0001,
      "step": 780
    },
    {
      "epoch": 1.3256948864841926,
      "grad_norm": 0.0006237781490199268,
      "learning_rate": 3.47879464133652e-05,
      "loss": 0.0,
      "step": 781
    },
    {
      "epoch": 1.327392319117335,
      "grad_norm": 0.0015418545808643103,
      "learning_rate": 3.448371947867763e-05,
      "loss": 0.0001,
      "step": 782
    },
    {
      "epoch": 1.3290897517504774,
      "grad_norm": 0.0035702355671674013,
      "learning_rate": 3.4180655791652476e-05,
      "loss": 0.0001,
      "step": 783
    },
    {
      "epoch": 1.3307871843836199,
      "grad_norm": 0.0013561249943450093,
      "learning_rate": 3.3878758404137624e-05,
      "loss": 0.0001,
      "step": 784
    },
    {
      "epoch": 1.3324846170167621,
      "grad_norm": 0.001489428337663412,
      "learning_rate": 3.3578030356236455e-05,
      "loss": 0.0001,
      "step": 785
    },
    {
      "epoch": 1.3341820496499044,
      "grad_norm": 0.0011818065540865064,
      "learning_rate": 3.3278474676277114e-05,
      "loss": 0.0,
      "step": 786
    },
    {
      "epoch": 1.3358794822830469,
      "grad_norm": 0.0076867276802659035,
      "learning_rate": 3.298009438078194e-05,
      "loss": 0.0003,
      "step": 787
    },
    {
      "epoch": 1.3375769149161894,
      "grad_norm": 0.002071813913062215,
      "learning_rate": 3.268289247443713e-05,
      "loss": 0.0001,
      "step": 788
    },
    {
      "epoch": 1.3392743475493316,
      "grad_norm": 0.002192431129515171,
      "learning_rate": 3.238687195006264e-05,
      "loss": 0.0001,
      "step": 789
    },
    {
      "epoch": 1.3409717801824739,
      "grad_norm": 0.24951210618019104,
      "learning_rate": 3.209203578858191e-05,
      "loss": 0.6115,
      "step": 790
    },
    {
      "epoch": 1.3426692128156164,
      "grad_norm": 0.29264548420906067,
      "learning_rate": 3.1798386958991714e-05,
      "loss": 0.71,
      "step": 791
    },
    {
      "epoch": 1.3443666454487588,
      "grad_norm": 0.2815876603126526,
      "learning_rate": 3.1505928418332574e-05,
      "loss": 0.6586,
      "step": 792
    },
    {
      "epoch": 1.346064078081901,
      "grad_norm": 0.25446027517318726,
      "learning_rate": 3.121466311165875e-05,
      "loss": 0.5623,
      "step": 793
    },
    {
      "epoch": 1.3477615107150436,
      "grad_norm": 0.2643551230430603,
      "learning_rate": 3.092459397200861e-05,
      "loss": 0.6298,
      "step": 794
    },
    {
      "epoch": 1.3494589433481858,
      "grad_norm": 0.24555166065692902,
      "learning_rate": 3.0635723920375164e-05,
      "loss": 0.5237,
      "step": 795
    },
    {
      "epoch": 1.3511563759813283,
      "grad_norm": 0.2268795222043991,
      "learning_rate": 3.0348055865676707e-05,
      "loss": 0.3814,
      "step": 796
    },
    {
      "epoch": 1.3528538086144706,
      "grad_norm": 0.25621020793914795,
      "learning_rate": 3.0061592704727257e-05,
      "loss": 0.5183,
      "step": 797
    },
    {
      "epoch": 1.354551241247613,
      "grad_norm": 0.2662016451358795,
      "learning_rate": 2.9776337322207687e-05,
      "loss": 0.5679,
      "step": 798
    },
    {
      "epoch": 1.3562486738807553,
      "grad_norm": 0.20577247440814972,
      "learning_rate": 2.9492292590636613e-05,
      "loss": 0.3231,
      "step": 799
    },
    {
      "epoch": 1.3579461065138978,
      "grad_norm": 0.23013556003570557,
      "learning_rate": 2.9209461370341204e-05,
      "loss": 0.4158,
      "step": 800
    },
    {
      "epoch": 1.3579461065138978,
      "eval_loss": 0.36441436409950256,
      "eval_runtime": 65.9028,
      "eval_samples_per_second": 2.929,
      "eval_steps_per_second": 2.929,
      "step": 800
    }
  ],
  "logging_steps": 1,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.185996556504924e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}