{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 506,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003954522985664854,
      "grad_norm": 0.2544356882572174,
      "learning_rate": 0.0,
      "loss": 1.180017113685608,
      "step": 1
    },
    {
      "epoch": 0.007909045971329708,
      "grad_norm": 0.2469092607498169,
      "learning_rate": 4e-05,
      "loss": 1.1813130378723145,
      "step": 2
    },
    {
      "epoch": 0.011863568956994563,
      "grad_norm": 0.20873534679412842,
      "learning_rate": 8e-05,
      "loss": 1.1847681999206543,
      "step": 3
    },
    {
      "epoch": 0.015818091942659415,
      "grad_norm": 0.22851118445396423,
      "learning_rate": 0.00012,
      "loss": 1.1241787672042847,
      "step": 4
    },
    {
      "epoch": 0.019772614928324272,
      "grad_norm": 0.22521217167377472,
      "learning_rate": 0.00016,
      "loss": 1.1387571096420288,
      "step": 5
    },
    {
      "epoch": 0.023727137913989126,
      "grad_norm": 0.21741724014282227,
      "learning_rate": 0.0002,
      "loss": 1.103634238243103,
      "step": 6
    },
    {
      "epoch": 0.02768166089965398,
      "grad_norm": 0.1713864952325821,
      "learning_rate": 0.0001996007984031936,
      "loss": 1.1193780899047852,
      "step": 7
    },
    {
      "epoch": 0.03163618388531883,
      "grad_norm": 0.1551392674446106,
      "learning_rate": 0.00019920159680638725,
      "loss": 1.209862470626831,
      "step": 8
    },
    {
      "epoch": 0.03559070687098369,
      "grad_norm": 0.17870232462882996,
      "learning_rate": 0.00019880239520958084,
      "loss": 1.1225727796554565,
      "step": 9
    },
    {
      "epoch": 0.039545229856648545,
      "grad_norm": 0.20667865872383118,
      "learning_rate": 0.00019840319361277446,
      "loss": 1.0327069759368896,
      "step": 10
    },
    {
      "epoch": 0.043499752842313395,
      "grad_norm": 0.19965171813964844,
      "learning_rate": 0.00019800399201596808,
      "loss": 0.9479315280914307,
      "step": 11
    },
    {
      "epoch": 0.04745427582797825,
      "grad_norm": 0.21041055023670197,
      "learning_rate": 0.0001976047904191617,
      "loss": 1.1442006826400757,
      "step": 12
    },
    {
      "epoch": 0.0514087988136431,
      "grad_norm": 0.16018487513065338,
      "learning_rate": 0.0001972055888223553,
      "loss": 1.0416808128356934,
      "step": 13
    },
    {
      "epoch": 0.05536332179930796,
      "grad_norm": 0.141277477145195,
      "learning_rate": 0.0001968063872255489,
      "loss": 1.1698994636535645,
      "step": 14
    },
    {
      "epoch": 0.05931784478497281,
      "grad_norm": 0.12079285830259323,
      "learning_rate": 0.00019640718562874253,
      "loss": 0.9101760983467102,
      "step": 15
    },
    {
      "epoch": 0.06327236777063766,
      "grad_norm": 0.13878197968006134,
      "learning_rate": 0.00019600798403193614,
      "loss": 1.1655550003051758,
      "step": 16
    },
    {
      "epoch": 0.06722689075630252,
      "grad_norm": 0.16896755993366241,
      "learning_rate": 0.00019560878243512974,
      "loss": 1.0796542167663574,
      "step": 17
    },
    {
      "epoch": 0.07118141374196738,
      "grad_norm": 0.12621314823627472,
      "learning_rate": 0.00019520958083832338,
      "loss": 1.1336424350738525,
      "step": 18
    },
    {
      "epoch": 0.07513593672763223,
      "grad_norm": 0.1260470598936081,
      "learning_rate": 0.00019481037924151697,
      "loss": 1.02823805809021,
      "step": 19
    },
    {
      "epoch": 0.07909045971329709,
      "grad_norm": 0.1230599507689476,
      "learning_rate": 0.0001944111776447106,
      "loss": 0.9280879497528076,
      "step": 20
    },
    {
      "epoch": 0.08304498269896193,
      "grad_norm": 0.11235114187002182,
      "learning_rate": 0.00019401197604790419,
      "loss": 1.0234721899032593,
      "step": 21
    },
    {
      "epoch": 0.08699950568462679,
      "grad_norm": 0.1244259923696518,
      "learning_rate": 0.00019361277445109783,
      "loss": 0.9619145393371582,
      "step": 22
    },
    {
      "epoch": 0.09095402867029165,
      "grad_norm": 0.10888625681400299,
      "learning_rate": 0.00019321357285429142,
      "loss": 1.0350663661956787,
      "step": 23
    },
    {
      "epoch": 0.0949085516559565,
      "grad_norm": 0.12405306845903397,
      "learning_rate": 0.00019281437125748504,
      "loss": 1.1137639284133911,
      "step": 24
    },
    {
      "epoch": 0.09886307464162135,
      "grad_norm": 0.1365104615688324,
      "learning_rate": 0.00019241516966067866,
      "loss": 1.082958459854126,
      "step": 25
    },
    {
      "epoch": 0.1028175976272862,
      "grad_norm": 0.12047652900218964,
      "learning_rate": 0.00019201596806387228,
      "loss": 1.031674861907959,
      "step": 26
    },
    {
      "epoch": 0.10677212061295106,
      "grad_norm": 0.10935146361589432,
      "learning_rate": 0.00019161676646706587,
      "loss": 0.9122903347015381,
      "step": 27
    },
    {
      "epoch": 0.11072664359861592,
      "grad_norm": 0.1395711451768875,
      "learning_rate": 0.0001912175648702595,
      "loss": 0.9628266096115112,
      "step": 28
    },
    {
      "epoch": 0.11468116658428078,
      "grad_norm": 0.13380995392799377,
      "learning_rate": 0.0001908183632734531,
      "loss": 0.962996244430542,
      "step": 29
    },
    {
      "epoch": 0.11863568956994562,
      "grad_norm": 0.12701313197612762,
      "learning_rate": 0.0001904191616766467,
      "loss": 0.9316821694374084,
      "step": 30
    },
    {
      "epoch": 0.12259021255561048,
      "grad_norm": 0.12657427787780762,
      "learning_rate": 0.00019001996007984032,
      "loss": 1.0292439460754395,
      "step": 31
    },
    {
      "epoch": 0.12654473554127532,
      "grad_norm": 0.13929884135723114,
      "learning_rate": 0.00018962075848303394,
      "loss": 1.0495136976242065,
      "step": 32
    },
    {
      "epoch": 0.1304992585269402,
      "grad_norm": 0.1292039155960083,
      "learning_rate": 0.00018922155688622756,
      "loss": 1.0562491416931152,
      "step": 33
    },
    {
      "epoch": 0.13445378151260504,
      "grad_norm": 0.1383693516254425,
      "learning_rate": 0.00018882235528942115,
      "loss": 1.012336015701294,
      "step": 34
    },
    {
      "epoch": 0.1384083044982699,
      "grad_norm": 0.11728740483522415,
      "learning_rate": 0.0001884231536926148,
      "loss": 0.903199315071106,
      "step": 35
    },
    {
      "epoch": 0.14236282748393475,
      "grad_norm": 0.12921994924545288,
      "learning_rate": 0.0001880239520958084,
      "loss": 1.0892961025238037,
      "step": 36
    },
    {
      "epoch": 0.1463173504695996,
      "grad_norm": 0.1262505203485489,
      "learning_rate": 0.000187624750499002,
      "loss": 1.1606205701828003,
      "step": 37
    },
    {
      "epoch": 0.15027187345526447,
      "grad_norm": 0.12508349120616913,
      "learning_rate": 0.00018722554890219563,
      "loss": 1.0895495414733887,
      "step": 38
    },
    {
      "epoch": 0.1542263964409293,
      "grad_norm": 0.12130790203809738,
      "learning_rate": 0.00018682634730538924,
      "loss": 1.0368725061416626,
      "step": 39
    },
    {
      "epoch": 0.15818091942659418,
      "grad_norm": 0.12927809357643127,
      "learning_rate": 0.00018642714570858284,
      "loss": 1.0340652465820312,
      "step": 40
    },
    {
      "epoch": 0.16213544241225902,
      "grad_norm": 0.12635737657546997,
      "learning_rate": 0.00018602794411177646,
      "loss": 1.1098253726959229,
      "step": 41
    },
    {
      "epoch": 0.16608996539792387,
      "grad_norm": 0.1303265392780304,
      "learning_rate": 0.00018562874251497007,
      "loss": 1.0297881364822388,
      "step": 42
    },
    {
      "epoch": 0.17004448838358874,
      "grad_norm": 0.12825307250022888,
      "learning_rate": 0.0001852295409181637,
      "loss": 0.9129877090454102,
      "step": 43
    },
    {
      "epoch": 0.17399901136925358,
      "grad_norm": 0.12521876394748688,
      "learning_rate": 0.00018483033932135728,
      "loss": 0.97171550989151,
      "step": 44
    },
    {
      "epoch": 0.17795353435491842,
      "grad_norm": 0.13904021680355072,
      "learning_rate": 0.00018443113772455093,
      "loss": 1.097721815109253,
      "step": 45
    },
    {
      "epoch": 0.1819080573405833,
      "grad_norm": 0.14009957015514374,
      "learning_rate": 0.00018403193612774452,
      "loss": 0.9984307885169983,
      "step": 46
    },
    {
      "epoch": 0.18586258032624814,
      "grad_norm": 0.12277879565954208,
      "learning_rate": 0.00018363273453093811,
      "loss": 0.9881635904312134,
      "step": 47
    },
    {
      "epoch": 0.189817103311913,
      "grad_norm": 0.13878905773162842,
      "learning_rate": 0.00018323353293413173,
      "loss": 0.9900161027908325,
      "step": 48
    },
    {
      "epoch": 0.19377162629757785,
      "grad_norm": 0.1394307166337967,
      "learning_rate": 0.00018283433133732535,
      "loss": 0.8905137777328491,
      "step": 49
    },
    {
      "epoch": 0.1977261492832427,
      "grad_norm": 0.1348118931055069,
      "learning_rate": 0.00018243512974051897,
      "loss": 1.001299500465393,
      "step": 50
    },
    {
      "epoch": 0.20168067226890757,
      "grad_norm": 0.14841432869434357,
      "learning_rate": 0.00018203592814371256,
      "loss": 1.114479899406433,
      "step": 51
    },
    {
      "epoch": 0.2056351952545724,
      "grad_norm": 0.12918154895305634,
      "learning_rate": 0.0001816367265469062,
      "loss": 1.075540542602539,
      "step": 52
    },
    {
      "epoch": 0.20958971824023728,
      "grad_norm": 0.137839674949646,
      "learning_rate": 0.0001812375249500998,
      "loss": 0.9629291892051697,
      "step": 53
    },
    {
      "epoch": 0.21354424122590213,
      "grad_norm": 0.12743251025676727,
      "learning_rate": 0.00018083832335329342,
      "loss": 0.8884077668190002,
      "step": 54
    },
    {
      "epoch": 0.21749876421156697,
      "grad_norm": 0.14579665660858154,
      "learning_rate": 0.00018043912175648704,
      "loss": 1.0494593381881714,
      "step": 55
    },
    {
      "epoch": 0.22145328719723184,
      "grad_norm": 0.1444905400276184,
      "learning_rate": 0.00018003992015968066,
      "loss": 0.8838294744491577,
      "step": 56
    },
    {
      "epoch": 0.22540781018289668,
      "grad_norm": 0.13476018607616425,
      "learning_rate": 0.00017964071856287425,
      "loss": 0.9571032524108887,
      "step": 57
    },
    {
      "epoch": 0.22936233316856156,
      "grad_norm": 0.1387203335762024,
      "learning_rate": 0.00017924151696606787,
      "loss": 1.0317763090133667,
      "step": 58
    },
    {
      "epoch": 0.2333168561542264,
      "grad_norm": 0.14424876868724823,
      "learning_rate": 0.0001788423153692615,
      "loss": 1.0047612190246582,
      "step": 59
    },
    {
      "epoch": 0.23727137913989124,
      "grad_norm": 0.13895335793495178,
      "learning_rate": 0.0001784431137724551,
      "loss": 1.0508701801300049,
      "step": 60
    },
    {
      "epoch": 0.2412259021255561,
      "grad_norm": 0.1239890530705452,
      "learning_rate": 0.0001780439121756487,
      "loss": 1.003294587135315,
      "step": 61
    },
    {
      "epoch": 0.24518042511122096,
      "grad_norm": 0.13500665128231049,
      "learning_rate": 0.00017764471057884234,
      "loss": 0.9486382007598877,
      "step": 62
    },
    {
      "epoch": 0.2491349480968858,
      "grad_norm": 0.14559301733970642,
      "learning_rate": 0.00017724550898203594,
      "loss": 1.0008798837661743,
      "step": 63
    },
    {
      "epoch": 0.25308947108255064,
      "grad_norm": 0.15551623702049255,
      "learning_rate": 0.00017684630738522955,
      "loss": 0.9119284749031067,
      "step": 64
    },
    {
      "epoch": 0.25704399406821554,
      "grad_norm": 0.12912505865097046,
      "learning_rate": 0.00017644710578842317,
      "loss": 1.041481614112854,
      "step": 65
    },
    {
      "epoch": 0.2609985170538804,
      "grad_norm": 0.14489996433258057,
      "learning_rate": 0.0001760479041916168,
      "loss": 0.8673788905143738,
      "step": 66
    },
    {
      "epoch": 0.26495304003954523,
      "grad_norm": 0.14056646823883057,
      "learning_rate": 0.00017564870259481038,
      "loss": 0.9839107394218445,
      "step": 67
    },
    {
      "epoch": 0.2689075630252101,
      "grad_norm": 0.16830863058567047,
      "learning_rate": 0.000175249500998004,
      "loss": 1.0539538860321045,
      "step": 68
    },
    {
      "epoch": 0.2728620860108749,
      "grad_norm": 0.14673052728176117,
      "learning_rate": 0.00017485029940119762,
      "loss": 0.9210308790206909,
      "step": 69
    },
    {
      "epoch": 0.2768166089965398,
      "grad_norm": 0.1400182992219925,
      "learning_rate": 0.00017445109780439121,
      "loss": 0.9093458652496338,
      "step": 70
    },
    {
      "epoch": 0.28077113198220466,
      "grad_norm": 0.14567220211029053,
      "learning_rate": 0.00017405189620758483,
      "loss": 0.9801154136657715,
      "step": 71
    },
    {
      "epoch": 0.2847256549678695,
      "grad_norm": 0.15140396356582642,
      "learning_rate": 0.00017365269461077845,
      "loss": 1.0192142724990845,
      "step": 72
    },
    {
      "epoch": 0.28868017795353434,
      "grad_norm": 0.15245863795280457,
      "learning_rate": 0.00017325349301397207,
      "loss": 1.0319201946258545,
      "step": 73
    },
    {
      "epoch": 0.2926347009391992,
      "grad_norm": 0.15047654509544373,
      "learning_rate": 0.00017285429141716566,
      "loss": 1.0096640586853027,
      "step": 74
    },
    {
      "epoch": 0.2965892239248641,
      "grad_norm": 0.14069028198719025,
      "learning_rate": 0.00017245508982035928,
      "loss": 0.9506325125694275,
      "step": 75
    },
    {
      "epoch": 0.30054374691052893,
      "grad_norm": 0.13782000541687012,
      "learning_rate": 0.0001720558882235529,
      "loss": 0.8749170303344727,
      "step": 76
    },
    {
      "epoch": 0.3044982698961938,
      "grad_norm": 0.1548694223165512,
      "learning_rate": 0.00017165668662674652,
      "loss": 0.9927857518196106,
      "step": 77
    },
    {
      "epoch": 0.3084527928818586,
      "grad_norm": 0.14958986639976501,
      "learning_rate": 0.0001712574850299401,
      "loss": 0.7992951273918152,
      "step": 78
    },
    {
      "epoch": 0.31240731586752346,
      "grad_norm": 0.14522351324558258,
      "learning_rate": 0.00017085828343313376,
      "loss": 0.9930732846260071,
      "step": 79
    },
    {
      "epoch": 0.31636183885318836,
      "grad_norm": 0.14936009049415588,
      "learning_rate": 0.00017045908183632735,
      "loss": 1.0836726427078247,
      "step": 80
    },
    {
      "epoch": 0.3203163618388532,
      "grad_norm": 0.13863688707351685,
      "learning_rate": 0.00017005988023952097,
      "loss": 0.9540154933929443,
      "step": 81
    },
    {
      "epoch": 0.32427088482451805,
      "grad_norm": 0.14704303443431854,
      "learning_rate": 0.0001696606786427146,
      "loss": 1.03548002243042,
      "step": 82
    },
    {
      "epoch": 0.3282254078101829,
      "grad_norm": 0.13630537688732147,
      "learning_rate": 0.0001692614770459082,
      "loss": 0.9100798964500427,
      "step": 83
    },
    {
      "epoch": 0.33217993079584773,
      "grad_norm": 0.14166879653930664,
      "learning_rate": 0.0001688622754491018,
      "loss": 1.0137436389923096,
      "step": 84
    },
    {
      "epoch": 0.33613445378151263,
      "grad_norm": 0.14558711647987366,
      "learning_rate": 0.00016846307385229542,
      "loss": 1.0042855739593506,
      "step": 85
    },
    {
      "epoch": 0.3400889767671775,
      "grad_norm": 0.13049034774303436,
      "learning_rate": 0.00016806387225548904,
      "loss": 0.9128093123435974,
      "step": 86
    },
    {
      "epoch": 0.3440434997528423,
      "grad_norm": 0.1458376795053482,
      "learning_rate": 0.00016766467065868263,
      "loss": 0.9017834663391113,
      "step": 87
    },
    {
      "epoch": 0.34799802273850716,
      "grad_norm": 0.13847292959690094,
      "learning_rate": 0.00016726546906187625,
      "loss": 0.9473759531974792,
      "step": 88
    },
    {
      "epoch": 0.351952545724172,
      "grad_norm": 0.15093441307544708,
      "learning_rate": 0.00016686626746506987,
      "loss": 0.9916189312934875,
      "step": 89
    },
    {
      "epoch": 0.35590706870983685,
      "grad_norm": 0.1472613364458084,
      "learning_rate": 0.00016646706586826348,
      "loss": 0.9674598574638367,
      "step": 90
    },
    {
      "epoch": 0.35986159169550175,
      "grad_norm": 0.13850581645965576,
      "learning_rate": 0.00016606786427145708,
      "loss": 0.972917377948761,
      "step": 91
    },
    {
      "epoch": 0.3638161146811666,
      "grad_norm": 0.15554893016815186,
      "learning_rate": 0.00016566866267465072,
      "loss": 0.8598817586898804,
      "step": 92
    },
    {
      "epoch": 0.36777063766683143,
      "grad_norm": 0.15589317679405212,
      "learning_rate": 0.00016526946107784431,
      "loss": 1.0263655185699463,
      "step": 93
    },
    {
      "epoch": 0.3717251606524963,
      "grad_norm": 0.14788870513439178,
      "learning_rate": 0.00016487025948103793,
      "loss": 1.0757544040679932,
      "step": 94
    },
    {
      "epoch": 0.3756796836381611,
      "grad_norm": 0.15305693447589874,
      "learning_rate": 0.00016447105788423155,
      "loss": 0.9259313344955444,
      "step": 95
    },
    {
      "epoch": 0.379634206623826,
      "grad_norm": 0.14788882434368134,
      "learning_rate": 0.00016407185628742517,
      "loss": 1.0758525133132935,
      "step": 96
    },
    {
      "epoch": 0.38358872960949086,
      "grad_norm": 0.15263086557388306,
      "learning_rate": 0.00016367265469061876,
      "loss": 0.9790467023849487,
      "step": 97
    },
    {
      "epoch": 0.3875432525951557,
      "grad_norm": 0.16988050937652588,
      "learning_rate": 0.00016327345309381238,
      "loss": 1.180403470993042,
      "step": 98
    },
    {
      "epoch": 0.39149777558082055,
      "grad_norm": 0.142135351896286,
      "learning_rate": 0.000162874251497006,
      "loss": 1.0949641466140747,
      "step": 99
    },
    {
      "epoch": 0.3954522985664854,
      "grad_norm": 0.1378023624420166,
      "learning_rate": 0.00016247504990019962,
      "loss": 1.0425848960876465,
      "step": 100
    },
    {
      "epoch": 0.3994068215521503,
      "grad_norm": 0.1591092050075531,
      "learning_rate": 0.0001620758483033932,
      "loss": 0.9338038563728333,
      "step": 101
    },
    {
      "epoch": 0.40336134453781514,
      "grad_norm": 0.1520695835351944,
      "learning_rate": 0.00016167664670658683,
      "loss": 0.8926813006401062,
      "step": 102
    },
    {
      "epoch": 0.40731586752348,
      "grad_norm": 0.14733289182186127,
      "learning_rate": 0.00016127744510978045,
      "loss": 1.082033395767212,
      "step": 103
    },
    {
      "epoch": 0.4112703905091448,
      "grad_norm": 0.14460161328315735,
      "learning_rate": 0.00016087824351297407,
      "loss": 0.9306143522262573,
      "step": 104
    },
    {
      "epoch": 0.41522491349480967,
      "grad_norm": 0.16207540035247803,
      "learning_rate": 0.00016047904191616766,
      "loss": 1.0030015707015991,
      "step": 105
    },
    {
      "epoch": 0.41917943648047457,
      "grad_norm": 0.1540522575378418,
      "learning_rate": 0.0001600798403193613,
      "loss": 1.1492794752120972,
      "step": 106
    },
    {
      "epoch": 0.4231339594661394,
      "grad_norm": 0.13939417898654938,
      "learning_rate": 0.0001596806387225549,
      "loss": 0.9942459464073181,
      "step": 107
    },
    {
      "epoch": 0.42708848245180425,
      "grad_norm": 0.17469069361686707,
      "learning_rate": 0.0001592814371257485,
      "loss": 0.9437049031257629,
      "step": 108
    },
    {
      "epoch": 0.4310430054374691,
      "grad_norm": 0.15532726049423218,
      "learning_rate": 0.00015888223552894214,
      "loss": 0.8414091467857361,
      "step": 109
    },
    {
      "epoch": 0.43499752842313394,
      "grad_norm": 0.1431339681148529,
      "learning_rate": 0.00015848303393213573,
      "loss": 0.909614086151123,
      "step": 110
    },
    {
      "epoch": 0.43895205140879884,
      "grad_norm": 0.1456097513437271,
      "learning_rate": 0.00015808383233532935,
      "loss": 1.0974111557006836,
      "step": 111
    },
    {
      "epoch": 0.4429065743944637,
      "grad_norm": 0.14371022582054138,
      "learning_rate": 0.00015768463073852296,
      "loss": 1.0514923334121704,
      "step": 112
    },
    {
      "epoch": 0.4468610973801285,
      "grad_norm": 0.14185507595539093,
      "learning_rate": 0.00015728542914171658,
      "loss": 0.856088399887085,
      "step": 113
    },
    {
      "epoch": 0.45081562036579337,
      "grad_norm": 0.14548474550247192,
      "learning_rate": 0.00015688622754491018,
      "loss": 0.9919300079345703,
      "step": 114
    },
    {
      "epoch": 0.4547701433514582,
      "grad_norm": 0.1524973064661026,
      "learning_rate": 0.0001564870259481038,
      "loss": 0.8925392031669617,
      "step": 115
    },
    {
      "epoch": 0.4587246663371231,
      "grad_norm": 0.14767196774482727,
      "learning_rate": 0.0001560878243512974,
      "loss": 0.8464489579200745,
      "step": 116
    },
    {
      "epoch": 0.46267918932278795,
      "grad_norm": 0.15779703855514526,
      "learning_rate": 0.00015568862275449103,
      "loss": 1.0465806722640991,
      "step": 117
    },
    {
      "epoch": 0.4666337123084528,
      "grad_norm": 0.15219292044639587,
      "learning_rate": 0.00015528942115768462,
      "loss": 0.9196197986602783,
      "step": 118
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 0.15147675573825836,
      "learning_rate": 0.00015489021956087827,
      "loss": 0.9819110631942749,
      "step": 119
    },
    {
      "epoch": 0.4745427582797825,
      "grad_norm": 0.1430458277463913,
      "learning_rate": 0.00015449101796407186,
      "loss": 0.9948022365570068,
      "step": 120
    },
    {
      "epoch": 0.4784972812654474,
      "grad_norm": 0.15081898868083954,
      "learning_rate": 0.00015409181636726548,
      "loss": 0.9605839252471924,
      "step": 121
    },
    {
      "epoch": 0.4824518042511122,
      "grad_norm": 0.1469513326883316,
      "learning_rate": 0.0001536926147704591,
      "loss": 0.876885175704956,
      "step": 122
    },
    {
      "epoch": 0.48640632723677707,
      "grad_norm": 0.1487644910812378,
      "learning_rate": 0.00015329341317365272,
      "loss": 0.8893944025039673,
      "step": 123
    },
    {
      "epoch": 0.4903608502224419,
      "grad_norm": 0.1546425074338913,
      "learning_rate": 0.0001528942115768463,
      "loss": 0.8940907120704651,
      "step": 124
    },
    {
      "epoch": 0.49431537320810676,
      "grad_norm": 0.15078657865524292,
      "learning_rate": 0.00015249500998003993,
      "loss": 1.0783774852752686,
      "step": 125
    },
    {
      "epoch": 0.4982698961937716,
      "grad_norm": 0.1505594104528427,
      "learning_rate": 0.00015209580838323355,
      "loss": 0.9070993661880493,
      "step": 126
    },
    {
      "epoch": 0.5022244191794365,
      "grad_norm": 0.15631473064422607,
      "learning_rate": 0.00015169660678642714,
      "loss": 0.9393852353096008,
      "step": 127
    },
    {
      "epoch": 0.5061789421651013,
      "grad_norm": 0.1533495932817459,
      "learning_rate": 0.00015129740518962076,
      "loss": 1.0298182964324951,
      "step": 128
    },
    {
      "epoch": 0.5101334651507662,
      "grad_norm": 0.15687382221221924,
      "learning_rate": 0.00015089820359281438,
      "loss": 0.9548342227935791,
      "step": 129
    },
    {
      "epoch": 0.5140879881364311,
      "grad_norm": 0.13609541952610016,
      "learning_rate": 0.000150499001996008,
      "loss": 0.9333449602127075,
      "step": 130
    },
    {
      "epoch": 0.5180425111220959,
      "grad_norm": 0.1493511199951172,
      "learning_rate": 0.0001500998003992016,
      "loss": 0.9676602482795715,
      "step": 131
    },
    {
      "epoch": 0.5219970341077608,
      "grad_norm": 0.1547534167766571,
      "learning_rate": 0.0001497005988023952,
      "loss": 1.0927131175994873,
      "step": 132
    },
    {
      "epoch": 0.5259515570934256,
      "grad_norm": 0.155633345246315,
      "learning_rate": 0.00014930139720558883,
      "loss": 0.762495219707489,
      "step": 133
    },
    {
      "epoch": 0.5299060800790905,
      "grad_norm": 0.1558597981929779,
      "learning_rate": 0.00014890219560878245,
      "loss": 0.957042396068573,
      "step": 134
    },
    {
      "epoch": 0.5338606030647554,
      "grad_norm": 0.1418825089931488,
      "learning_rate": 0.00014850299401197604,
      "loss": 1.0327900648117065,
      "step": 135
    },
    {
      "epoch": 0.5378151260504201,
      "grad_norm": 0.1431950032711029,
      "learning_rate": 0.00014810379241516968,
      "loss": 0.9374012351036072,
      "step": 136
    },
    {
      "epoch": 0.541769649036085,
      "grad_norm": 0.16276349127292633,
      "learning_rate": 0.00014770459081836328,
      "loss": 0.9466843605041504,
      "step": 137
    },
    {
      "epoch": 0.5457241720217498,
      "grad_norm": 0.14857441186904907,
      "learning_rate": 0.0001473053892215569,
      "loss": 0.9261118769645691,
      "step": 138
    },
    {
      "epoch": 0.5496786950074147,
      "grad_norm": 0.16782596707344055,
      "learning_rate": 0.0001469061876247505,
      "loss": 1.0146270990371704,
      "step": 139
    },
    {
      "epoch": 0.5536332179930796,
      "grad_norm": 0.15024535357952118,
      "learning_rate": 0.00014650698602794413,
      "loss": 0.8856394290924072,
      "step": 140
    },
    {
      "epoch": 0.5575877409787444,
      "grad_norm": 0.1513880342245102,
      "learning_rate": 0.00014610778443113772,
      "loss": 1.0763099193572998,
      "step": 141
    },
    {
      "epoch": 0.5615422639644093,
      "grad_norm": 0.14922404289245605,
      "learning_rate": 0.00014570858283433134,
      "loss": 1.0585473775863647,
      "step": 142
    },
    {
      "epoch": 0.5654967869500741,
      "grad_norm": 0.14560917019844055,
      "learning_rate": 0.00014530938123752496,
      "loss": 0.8189446330070496,
      "step": 143
    },
    {
      "epoch": 0.569451309935739,
      "grad_norm": 0.1498928666114807,
      "learning_rate": 0.00014491017964071858,
      "loss": 0.9366933703422546,
      "step": 144
    },
    {
      "epoch": 0.5734058329214039,
      "grad_norm": 0.14731937646865845,
      "learning_rate": 0.00014451097804391217,
      "loss": 0.978458821773529,
      "step": 145
    },
    {
      "epoch": 0.5773603559070687,
      "grad_norm": 0.14156509935855865,
      "learning_rate": 0.00014411177644710582,
      "loss": 0.9639441967010498,
      "step": 146
    },
    {
      "epoch": 0.5813148788927336,
      "grad_norm": 0.17466521263122559,
      "learning_rate": 0.0001437125748502994,
      "loss": 0.9246646165847778,
      "step": 147
    },
    {
      "epoch": 0.5852694018783984,
      "grad_norm": 0.15222910046577454,
      "learning_rate": 0.000143313373253493,
      "loss": 0.9557418823242188,
      "step": 148
    },
    {
      "epoch": 0.5892239248640633,
      "grad_norm": 0.14972400665283203,
      "learning_rate": 0.00014291417165668665,
      "loss": 0.8998520970344543,
      "step": 149
    },
    {
      "epoch": 0.5931784478497282,
      "grad_norm": 0.16542503237724304,
      "learning_rate": 0.00014251497005988024,
      "loss": 0.8584086298942566,
      "step": 150
    },
    {
      "epoch": 0.597132970835393,
      "grad_norm": 0.1549108326435089,
      "learning_rate": 0.00014211576846307386,
      "loss": 0.9696409702301025,
      "step": 151
    },
    {
      "epoch": 0.6010874938210579,
      "grad_norm": 0.14827242493629456,
      "learning_rate": 0.00014171656686626745,
      "loss": 0.8613938093185425,
      "step": 152
    },
    {
      "epoch": 0.6050420168067226,
      "grad_norm": 0.15346549451351166,
      "learning_rate": 0.0001413173652694611,
      "loss": 0.7989118695259094,
      "step": 153
    },
    {
      "epoch": 0.6089965397923875,
      "grad_norm": 0.15291966497898102,
      "learning_rate": 0.0001409181636726547,
      "loss": 1.0761021375656128,
      "step": 154
    },
    {
      "epoch": 0.6129510627780524,
      "grad_norm": 0.13826234638690948,
      "learning_rate": 0.0001405189620758483,
      "loss": 0.9109746217727661,
      "step": 155
    },
    {
      "epoch": 0.6169055857637172,
      "grad_norm": 0.14913445711135864,
      "learning_rate": 0.00014011976047904193,
      "loss": 1.0017129182815552,
      "step": 156
    },
    {
      "epoch": 0.6208601087493821,
      "grad_norm": 0.1526130735874176,
      "learning_rate": 0.00013972055888223555,
      "loss": 0.8955498933792114,
      "step": 157
    },
    {
      "epoch": 0.6248146317350469,
      "grad_norm": 0.15382827818393707,
      "learning_rate": 0.00013932135728542914,
      "loss": 1.1069719791412354,
      "step": 158
    },
    {
      "epoch": 0.6287691547207118,
      "grad_norm": 0.14784258604049683,
      "learning_rate": 0.00013892215568862276,
      "loss": 0.9784612655639648,
      "step": 159
    },
    {
      "epoch": 0.6327236777063767,
      "grad_norm": 0.15217405557632446,
      "learning_rate": 0.00013852295409181638,
      "loss": 0.9924787878990173,
      "step": 160
    },
    {
      "epoch": 0.6366782006920415,
      "grad_norm": 0.17497238516807556,
      "learning_rate": 0.00013812375249501,
      "loss": 0.8755843043327332,
      "step": 161
    },
    {
      "epoch": 0.6406327236777064,
      "grad_norm": 0.15077446401119232,
      "learning_rate": 0.00013772455089820359,
      "loss": 0.9884225726127625,
      "step": 162
    },
    {
      "epoch": 0.6445872466633712,
      "grad_norm": 0.1486707627773285,
      "learning_rate": 0.00013732534930139723,
      "loss": 1.0523698329925537,
      "step": 163
    },
    {
      "epoch": 0.6485417696490361,
      "grad_norm": 0.13988643884658813,
      "learning_rate": 0.00013692614770459082,
      "loss": 0.9002912640571594,
      "step": 164
    },
    {
      "epoch": 0.652496292634701,
      "grad_norm": 0.15143455564975739,
      "learning_rate": 0.00013652694610778444,
      "loss": 0.9852843284606934,
      "step": 165
    },
    {
      "epoch": 0.6564508156203658,
      "grad_norm": 0.15765251219272614,
      "learning_rate": 0.00013612774451097806,
      "loss": 0.9757329225540161,
      "step": 166
    },
    {
      "epoch": 0.6604053386060307,
      "grad_norm": 0.15192811191082,
      "learning_rate": 0.00013572854291417165,
      "loss": 0.9793543815612793,
      "step": 167
    },
    {
      "epoch": 0.6643598615916955,
      "grad_norm": 0.1370113044977188,
      "learning_rate": 0.00013532934131736527,
      "loss": 0.8899397253990173,
      "step": 168
    },
    {
      "epoch": 0.6683143845773604,
      "grad_norm": 0.16300129890441895,
      "learning_rate": 0.0001349301397205589,
      "loss": 0.9691711664199829,
      "step": 169
    },
    {
      "epoch": 0.6722689075630253,
      "grad_norm": 0.1447598934173584,
      "learning_rate": 0.0001345309381237525,
      "loss": 1.0262728929519653,
      "step": 170
    },
    {
      "epoch": 0.67622343054869,
      "grad_norm": 0.1426248848438263,
      "learning_rate": 0.0001341317365269461,
      "loss": 0.8865811824798584,
      "step": 171
    },
    {
      "epoch": 0.680177953534355,
      "grad_norm": 0.1596144288778305,
      "learning_rate": 0.00013373253493013972,
      "loss": 1.041471242904663,
      "step": 172
    },
    {
      "epoch": 0.6841324765200197,
      "grad_norm": 0.16748711466789246,
      "learning_rate": 0.00013333333333333334,
      "loss": 1.060260534286499,
      "step": 173
    },
    {
      "epoch": 0.6880869995056846,
      "grad_norm": 0.14779865741729736,
      "learning_rate": 0.00013293413173652696,
      "loss": 0.9902845025062561,
      "step": 174
    },
    {
      "epoch": 0.6920415224913494,
      "grad_norm": 0.1514303982257843,
      "learning_rate": 0.00013253493013972055,
      "loss": 0.9630454778671265,
      "step": 175
    },
    {
      "epoch": 0.6959960454770143,
      "grad_norm": 0.16021154820919037,
      "learning_rate": 0.0001321357285429142,
      "loss": 0.8938897848129272,
      "step": 176
    },
    {
      "epoch": 0.6999505684626792,
      "grad_norm": 0.1604602336883545,
      "learning_rate": 0.0001317365269461078,
      "loss": 0.7806445956230164,
      "step": 177
    },
    {
      "epoch": 0.703905091448344,
      "grad_norm": 0.14814768731594086,
      "learning_rate": 0.0001313373253493014,
      "loss": 0.7236217856407166,
      "step": 178
    },
    {
      "epoch": 0.7078596144340089,
      "grad_norm": 0.13816480338573456,
      "learning_rate": 0.000130938123752495,
      "loss": 1.059952974319458,
      "step": 179
    },
    {
      "epoch": 0.7118141374196737,
      "grad_norm": 0.15320385992527008,
      "learning_rate": 0.00013053892215568865,
      "loss": 1.037667989730835,
      "step": 180
    },
    {
      "epoch": 0.7157686604053386,
      "grad_norm": 0.14675435423851013,
      "learning_rate": 0.00013013972055888224,
      "loss": 1.0143626928329468,
      "step": 181
    },
    {
      "epoch": 0.7197231833910035,
      "grad_norm": 0.13777698576450348,
      "learning_rate": 0.00012974051896207586,
      "loss": 0.8841183185577393,
      "step": 182
    },
    {
      "epoch": 0.7236777063766683,
      "grad_norm": 0.14622290432453156,
      "learning_rate": 0.00012934131736526947,
      "loss": 0.9912742376327515,
      "step": 183
    },
    {
      "epoch": 0.7276322293623332,
      "grad_norm": 0.14383630454540253,
      "learning_rate": 0.0001289421157684631,
      "loss": 1.031080722808838,
      "step": 184
    },
    {
      "epoch": 0.731586752347998,
      "grad_norm": 0.14537449181079865,
      "learning_rate": 0.00012854291417165669,
      "loss": 0.9928056001663208,
      "step": 185
    },
    {
      "epoch": 0.7355412753336629,
      "grad_norm": 0.1553298830986023,
      "learning_rate": 0.0001281437125748503,
      "loss": 1.0729012489318848,
      "step": 186
    },
    {
      "epoch": 0.7394957983193278,
      "grad_norm": 0.15434440970420837,
      "learning_rate": 0.00012774451097804392,
      "loss": 0.9299134016036987,
      "step": 187
    },
    {
      "epoch": 0.7434503213049926,
      "grad_norm": 0.1517597734928131,
      "learning_rate": 0.00012734530938123752,
      "loss": 0.8981556296348572,
      "step": 188
    },
    {
      "epoch": 0.7474048442906575,
      "grad_norm": 0.14408698678016663,
      "learning_rate": 0.00012694610778443113,
      "loss": 0.7834718227386475,
      "step": 189
    },
    {
      "epoch": 0.7513593672763222,
      "grad_norm": 0.1524432897567749,
      "learning_rate": 0.00012654690618762475,
      "loss": 0.9502565264701843,
      "step": 190
    },
    {
      "epoch": 0.7553138902619871,
      "grad_norm": 0.16056875884532928,
      "learning_rate": 0.00012614770459081837,
      "loss": 1.0030090808868408,
      "step": 191
    },
    {
      "epoch": 0.759268413247652,
      "grad_norm": 0.14580710232257843,
      "learning_rate": 0.00012574850299401196,
      "loss": 0.937939465045929,
      "step": 192
    },
    {
      "epoch": 0.7632229362333168,
      "grad_norm": 0.14517466723918915,
      "learning_rate": 0.0001253493013972056,
      "loss": 1.1117490530014038,
      "step": 193
    },
    {
      "epoch": 0.7671774592189817,
      "grad_norm": 0.15558141469955444,
      "learning_rate": 0.0001249500998003992,
      "loss": 0.8213934898376465,
      "step": 194
    },
    {
      "epoch": 0.7711319822046465,
      "grad_norm": 0.14642053842544556,
      "learning_rate": 0.00012455089820359282,
      "loss": 0.8714714646339417,
      "step": 195
    },
    {
      "epoch": 0.7750865051903114,
      "grad_norm": 0.15025141835212708,
      "learning_rate": 0.00012415169660678644,
      "loss": 1.0590744018554688,
      "step": 196
    },
    {
      "epoch": 0.7790410281759763,
      "grad_norm": 0.1296977996826172,
      "learning_rate": 0.00012375249500998006,
      "loss": 1.0535149574279785,
      "step": 197
    },
    {
      "epoch": 0.7829955511616411,
      "grad_norm": 0.15777179598808289,
      "learning_rate": 0.00012335329341317365,
      "loss": 1.0486925840377808,
      "step": 198
    },
    {
      "epoch": 0.786950074147306,
      "grad_norm": 0.13769429922103882,
      "learning_rate": 0.00012295409181636727,
      "loss": 0.9360702633857727,
      "step": 199
    },
    {
      "epoch": 0.7909045971329708,
      "grad_norm": 0.15268363058567047,
      "learning_rate": 0.0001225548902195609,
      "loss": 0.8887878656387329,
      "step": 200
    },
    {
      "epoch": 0.7948591201186357,
      "grad_norm": 0.13850852847099304,
      "learning_rate": 0.0001221556886227545,
      "loss": 1.083563208580017,
      "step": 201
    },
    {
      "epoch": 0.7988136431043006,
      "grad_norm": 0.16249485313892365,
      "learning_rate": 0.00012175648702594811,
      "loss": 1.0185102224349976,
      "step": 202
    },
    {
      "epoch": 0.8027681660899654,
      "grad_norm": 0.14542728662490845,
      "learning_rate": 0.00012135728542914173,
      "loss": 0.985219419002533,
      "step": 203
    },
    {
      "epoch": 0.8067226890756303,
      "grad_norm": 0.1401057094335556,
      "learning_rate": 0.00012095808383233534,
      "loss": 0.9981472492218018,
      "step": 204
    },
    {
      "epoch": 0.8106772120612951,
      "grad_norm": 0.16163145005702972,
      "learning_rate": 0.00012055888223552896,
      "loss": 0.9624532461166382,
      "step": 205
    },
    {
      "epoch": 0.81463173504696,
      "grad_norm": 0.1544468253850937,
      "learning_rate": 0.00012015968063872256,
      "loss": 0.9114558696746826,
      "step": 206
    },
    {
      "epoch": 0.8185862580326249,
      "grad_norm": 0.15567342936992645,
      "learning_rate": 0.00011976047904191617,
      "loss": 0.9480348825454712,
      "step": 207
    },
    {
      "epoch": 0.8225407810182896,
      "grad_norm": 0.15945857763290405,
      "learning_rate": 0.00011936127744510979,
      "loss": 0.9799912571907043,
      "step": 208
    },
    {
      "epoch": 0.8264953040039545,
      "grad_norm": 0.15980277955532074,
      "learning_rate": 0.00011896207584830339,
      "loss": 1.0797210931777954,
      "step": 209
    },
    {
      "epoch": 0.8304498269896193,
      "grad_norm": 0.14261196553707123,
      "learning_rate": 0.00011856287425149701,
      "loss": 1.0038321018218994,
      "step": 210
    },
    {
      "epoch": 0.8344043499752842,
      "grad_norm": 0.15023842453956604,
      "learning_rate": 0.00011816367265469061,
      "loss": 1.0017417669296265,
      "step": 211
    },
    {
      "epoch": 0.8383588729609491,
      "grad_norm": 0.14774499833583832,
      "learning_rate": 0.00011776447105788423,
      "loss": 1.056884765625,
      "step": 212
    },
    {
      "epoch": 0.8423133959466139,
      "grad_norm": 0.1311042457818985,
      "learning_rate": 0.00011736526946107784,
      "loss": 1.015238881111145,
      "step": 213
    },
    {
      "epoch": 0.8462679189322788,
      "grad_norm": 0.14513953030109406,
      "learning_rate": 0.00011696606786427147,
      "loss": 1.0354350805282593,
      "step": 214
    },
    {
      "epoch": 0.8502224419179436,
      "grad_norm": 0.1631115972995758,
      "learning_rate": 0.00011656686626746506,
      "loss": 0.9117772579193115,
      "step": 215
    },
    {
      "epoch": 0.8541769649036085,
      "grad_norm": 0.16442656517028809,
      "learning_rate": 0.0001161676646706587,
      "loss": 1.0395290851593018,
      "step": 216
    },
    {
      "epoch": 0.8581314878892734,
      "grad_norm": 0.14986057579517365,
      "learning_rate": 0.0001157684630738523,
      "loss": 0.9993502497673035,
      "step": 217
    },
    {
      "epoch": 0.8620860108749382,
      "grad_norm": 0.16269713640213013,
      "learning_rate": 0.00011536926147704592,
      "loss": 0.8923558592796326,
      "step": 218
    },
    {
      "epoch": 0.8660405338606031,
      "grad_norm": 0.14905333518981934,
      "learning_rate": 0.00011497005988023953,
      "loss": 0.846024751663208,
      "step": 219
    },
    {
      "epoch": 0.8699950568462679,
      "grad_norm": 0.14860469102859497,
      "learning_rate": 0.00011457085828343314,
      "loss": 0.933295488357544,
      "step": 220
    },
    {
      "epoch": 0.8739495798319328,
      "grad_norm": 0.15000364184379578,
      "learning_rate": 0.00011417165668662675,
      "loss": 0.9875235557556152,
      "step": 221
    },
    {
      "epoch": 0.8779041028175977,
      "grad_norm": 0.15674816071987152,
      "learning_rate": 0.00011377245508982037,
      "loss": 0.8917112946510315,
      "step": 222
    },
    {
      "epoch": 0.8818586258032625,
      "grad_norm": 0.16109170019626617,
      "learning_rate": 0.00011337325349301397,
      "loss": 0.9784120321273804,
      "step": 223
    },
    {
      "epoch": 0.8858131487889274,
      "grad_norm": 0.15252313017845154,
      "learning_rate": 0.0001129740518962076,
      "loss": 0.7924797534942627,
      "step": 224
    },
    {
      "epoch": 0.8897676717745922,
      "grad_norm": 0.15269458293914795,
      "learning_rate": 0.0001125748502994012,
      "loss": 0.9920112490653992,
      "step": 225
    },
    {
      "epoch": 0.893722194760257,
      "grad_norm": 0.17212046682834625,
      "learning_rate": 0.00011217564870259483,
      "loss": 0.9893192052841187,
      "step": 226
    },
    {
      "epoch": 0.897676717745922,
      "grad_norm": 0.15529413521289825,
      "learning_rate": 0.00011177644710578842,
      "loss": 1.0025854110717773,
      "step": 227
    },
    {
      "epoch": 0.9016312407315867,
      "grad_norm": 0.17252163589000702,
      "learning_rate": 0.00011137724550898203,
      "loss": 0.8992288112640381,
      "step": 228
    },
    {
      "epoch": 0.9055857637172516,
      "grad_norm": 0.1746063530445099,
      "learning_rate": 0.00011097804391217566,
      "loss": 0.8158121705055237,
      "step": 229
    },
    {
      "epoch": 0.9095402867029164,
      "grad_norm": 0.13989895582199097,
      "learning_rate": 0.00011057884231536925,
      "loss": 1.0338526964187622,
      "step": 230
    },
    {
      "epoch": 0.9134948096885813,
      "grad_norm": 0.16055206954479218,
      "learning_rate": 0.00011017964071856288,
      "loss": 0.9847093224525452,
      "step": 231
    },
    {
      "epoch": 0.9174493326742462,
      "grad_norm": 0.16400660574436188,
      "learning_rate": 0.00010978043912175649,
      "loss": 0.9464921951293945,
      "step": 232
    },
    {
      "epoch": 0.921403855659911,
      "grad_norm": 0.14987632632255554,
      "learning_rate": 0.00010938123752495011,
      "loss": 0.8394877910614014,
      "step": 233
    },
    {
      "epoch": 0.9253583786455759,
      "grad_norm": 0.16941316425800323,
      "learning_rate": 0.00010898203592814371,
      "loss": 0.8612609505653381,
      "step": 234
    },
    {
      "epoch": 0.9293129016312407,
      "grad_norm": 0.16219089925289154,
      "learning_rate": 0.00010858283433133733,
      "loss": 0.8607385158538818,
      "step": 235
    },
    {
      "epoch": 0.9332674246169056,
      "grad_norm": 0.1656905710697174,
      "learning_rate": 0.00010818363273453094,
      "loss": 1.0054378509521484,
      "step": 236
    },
    {
      "epoch": 0.9372219476025705,
      "grad_norm": 0.15206600725650787,
      "learning_rate": 0.00010778443113772456,
      "loss": 1.0277290344238281,
      "step": 237
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 0.1560627520084381,
      "learning_rate": 0.00010738522954091816,
      "loss": 0.9026745557785034,
      "step": 238
    },
    {
      "epoch": 0.9451309935739002,
      "grad_norm": 0.16465218365192413,
      "learning_rate": 0.00010698602794411178,
      "loss": 0.9656213521957397,
      "step": 239
    },
    {
      "epoch": 0.949085516559565,
      "grad_norm": 0.16291505098342896,
      "learning_rate": 0.00010658682634730539,
      "loss": 0.940356433391571,
      "step": 240
    },
    {
      "epoch": 0.9530400395452299,
      "grad_norm": 0.16686119139194489,
      "learning_rate": 0.00010618762475049902,
      "loss": 0.8976022601127625,
      "step": 241
    },
    {
      "epoch": 0.9569945625308948,
      "grad_norm": 0.1607900708913803,
      "learning_rate": 0.00010578842315369261,
      "loss": 0.9073758125305176,
      "step": 242
    },
    {
      "epoch": 0.9609490855165596,
      "grad_norm": 0.15350642800331116,
      "learning_rate": 0.00010538922155688624,
      "loss": 0.8798397779464722,
      "step": 243
    },
    {
      "epoch": 0.9649036085022245,
      "grad_norm": 0.13445277512073517,
      "learning_rate": 0.00010499001996007985,
      "loss": 0.8960294723510742,
      "step": 244
    },
    {
      "epoch": 0.9688581314878892,
      "grad_norm": 0.15072865784168243,
      "learning_rate": 0.00010459081836327347,
      "loss": 0.9184878468513489,
      "step": 245
    },
    {
      "epoch": 0.9728126544735541,
      "grad_norm": 0.1483660340309143,
      "learning_rate": 0.00010419161676646707,
      "loss": 1.000427484512329,
      "step": 246
    },
    {
      "epoch": 0.9767671774592189,
      "grad_norm": 0.16323480010032654,
      "learning_rate": 0.00010379241516966068,
      "loss": 0.9598352909088135,
      "step": 247
    },
    {
      "epoch": 0.9807217004448838,
      "grad_norm": 0.15449391305446625,
      "learning_rate": 0.0001033932135728543,
      "loss": 1.1161832809448242,
      "step": 248
    },
    {
      "epoch": 0.9846762234305487,
      "grad_norm": 0.15927913784980774,
      "learning_rate": 0.0001029940119760479,
      "loss": 0.9797319769859314,
      "step": 249
    },
    {
      "epoch": 0.9886307464162135,
      "grad_norm": 0.1711476743221283,
      "learning_rate": 0.00010259481037924152,
      "loss": 1.0162928104400635,
      "step": 250
    },
    {
      "epoch": 0.9925852694018784,
      "grad_norm": 0.15978345274925232,
      "learning_rate": 0.00010219560878243513,
      "loss": 0.8991297483444214,
      "step": 251
    },
    {
      "epoch": 0.9965397923875432,
      "grad_norm": 0.15758229792118073,
      "learning_rate": 0.00010179640718562875,
      "loss": 0.9805660843849182,
      "step": 252
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.17985662817955017,
      "learning_rate": 0.00010139720558882235,
      "loss": 1.0062508583068848,
      "step": 253
    },
    {
      "epoch": 1.0039545229856648,
      "grad_norm": 0.16520218551158905,
      "learning_rate": 0.00010099800399201597,
      "loss": 1.0412254333496094,
      "step": 254
    },
    {
      "epoch": 1.0079090459713298,
      "grad_norm": 0.16414225101470947,
      "learning_rate": 0.00010059880239520958,
      "loss": 0.9039946794509888,
      "step": 255
    },
    {
      "epoch": 1.0118635689569946,
      "grad_norm": 0.15268850326538086,
      "learning_rate": 0.00010019960079840321,
      "loss": 0.9569994807243347,
      "step": 256
    },
    {
      "epoch": 1.0158180919426594,
      "grad_norm": 0.15560995042324066,
      "learning_rate": 9.98003992015968e-05,
      "loss": 1.1160976886749268,
      "step": 257
    },
    {
      "epoch": 1.0197726149283244,
      "grad_norm": 0.15324212610721588,
      "learning_rate": 9.940119760479042e-05,
      "loss": 1.0373631715774536,
      "step": 258
    },
    {
      "epoch": 1.0237271379139892,
      "grad_norm": 0.15931884944438934,
      "learning_rate": 9.900199600798404e-05,
      "loss": 0.9546667337417603,
      "step": 259
    },
    {
      "epoch": 1.027681660899654,
      "grad_norm": 0.16295117139816284,
      "learning_rate": 9.860279441117764e-05,
      "loss": 1.002548098564148,
      "step": 260
    },
    {
      "epoch": 1.0316361838853187,
      "grad_norm": 0.17251881957054138,
      "learning_rate": 9.820359281437126e-05,
      "loss": 0.922970175743103,
      "step": 261
    },
    {
      "epoch": 1.0355907068709838,
      "grad_norm": 0.1694485992193222,
      "learning_rate": 9.780439121756487e-05,
      "loss": 1.0178519487380981,
      "step": 262
    },
    {
      "epoch": 1.0395452298566485,
      "grad_norm": 0.16809332370758057,
      "learning_rate": 9.740518962075849e-05,
      "loss": 0.9237082004547119,
      "step": 263
    },
    {
      "epoch": 1.0434997528423133,
      "grad_norm": 0.16604508459568024,
      "learning_rate": 9.700598802395209e-05,
      "loss": 0.9441342353820801,
      "step": 264
    },
    {
      "epoch": 1.0474542758279783,
      "grad_norm": 0.16178838908672333,
      "learning_rate": 9.660678642714571e-05,
      "loss": 0.9563836455345154,
      "step": 265
    },
    {
      "epoch": 1.0514087988136431,
      "grad_norm": 0.17229746282100677,
      "learning_rate": 9.620758483033933e-05,
      "loss": 0.9493328928947449,
      "step": 266
    },
    {
      "epoch": 1.055363321799308,
      "grad_norm": 0.17116741836071014,
      "learning_rate": 9.580838323353294e-05,
      "loss": 0.7871612906455994,
      "step": 267
    },
    {
      "epoch": 1.0593178447849727,
      "grad_norm": 0.19620539247989655,
      "learning_rate": 9.540918163672655e-05,
      "loss": 0.7880710959434509,
      "step": 268
    },
    {
      "epoch": 1.0632723677706377,
      "grad_norm": 0.17312850058078766,
      "learning_rate": 9.500998003992016e-05,
      "loss": 0.8220570683479309,
      "step": 269
    },
    {
      "epoch": 1.0672268907563025,
      "grad_norm": 0.2012282907962799,
      "learning_rate": 9.461077844311378e-05,
      "loss": 0.8117949962615967,
      "step": 270
    },
    {
      "epoch": 1.0711814137419673,
      "grad_norm": 0.16529391705989838,
      "learning_rate": 9.42115768463074e-05,
      "loss": 1.000198483467102,
      "step": 271
    },
    {
      "epoch": 1.0751359367276323,
      "grad_norm": 0.17409488558769226,
      "learning_rate": 9.3812375249501e-05,
      "loss": 0.9956350922584534,
      "step": 272
    },
    {
      "epoch": 1.079090459713297,
      "grad_norm": 0.18472394347190857,
      "learning_rate": 9.341317365269462e-05,
      "loss": 1.0315921306610107,
      "step": 273
    },
    {
      "epoch": 1.0830449826989619,
      "grad_norm": 0.16941356658935547,
      "learning_rate": 9.301397205588823e-05,
      "loss": 0.95827716588974,
      "step": 274
    },
    {
      "epoch": 1.0869995056846269,
      "grad_norm": 0.16447168588638306,
      "learning_rate": 9.261477045908185e-05,
      "loss": 0.8616600036621094,
      "step": 275
    },
    {
      "epoch": 1.0909540286702917,
      "grad_norm": 0.19374088943004608,
      "learning_rate": 9.221556886227547e-05,
      "loss": 0.7994685173034668,
      "step": 276
    },
    {
      "epoch": 1.0949085516559565,
      "grad_norm": 0.16742141544818878,
      "learning_rate": 9.181636726546906e-05,
      "loss": 0.8132893443107605,
      "step": 277
    },
    {
      "epoch": 1.0988630746416213,
      "grad_norm": 0.20061492919921875,
      "learning_rate": 9.141716566866268e-05,
      "loss": 0.9603545665740967,
      "step": 278
    },
    {
      "epoch": 1.1028175976272863,
      "grad_norm": 0.16895346343517303,
      "learning_rate": 9.101796407185628e-05,
      "loss": 1.0123639106750488,
      "step": 279
    },
    {
      "epoch": 1.106772120612951,
      "grad_norm": 0.1848328411579132,
      "learning_rate": 9.06187624750499e-05,
      "loss": 0.9767408967018127,
      "step": 280
    },
    {
      "epoch": 1.1107266435986158,
      "grad_norm": 0.1762303113937378,
      "learning_rate": 9.021956087824352e-05,
      "loss": 1.0461487770080566,
      "step": 281
    },
    {
      "epoch": 1.1146811665842808,
      "grad_norm": 0.18317660689353943,
      "learning_rate": 8.982035928143712e-05,
      "loss": 0.8694061636924744,
      "step": 282
    },
    {
      "epoch": 1.1186356895699456,
      "grad_norm": 0.275339812040329,
      "learning_rate": 8.942115768463074e-05,
      "loss": 0.859940767288208,
      "step": 283
    },
    {
      "epoch": 1.1225902125556104,
      "grad_norm": 0.18906059861183167,
      "learning_rate": 8.902195608782435e-05,
      "loss": 0.9108320474624634,
      "step": 284
    },
    {
      "epoch": 1.1265447355412754,
      "grad_norm": 0.1821734756231308,
      "learning_rate": 8.862275449101797e-05,
      "loss": 0.8772467970848083,
      "step": 285
    },
    {
      "epoch": 1.1304992585269402,
      "grad_norm": 0.1746835559606552,
      "learning_rate": 8.822355289421159e-05,
      "loss": 0.9596457481384277,
      "step": 286
    },
    {
      "epoch": 1.134453781512605,
      "grad_norm": 0.17881642282009125,
      "learning_rate": 8.782435129740519e-05,
      "loss": 0.9305652379989624,
      "step": 287
    },
    {
      "epoch": 1.1384083044982698,
      "grad_norm": 0.18960846960544586,
      "learning_rate": 8.742514970059881e-05,
      "loss": 0.9538063406944275,
      "step": 288
    },
    {
      "epoch": 1.1423628274839348,
      "grad_norm": 0.17049920558929443,
      "learning_rate": 8.702594810379242e-05,
      "loss": 0.8245007395744324,
      "step": 289
    },
    {
      "epoch": 1.1463173504695996,
      "grad_norm": 0.18376107513904572,
      "learning_rate": 8.662674650698604e-05,
      "loss": 0.888431966304779,
      "step": 290
    },
    {
      "epoch": 1.1502718734552644,
      "grad_norm": 0.1948973834514618,
      "learning_rate": 8.622754491017964e-05,
      "loss": 0.9021210074424744,
      "step": 291
    },
    {
      "epoch": 1.1542263964409294,
      "grad_norm": 0.2063995599746704,
      "learning_rate": 8.582834331337326e-05,
      "loss": 0.9560433030128479,
      "step": 292
    },
    {
      "epoch": 1.1581809194265942,
      "grad_norm": 0.1944153606891632,
      "learning_rate": 8.542914171656688e-05,
      "loss": 0.9102143049240112,
      "step": 293
    },
    {
      "epoch": 1.162135442412259,
      "grad_norm": 0.19204482436180115,
      "learning_rate": 8.502994011976048e-05,
      "loss": 0.8926071524620056,
      "step": 294
    },
    {
      "epoch": 1.1660899653979238,
      "grad_norm": 0.20266790688037872,
      "learning_rate": 8.46307385229541e-05,
      "loss": 1.0379507541656494,
      "step": 295
    },
    {
      "epoch": 1.1700444883835888,
      "grad_norm": 0.18556608259677887,
      "learning_rate": 8.423153692614771e-05,
      "loss": 0.8484141826629639,
      "step": 296
    },
    {
      "epoch": 1.1739990113692536,
      "grad_norm": 0.20597191154956818,
      "learning_rate": 8.383233532934131e-05,
      "loss": 0.7798240780830383,
      "step": 297
    },
    {
      "epoch": 1.1779535343549183,
      "grad_norm": 0.18532755970954895,
      "learning_rate": 8.343313373253493e-05,
      "loss": 0.8546709418296814,
      "step": 298
    },
    {
      "epoch": 1.1819080573405834,
      "grad_norm": 0.19410572946071625,
      "learning_rate": 8.303393213572854e-05,
      "loss": 1.0295960903167725,
      "step": 299
    },
    {
      "epoch": 1.1858625803262481,
      "grad_norm": 0.1959802806377411,
      "learning_rate": 8.263473053892216e-05,
      "loss": 0.8178250193595886,
      "step": 300
    },
    {
      "epoch": 1.189817103311913,
      "grad_norm": 0.1843615621328354,
      "learning_rate": 8.223552894211578e-05,
      "loss": 0.9791051745414734,
      "step": 301
    },
    {
      "epoch": 1.193771626297578,
      "grad_norm": 0.19072717428207397,
      "learning_rate": 8.183632734530938e-05,
      "loss": 0.8327443599700928,
      "step": 302
    },
    {
      "epoch": 1.1977261492832427,
      "grad_norm": 0.18121100962162018,
      "learning_rate": 8.1437125748503e-05,
      "loss": 0.9626063704490662,
      "step": 303
    },
    {
      "epoch": 1.2016806722689075,
      "grad_norm": 0.1815863400697708,
      "learning_rate": 8.10379241516966e-05,
      "loss": 0.9914010763168335,
      "step": 304
    },
    {
      "epoch": 1.2056351952545725,
      "grad_norm": 0.17102938890457153,
      "learning_rate": 8.063872255489022e-05,
      "loss": 0.8116806149482727,
      "step": 305
    },
    {
      "epoch": 1.2095897182402373,
      "grad_norm": 0.18805690109729767,
      "learning_rate": 8.023952095808383e-05,
      "loss": 0.8748471140861511,
      "step": 306
    },
    {
      "epoch": 1.213544241225902,
      "grad_norm": 0.18052758276462555,
      "learning_rate": 7.984031936127745e-05,
      "loss": 0.9938658475875854,
      "step": 307
    },
    {
      "epoch": 1.2174987642115669,
      "grad_norm": 0.19235683977603912,
      "learning_rate": 7.944111776447107e-05,
      "loss": 1.1100804805755615,
      "step": 308
    },
    {
      "epoch": 1.221453287197232,
      "grad_norm": 0.18457858264446259,
      "learning_rate": 7.904191616766467e-05,
      "loss": 0.9189471006393433,
      "step": 309
    },
    {
      "epoch": 1.2254078101828967,
      "grad_norm": 0.18914006650447845,
      "learning_rate": 7.864271457085829e-05,
      "loss": 0.8920475840568542,
      "step": 310
    },
    {
      "epoch": 1.2293623331685615,
      "grad_norm": 0.19251829385757446,
      "learning_rate": 7.82435129740519e-05,
      "loss": 0.939852774143219,
      "step": 311
    },
    {
      "epoch": 1.2333168561542265,
      "grad_norm": 0.17629219591617584,
      "learning_rate": 7.784431137724552e-05,
      "loss": 1.0373430252075195,
      "step": 312
    },
    {
      "epoch": 1.2372713791398913,
      "grad_norm": 0.18412235379219055,
      "learning_rate": 7.744510978043914e-05,
      "loss": 0.9560478329658508,
      "step": 313
    },
    {
      "epoch": 1.241225902125556,
      "grad_norm": 0.191380113363266,
      "learning_rate": 7.704590818363274e-05,
      "loss": 0.8593218326568604,
      "step": 314
    },
    {
      "epoch": 1.2451804251112208,
      "grad_norm": 0.18198034167289734,
      "learning_rate": 7.664670658682636e-05,
      "loss": 0.8392094969749451,
      "step": 315
    },
    {
      "epoch": 1.2491349480968859,
      "grad_norm": 0.18671447038650513,
      "learning_rate": 7.624750499001996e-05,
      "loss": 0.9436869621276855,
      "step": 316
    },
    {
      "epoch": 1.2530894710825506,
      "grad_norm": 0.17818371951580048,
      "learning_rate": 7.584830339321357e-05,
      "loss": 0.886319100856781,
      "step": 317
    },
    {
      "epoch": 1.2570439940682157,
      "grad_norm": 0.18418045341968536,
      "learning_rate": 7.544910179640719e-05,
      "loss": 0.8711346983909607,
      "step": 318
    },
    {
      "epoch": 1.2609985170538804,
      "grad_norm": 0.18546275794506073,
      "learning_rate": 7.50499001996008e-05,
      "loss": 0.9372309446334839,
      "step": 319
    },
    {
      "epoch": 1.2649530400395452,
      "grad_norm": 0.19021575152873993,
      "learning_rate": 7.465069860279441e-05,
      "loss": 0.9252364039421082,
      "step": 320
    },
    {
      "epoch": 1.26890756302521,
      "grad_norm": 0.185474693775177,
      "learning_rate": 7.425149700598802e-05,
      "loss": 0.8521521687507629,
      "step": 321
    },
    {
      "epoch": 1.2728620860108748,
      "grad_norm": 0.20583201944828033,
      "learning_rate": 7.385229540918164e-05,
      "loss": 0.9617403149604797,
      "step": 322
    },
    {
      "epoch": 1.2768166089965398,
      "grad_norm": 0.19673901796340942,
      "learning_rate": 7.345309381237526e-05,
      "loss": 1.0314775705337524,
      "step": 323
    },
    {
      "epoch": 1.2807711319822046,
      "grad_norm": 0.18468639254570007,
      "learning_rate": 7.305389221556886e-05,
      "loss": 0.9060774445533752,
      "step": 324
    },
    {
      "epoch": 1.2847256549678696,
      "grad_norm": 0.18173182010650635,
      "learning_rate": 7.265469061876248e-05,
      "loss": 0.7989869117736816,
      "step": 325
    },
    {
      "epoch": 1.2886801779535344,
      "grad_norm": 0.1873815804719925,
      "learning_rate": 7.225548902195609e-05,
      "loss": 0.980597972869873,
      "step": 326
    },
    {
      "epoch": 1.2926347009391992,
      "grad_norm": 0.19111032783985138,
      "learning_rate": 7.18562874251497e-05,
      "loss": 0.9921055436134338,
      "step": 327
    },
    {
      "epoch": 1.296589223924864,
      "grad_norm": 0.1846132129430771,
      "learning_rate": 7.145708582834332e-05,
      "loss": 0.9843934178352356,
      "step": 328
    },
    {
      "epoch": 1.300543746910529,
      "grad_norm": 0.23496906459331512,
      "learning_rate": 7.105788423153693e-05,
      "loss": 1.000301480293274,
      "step": 329
    },
    {
      "epoch": 1.3044982698961938,
      "grad_norm": 0.1931312382221222,
      "learning_rate": 7.065868263473055e-05,
      "loss": 0.8303369283676147,
      "step": 330
    },
    {
      "epoch": 1.3084527928818586,
      "grad_norm": 0.185639426112175,
      "learning_rate": 7.025948103792415e-05,
      "loss": 0.898432731628418,
      "step": 331
    },
    {
      "epoch": 1.3124073158675236,
      "grad_norm": 0.20121130347251892,
      "learning_rate": 6.986027944111777e-05,
      "loss": 0.9152477383613586,
      "step": 332
    },
    {
      "epoch": 1.3163618388531884,
      "grad_norm": 0.21694481372833252,
      "learning_rate": 6.946107784431138e-05,
      "loss": 0.82918781042099,
      "step": 333
    },
    {
      "epoch": 1.3203163618388531,
      "grad_norm": 0.1961311399936676,
      "learning_rate": 6.9061876247505e-05,
      "loss": 0.7353627681732178,
      "step": 334
    },
    {
      "epoch": 1.324270884824518,
      "grad_norm": 0.18697749078273773,
      "learning_rate": 6.866267465069862e-05,
      "loss": 0.9976124167442322,
      "step": 335
    },
    {
      "epoch": 1.328225407810183,
      "grad_norm": 0.20015275478363037,
      "learning_rate": 6.826347305389222e-05,
      "loss": 0.9885960221290588,
      "step": 336
    },
    {
      "epoch": 1.3321799307958477,
      "grad_norm": 0.170740008354187,
      "learning_rate": 6.786427145708583e-05,
      "loss": 0.8704991936683655,
      "step": 337
    },
    {
      "epoch": 1.3361344537815127,
      "grad_norm": 0.2036600261926651,
      "learning_rate": 6.746506986027945e-05,
      "loss": 0.8373860120773315,
      "step": 338
    },
    {
      "epoch": 1.3400889767671775,
      "grad_norm": 0.1967741847038269,
      "learning_rate": 6.706586826347305e-05,
      "loss": 0.9344059228897095,
      "step": 339
    },
    {
      "epoch": 1.3440434997528423,
      "grad_norm": 0.18084974586963654,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.9507811069488525,
      "step": 340
    },
    {
      "epoch": 1.347998022738507,
      "grad_norm": 0.1890396773815155,
      "learning_rate": 6.626746506986028e-05,
      "loss": 0.9278057217597961,
      "step": 341
    },
    {
      "epoch": 1.351952545724172,
      "grad_norm": 0.20094835758209229,
      "learning_rate": 6.58682634730539e-05,
      "loss": 0.9359115362167358,
      "step": 342
    },
    {
      "epoch": 1.355907068709837,
      "grad_norm": 0.19261251389980316,
      "learning_rate": 6.54690618762475e-05,
      "loss": 0.9001166820526123,
      "step": 343
    },
    {
      "epoch": 1.3598615916955017,
      "grad_norm": 0.19089815020561218,
      "learning_rate": 6.506986027944112e-05,
      "loss": 0.9219706654548645,
      "step": 344
    },
    {
      "epoch": 1.3638161146811667,
      "grad_norm": 0.20358265936374664,
      "learning_rate": 6.467065868263474e-05,
      "loss": 0.8198409080505371,
      "step": 345
    },
    {
      "epoch": 1.3677706376668315,
      "grad_norm": 0.20188573002815247,
      "learning_rate": 6.427145708582834e-05,
      "loss": 0.9551017880439758,
      "step": 346
    },
    {
      "epoch": 1.3717251606524963,
      "grad_norm": 0.18636231124401093,
      "learning_rate": 6.387225548902196e-05,
      "loss": 1.007879376411438,
      "step": 347
    },
    {
      "epoch": 1.375679683638161,
      "grad_norm": 0.20502787828445435,
      "learning_rate": 6.347305389221557e-05,
      "loss": 0.7461677193641663,
      "step": 348
    },
    {
      "epoch": 1.379634206623826,
      "grad_norm": 0.1991313099861145,
      "learning_rate": 6.307385229540919e-05,
      "loss": 0.9965579509735107,
      "step": 349
    },
    {
      "epoch": 1.3835887296094909,
      "grad_norm": 0.18065449595451355,
      "learning_rate": 6.26746506986028e-05,
      "loss": 0.7860137820243835,
      "step": 350
    },
    {
      "epoch": 1.3875432525951557,
      "grad_norm": 0.1943470537662506,
      "learning_rate": 6.227544910179641e-05,
      "loss": 0.9140808582305908,
      "step": 351
    },
    {
      "epoch": 1.3914977755808207,
      "grad_norm": 0.18946987390518188,
      "learning_rate": 6.187624750499003e-05,
      "loss": 0.813644289970398,
      "step": 352
    },
    {
      "epoch": 1.3954522985664854,
      "grad_norm": 0.18935807049274445,
      "learning_rate": 6.147704590818363e-05,
      "loss": 0.7775428891181946,
      "step": 353
    },
    {
      "epoch": 1.3994068215521502,
      "grad_norm": 0.17212191224098206,
      "learning_rate": 6.107784431137725e-05,
      "loss": 0.791588306427002,
      "step": 354
    },
    {
      "epoch": 1.403361344537815,
      "grad_norm": 0.1845926195383072,
      "learning_rate": 6.0678642714570866e-05,
      "loss": 0.8854494690895081,
      "step": 355
    },
    {
      "epoch": 1.40731586752348,
      "grad_norm": 0.19545923173427582,
      "learning_rate": 6.027944111776448e-05,
      "loss": 0.9289248585700989,
      "step": 356
    },
    {
      "epoch": 1.4112703905091448,
      "grad_norm": 0.23064754903316498,
      "learning_rate": 5.988023952095808e-05,
      "loss": 0.8877400755882263,
      "step": 357
    },
    {
      "epoch": 1.4152249134948096,
      "grad_norm": 0.18640878796577454,
      "learning_rate": 5.9481037924151695e-05,
      "loss": 0.8007562160491943,
      "step": 358
    },
    {
      "epoch": 1.4191794364804746,
      "grad_norm": 0.196823850274086,
      "learning_rate": 5.908183632734531e-05,
      "loss": 0.9147028923034668,
      "step": 359
    },
    {
      "epoch": 1.4231339594661394,
      "grad_norm": 0.18492864072322845,
      "learning_rate": 5.868263473053892e-05,
      "loss": 1.0567796230316162,
      "step": 360
    },
    {
      "epoch": 1.4270884824518042,
      "grad_norm": 0.19871287047863007,
      "learning_rate": 5.828343313373253e-05,
      "loss": 0.858993411064148,
      "step": 361
    },
    {
      "epoch": 1.431043005437469,
      "grad_norm": 0.1865636110305786,
      "learning_rate": 5.788423153692615e-05,
      "loss": 0.9598185420036316,
      "step": 362
    },
    {
      "epoch": 1.434997528423134,
      "grad_norm": 0.1950787603855133,
      "learning_rate": 5.748502994011976e-05,
      "loss": 0.866109311580658,
      "step": 363
    },
    {
      "epoch": 1.4389520514087988,
      "grad_norm": 0.19537241756916046,
      "learning_rate": 5.7085828343313375e-05,
      "loss": 0.9231923818588257,
      "step": 364
    },
    {
      "epoch": 1.4429065743944638,
      "grad_norm": 0.1848801076412201,
      "learning_rate": 5.668662674650699e-05,
      "loss": 0.9152354001998901,
      "step": 365
    },
    {
      "epoch": 1.4468610973801286,
      "grad_norm": 0.19516348838806152,
      "learning_rate": 5.62874251497006e-05,
      "loss": 0.9022656679153442,
      "step": 366
    },
    {
      "epoch": 1.4508156203657934,
      "grad_norm": 0.1875586360692978,
      "learning_rate": 5.588822355289421e-05,
      "loss": 0.9204172492027283,
      "step": 367
    },
    {
      "epoch": 1.4547701433514582,
      "grad_norm": 0.19239316880702972,
      "learning_rate": 5.548902195608783e-05,
      "loss": 0.9383366107940674,
      "step": 368
    },
    {
      "epoch": 1.4587246663371232,
      "grad_norm": 0.19720111787319183,
      "learning_rate": 5.508982035928144e-05,
      "loss": 0.961857795715332,
      "step": 369
    },
    {
      "epoch": 1.462679189322788,
      "grad_norm": 0.213732048869133,
      "learning_rate": 5.4690618762475055e-05,
      "loss": 0.8472163081169128,
      "step": 370
    },
    {
      "epoch": 1.4666337123084527,
      "grad_norm": 0.1938932090997696,
      "learning_rate": 5.429141716566867e-05,
      "loss": 0.8686806559562683,
      "step": 371
    },
    {
      "epoch": 1.4705882352941178,
      "grad_norm": 0.19152139127254486,
      "learning_rate": 5.389221556886228e-05,
      "loss": 0.8825725317001343,
      "step": 372
    },
    {
      "epoch": 1.4745427582797825,
      "grad_norm": 0.19953249394893646,
      "learning_rate": 5.349301397205589e-05,
      "loss": 1.0075819492340088,
      "step": 373
    },
    {
      "epoch": 1.4784972812654473,
      "grad_norm": 0.19870170950889587,
      "learning_rate": 5.309381237524951e-05,
      "loss": 0.8033257126808167,
      "step": 374
    },
    {
      "epoch": 1.4824518042511121,
      "grad_norm": 0.21190565824508667,
      "learning_rate": 5.269461077844312e-05,
      "loss": 0.9029344916343689,
      "step": 375
    },
    {
      "epoch": 1.4864063272367771,
      "grad_norm": 0.20307143032550812,
      "learning_rate": 5.2295409181636734e-05,
      "loss": 0.9491141438484192,
      "step": 376
    },
    {
      "epoch": 1.490360850222442,
      "grad_norm": 0.21230387687683105,
      "learning_rate": 5.189620758483034e-05,
      "loss": 0.9077959060668945,
      "step": 377
    },
    {
      "epoch": 1.4943153732081067,
      "grad_norm": 0.20202863216400146,
      "learning_rate": 5.149700598802395e-05,
      "loss": 0.9439913630485535,
      "step": 378
    },
    {
      "epoch": 1.4982698961937717,
      "grad_norm": 0.1929042786359787,
      "learning_rate": 5.1097804391217564e-05,
      "loss": 0.9769095778465271,
      "step": 379
    },
    {
      "epoch": 1.5022244191794365,
      "grad_norm": 0.21215690672397614,
      "learning_rate": 5.0698602794411176e-05,
      "loss": 0.7954482436180115,
      "step": 380
    },
    {
      "epoch": 1.5061789421651013,
      "grad_norm": 0.19395476579666138,
      "learning_rate": 5.029940119760479e-05,
      "loss": 0.8338028192520142,
      "step": 381
    },
    {
      "epoch": 1.510133465150766,
      "grad_norm": 0.2140199989080429,
      "learning_rate": 4.99001996007984e-05,
      "loss": 0.7927234172821045,
      "step": 382
    },
    {
      "epoch": 1.514087988136431,
      "grad_norm": 0.20886200666427612,
      "learning_rate": 4.950099800399202e-05,
      "loss": 0.9537109136581421,
      "step": 383
    },
    {
      "epoch": 1.5180425111220959,
      "grad_norm": 0.21319736540317535,
      "learning_rate": 4.910179640718563e-05,
      "loss": 0.7856256365776062,
      "step": 384
    },
    {
      "epoch": 1.5219970341077609,
      "grad_norm": 0.21167606115341187,
      "learning_rate": 4.8702594810379244e-05,
      "loss": 0.9939818978309631,
      "step": 385
    },
    {
      "epoch": 1.5259515570934257,
      "grad_norm": 0.20061740279197693,
      "learning_rate": 4.8303393213572856e-05,
      "loss": 0.9484026432037354,
      "step": 386
    },
    {
      "epoch": 1.5299060800790905,
      "grad_norm": 0.2059990018606186,
      "learning_rate": 4.790419161676647e-05,
      "loss": 0.8519854545593262,
      "step": 387
    },
    {
      "epoch": 1.5338606030647552,
      "grad_norm": 0.1978318989276886,
      "learning_rate": 4.750499001996008e-05,
      "loss": 0.8361144065856934,
      "step": 388
    },
    {
      "epoch": 1.53781512605042,
      "grad_norm": 0.2057390809059143,
      "learning_rate": 4.71057884231537e-05,
      "loss": 0.8409650325775146,
      "step": 389
    },
    {
      "epoch": 1.541769649036085,
      "grad_norm": 0.1905912309885025,
      "learning_rate": 4.670658682634731e-05,
      "loss": 0.8437705039978027,
      "step": 390
    },
    {
      "epoch": 1.5457241720217498,
      "grad_norm": 0.23166270554065704,
      "learning_rate": 4.630738522954092e-05,
      "loss": 1.1090465784072876,
      "step": 391
    },
    {
      "epoch": 1.5496786950074148,
      "grad_norm": 0.19709770381450653,
      "learning_rate": 4.590818363273453e-05,
      "loss": 0.9146186709403992,
      "step": 392
    },
    {
      "epoch": 1.5536332179930796,
      "grad_norm": 0.24494928121566772,
      "learning_rate": 4.550898203592814e-05,
      "loss": 0.8773439526557922,
      "step": 393
    },
    {
      "epoch": 1.5575877409787444,
      "grad_norm": 0.1936318725347519,
      "learning_rate": 4.510978043912176e-05,
      "loss": 0.8627104163169861,
      "step": 394
    },
    {
      "epoch": 1.5615422639644092,
      "grad_norm": 0.1917494237422943,
      "learning_rate": 4.471057884231537e-05,
      "loss": 0.9282490015029907,
      "step": 395
    },
    {
      "epoch": 1.565496786950074,
      "grad_norm": 0.20790532231330872,
      "learning_rate": 4.4311377245508984e-05,
      "loss": 0.9672350883483887,
      "step": 396
    },
    {
      "epoch": 1.569451309935739,
      "grad_norm": 0.21338993310928345,
      "learning_rate": 4.3912175648702596e-05,
      "loss": 0.9289650321006775,
      "step": 397
    },
    {
      "epoch": 1.573405832921404,
      "grad_norm": 0.20963947474956512,
      "learning_rate": 4.351297405189621e-05,
      "loss": 0.9762122631072998,
      "step": 398
    },
    {
      "epoch": 1.5773603559070688,
      "grad_norm": 0.20937083661556244,
      "learning_rate": 4.311377245508982e-05,
      "loss": 0.9213401079177856,
      "step": 399
    },
    {
      "epoch": 1.5813148788927336,
      "grad_norm": 0.20903795957565308,
      "learning_rate": 4.271457085828344e-05,
      "loss": 0.9836536645889282,
      "step": 400
    },
    {
      "epoch": 1.5852694018783984,
      "grad_norm": 0.20544159412384033,
      "learning_rate": 4.231536926147705e-05,
      "loss": 0.8152018785476685,
      "step": 401
    },
    {
      "epoch": 1.5892239248640632,
      "grad_norm": 0.1830497533082962,
      "learning_rate": 4.191616766467066e-05,
      "loss": 0.9987653493881226,
      "step": 402
    },
    {
      "epoch": 1.5931784478497282,
      "grad_norm": 0.1913018822669983,
      "learning_rate": 4.151696606786427e-05,
      "loss": 0.867318332195282,
      "step": 403
    },
    {
      "epoch": 1.597132970835393,
      "grad_norm": 0.19043081998825073,
      "learning_rate": 4.111776447105789e-05,
      "loss": 0.8715974688529968,
      "step": 404
    },
    {
      "epoch": 1.601087493821058,
      "grad_norm": 0.18875691294670105,
      "learning_rate": 4.07185628742515e-05,
      "loss": 0.904281735420227,
      "step": 405
    },
    {
      "epoch": 1.6050420168067228,
      "grad_norm": 0.2014741152524948,
      "learning_rate": 4.031936127744511e-05,
      "loss": 0.9567676186561584,
      "step": 406
    },
    {
      "epoch": 1.6089965397923875,
      "grad_norm": 0.17751306295394897,
      "learning_rate": 3.9920159680638724e-05,
      "loss": 0.8185122013092041,
      "step": 407
    },
    {
      "epoch": 1.6129510627780523,
      "grad_norm": 0.20318663120269775,
      "learning_rate": 3.9520958083832336e-05,
      "loss": 0.9554027318954468,
      "step": 408
    },
    {
      "epoch": 1.6169055857637171,
      "grad_norm": 0.1872302144765854,
      "learning_rate": 3.912175648702595e-05,
      "loss": 0.9051477313041687,
      "step": 409
    },
    {
      "epoch": 1.6208601087493821,
      "grad_norm": 0.21332977712154388,
      "learning_rate": 3.872255489021957e-05,
      "loss": 0.944547712802887,
      "step": 410
    },
    {
      "epoch": 1.624814631735047,
      "grad_norm": 0.18820840120315552,
      "learning_rate": 3.832335329341318e-05,
      "loss": 0.9271795749664307,
      "step": 411
    },
    {
      "epoch": 1.628769154720712,
      "grad_norm": 0.2146555483341217,
      "learning_rate": 3.7924151696606785e-05,
      "loss": 0.8307335376739502,
      "step": 412
    },
    {
      "epoch": 1.6327236777063767,
      "grad_norm": 0.2196199744939804,
      "learning_rate": 3.75249500998004e-05,
      "loss": 0.8816962242126465,
      "step": 413
    },
    {
      "epoch": 1.6366782006920415,
      "grad_norm": 0.1986646205186844,
      "learning_rate": 3.712574850299401e-05,
      "loss": 0.9725742936134338,
      "step": 414
    },
    {
      "epoch": 1.6406327236777063,
      "grad_norm": 0.18679843842983246,
      "learning_rate": 3.672654690618763e-05,
      "loss": 0.9385328888893127,
      "step": 415
    },
    {
      "epoch": 1.644587246663371,
      "grad_norm": 0.18637174367904663,
      "learning_rate": 3.632734530938124e-05,
      "loss": 0.9450833201408386,
      "step": 416
    },
    {
      "epoch": 1.648541769649036,
      "grad_norm": 0.20110389590263367,
      "learning_rate": 3.592814371257485e-05,
      "loss": 0.9009251594543457,
      "step": 417
    },
    {
      "epoch": 1.652496292634701,
      "grad_norm": 0.22820661962032318,
      "learning_rate": 3.5528942115768465e-05,
      "loss": 0.9610739350318909,
      "step": 418
    },
    {
      "epoch": 1.656450815620366,
      "grad_norm": 0.20116274058818817,
      "learning_rate": 3.512974051896208e-05,
      "loss": 0.9576656818389893,
      "step": 419
    },
    {
      "epoch": 1.6604053386060307,
      "grad_norm": 0.19964101910591125,
      "learning_rate": 3.473053892215569e-05,
      "loss": 0.9899635314941406,
      "step": 420
    },
    {
      "epoch": 1.6643598615916955,
      "grad_norm": 0.21723447740077972,
      "learning_rate": 3.433133732534931e-05,
      "loss": 0.7412058115005493,
      "step": 421
    },
    {
      "epoch": 1.6683143845773603,
      "grad_norm": 0.21164871752262115,
      "learning_rate": 3.393213572854291e-05,
      "loss": 1.107064127922058,
      "step": 422
    },
    {
      "epoch": 1.6722689075630253,
      "grad_norm": 0.20853902399539948,
      "learning_rate": 3.3532934131736525e-05,
      "loss": 1.0325095653533936,
      "step": 423
    },
    {
      "epoch": 1.67622343054869,
      "grad_norm": 0.1993069052696228,
      "learning_rate": 3.313373253493014e-05,
      "loss": 0.8811869621276855,
      "step": 424
    },
    {
      "epoch": 1.680177953534355,
      "grad_norm": 0.2086590826511383,
      "learning_rate": 3.273453093812375e-05,
      "loss": 0.8045269846916199,
      "step": 425
    },
    {
      "epoch": 1.6841324765200198,
      "grad_norm": 0.19502981007099152,
      "learning_rate": 3.233532934131737e-05,
      "loss": 1.0250900983810425,
      "step": 426
    },
    {
      "epoch": 1.6880869995056846,
      "grad_norm": 0.1864766627550125,
      "learning_rate": 3.193612774451098e-05,
      "loss": 0.7248687744140625,
      "step": 427
    },
    {
      "epoch": 1.6920415224913494,
      "grad_norm": 0.20849153399467468,
      "learning_rate": 3.153692614770459e-05,
      "loss": 0.8926454186439514,
      "step": 428
    },
    {
      "epoch": 1.6959960454770142,
      "grad_norm": 0.20903082191944122,
      "learning_rate": 3.1137724550898205e-05,
      "loss": 0.8962099552154541,
      "step": 429
    },
    {
      "epoch": 1.6999505684626792,
      "grad_norm": 0.1925486922264099,
      "learning_rate": 3.073852295409182e-05,
      "loss": 0.9962249994277954,
      "step": 430
    },
    {
      "epoch": 1.703905091448344,
      "grad_norm": 0.20653171837329865,
      "learning_rate": 3.0339321357285433e-05,
      "loss": 0.8618420958518982,
      "step": 431
    },
    {
      "epoch": 1.707859614434009,
      "grad_norm": 0.21909548342227936,
      "learning_rate": 2.994011976047904e-05,
      "loss": 1.0019207000732422,
      "step": 432
    },
    {
      "epoch": 1.7118141374196738,
      "grad_norm": 0.1952063888311386,
      "learning_rate": 2.9540918163672654e-05,
      "loss": 0.7654832005500793,
      "step": 433
    },
    {
      "epoch": 1.7157686604053386,
      "grad_norm": 0.20689325034618378,
      "learning_rate": 2.9141716566866266e-05,
      "loss": 0.9330834746360779,
      "step": 434
    },
    {
      "epoch": 1.7197231833910034,
      "grad_norm": 0.20880067348480225,
      "learning_rate": 2.874251497005988e-05,
      "loss": 0.9945483803749084,
      "step": 435
    },
    {
      "epoch": 1.7236777063766682,
      "grad_norm": 0.18159128725528717,
      "learning_rate": 2.8343313373253494e-05,
      "loss": 0.9131766557693481,
      "step": 436
    },
    {
      "epoch": 1.7276322293623332,
      "grad_norm": 0.19038815796375275,
      "learning_rate": 2.7944111776447106e-05,
      "loss": 0.8274218440055847,
      "step": 437
    },
    {
      "epoch": 1.731586752347998,
      "grad_norm": 0.20182478427886963,
      "learning_rate": 2.754491017964072e-05,
      "loss": 0.8425199389457703,
      "step": 438
    },
    {
      "epoch": 1.735541275333663,
      "grad_norm": 0.20511551201343536,
      "learning_rate": 2.7145708582834333e-05,
      "loss": 0.8865355253219604,
      "step": 439
    },
    {
      "epoch": 1.7394957983193278,
      "grad_norm": 0.2129596769809723,
      "learning_rate": 2.6746506986027946e-05,
      "loss": 0.9642688035964966,
      "step": 440
    },
    {
      "epoch": 1.7434503213049926,
      "grad_norm": 0.20142444968223572,
      "learning_rate": 2.634730538922156e-05,
      "loss": 1.0012695789337158,
      "step": 441
    },
    {
      "epoch": 1.7474048442906573,
      "grad_norm": 0.20275944471359253,
      "learning_rate": 2.594810379241517e-05,
      "loss": 0.8509343266487122,
      "step": 442
    },
    {
      "epoch": 1.7513593672763221,
      "grad_norm": 0.20978280901908875,
      "learning_rate": 2.5548902195608782e-05,
      "loss": 0.8017287850379944,
      "step": 443
    },
    {
      "epoch": 1.7553138902619871,
      "grad_norm": 0.2030046135187149,
      "learning_rate": 2.5149700598802394e-05,
      "loss": 0.9278156757354736,
      "step": 444
    },
    {
      "epoch": 1.7592684132476522,
      "grad_norm": 0.2252151072025299,
      "learning_rate": 2.475049900199601e-05,
      "loss": 0.9012824296951294,
      "step": 445
    },
    {
      "epoch": 1.763222936233317,
      "grad_norm": 0.20253197848796844,
      "learning_rate": 2.4351297405189622e-05,
      "loss": 0.8817086815834045,
      "step": 446
    },
    {
      "epoch": 1.7671774592189817,
      "grad_norm": 0.22054298222064972,
      "learning_rate": 2.3952095808383234e-05,
      "loss": 0.9003196954727173,
      "step": 447
    },
    {
      "epoch": 1.7711319822046465,
      "grad_norm": 0.2037447839975357,
      "learning_rate": 2.355289421157685e-05,
      "loss": 0.8119622468948364,
      "step": 448
    },
    {
      "epoch": 1.7750865051903113,
      "grad_norm": 0.21892541646957397,
      "learning_rate": 2.315369261477046e-05,
      "loss": 0.9405473470687866,
      "step": 449
    },
    {
      "epoch": 1.7790410281759763,
      "grad_norm": 0.20719027519226074,
      "learning_rate": 2.275449101796407e-05,
      "loss": 0.8205680847167969,
      "step": 450
    },
    {
      "epoch": 1.782995551161641,
      "grad_norm": 0.20699091255664825,
      "learning_rate": 2.2355289421157686e-05,
      "loss": 0.8950562477111816,
      "step": 451
    },
    {
      "epoch": 1.7869500741473061,
      "grad_norm": 0.19834667444229126,
      "learning_rate": 2.1956087824351298e-05,
      "loss": 0.8222463130950928,
      "step": 452
    },
    {
      "epoch": 1.790904597132971,
      "grad_norm": 0.19083131849765778,
      "learning_rate": 2.155688622754491e-05,
      "loss": 0.9506749510765076,
      "step": 453
    },
    {
      "epoch": 1.7948591201186357,
      "grad_norm": 0.21305403113365173,
      "learning_rate": 2.1157684630738526e-05,
      "loss": 0.833589494228363,
      "step": 454
    },
    {
      "epoch": 1.7988136431043005,
      "grad_norm": 0.21756337583065033,
      "learning_rate": 2.0758483033932134e-05,
      "loss": 0.7631924152374268,
      "step": 455
    },
    {
      "epoch": 1.8027681660899653,
      "grad_norm": 0.20038093626499176,
      "learning_rate": 2.035928143712575e-05,
      "loss": 1.037887692451477,
      "step": 456
    },
    {
      "epoch": 1.8067226890756303,
      "grad_norm": 0.20598313212394714,
      "learning_rate": 1.9960079840319362e-05,
      "loss": 0.9344784617424011,
      "step": 457
    },
    {
      "epoch": 1.810677212061295,
      "grad_norm": 0.19507546722888947,
      "learning_rate": 1.9560878243512974e-05,
      "loss": 0.9052549600601196,
      "step": 458
    },
    {
      "epoch": 1.81463173504696,
      "grad_norm": 0.20818522572517395,
      "learning_rate": 1.916167664670659e-05,
      "loss": 0.8613417148590088,
      "step": 459
    },
    {
      "epoch": 1.8185862580326249,
      "grad_norm": 0.18870945274829865,
      "learning_rate": 1.87624750499002e-05,
      "loss": 0.793246865272522,
      "step": 460
    },
    {
      "epoch": 1.8225407810182896,
      "grad_norm": 0.21497206389904022,
      "learning_rate": 1.8363273453093814e-05,
      "loss": 0.9714541435241699,
      "step": 461
    },
    {
      "epoch": 1.8264953040039544,
      "grad_norm": 0.21383772790431976,
      "learning_rate": 1.7964071856287426e-05,
      "loss": 1.0128012895584106,
      "step": 462
    },
    {
      "epoch": 1.8304498269896192,
      "grad_norm": 0.21303774416446686,
      "learning_rate": 1.756487025948104e-05,
      "loss": 0.8802911639213562,
      "step": 463
    },
    {
      "epoch": 1.8344043499752842,
      "grad_norm": 0.18445076048374176,
      "learning_rate": 1.7165668662674654e-05,
      "loss": 1.0024535655975342,
      "step": 464
    },
    {
      "epoch": 1.8383588729609492,
      "grad_norm": 0.20212195813655853,
      "learning_rate": 1.6766467065868263e-05,
      "loss": 1.1197216510772705,
      "step": 465
    },
    {
      "epoch": 1.842313395946614,
      "grad_norm": 0.2088390588760376,
      "learning_rate": 1.6367265469061875e-05,
      "loss": 0.9632558226585388,
      "step": 466
    },
    {
      "epoch": 1.8462679189322788,
      "grad_norm": 0.20784492790699005,
      "learning_rate": 1.596806387225549e-05,
      "loss": 0.734897255897522,
      "step": 467
    },
    {
      "epoch": 1.8502224419179436,
      "grad_norm": 0.19716675579547882,
      "learning_rate": 1.5568862275449103e-05,
      "loss": 0.9311115145683289,
      "step": 468
    },
    {
      "epoch": 1.8541769649036084,
      "grad_norm": 0.20142972469329834,
      "learning_rate": 1.5169660678642716e-05,
      "loss": 0.9369468688964844,
      "step": 469
    },
    {
      "epoch": 1.8581314878892734,
      "grad_norm": 0.20825821161270142,
      "learning_rate": 1.4770459081836327e-05,
      "loss": 1.135632038116455,
      "step": 470
    },
    {
      "epoch": 1.8620860108749382,
      "grad_norm": 0.20531900227069855,
      "learning_rate": 1.437125748502994e-05,
      "loss": 0.817120373249054,
      "step": 471
    },
    {
      "epoch": 1.8660405338606032,
      "grad_norm": 0.2101070135831833,
      "learning_rate": 1.3972055888223553e-05,
      "loss": 0.8993910551071167,
      "step": 472
    },
    {
      "epoch": 1.869995056846268,
      "grad_norm": 0.1841268241405487,
      "learning_rate": 1.3572854291417167e-05,
      "loss": 0.9081541299819946,
      "step": 473
    },
    {
      "epoch": 1.8739495798319328,
      "grad_norm": 0.19929905235767365,
      "learning_rate": 1.317365269461078e-05,
      "loss": 0.8846563696861267,
      "step": 474
    },
    {
      "epoch": 1.8779041028175976,
      "grad_norm": 0.21067850291728973,
      "learning_rate": 1.2774451097804391e-05,
      "loss": 0.8508776426315308,
      "step": 475
    },
    {
      "epoch": 1.8818586258032624,
      "grad_norm": 0.19630905985832214,
      "learning_rate": 1.2375249500998005e-05,
      "loss": 0.9228495359420776,
      "step": 476
    },
    {
      "epoch": 1.8858131487889274,
      "grad_norm": 0.22471991181373596,
      "learning_rate": 1.1976047904191617e-05,
      "loss": 0.8360285758972168,
      "step": 477
    },
    {
      "epoch": 1.8897676717745922,
      "grad_norm": 0.18797798454761505,
      "learning_rate": 1.157684630738523e-05,
      "loss": 0.8709227442741394,
      "step": 478
    },
    {
      "epoch": 1.8937221947602572,
      "grad_norm": 0.20813153684139252,
      "learning_rate": 1.1177644710578843e-05,
      "loss": 1.0134263038635254,
      "step": 479
    },
    {
      "epoch": 1.897676717745922,
      "grad_norm": 0.20971933007240295,
      "learning_rate": 1.0778443113772455e-05,
      "loss": 0.8753843307495117,
      "step": 480
    },
    {
      "epoch": 1.9016312407315867,
      "grad_norm": 0.19115358591079712,
      "learning_rate": 1.0379241516966067e-05,
      "loss": 0.8529820442199707,
      "step": 481
    },
    {
      "epoch": 1.9055857637172515,
      "grad_norm": 0.23405560851097107,
      "learning_rate": 9.980039920159681e-06,
      "loss": 0.9483686685562134,
      "step": 482
    },
    {
      "epoch": 1.9095402867029163,
      "grad_norm": 0.23471501469612122,
      "learning_rate": 9.580838323353295e-06,
      "loss": 0.9428390860557556,
      "step": 483
    },
    {
      "epoch": 1.9134948096885813,
      "grad_norm": 0.21804015338420868,
      "learning_rate": 9.181636726546907e-06,
      "loss": 0.8681425452232361,
      "step": 484
    },
    {
      "epoch": 1.9174493326742463,
      "grad_norm": 0.20593298971652985,
      "learning_rate": 8.78243512974052e-06,
      "loss": 0.9854474067687988,
      "step": 485
    },
    {
      "epoch": 1.9214038556599111,
      "grad_norm": 0.20268182456493378,
      "learning_rate": 8.383233532934131e-06,
      "loss": 0.8769013285636902,
      "step": 486
    },
    {
      "epoch": 1.925358378645576,
      "grad_norm": 0.20166848599910736,
      "learning_rate": 7.984031936127745e-06,
      "loss": 0.8038483262062073,
      "step": 487
    },
    {
      "epoch": 1.9293129016312407,
      "grad_norm": 0.20438715815544128,
      "learning_rate": 7.584830339321358e-06,
      "loss": 0.8820595741271973,
      "step": 488
    },
    {
      "epoch": 1.9332674246169055,
      "grad_norm": 0.22562836110591888,
      "learning_rate": 7.18562874251497e-06,
      "loss": 0.8607326745986938,
      "step": 489
    },
    {
      "epoch": 1.9372219476025705,
      "grad_norm": 0.24032363295555115,
      "learning_rate": 6.786427145708583e-06,
      "loss": 0.9563621878623962,
      "step": 490
    },
    {
      "epoch": 1.9411764705882353,
      "grad_norm": 0.22053006291389465,
      "learning_rate": 6.3872255489021955e-06,
      "loss": 0.9206818342208862,
      "step": 491
    },
    {
      "epoch": 1.9451309935739003,
      "grad_norm": 0.201730415225029,
      "learning_rate": 5.9880239520958085e-06,
      "loss": 0.8101902604103088,
      "step": 492
    },
    {
      "epoch": 1.949085516559565,
      "grad_norm": 0.2032587230205536,
      "learning_rate": 5.5888223552894215e-06,
      "loss": 0.8570499420166016,
      "step": 493
    },
    {
      "epoch": 1.9530400395452299,
      "grad_norm": 0.21162763237953186,
      "learning_rate": 5.189620758483034e-06,
      "loss": 0.8345759510993958,
      "step": 494
    },
    {
      "epoch": 1.9569945625308947,
      "grad_norm": 0.19271045923233032,
      "learning_rate": 4.7904191616766475e-06,
      "loss": 0.9391037821769714,
      "step": 495
    },
    {
      "epoch": 1.9609490855165594,
      "grad_norm": 0.20637477934360504,
      "learning_rate": 4.39121756487026e-06,
      "loss": 0.8780249953269958,
      "step": 496
    },
    {
      "epoch": 1.9649036085022245,
      "grad_norm": 0.20201361179351807,
      "learning_rate": 3.992015968063873e-06,
      "loss": 0.9155791997909546,
      "step": 497
    },
    {
      "epoch": 1.9688581314878892,
      "grad_norm": 0.21115684509277344,
      "learning_rate": 3.592814371257485e-06,
      "loss": 0.7178623676300049,
      "step": 498
    },
    {
      "epoch": 1.9728126544735543,
      "grad_norm": 0.22672364115715027,
      "learning_rate": 3.1936127744510977e-06,
      "loss": 0.8261544704437256,
      "step": 499
    },
    {
      "epoch": 1.976767177459219,
      "grad_norm": 0.18823912739753723,
      "learning_rate": 2.7944111776447107e-06,
      "loss": 0.8679497241973877,
      "step": 500
    },
    {
      "epoch": 1.9807217004448838,
      "grad_norm": 0.2101755440235138,
      "learning_rate": 2.3952095808383237e-06,
      "loss": 0.950539231300354,
      "step": 501
    },
    {
      "epoch": 1.9846762234305486,
      "grad_norm": 0.21033525466918945,
      "learning_rate": 1.9960079840319363e-06,
      "loss": 0.7960910797119141,
      "step": 502
    },
    {
      "epoch": 1.9886307464162134,
      "grad_norm": 0.21546964347362518,
      "learning_rate": 1.5968063872255489e-06,
      "loss": 0.9860714077949524,
      "step": 503
    },
    {
      "epoch": 1.9925852694018784,
      "grad_norm": 0.19765757024288177,
      "learning_rate": 1.1976047904191619e-06,
      "loss": 1.025565505027771,
      "step": 504
    },
    {
      "epoch": 1.9965397923875432,
      "grad_norm": 0.20392237603664398,
      "learning_rate": 7.984031936127744e-07,
      "loss": 0.8897353410720825,
      "step": 505
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.2248964011669159,
      "learning_rate": 3.992015968063872e-07,
      "loss": 0.7869975566864014,
      "step": 506
    }
  ],
  "logging_steps": 1,
  "max_steps": 506,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.5380020501658665e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}