{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.99867197875166,
  "eval_steps": 500,
  "global_step": 564,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0017706949977866313,
      "grad_norm": 0.04067350242893886,
      "learning_rate": 2.9411764705882355e-06,
      "loss": 1.1388,
      "step": 1
    },
    {
      "epoch": 0.0035413899955732625,
      "grad_norm": 0.03571357258993351,
      "learning_rate": 5.882352941176471e-06,
      "loss": 1.1477,
      "step": 2
    },
    {
      "epoch": 0.005312084993359893,
      "grad_norm": 0.04183886653613989,
      "learning_rate": 8.823529411764707e-06,
      "loss": 1.175,
      "step": 3
    },
    {
      "epoch": 0.007082779991146525,
      "grad_norm": 0.07886874790449751,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 1.1815,
      "step": 4
    },
    {
      "epoch": 0.008853474988933156,
      "grad_norm": 0.17347010940455646,
      "learning_rate": 1.4705882352941177e-05,
      "loss": 1.1954,
      "step": 5
    },
    {
      "epoch": 0.010624169986719787,
      "grad_norm": 0.3015542111114723,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 1.1512,
      "step": 6
    },
    {
      "epoch": 0.01239486498450642,
      "grad_norm": 0.3282039705400138,
      "learning_rate": 2.058823529411765e-05,
      "loss": 1.237,
      "step": 7
    },
    {
      "epoch": 0.01416555998229305,
      "grad_norm": 0.3899370552442461,
      "learning_rate": 2.3529411764705884e-05,
      "loss": 1.1839,
      "step": 8
    },
    {
      "epoch": 0.01593625498007968,
      "grad_norm": 0.7084561017436252,
      "learning_rate": 2.647058823529412e-05,
      "loss": 1.2044,
      "step": 9
    },
    {
      "epoch": 0.017706949977866312,
      "grad_norm": 0.8624009490205696,
      "learning_rate": 2.9411764705882354e-05,
      "loss": 1.1773,
      "step": 10
    },
    {
      "epoch": 0.019477644975652943,
      "grad_norm": 0.822640929203826,
      "learning_rate": 3.235294117647059e-05,
      "loss": 1.0789,
      "step": 11
    },
    {
      "epoch": 0.021248339973439574,
      "grad_norm": 1.0050223861595484,
      "learning_rate": 3.529411764705883e-05,
      "loss": 1.1022,
      "step": 12
    },
    {
      "epoch": 0.023019034971226208,
      "grad_norm": 0.9293096655184463,
      "learning_rate": 3.8235294117647055e-05,
      "loss": 1.0174,
      "step": 13
    },
    {
      "epoch": 0.02478972996901284,
      "grad_norm": 0.6264204491097409,
      "learning_rate": 4.11764705882353e-05,
      "loss": 1.0681,
      "step": 14
    },
    {
      "epoch": 0.02656042496679947,
      "grad_norm": 0.6017157125250685,
      "learning_rate": 4.411764705882353e-05,
      "loss": 0.9436,
      "step": 15
    },
    {
      "epoch": 0.0283311199645861,
      "grad_norm": 0.3721271622522488,
      "learning_rate": 4.705882352941177e-05,
      "loss": 0.8987,
      "step": 16
    },
    {
      "epoch": 0.03010181496237273,
      "grad_norm": 0.3731267374438093,
      "learning_rate": 5e-05,
      "loss": 0.8522,
      "step": 17
    },
    {
      "epoch": 0.03187250996015936,
      "grad_norm": 0.1929052670683848,
      "learning_rate": 4.999958768046451e-05,
      "loss": 1.0107,
      "step": 18
    },
    {
      "epoch": 0.033643204957945996,
      "grad_norm": 0.2727941789159395,
      "learning_rate": 4.9998350735458646e-05,
      "loss": 0.9191,
      "step": 19
    },
    {
      "epoch": 0.035413899955732624,
      "grad_norm": 0.1746604324377453,
      "learning_rate": 4.999628920578371e-05,
      "loss": 1.002,
      "step": 20
    },
    {
      "epoch": 0.03718459495351926,
      "grad_norm": 0.2506599027784788,
      "learning_rate": 4.9993403159440443e-05,
      "loss": 0.9504,
      "step": 21
    },
    {
      "epoch": 0.038955289951305885,
      "grad_norm": 0.22350986122272237,
      "learning_rate": 4.99896926916267e-05,
      "loss": 0.9707,
      "step": 22
    },
    {
      "epoch": 0.04072598494909252,
      "grad_norm": 0.1646868965234265,
      "learning_rate": 4.998515792473434e-05,
      "loss": 0.9237,
      "step": 23
    },
    {
      "epoch": 0.04249667994687915,
      "grad_norm": 0.15740761556538474,
      "learning_rate": 4.9979799008345215e-05,
      "loss": 1.0375,
      "step": 24
    },
    {
      "epoch": 0.04426737494466578,
      "grad_norm": 0.23932871764957392,
      "learning_rate": 4.99736161192262e-05,
      "loss": 0.8704,
      "step": 25
    },
    {
      "epoch": 0.046038069942452416,
      "grad_norm": 0.20499097161314062,
      "learning_rate": 4.996660946132336e-05,
      "loss": 0.905,
      "step": 26
    },
    {
      "epoch": 0.04780876494023904,
      "grad_norm": 0.4850969949534864,
      "learning_rate": 4.9958779265755255e-05,
      "loss": 0.8724,
      "step": 27
    },
    {
      "epoch": 0.04957945993802568,
      "grad_norm": 0.32667056608406353,
      "learning_rate": 4.99501257908053e-05,
      "loss": 0.9177,
      "step": 28
    },
    {
      "epoch": 0.051350154935812305,
      "grad_norm": 0.21750174028407482,
      "learning_rate": 4.9940649321913227e-05,
      "loss": 0.9828,
      "step": 29
    },
    {
      "epoch": 0.05312084993359894,
      "grad_norm": 0.32317627448409075,
      "learning_rate": 4.9930350171665696e-05,
      "loss": 0.8493,
      "step": 30
    },
    {
      "epoch": 0.054891544931385566,
      "grad_norm": 0.7207972708664862,
      "learning_rate": 4.991922867978598e-05,
      "loss": 0.8624,
      "step": 31
    },
    {
      "epoch": 0.0566622399291722,
      "grad_norm": 0.24772761948518315,
      "learning_rate": 4.990728521312275e-05,
      "loss": 1.0625,
      "step": 32
    },
    {
      "epoch": 0.05843293492695883,
      "grad_norm": 0.8459472448596599,
      "learning_rate": 4.9894520165637967e-05,
      "loss": 0.8854,
      "step": 33
    },
    {
      "epoch": 0.06020362992474546,
      "grad_norm": 0.535080431436613,
      "learning_rate": 4.988093395839391e-05,
      "loss": 0.9455,
      "step": 34
    },
    {
      "epoch": 0.0619743249225321,
      "grad_norm": 0.33740240974220903,
      "learning_rate": 4.9866527039539276e-05,
      "loss": 0.8798,
      "step": 35
    },
    {
      "epoch": 0.06374501992031872,
      "grad_norm": 0.33381143331498303,
      "learning_rate": 4.98512998842944e-05,
      "loss": 0.8614,
      "step": 36
    },
    {
      "epoch": 0.06551571491810536,
      "grad_norm": 0.6217574308414473,
      "learning_rate": 4.9835252994935555e-05,
      "loss": 0.942,
      "step": 37
    },
    {
      "epoch": 0.06728640991589199,
      "grad_norm": 0.525237410413068,
      "learning_rate": 4.981838690077841e-05,
      "loss": 1.008,
      "step": 38
    },
    {
      "epoch": 0.06905710491367861,
      "grad_norm": 0.3336975005047153,
      "learning_rate": 4.9800702158160605e-05,
      "loss": 0.8896,
      "step": 39
    },
    {
      "epoch": 0.07082779991146525,
      "grad_norm": 0.30955852476478446,
      "learning_rate": 4.97821993504233e-05,
      "loss": 0.896,
      "step": 40
    },
    {
      "epoch": 0.07259849490925188,
      "grad_norm": 0.16848746517467478,
      "learning_rate": 4.9762879087892035e-05,
      "loss": 0.9617,
      "step": 41
    },
    {
      "epoch": 0.07436918990703852,
      "grad_norm": 0.22494541758236525,
      "learning_rate": 4.974274200785654e-05,
      "loss": 0.8974,
      "step": 42
    },
    {
      "epoch": 0.07613988490482515,
      "grad_norm": 0.1836707495912769,
      "learning_rate": 4.9721788774549725e-05,
      "loss": 0.9182,
      "step": 43
    },
    {
      "epoch": 0.07791057990261177,
      "grad_norm": 0.352503322800585,
      "learning_rate": 4.9700020079125796e-05,
      "loss": 0.8815,
      "step": 44
    },
    {
      "epoch": 0.0796812749003984,
      "grad_norm": 0.15825442915633567,
      "learning_rate": 4.967743663963743e-05,
      "loss": 0.9405,
      "step": 45
    },
    {
      "epoch": 0.08145196989818504,
      "grad_norm": 0.16060296728582993,
      "learning_rate": 4.965403920101208e-05,
      "loss": 0.8014,
      "step": 46
    },
    {
      "epoch": 0.08322266489597167,
      "grad_norm": 0.24889340135068322,
      "learning_rate": 4.962982853502742e-05,
      "loss": 0.8797,
      "step": 47
    },
    {
      "epoch": 0.0849933598937583,
      "grad_norm": 2.613720189951253,
      "learning_rate": 4.960480544028592e-05,
      "loss": 0.8755,
      "step": 48
    },
    {
      "epoch": 0.08676405489154493,
      "grad_norm": 0.5318844299037946,
      "learning_rate": 4.9578970742188414e-05,
      "loss": 0.9757,
      "step": 49
    },
    {
      "epoch": 0.08853474988933156,
      "grad_norm": 0.33711948257502306,
      "learning_rate": 4.955232529290697e-05,
      "loss": 0.801,
      "step": 50
    },
    {
      "epoch": 0.0903054448871182,
      "grad_norm": 0.3725949418368921,
      "learning_rate": 4.952486997135674e-05,
      "loss": 0.9484,
      "step": 51
    },
    {
      "epoch": 0.09207613988490483,
      "grad_norm": 0.8231511496768019,
      "learning_rate": 4.9496605683166946e-05,
      "loss": 0.9696,
      "step": 52
    },
    {
      "epoch": 0.09384683488269145,
      "grad_norm": 0.2662481508354014,
      "learning_rate": 4.9467533360651054e-05,
      "loss": 0.8787,
      "step": 53
    },
    {
      "epoch": 0.09561752988047809,
      "grad_norm": 0.4390130392914871,
      "learning_rate": 4.943765396277596e-05,
      "loss": 1.0086,
      "step": 54
    },
    {
      "epoch": 0.09738822487826472,
      "grad_norm": 0.14996238556791847,
      "learning_rate": 4.9406968475130456e-05,
      "loss": 0.9648,
      "step": 55
    },
    {
      "epoch": 0.09915891987605135,
      "grad_norm": 0.265850427158205,
      "learning_rate": 4.93754779098926e-05,
      "loss": 0.8995,
      "step": 56
    },
    {
      "epoch": 0.10092961487383798,
      "grad_norm": 1.4301488532184896,
      "learning_rate": 4.9343183305796416e-05,
      "loss": 0.8523,
      "step": 57
    },
    {
      "epoch": 0.10270030987162461,
      "grad_norm": 0.3327933182626148,
      "learning_rate": 4.93100857280976e-05,
      "loss": 0.9951,
      "step": 58
    },
    {
      "epoch": 0.10447100486941124,
      "grad_norm": 0.25443026265863905,
      "learning_rate": 4.927618626853837e-05,
      "loss": 0.872,
      "step": 59
    },
    {
      "epoch": 0.10624169986719788,
      "grad_norm": 0.317972147336053,
      "learning_rate": 4.924148604531149e-05,
      "loss": 0.9474,
      "step": 60
    },
    {
      "epoch": 0.10801239486498451,
      "grad_norm": 0.3287496275367044,
      "learning_rate": 4.9205986203023346e-05,
      "loss": 0.9153,
      "step": 61
    },
    {
      "epoch": 0.10978308986277113,
      "grad_norm": 0.3667231485702587,
      "learning_rate": 4.9169687912656224e-05,
      "loss": 0.8904,
      "step": 62
    },
    {
      "epoch": 0.11155378486055777,
      "grad_norm": 0.34992748946069535,
      "learning_rate": 4.913259237152966e-05,
      "loss": 0.9581,
      "step": 63
    },
    {
      "epoch": 0.1133244798583444,
      "grad_norm": 0.1471542105751792,
      "learning_rate": 4.9094700803260964e-05,
      "loss": 0.8874,
      "step": 64
    },
    {
      "epoch": 0.11509517485613104,
      "grad_norm": 0.3041335858459816,
      "learning_rate": 4.9056014457724825e-05,
      "loss": 0.9076,
      "step": 65
    },
    {
      "epoch": 0.11686586985391766,
      "grad_norm": 0.3118683323960035,
      "learning_rate": 4.901653461101213e-05,
      "loss": 0.8524,
      "step": 66
    },
    {
      "epoch": 0.11863656485170429,
      "grad_norm": 0.230700819939072,
      "learning_rate": 4.897626256538786e-05,
      "loss": 0.9036,
      "step": 67
    },
    {
      "epoch": 0.12040725984949092,
      "grad_norm": 0.4772305688524569,
      "learning_rate": 4.893519964924809e-05,
      "loss": 0.8707,
      "step": 68
    },
    {
      "epoch": 0.12217795484727756,
      "grad_norm": 0.20420920296662842,
      "learning_rate": 4.889334721707622e-05,
      "loss": 0.9018,
      "step": 69
    },
    {
      "epoch": 0.1239486498450642,
      "grad_norm": 0.2320107025089752,
      "learning_rate": 4.8850706649398286e-05,
      "loss": 0.8808,
      "step": 70
    },
    {
      "epoch": 0.12571934484285083,
      "grad_norm": 0.4870768176858242,
      "learning_rate": 4.880727935273741e-05,
      "loss": 0.9113,
      "step": 71
    },
    {
      "epoch": 0.12749003984063745,
      "grad_norm": 0.2917338598589722,
      "learning_rate": 4.8763066759567425e-05,
      "loss": 0.8599,
      "step": 72
    },
    {
      "epoch": 0.12926073483842407,
      "grad_norm": 0.23868690561721356,
      "learning_rate": 4.8718070328265594e-05,
      "loss": 0.8625,
      "step": 73
    },
    {
      "epoch": 0.13103142983621072,
      "grad_norm": 0.3983889889581501,
      "learning_rate": 4.867229154306453e-05,
      "loss": 0.9301,
      "step": 74
    },
    {
      "epoch": 0.13280212483399734,
      "grad_norm": 0.6110414460258621,
      "learning_rate": 4.862573191400322e-05,
      "loss": 0.7919,
      "step": 75
    },
    {
      "epoch": 0.13457281983178399,
      "grad_norm": 0.2516084821308692,
      "learning_rate": 4.8578392976877244e-05,
      "loss": 0.8598,
      "step": 76
    },
    {
      "epoch": 0.1363435148295706,
      "grad_norm": 0.2295892632144525,
      "learning_rate": 4.8530276293188094e-05,
      "loss": 0.9318,
      "step": 77
    },
    {
      "epoch": 0.13811420982735723,
      "grad_norm": 0.5971727197361132,
      "learning_rate": 4.8481383450091644e-05,
      "loss": 0.9586,
      "step": 78
    },
    {
      "epoch": 0.13988490482514387,
      "grad_norm": 0.18726825668194075,
      "learning_rate": 4.843171606034587e-05,
      "loss": 0.8745,
      "step": 79
    },
    {
      "epoch": 0.1416555998229305,
      "grad_norm": 0.174616790172108,
      "learning_rate": 4.838127576225754e-05,
      "loss": 0.9534,
      "step": 80
    },
    {
      "epoch": 0.14342629482071714,
      "grad_norm": 0.20191905181462658,
      "learning_rate": 4.833006421962831e-05,
      "loss": 0.9453,
      "step": 81
    },
    {
      "epoch": 0.14519698981850376,
      "grad_norm": 0.29863678769316804,
      "learning_rate": 4.827808312169972e-05,
      "loss": 0.8443,
      "step": 82
    },
    {
      "epoch": 0.14696768481629038,
      "grad_norm": 0.2242944242367295,
      "learning_rate": 4.822533418309755e-05,
      "loss": 0.8641,
      "step": 83
    },
    {
      "epoch": 0.14873837981407703,
      "grad_norm": 0.3159995603420751,
      "learning_rate": 4.817181914377522e-05,
      "loss": 0.9697,
      "step": 84
    },
    {
      "epoch": 0.15050907481186365,
      "grad_norm": 0.29281746955196747,
      "learning_rate": 4.811753976895643e-05,
      "loss": 0.8692,
      "step": 85
    },
    {
      "epoch": 0.1522797698096503,
      "grad_norm": 0.2284724749705581,
      "learning_rate": 4.8062497849076913e-05,
      "loss": 0.9331,
      "step": 86
    },
    {
      "epoch": 0.15405046480743692,
      "grad_norm": 0.3011281269131844,
      "learning_rate": 4.800669519972537e-05,
      "loss": 0.9726,
      "step": 87
    },
    {
      "epoch": 0.15582115980522354,
      "grad_norm": 0.30269011697461334,
      "learning_rate": 4.79501336615836e-05,
      "loss": 0.9771,
      "step": 88
    },
    {
      "epoch": 0.1575918548030102,
      "grad_norm": 0.1951591666059543,
      "learning_rate": 4.7892815100365765e-05,
      "loss": 0.9858,
      "step": 89
    },
    {
      "epoch": 0.1593625498007968,
      "grad_norm": 0.15270953412928404,
      "learning_rate": 4.7834741406756866e-05,
      "loss": 0.9094,
      "step": 90
    },
    {
      "epoch": 0.16113324479858343,
      "grad_norm": 0.20273405829818558,
      "learning_rate": 4.777591449635039e-05,
      "loss": 0.9356,
      "step": 91
    },
    {
      "epoch": 0.16290393979637008,
      "grad_norm": 0.23227340595557205,
      "learning_rate": 4.771633630958508e-05,
      "loss": 0.8921,
      "step": 92
    },
    {
      "epoch": 0.1646746347941567,
      "grad_norm": 0.1912103144464483,
      "learning_rate": 4.765600881168095e-05,
      "loss": 0.937,
      "step": 93
    },
    {
      "epoch": 0.16644532979194335,
      "grad_norm": 0.19778441865813537,
      "learning_rate": 4.759493399257449e-05,
      "loss": 0.899,
      "step": 94
    },
    {
      "epoch": 0.16821602478972997,
      "grad_norm": 0.33139408398708703,
      "learning_rate": 4.753311386685297e-05,
      "loss": 0.9107,
      "step": 95
    },
    {
      "epoch": 0.1699867197875166,
      "grad_norm": 0.1468872355430697,
      "learning_rate": 4.747055047368803e-05,
      "loss": 0.9177,
      "step": 96
    },
    {
      "epoch": 0.17175741478530324,
      "grad_norm": 0.14183163853136685,
      "learning_rate": 4.7407245876768424e-05,
      "loss": 0.8197,
      "step": 97
    },
    {
      "epoch": 0.17352810978308986,
      "grad_norm": 0.22152800298880398,
      "learning_rate": 4.734320216423189e-05,
      "loss": 0.9262,
      "step": 98
    },
    {
      "epoch": 0.1752988047808765,
      "grad_norm": 0.25778220433194643,
      "learning_rate": 4.727842144859635e-05,
      "loss": 0.8893,
      "step": 99
    },
    {
      "epoch": 0.17706949977866313,
      "grad_norm": 0.150828090381125,
      "learning_rate": 4.721290586669016e-05,
      "loss": 0.8873,
      "step": 100
    },
    {
      "epoch": 0.17884019477644975,
      "grad_norm": 0.25393151599966984,
      "learning_rate": 4.714665757958167e-05,
      "loss": 0.9009,
      "step": 101
    },
    {
      "epoch": 0.1806108897742364,
      "grad_norm": 0.20082400129572026,
      "learning_rate": 4.707967877250791e-05,
      "loss": 0.9356,
      "step": 102
    },
    {
      "epoch": 0.18238158477202301,
      "grad_norm": 0.16228144167950773,
      "learning_rate": 4.701197165480253e-05,
      "loss": 0.96,
      "step": 103
    },
    {
      "epoch": 0.18415227976980966,
      "grad_norm": 0.23071889823409208,
      "learning_rate": 4.694353845982292e-05,
      "loss": 0.9405,
      "step": 104
    },
    {
      "epoch": 0.18592297476759628,
      "grad_norm": 0.1818069490742737,
      "learning_rate": 4.687438144487654e-05,
      "loss": 1.0057,
      "step": 105
    },
    {
      "epoch": 0.1876936697653829,
      "grad_norm": 0.4312414479092488,
      "learning_rate": 4.680450289114644e-05,
      "loss": 0.9164,
      "step": 106
    },
    {
      "epoch": 0.18946436476316955,
      "grad_norm": 0.324157904416991,
      "learning_rate": 4.6733905103616047e-05,
      "loss": 0.8111,
      "step": 107
    },
    {
      "epoch": 0.19123505976095617,
      "grad_norm": 0.23360876588072851,
      "learning_rate": 4.666259041099312e-05,
      "loss": 0.9343,
      "step": 108
    },
    {
      "epoch": 0.19300575475874282,
      "grad_norm": 0.25163445778667537,
      "learning_rate": 4.659056116563294e-05,
      "loss": 0.8958,
      "step": 109
    },
    {
      "epoch": 0.19477644975652944,
      "grad_norm": 0.18125345083042615,
      "learning_rate": 4.65178197434607e-05,
      "loss": 0.8463,
      "step": 110
    },
    {
      "epoch": 0.19654714475431606,
      "grad_norm": 1.2361912213955568,
      "learning_rate": 4.6444368543893155e-05,
      "loss": 0.9105,
      "step": 111
    },
    {
      "epoch": 0.1983178397521027,
      "grad_norm": 0.26106396797761083,
      "learning_rate": 4.637020998975945e-05,
      "loss": 0.9863,
      "step": 112
    },
    {
      "epoch": 0.20008853474988933,
      "grad_norm": 0.2544117035756562,
      "learning_rate": 4.629534652722126e-05,
      "loss": 0.9446,
      "step": 113
    },
    {
      "epoch": 0.20185922974767595,
      "grad_norm": 0.22914643012206734,
      "learning_rate": 4.621978062569201e-05,
      "loss": 0.9453,
      "step": 114
    },
    {
      "epoch": 0.2036299247454626,
      "grad_norm": 0.1901416409455657,
      "learning_rate": 4.6143514777755506e-05,
      "loss": 0.9018,
      "step": 115
    },
    {
      "epoch": 0.20540061974324922,
      "grad_norm": 0.27461902204066996,
      "learning_rate": 4.6066551499083654e-05,
      "loss": 0.9868,
      "step": 116
    },
    {
      "epoch": 0.20717131474103587,
      "grad_norm": 0.8087451909822339,
      "learning_rate": 4.598889332835353e-05,
      "loss": 0.9149,
      "step": 117
    },
    {
      "epoch": 0.2089420097388225,
      "grad_norm": 0.1644306698637651,
      "learning_rate": 4.59105428271636e-05,
      "loss": 1.0001,
      "step": 118
    },
    {
      "epoch": 0.2107127047366091,
      "grad_norm": 0.7362628248856402,
      "learning_rate": 4.583150257994925e-05,
      "loss": 1.0393,
      "step": 119
    },
    {
      "epoch": 0.21248339973439576,
      "grad_norm": 0.2689426035762804,
      "learning_rate": 4.575177519389752e-05,
      "loss": 0.8677,
      "step": 120
    },
    {
      "epoch": 0.21425409473218238,
      "grad_norm": 0.3060682471084595,
      "learning_rate": 4.5671363298861105e-05,
      "loss": 0.9353,
      "step": 121
    },
    {
      "epoch": 0.21602478972996902,
      "grad_norm": 0.35273670327071566,
      "learning_rate": 4.5590269547271624e-05,
      "loss": 1.0049,
      "step": 122
    },
    {
      "epoch": 0.21779548472775564,
      "grad_norm": 0.3910750856427213,
      "learning_rate": 4.550849661405212e-05,
      "loss": 0.932,
      "step": 123
    },
    {
      "epoch": 0.21956617972554227,
      "grad_norm": 0.19398286869636064,
      "learning_rate": 4.542604719652882e-05,
      "loss": 0.909,
      "step": 124
    },
    {
      "epoch": 0.2213368747233289,
      "grad_norm": 0.29474556455310014,
      "learning_rate": 4.534292401434217e-05,
      "loss": 0.9572,
      "step": 125
    },
    {
      "epoch": 0.22310756972111553,
      "grad_norm": 0.22800548347917354,
      "learning_rate": 4.525912980935711e-05,
      "loss": 0.791,
      "step": 126
    },
    {
      "epoch": 0.22487826471890218,
      "grad_norm": 0.1774141583279246,
      "learning_rate": 4.517466734557266e-05,
      "loss": 0.8988,
      "step": 127
    },
    {
      "epoch": 0.2266489597166888,
      "grad_norm": 0.9043399164951533,
      "learning_rate": 4.508953940903073e-05,
      "loss": 0.8841,
      "step": 128
    },
    {
      "epoch": 0.22841965471447542,
      "grad_norm": 0.3018664182806493,
      "learning_rate": 4.500374880772421e-05,
      "loss": 0.9553,
      "step": 129
    },
    {
      "epoch": 0.23019034971226207,
      "grad_norm": 0.533202700623235,
      "learning_rate": 4.491729837150438e-05,
      "loss": 1.0261,
      "step": 130
    },
    {
      "epoch": 0.2319610447100487,
      "grad_norm": 0.4035976823965726,
      "learning_rate": 4.483019095198754e-05,
      "loss": 0.8632,
      "step": 131
    },
    {
      "epoch": 0.2337317397078353,
      "grad_norm": 0.45038732712674995,
      "learning_rate": 4.474242942246093e-05,
      "loss": 0.9614,
      "step": 132
    },
    {
      "epoch": 0.23550243470562196,
      "grad_norm": 0.7669580492853936,
      "learning_rate": 4.465401667778801e-05,
      "loss": 0.9098,
      "step": 133
    },
    {
      "epoch": 0.23727312970340858,
      "grad_norm": 0.2040618786871846,
      "learning_rate": 4.456495563431293e-05,
      "loss": 0.9315,
      "step": 134
    },
    {
      "epoch": 0.23904382470119523,
      "grad_norm": 0.2595161485091969,
      "learning_rate": 4.447524922976434e-05,
      "loss": 0.9698,
      "step": 135
    },
    {
      "epoch": 0.24081451969898185,
      "grad_norm": 0.21656588278286332,
      "learning_rate": 4.4384900423158466e-05,
      "loss": 0.8389,
      "step": 136
    },
    {
      "epoch": 0.24258521469676847,
      "grad_norm": 0.2769007813218477,
      "learning_rate": 4.429391219470156e-05,
      "loss": 0.9281,
      "step": 137
    },
    {
      "epoch": 0.24435590969455512,
      "grad_norm": 0.40255946322275477,
      "learning_rate": 4.420228754569154e-05,
      "loss": 0.9038,
      "step": 138
    },
    {
      "epoch": 0.24612660469234174,
      "grad_norm": 0.35319242849718036,
      "learning_rate": 4.411002949841902e-05,
      "loss": 0.9336,
      "step": 139
    },
    {
      "epoch": 0.2478972996901284,
      "grad_norm": 1.654751021006555,
      "learning_rate": 4.401714109606764e-05,
      "loss": 0.9054,
      "step": 140
    },
    {
      "epoch": 0.249667994687915,
      "grad_norm": 2.1479643644004667,
      "learning_rate": 4.3923625402613614e-05,
      "loss": 0.9582,
      "step": 141
    },
    {
      "epoch": 0.25143868968570166,
      "grad_norm": 0.21540618941770087,
      "learning_rate": 4.3829485502724723e-05,
      "loss": 1.0594,
      "step": 142
    },
    {
      "epoch": 0.25320938468348825,
      "grad_norm": 1.766287783939771,
      "learning_rate": 4.3734724501658555e-05,
      "loss": 0.9602,
      "step": 143
    },
    {
      "epoch": 0.2549800796812749,
      "grad_norm": 0.3999735558575469,
      "learning_rate": 4.363934552516007e-05,
      "loss": 0.8308,
      "step": 144
    },
    {
      "epoch": 0.25675077467906154,
      "grad_norm": 0.32028655676082357,
      "learning_rate": 4.3543351719358485e-05,
      "loss": 0.8603,
      "step": 145
    },
    {
      "epoch": 0.25852146967684814,
      "grad_norm": 0.16285879786466181,
      "learning_rate": 4.344674625066351e-05,
      "loss": 0.9065,
      "step": 146
    },
    {
      "epoch": 0.2602921646746348,
      "grad_norm": 0.3886178686764519,
      "learning_rate": 4.334953230566091e-05,
      "loss": 0.8711,
      "step": 147
    },
    {
      "epoch": 0.26206285967242143,
      "grad_norm": 0.22492687350698337,
      "learning_rate": 4.3251713091007375e-05,
      "loss": 0.984,
      "step": 148
    },
    {
      "epoch": 0.2638335546702081,
      "grad_norm": 0.1899140166754581,
      "learning_rate": 4.315329183332476e-05,
      "loss": 0.9337,
      "step": 149
    },
    {
      "epoch": 0.2656042496679947,
      "grad_norm": 0.3822374834165277,
      "learning_rate": 4.305427177909363e-05,
      "loss": 0.9401,
      "step": 150
    },
    {
      "epoch": 0.2673749446657813,
      "grad_norm": 0.22208375360452923,
      "learning_rate": 4.2954656194546226e-05,
      "loss": 0.9138,
      "step": 151
    },
    {
      "epoch": 0.26914563966356797,
      "grad_norm": 0.23875033695869213,
      "learning_rate": 4.285444836555866e-05,
      "loss": 0.904,
      "step": 152
    },
    {
      "epoch": 0.27091633466135456,
      "grad_norm": 0.1687579570257605,
      "learning_rate": 4.275365159754258e-05,
      "loss": 0.9122,
      "step": 153
    },
    {
      "epoch": 0.2726870296591412,
      "grad_norm": 0.4973567540028455,
      "learning_rate": 4.265226921533611e-05,
      "loss": 0.8984,
      "step": 154
    },
    {
      "epoch": 0.27445772465692786,
      "grad_norm": 0.38929739982132716,
      "learning_rate": 4.255030456309418e-05,
      "loss": 0.9019,
      "step": 155
    },
    {
      "epoch": 0.27622841965471445,
      "grad_norm": 0.46680584038937817,
      "learning_rate": 4.244776100417824e-05,
      "loss": 0.8898,
      "step": 156
    },
    {
      "epoch": 0.2779991146525011,
      "grad_norm": 0.16506191619974353,
      "learning_rate": 4.23446419210453e-05,
      "loss": 0.9032,
      "step": 157
    },
    {
      "epoch": 0.27976980965028775,
      "grad_norm": 0.17829442157976785,
      "learning_rate": 4.2240950715136345e-05,
      "loss": 0.9034,
      "step": 158
    },
    {
      "epoch": 0.2815405046480744,
      "grad_norm": 0.3109653526057971,
      "learning_rate": 4.213669080676418e-05,
      "loss": 0.9211,
      "step": 159
    },
    {
      "epoch": 0.283311199645861,
      "grad_norm": 0.38886482462349964,
      "learning_rate": 4.203186563500055e-05,
      "loss": 0.9147,
      "step": 160
    },
    {
      "epoch": 0.28508189464364764,
      "grad_norm": 0.17319357826870102,
      "learning_rate": 4.192647865756275e-05,
      "loss": 0.9821,
      "step": 161
    },
    {
      "epoch": 0.2868525896414343,
      "grad_norm": 0.2006855746975817,
      "learning_rate": 4.182053335069955e-05,
      "loss": 0.9981,
      "step": 162
    },
    {
      "epoch": 0.2886232846392209,
      "grad_norm": 0.2147204296253265,
      "learning_rate": 4.171403320907652e-05,
      "loss": 0.9912,
      "step": 163
    },
    {
      "epoch": 0.2903939796370075,
      "grad_norm": 0.3925679725875204,
      "learning_rate": 4.160698174566078e-05,
      "loss": 0.8855,
      "step": 164
    },
    {
      "epoch": 0.2921646746347942,
      "grad_norm": 0.3607384833558982,
      "learning_rate": 4.149938249160511e-05,
      "loss": 1.01,
      "step": 165
    },
    {
      "epoch": 0.29393536963258077,
      "grad_norm": 0.4195680139194114,
      "learning_rate": 4.1391238996131456e-05,
      "loss": 0.9425,
      "step": 166
    },
    {
      "epoch": 0.2957060646303674,
      "grad_norm": 1.1721466741459532,
      "learning_rate": 4.128255482641388e-05,
      "loss": 0.9745,
      "step": 167
    },
    {
      "epoch": 0.29747675962815406,
      "grad_norm": 0.22216053985572431,
      "learning_rate": 4.117333356746089e-05,
      "loss": 0.9318,
      "step": 168
    },
    {
      "epoch": 0.29924745462594066,
      "grad_norm": 0.2713719933211703,
      "learning_rate": 4.1063578821997205e-05,
      "loss": 0.9779,
      "step": 169
    },
    {
      "epoch": 0.3010181496237273,
      "grad_norm": 0.4163387752337424,
      "learning_rate": 4.095329421034486e-05,
      "loss": 0.9762,
      "step": 170
    },
    {
      "epoch": 0.30278884462151395,
      "grad_norm": 0.15746943731384833,
      "learning_rate": 4.084248337030385e-05,
      "loss": 0.9825,
      "step": 171
    },
    {
      "epoch": 0.3045595396193006,
      "grad_norm": 0.21959082748811382,
      "learning_rate": 4.073114995703211e-05,
      "loss": 0.926,
      "step": 172
    },
    {
      "epoch": 0.3063302346170872,
      "grad_norm": 0.2882133682431939,
      "learning_rate": 4.061929764292493e-05,
      "loss": 0.9927,
      "step": 173
    },
    {
      "epoch": 0.30810092961487384,
      "grad_norm": 0.37449377076216317,
      "learning_rate": 4.050693011749384e-05,
      "loss": 0.9345,
      "step": 174
    },
    {
      "epoch": 0.3098716246126605,
      "grad_norm": 0.9486074675663788,
      "learning_rate": 4.039405108724493e-05,
      "loss": 0.8839,
      "step": 175
    },
    {
      "epoch": 0.3116423196104471,
      "grad_norm": 0.2584182326380468,
      "learning_rate": 4.0280664275556525e-05,
      "loss": 0.9219,
      "step": 176
    },
    {
      "epoch": 0.31341301460823373,
      "grad_norm": 0.28292796489036454,
      "learning_rate": 4.0166773422556435e-05,
      "loss": 0.8852,
      "step": 177
    },
    {
      "epoch": 0.3151837096060204,
      "grad_norm": 0.969958878003315,
      "learning_rate": 4.005238228499856e-05,
      "loss": 0.9166,
      "step": 178
    },
    {
      "epoch": 0.31695440460380697,
      "grad_norm": 0.35395848779977035,
      "learning_rate": 3.993749463613894e-05,
      "loss": 0.8829,
      "step": 179
    },
    {
      "epoch": 0.3187250996015936,
      "grad_norm": 0.3372358280733084,
      "learning_rate": 3.982211426561134e-05,
      "loss": 0.9394,
      "step": 180
    },
    {
      "epoch": 0.32049579459938027,
      "grad_norm": 0.2593098547788246,
      "learning_rate": 3.970624497930223e-05,
      "loss": 0.9151,
      "step": 181
    },
    {
      "epoch": 0.32226648959716686,
      "grad_norm": 0.24617656865709847,
      "learning_rate": 3.958989059922522e-05,
      "loss": 0.9393,
      "step": 182
    },
    {
      "epoch": 0.3240371845949535,
      "grad_norm": 0.2259494848322385,
      "learning_rate": 3.947305496339504e-05,
      "loss": 0.9341,
      "step": 183
    },
    {
      "epoch": 0.32580787959274016,
      "grad_norm": 0.953119938575492,
      "learning_rate": 3.9355741925700894e-05,
      "loss": 0.9188,
      "step": 184
    },
    {
      "epoch": 0.3275785745905268,
      "grad_norm": 0.1760190138076376,
      "learning_rate": 3.9237955355779353e-05,
      "loss": 0.9373,
      "step": 185
    },
    {
      "epoch": 0.3293492695883134,
      "grad_norm": 3.578023983467036,
      "learning_rate": 3.911969913888672e-05,
      "loss": 0.9815,
      "step": 186
    },
    {
      "epoch": 0.33111996458610005,
      "grad_norm": 0.6717558780538339,
      "learning_rate": 3.900097717577089e-05,
      "loss": 0.826,
      "step": 187
    },
    {
      "epoch": 0.3328906595838867,
      "grad_norm": 0.2391464322914367,
      "learning_rate": 3.888179338254261e-05,
      "loss": 0.9462,
      "step": 188
    },
    {
      "epoch": 0.3346613545816733,
      "grad_norm": 0.3042822457988573,
      "learning_rate": 3.876215169054639e-05,
      "loss": 0.9804,
      "step": 189
    },
    {
      "epoch": 0.33643204957945994,
      "grad_norm": 0.22598578787259924,
      "learning_rate": 3.864205604623078e-05,
      "loss": 1.0103,
      "step": 190
    },
    {
      "epoch": 0.3382027445772466,
      "grad_norm": 0.3068037686317651,
      "learning_rate": 3.8521510411018205e-05,
      "loss": 0.9039,
      "step": 191
    },
    {
      "epoch": 0.3399734395750332,
      "grad_norm": 0.24852065001355508,
      "learning_rate": 3.840051876117429e-05,
      "loss": 0.8307,
      "step": 192
    },
    {
      "epoch": 0.3417441345728198,
      "grad_norm": 1.7592923656750774,
      "learning_rate": 3.8279085087676695e-05,
      "loss": 0.8948,
      "step": 193
    },
    {
      "epoch": 0.3435148295706065,
      "grad_norm": 0.2469959978740295,
      "learning_rate": 3.815721339608351e-05,
      "loss": 1.0163,
      "step": 194
    },
    {
      "epoch": 0.3452855245683931,
      "grad_norm": 0.883824820802396,
      "learning_rate": 3.803490770640106e-05,
      "loss": 0.9455,
      "step": 195
    },
    {
      "epoch": 0.3470562195661797,
      "grad_norm": 0.2001243205514584,
      "learning_rate": 3.7912172052951346e-05,
      "loss": 0.9699,
      "step": 196
    },
    {
      "epoch": 0.34882691456396636,
      "grad_norm": 0.2435449127639474,
      "learning_rate": 3.778901048423899e-05,
      "loss": 0.987,
      "step": 197
    },
    {
      "epoch": 0.350597609561753,
      "grad_norm": 0.39186583286492993,
      "learning_rate": 3.766542706281767e-05,
      "loss": 0.9196,
      "step": 198
    },
    {
      "epoch": 0.3523683045595396,
      "grad_norm": 0.2503337209265072,
      "learning_rate": 3.754142586515608e-05,
      "loss": 0.9234,
      "step": 199
    },
    {
      "epoch": 0.35413899955732625,
      "grad_norm": 0.21104805697395498,
      "learning_rate": 3.7417010981503526e-05,
      "loss": 1.0313,
      "step": 200
    },
    {
      "epoch": 0.3559096945551129,
      "grad_norm": 0.3253980431987402,
      "learning_rate": 3.729218651575497e-05,
      "loss": 0.978,
      "step": 201
    },
    {
      "epoch": 0.3576803895528995,
      "grad_norm": 0.3258270412409668,
      "learning_rate": 3.716695658531567e-05,
      "loss": 0.9538,
      "step": 202
    },
    {
      "epoch": 0.35945108455068614,
      "grad_norm": 0.7207972824059042,
      "learning_rate": 3.704132532096536e-05,
      "loss": 0.9695,
      "step": 203
    },
    {
      "epoch": 0.3612217795484728,
      "grad_norm": 0.1810560881704239,
      "learning_rate": 3.691529686672201e-05,
      "loss": 0.8478,
      "step": 204
    },
    {
      "epoch": 0.3629924745462594,
      "grad_norm": 0.5469464551152138,
      "learning_rate": 3.6788875379705125e-05,
      "loss": 0.9405,
      "step": 205
    },
    {
      "epoch": 0.36476316954404603,
      "grad_norm": 0.25153727611666693,
      "learning_rate": 3.666206502999859e-05,
      "loss": 0.9946,
      "step": 206
    },
    {
      "epoch": 0.3665338645418327,
      "grad_norm": 0.16809816086120652,
      "learning_rate": 3.653487000051318e-05,
      "loss": 0.8595,
      "step": 207
    },
    {
      "epoch": 0.3683045595396193,
      "grad_norm": 0.48397866352458985,
      "learning_rate": 3.6407294486848534e-05,
      "loss": 0.9655,
      "step": 208
    },
    {
      "epoch": 0.3700752545374059,
      "grad_norm": 0.47552294279481494,
      "learning_rate": 3.6279342697154755e-05,
      "loss": 0.9568,
      "step": 209
    },
    {
      "epoch": 0.37184594953519257,
      "grad_norm": 3.622113202261123,
      "learning_rate": 3.615101885199367e-05,
      "loss": 1.0342,
      "step": 210
    },
    {
      "epoch": 0.3736166445329792,
      "grad_norm": 0.23196599289082925,
      "learning_rate": 3.6022327184199515e-05,
      "loss": 0.847,
      "step": 211
    },
    {
      "epoch": 0.3753873395307658,
      "grad_norm": 0.8767215140950758,
      "learning_rate": 3.589327193873939e-05,
      "loss": 0.9469,
      "step": 212
    },
    {
      "epoch": 0.37715803452855245,
      "grad_norm": 0.28509004522381437,
      "learning_rate": 3.576385737257321e-05,
      "loss": 0.9291,
      "step": 213
    },
    {
      "epoch": 0.3789287295263391,
      "grad_norm": 0.57272278216321,
      "learning_rate": 3.5634087754513276e-05,
      "loss": 0.9131,
      "step": 214
    },
    {
      "epoch": 0.3806994245241257,
      "grad_norm": 0.5342892058280704,
      "learning_rate": 3.550396736508349e-05,
      "loss": 1.0315,
      "step": 215
    },
    {
      "epoch": 0.38247011952191234,
      "grad_norm": 0.38035756524906683,
      "learning_rate": 3.5373500496378115e-05,
      "loss": 0.9987,
      "step": 216
    },
    {
      "epoch": 0.384240814519699,
      "grad_norm": 0.35697153182612773,
      "learning_rate": 3.5242691451920256e-05,
      "loss": 1.0385,
      "step": 217
    },
    {
      "epoch": 0.38601150951748564,
      "grad_norm": 1.043244186564532,
      "learning_rate": 3.511154454651987e-05,
      "loss": 1.0378,
      "step": 218
    },
    {
      "epoch": 0.38778220451527223,
      "grad_norm": 0.9199082860559846,
      "learning_rate": 3.498006410613144e-05,
      "loss": 0.9421,
      "step": 219
    },
    {
      "epoch": 0.3895528995130589,
      "grad_norm": 0.31074175696932516,
      "learning_rate": 3.48482544677113e-05,
      "loss": 1.0114,
      "step": 220
    },
    {
      "epoch": 0.39132359451084553,
      "grad_norm": 0.884504473487445,
      "learning_rate": 3.4716119979074565e-05,
      "loss": 0.8604,
      "step": 221
    },
    {
      "epoch": 0.3930942895086321,
      "grad_norm": 0.2630034417791142,
      "learning_rate": 3.458366499875172e-05,
      "loss": 0.9028,
      "step": 222
    },
    {
      "epoch": 0.39486498450641877,
      "grad_norm": 0.36755349981775337,
      "learning_rate": 3.445089389584481e-05,
      "loss": 0.8723,
      "step": 223
    },
    {
      "epoch": 0.3966356795042054,
      "grad_norm": 0.35911434077867294,
      "learning_rate": 3.4317811049883426e-05,
      "loss": 0.9637,
      "step": 224
    },
    {
      "epoch": 0.398406374501992,
      "grad_norm": 0.23942012520247954,
      "learning_rate": 3.4184420850680134e-05,
      "loss": 0.853,
      "step": 225
    },
    {
      "epoch": 0.40017706949977866,
      "grad_norm": 0.30060473268301274,
      "learning_rate": 3.405072769818573e-05,
      "loss": 0.8906,
      "step": 226
    },
    {
      "epoch": 0.4019477644975653,
      "grad_norm": 0.31243267633464294,
      "learning_rate": 3.3916736002344084e-05,
      "loss": 0.9686,
      "step": 227
    },
    {
      "epoch": 0.4037184594953519,
      "grad_norm": 0.4884698459573586,
      "learning_rate": 3.378245018294673e-05,
      "loss": 1.033,
      "step": 228
    },
    {
      "epoch": 0.40548915449313855,
      "grad_norm": 0.3568000046724811,
      "learning_rate": 3.3647874669486983e-05,
      "loss": 0.9628,
      "step": 229
    },
    {
      "epoch": 0.4072598494909252,
      "grad_norm": 0.3185989536740807,
      "learning_rate": 3.3513013901013894e-05,
      "loss": 0.9981,
      "step": 230
    },
    {
      "epoch": 0.40903054448871184,
      "grad_norm": 0.4096240173547323,
      "learning_rate": 3.3377872325985835e-05,
      "loss": 0.9599,
      "step": 231
    },
    {
      "epoch": 0.41080123948649844,
      "grad_norm": 0.2962075775455029,
      "learning_rate": 3.32424544021237e-05,
      "loss": 0.9472,
      "step": 232
    },
    {
      "epoch": 0.4125719344842851,
      "grad_norm": 0.3033192456931374,
      "learning_rate": 3.310676459626394e-05,
      "loss": 0.8378,
      "step": 233
    },
    {
      "epoch": 0.41434262948207173,
      "grad_norm": 0.24379067701182527,
      "learning_rate": 3.297080738421117e-05,
      "loss": 0.9743,
      "step": 234
    },
    {
      "epoch": 0.4161133244798583,
      "grad_norm": 0.2704564352096967,
      "learning_rate": 3.283458725059054e-05,
      "loss": 0.9209,
      "step": 235
    },
    {
      "epoch": 0.417884019477645,
      "grad_norm": 0.25981899770130973,
      "learning_rate": 3.269810868869985e-05,
      "loss": 0.928,
      "step": 236
    },
    {
      "epoch": 0.4196547144754316,
      "grad_norm": 0.28875530836752417,
      "learning_rate": 3.2561376200361263e-05,
      "loss": 0.9109,
      "step": 237
    },
    {
      "epoch": 0.4214254094732182,
      "grad_norm": 0.4589802694764348,
      "learning_rate": 3.242439429577288e-05,
      "loss": 0.9868,
      "step": 238
    },
    {
      "epoch": 0.42319610447100486,
      "grad_norm": 0.5314292148331783,
      "learning_rate": 3.228716749335989e-05,
      "loss": 0.9079,
      "step": 239
    },
    {
      "epoch": 0.4249667994687915,
      "grad_norm": 0.5721390310207668,
      "learning_rate": 3.214970031962564e-05,
      "loss": 0.9972,
      "step": 240
    },
    {
      "epoch": 0.4267374944665781,
      "grad_norm": 0.5251884576340393,
      "learning_rate": 3.2011997309002216e-05,
      "loss": 0.9321,
      "step": 241
    },
    {
      "epoch": 0.42850818946436475,
      "grad_norm": 0.4071004946331771,
      "learning_rate": 3.187406300370094e-05,
      "loss": 0.8727,
      "step": 242
    },
    {
      "epoch": 0.4302788844621514,
      "grad_norm": 0.6084387531462638,
      "learning_rate": 3.1735901953562484e-05,
      "loss": 0.9639,
      "step": 243
    },
    {
      "epoch": 0.43204957945993805,
      "grad_norm": 0.8509906276378774,
      "learning_rate": 3.159751871590686e-05,
      "loss": 0.9757,
      "step": 244
    },
    {
      "epoch": 0.43382027445772464,
      "grad_norm": 0.2860912557436344,
      "learning_rate": 3.145891785538306e-05,
      "loss": 0.9213,
      "step": 245
    },
    {
      "epoch": 0.4355909694555113,
      "grad_norm": 0.27976363601015025,
      "learning_rate": 3.1320103943818456e-05,
      "loss": 0.8948,
      "step": 246
    },
    {
      "epoch": 0.43736166445329794,
      "grad_norm": 0.36560896870133774,
      "learning_rate": 3.118108156006807e-05,
      "loss": 0.9654,
      "step": 247
    },
    {
      "epoch": 0.43913235945108453,
      "grad_norm": 1.4700348206255711,
      "learning_rate": 3.104185528986347e-05,
      "loss": 0.8762,
      "step": 248
    },
    {
      "epoch": 0.4409030544488712,
      "grad_norm": 0.3393458188347256,
      "learning_rate": 3.090242972566155e-05,
      "loss": 1.0014,
      "step": 249
    },
    {
      "epoch": 0.4426737494466578,
      "grad_norm": 0.7608076608361319,
      "learning_rate": 3.0762809466493e-05,
      "loss": 0.8603,
      "step": 250
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.18697801225245345,
      "learning_rate": 3.0622999117810674e-05,
      "loss": 1.054,
      "step": 251
    },
    {
      "epoch": 0.44621513944223107,
      "grad_norm": 0.33012473762688077,
      "learning_rate": 3.0483003291337596e-05,
      "loss": 0.9788,
      "step": 252
    },
    {
      "epoch": 0.4479858344400177,
      "grad_norm": 0.3351559086725971,
      "learning_rate": 3.034282660491491e-05,
      "loss": 1.0098,
      "step": 253
    },
    {
      "epoch": 0.44975652943780436,
      "grad_norm": 0.21121387033434535,
      "learning_rate": 3.0202473682349502e-05,
      "loss": 0.9563,
      "step": 254
    },
    {
      "epoch": 0.45152722443559096,
      "grad_norm": 0.4080726867259667,
      "learning_rate": 3.0061949153261533e-05,
      "loss": 1.0084,
      "step": 255
    },
    {
      "epoch": 0.4532979194333776,
      "grad_norm": 0.9902024269331046,
      "learning_rate": 2.9921257652931685e-05,
      "loss": 1.0061,
      "step": 256
    },
    {
      "epoch": 0.45506861443116425,
      "grad_norm": 0.7438797129219429,
      "learning_rate": 2.9780403822148266e-05,
      "loss": 0.8972,
      "step": 257
    },
    {
      "epoch": 0.45683930942895085,
      "grad_norm": 0.418228199805306,
      "learning_rate": 2.9639392307054188e-05,
      "loss": 1.0015,
      "step": 258
    },
    {
      "epoch": 0.4586100044267375,
      "grad_norm": 0.31331600205539234,
      "learning_rate": 2.9498227758993626e-05,
      "loss": 1.0026,
      "step": 259
    },
    {
      "epoch": 0.46038069942452414,
      "grad_norm": 0.5859053772359949,
      "learning_rate": 2.9356914834358646e-05,
      "loss": 0.9116,
      "step": 260
    },
    {
      "epoch": 0.46215139442231074,
      "grad_norm": 0.3449519498341499,
      "learning_rate": 2.9215458194435624e-05,
      "loss": 0.8268,
      "step": 261
    },
    {
      "epoch": 0.4639220894200974,
      "grad_norm": 0.43870449619323154,
      "learning_rate": 2.9073862505251432e-05,
      "loss": 0.9239,
      "step": 262
    },
    {
      "epoch": 0.46569278441788403,
      "grad_norm": 0.3541192619985061,
      "learning_rate": 2.8932132437419572e-05,
      "loss": 0.9752,
      "step": 263
    },
    {
      "epoch": 0.4674634794156706,
      "grad_norm": 0.3052220494672347,
      "learning_rate": 2.8790272665986114e-05,
      "loss": 0.9307,
      "step": 264
    },
    {
      "epoch": 0.4692341744134573,
      "grad_norm": 0.17338226818800737,
      "learning_rate": 2.864828787027545e-05,
      "loss": 0.9268,
      "step": 265
    },
    {
      "epoch": 0.4710048694112439,
      "grad_norm": 0.2738223660921174,
      "learning_rate": 2.8506182733735988e-05,
      "loss": 0.9304,
      "step": 266
    },
    {
      "epoch": 0.47277556440903057,
      "grad_norm": 0.2345715655847049,
      "learning_rate": 2.8363961943785633e-05,
      "loss": 1.0127,
      "step": 267
    },
    {
      "epoch": 0.47454625940681716,
      "grad_norm": 0.21364433463364352,
      "learning_rate": 2.8221630191657196e-05,
      "loss": 0.8905,
      "step": 268
    },
    {
      "epoch": 0.4763169544046038,
      "grad_norm": 0.36936323196166665,
      "learning_rate": 2.807919217224363e-05,
      "loss": 0.7888,
      "step": 269
    },
    {
      "epoch": 0.47808764940239046,
      "grad_norm": 0.47255630812728305,
      "learning_rate": 2.7936652583943167e-05,
      "loss": 0.8482,
      "step": 270
    },
    {
      "epoch": 0.47985834440017705,
      "grad_norm": 0.2922932880103908,
      "learning_rate": 2.7794016128504363e-05,
      "loss": 0.9469,
      "step": 271
    },
    {
      "epoch": 0.4816290393979637,
      "grad_norm": 0.6280198782885037,
      "learning_rate": 2.7651287510870983e-05,
      "loss": 0.9411,
      "step": 272
    },
    {
      "epoch": 0.48339973439575035,
      "grad_norm": 0.4947319172697396,
      "learning_rate": 2.7508471439026806e-05,
      "loss": 0.9645,
      "step": 273
    },
    {
      "epoch": 0.48517042939353694,
      "grad_norm": 0.18886931632237525,
      "learning_rate": 2.736557262384034e-05,
      "loss": 0.8784,
      "step": 274
    },
    {
      "epoch": 0.4869411243913236,
      "grad_norm": 0.5566948183222146,
      "learning_rate": 2.7222595778909447e-05,
      "loss": 0.9974,
      "step": 275
    },
    {
      "epoch": 0.48871181938911024,
      "grad_norm": 0.828833673010325,
      "learning_rate": 2.7079545620405823e-05,
      "loss": 1.0146,
      "step": 276
    },
    {
      "epoch": 0.4904825143868969,
      "grad_norm": 0.41871028029233737,
      "learning_rate": 2.693642686691946e-05,
      "loss": 0.9442,
      "step": 277
    },
    {
      "epoch": 0.4922532093846835,
      "grad_norm": 0.23617944856271675,
      "learning_rate": 2.6793244239302996e-05,
      "loss": 0.9412,
      "step": 278
    },
    {
      "epoch": 0.4940239043824701,
      "grad_norm": 0.2633001458232772,
      "learning_rate": 2.6650002460515987e-05,
      "loss": 0.9075,
      "step": 279
    },
    {
      "epoch": 0.4957945993802568,
      "grad_norm": 0.6148131158757306,
      "learning_rate": 2.650670625546914e-05,
      "loss": 0.94,
      "step": 280
    },
    {
      "epoch": 0.49756529437804337,
      "grad_norm": 0.43610188185653537,
      "learning_rate": 2.636336035086841e-05,
      "loss": 0.96,
      "step": 281
    },
    {
      "epoch": 0.49933598937583,
      "grad_norm": 0.9125855273566161,
      "learning_rate": 2.6219969475059165e-05,
      "loss": 0.8762,
      "step": 282
    },
    {
      "epoch": 0.5011066843736166,
      "grad_norm": 0.7506173670037419,
      "learning_rate": 2.6076538357870133e-05,
      "loss": 1.0093,
      "step": 283
    },
    {
      "epoch": 0.5028773793714033,
      "grad_norm": 0.2546750050116299,
      "learning_rate": 2.5933071730457454e-05,
      "loss": 0.984,
      "step": 284
    },
    {
      "epoch": 0.5046480743691899,
      "grad_norm": 0.3631148423677886,
      "learning_rate": 2.5789574325148576e-05,
      "loss": 0.9099,
      "step": 285
    },
    {
      "epoch": 0.5064187693669765,
      "grad_norm": 0.4687187667519408,
      "learning_rate": 2.564605087528618e-05,
      "loss": 1.0321,
      "step": 286
    },
    {
      "epoch": 0.5081894643647632,
      "grad_norm": 0.2578204804041681,
      "learning_rate": 2.550250611507204e-05,
      "loss": 0.9909,
      "step": 287
    },
    {
      "epoch": 0.5099601593625498,
      "grad_norm": 1.1781765809488045,
      "learning_rate": 2.5358944779410854e-05,
      "loss": 0.9178,
      "step": 288
    },
    {
      "epoch": 0.5117308543603364,
      "grad_norm": 0.34012341981659633,
      "learning_rate": 2.52153716037541e-05,
      "loss": 0.9307,
      "step": 289
    },
    {
      "epoch": 0.5135015493581231,
      "grad_norm": 0.32443277896731165,
      "learning_rate": 2.5071791323943778e-05,
      "loss": 0.8934,
      "step": 290
    },
    {
      "epoch": 0.5152722443559097,
      "grad_norm": 0.6486441280360966,
      "learning_rate": 2.4928208676056228e-05,
      "loss": 0.8362,
      "step": 291
    },
    {
      "epoch": 0.5170429393536963,
      "grad_norm": 0.17880024942931844,
      "learning_rate": 2.47846283962459e-05,
      "loss": 1.0102,
      "step": 292
    },
    {
      "epoch": 0.518813634351483,
      "grad_norm": 0.7858132461611242,
      "learning_rate": 2.464105522058915e-05,
      "loss": 1.0281,
      "step": 293
    },
    {
      "epoch": 0.5205843293492696,
      "grad_norm": 0.3114654772495658,
      "learning_rate": 2.4497493884927973e-05,
      "loss": 0.8739,
      "step": 294
    },
    {
      "epoch": 0.5223550243470563,
      "grad_norm": 0.4646124146689414,
      "learning_rate": 2.4353949124713826e-05,
      "loss": 0.9985,
      "step": 295
    },
    {
      "epoch": 0.5241257193448429,
      "grad_norm": 0.42307776754441273,
      "learning_rate": 2.4210425674851433e-05,
      "loss": 0.9176,
      "step": 296
    },
    {
      "epoch": 0.5258964143426295,
      "grad_norm": 0.2376236108580899,
      "learning_rate": 2.4066928269542548e-05,
      "loss": 0.8918,
      "step": 297
    },
    {
      "epoch": 0.5276671093404162,
      "grad_norm": 0.33198139193979564,
      "learning_rate": 2.392346164212987e-05,
      "loss": 0.93,
      "step": 298
    },
    {
      "epoch": 0.5294378043382028,
      "grad_norm": 0.30560700569807453,
      "learning_rate": 2.3780030524940837e-05,
      "loss": 0.9081,
      "step": 299
    },
    {
      "epoch": 0.5312084993359893,
      "grad_norm": 0.22108670094014082,
      "learning_rate": 2.3636639649131593e-05,
      "loss": 0.935,
      "step": 300
    },
    {
      "epoch": 0.532979194333776,
      "grad_norm": 0.39027279990313063,
      "learning_rate": 2.3493293744530873e-05,
      "loss": 0.9916,
      "step": 301
    },
    {
      "epoch": 0.5347498893315626,
      "grad_norm": 0.9338885376185818,
      "learning_rate": 2.3349997539484016e-05,
      "loss": 0.9607,
      "step": 302
    },
    {
      "epoch": 0.5365205843293492,
      "grad_norm": 0.31110393244582635,
      "learning_rate": 2.3206755760697013e-05,
      "loss": 0.9264,
      "step": 303
    },
    {
      "epoch": 0.5382912793271359,
      "grad_norm": 0.2810259350016861,
      "learning_rate": 2.3063573133080545e-05,
      "loss": 0.8119,
      "step": 304
    },
    {
      "epoch": 0.5400619743249225,
      "grad_norm": 0.22280575919190276,
      "learning_rate": 2.292045437959418e-05,
      "loss": 0.9158,
      "step": 305
    },
    {
      "epoch": 0.5418326693227091,
      "grad_norm": 0.30490137619379387,
      "learning_rate": 2.2777404221090555e-05,
      "loss": 0.9249,
      "step": 306
    },
    {
      "epoch": 0.5436033643204958,
      "grad_norm": 0.4406181580406502,
      "learning_rate": 2.2634427376159663e-05,
      "loss": 0.9481,
      "step": 307
    },
    {
      "epoch": 0.5453740593182824,
      "grad_norm": 0.3309962753725827,
      "learning_rate": 2.2491528560973207e-05,
      "loss": 0.8674,
      "step": 308
    },
    {
      "epoch": 0.547144754316069,
      "grad_norm": 0.2470351271322516,
      "learning_rate": 2.2348712489129022e-05,
      "loss": 0.9629,
      "step": 309
    },
    {
      "epoch": 0.5489154493138557,
      "grad_norm": 0.6483018220935787,
      "learning_rate": 2.2205983871495646e-05,
      "loss": 0.9759,
      "step": 310
    },
    {
      "epoch": 0.5506861443116423,
      "grad_norm": 0.3722889449356353,
      "learning_rate": 2.206334741605684e-05,
      "loss": 1.1092,
      "step": 311
    },
    {
      "epoch": 0.5524568393094289,
      "grad_norm": 0.22508751906469765,
      "learning_rate": 2.192080782775638e-05,
      "loss": 0.914,
      "step": 312
    },
    {
      "epoch": 0.5542275343072156,
      "grad_norm": 0.25233841381997263,
      "learning_rate": 2.1778369808342806e-05,
      "loss": 0.9202,
      "step": 313
    },
    {
      "epoch": 0.5559982293050022,
      "grad_norm": 0.3326427717212983,
      "learning_rate": 2.1636038056214376e-05,
      "loss": 0.9573,
      "step": 314
    },
    {
      "epoch": 0.5577689243027888,
      "grad_norm": 0.3550626927630641,
      "learning_rate": 2.1493817266264025e-05,
      "loss": 0.9237,
      "step": 315
    },
    {
      "epoch": 0.5595396193005755,
      "grad_norm": 0.37530935151376893,
      "learning_rate": 2.1351712129724553e-05,
      "loss": 0.9804,
      "step": 316
    },
    {
      "epoch": 0.5613103142983621,
      "grad_norm": 0.4570893939077887,
      "learning_rate": 2.1209727334013895e-05,
      "loss": 0.98,
      "step": 317
    },
    {
      "epoch": 0.5630810092961488,
      "grad_norm": 0.3860640828230648,
      "learning_rate": 2.106786756258043e-05,
      "loss": 0.9773,
      "step": 318
    },
    {
      "epoch": 0.5648517042939354,
      "grad_norm": 0.28840910583872814,
      "learning_rate": 2.0926137494748574e-05,
      "loss": 0.864,
      "step": 319
    },
    {
      "epoch": 0.566622399291722,
      "grad_norm": 0.9291065738211649,
      "learning_rate": 2.078454180556438e-05,
      "loss": 1.0361,
      "step": 320
    },
    {
      "epoch": 0.5683930942895087,
      "grad_norm": 0.7778934851454075,
      "learning_rate": 2.0643085165641356e-05,
      "loss": 0.935,
      "step": 321
    },
    {
      "epoch": 0.5701637892872953,
      "grad_norm": 0.3192675422976536,
      "learning_rate": 2.050177224100639e-05,
      "loss": 0.8389,
      "step": 322
    },
    {
      "epoch": 0.5719344842850819,
      "grad_norm": 0.3337296657926687,
      "learning_rate": 2.036060769294582e-05,
      "loss": 0.9185,
      "step": 323
    },
    {
      "epoch": 0.5737051792828686,
      "grad_norm": 0.3243573832685689,
      "learning_rate": 2.021959617785174e-05,
      "loss": 0.8513,
      "step": 324
    },
    {
      "epoch": 0.5754758742806552,
      "grad_norm": 0.3714824030365526,
      "learning_rate": 2.007874234706832e-05,
      "loss": 0.9534,
      "step": 325
    },
    {
      "epoch": 0.5772465692784418,
      "grad_norm": 0.4225911556933969,
      "learning_rate": 1.9938050846738472e-05,
      "loss": 0.9302,
      "step": 326
    },
    {
      "epoch": 0.5790172642762285,
      "grad_norm": 0.3112822185252556,
      "learning_rate": 1.97975263176505e-05,
      "loss": 0.9749,
      "step": 327
    },
    {
      "epoch": 0.580787959274015,
      "grad_norm": 0.4042396077063942,
      "learning_rate": 1.9657173395085096e-05,
      "loss": 0.9645,
      "step": 328
    },
    {
      "epoch": 0.5825586542718016,
      "grad_norm": 0.292714779990985,
      "learning_rate": 1.9516996708662413e-05,
      "loss": 0.9259,
      "step": 329
    },
    {
      "epoch": 0.5843293492695883,
      "grad_norm": 0.2934219769313889,
      "learning_rate": 1.9377000882189332e-05,
      "loss": 1.0104,
      "step": 330
    },
    {
      "epoch": 0.5861000442673749,
      "grad_norm": 0.19886856594019406,
      "learning_rate": 1.9237190533507e-05,
      "loss": 0.9642,
      "step": 331
    },
    {
      "epoch": 0.5878707392651615,
      "grad_norm": 0.36400505731700195,
      "learning_rate": 1.9097570274338453e-05,
      "loss": 0.9708,
      "step": 332
    },
    {
      "epoch": 0.5896414342629482,
      "grad_norm": 0.4129023937704246,
      "learning_rate": 1.8958144710136534e-05,
      "loss": 0.9814,
      "step": 333
    },
    {
      "epoch": 0.5914121292607348,
      "grad_norm": 0.36525244221778325,
      "learning_rate": 1.8818918439931928e-05,
      "loss": 0.9646,
      "step": 334
    },
    {
      "epoch": 0.5931828242585214,
      "grad_norm": 0.26883868720424353,
      "learning_rate": 1.8679896056181543e-05,
      "loss": 0.9838,
      "step": 335
    },
    {
      "epoch": 0.5949535192563081,
      "grad_norm": 0.5207805307603729,
      "learning_rate": 1.8541082144616956e-05,
      "loss": 0.9222,
      "step": 336
    },
    {
      "epoch": 0.5967242142540947,
      "grad_norm": 0.3823340985819467,
      "learning_rate": 1.8402481284093143e-05,
      "loss": 0.9045,
      "step": 337
    },
    {
      "epoch": 0.5984949092518813,
      "grad_norm": 0.34698176666746006,
      "learning_rate": 1.8264098046437522e-05,
      "loss": 0.856,
      "step": 338
    },
    {
      "epoch": 0.600265604249668,
      "grad_norm": 0.2968641547172766,
      "learning_rate": 1.8125936996299066e-05,
      "loss": 0.8879,
      "step": 339
    },
    {
      "epoch": 0.6020362992474546,
      "grad_norm": 0.25913022951941206,
      "learning_rate": 1.7988002690997786e-05,
      "loss": 0.9156,
      "step": 340
    },
    {
      "epoch": 0.6038069942452412,
      "grad_norm": 0.3930348429749727,
      "learning_rate": 1.7850299680374358e-05,
      "loss": 0.8648,
      "step": 341
    },
    {
      "epoch": 0.6055776892430279,
      "grad_norm": 0.23987933830325164,
      "learning_rate": 1.7712832506640108e-05,
      "loss": 0.9832,
      "step": 342
    },
    {
      "epoch": 0.6073483842408145,
      "grad_norm": 0.29847630577991413,
      "learning_rate": 1.7575605704227138e-05,
      "loss": 0.8995,
      "step": 343
    },
    {
      "epoch": 0.6091190792386012,
      "grad_norm": 0.3096754727722838,
      "learning_rate": 1.7438623799638736e-05,
      "loss": 0.9978,
      "step": 344
    },
    {
      "epoch": 0.6108897742363878,
      "grad_norm": 0.3969664961844253,
      "learning_rate": 1.7301891311300153e-05,
      "loss": 0.921,
      "step": 345
    },
    {
      "epoch": 0.6126604692341744,
      "grad_norm": 0.5786611217897193,
      "learning_rate": 1.7165412749409455e-05,
      "loss": 0.9564,
      "step": 346
    },
    {
      "epoch": 0.6144311642319611,
      "grad_norm": 0.6139726407829325,
      "learning_rate": 1.7029192615788837e-05,
      "loss": 1.0717,
      "step": 347
    },
    {
      "epoch": 0.6162018592297477,
      "grad_norm": 0.22687904713252216,
      "learning_rate": 1.6893235403736064e-05,
      "loss": 0.9854,
      "step": 348
    },
    {
      "epoch": 0.6179725542275343,
      "grad_norm": 0.2623178610278702,
      "learning_rate": 1.67575455978763e-05,
      "loss": 0.9432,
      "step": 349
    },
    {
      "epoch": 0.619743249225321,
      "grad_norm": 0.8709178446347335,
      "learning_rate": 1.6622127674014178e-05,
      "loss": 0.9347,
      "step": 350
    },
    {
      "epoch": 0.6215139442231076,
      "grad_norm": 0.3286512466286676,
      "learning_rate": 1.6486986098986108e-05,
      "loss": 1.0409,
      "step": 351
    },
    {
      "epoch": 0.6232846392208942,
      "grad_norm": 0.37460544391818984,
      "learning_rate": 1.6352125330513022e-05,
      "loss": 0.995,
      "step": 352
    },
    {
      "epoch": 0.6250553342186809,
      "grad_norm": 0.3176160419800961,
      "learning_rate": 1.6217549817053272e-05,
      "loss": 0.9439,
      "step": 353
    },
    {
      "epoch": 0.6268260292164675,
      "grad_norm": 0.49937052774367163,
      "learning_rate": 1.6083263997655918e-05,
      "loss": 0.9386,
      "step": 354
    },
    {
      "epoch": 0.628596724214254,
      "grad_norm": 0.242635443611519,
      "learning_rate": 1.5949272301814282e-05,
      "loss": 0.8785,
      "step": 355
    },
    {
      "epoch": 0.6303674192120408,
      "grad_norm": 0.24337737025604078,
      "learning_rate": 1.5815579149319875e-05,
      "loss": 0.9036,
      "step": 356
    },
    {
      "epoch": 0.6321381142098274,
      "grad_norm": 0.4204210847866521,
      "learning_rate": 1.5682188950116583e-05,
      "loss": 0.9278,
      "step": 357
    },
    {
      "epoch": 0.6339088092076139,
      "grad_norm": 0.22848506825196985,
      "learning_rate": 1.5549106104155193e-05,
      "loss": 0.9428,
      "step": 358
    },
    {
      "epoch": 0.6356795042054006,
      "grad_norm": 0.2782329341234698,
      "learning_rate": 1.5416335001248292e-05,
      "loss": 0.9646,
      "step": 359
    },
    {
      "epoch": 0.6374501992031872,
      "grad_norm": 0.3253577617031556,
      "learning_rate": 1.5283880020925427e-05,
      "loss": 1.0055,
      "step": 360
    },
    {
      "epoch": 0.6392208942009738,
      "grad_norm": 0.28066712504842944,
      "learning_rate": 1.51517455322887e-05,
      "loss": 0.9741,
      "step": 361
    },
    {
      "epoch": 0.6409915891987605,
      "grad_norm": 0.3717154391379734,
      "learning_rate": 1.5019935893868559e-05,
      "loss": 1.0111,
      "step": 362
    },
    {
      "epoch": 0.6427622841965471,
      "grad_norm": 0.21577905412037343,
      "learning_rate": 1.4888455453480135e-05,
      "loss": 0.9496,
      "step": 363
    },
    {
      "epoch": 0.6445329791943337,
      "grad_norm": 0.22001241933957813,
      "learning_rate": 1.4757308548079753e-05,
      "loss": 0.9088,
      "step": 364
    },
    {
      "epoch": 0.6463036741921204,
      "grad_norm": 0.32082145093930425,
      "learning_rate": 1.4626499503621892e-05,
      "loss": 0.907,
      "step": 365
    },
    {
      "epoch": 0.648074369189907,
      "grad_norm": 0.8830242064048957,
      "learning_rate": 1.4496032634916518e-05,
      "loss": 0.9665,
      "step": 366
    },
    {
      "epoch": 0.6498450641876937,
      "grad_norm": 0.4351072025366222,
      "learning_rate": 1.4365912245486723e-05,
      "loss": 0.9665,
      "step": 367
    },
    {
      "epoch": 0.6516157591854803,
      "grad_norm": 0.4170405225533134,
      "learning_rate": 1.4236142627426797e-05,
      "loss": 0.9319,
      "step": 368
    },
    {
      "epoch": 0.6533864541832669,
      "grad_norm": 1.0782062667479957,
      "learning_rate": 1.4106728061260607e-05,
      "loss": 0.8814,
      "step": 369
    },
    {
      "epoch": 0.6551571491810536,
      "grad_norm": 1.3871287315513103,
      "learning_rate": 1.3977672815800496e-05,
      "loss": 1.033,
      "step": 370
    },
    {
      "epoch": 0.6569278441788402,
      "grad_norm": 0.590328167658124,
      "learning_rate": 1.3848981148006346e-05,
      "loss": 0.9704,
      "step": 371
    },
    {
      "epoch": 0.6586985391766268,
      "grad_norm": 0.3355686955263331,
      "learning_rate": 1.3720657302845244e-05,
      "loss": 0.9019,
      "step": 372
    },
    {
      "epoch": 0.6604692341744135,
      "grad_norm": 0.332778925074737,
      "learning_rate": 1.3592705513151482e-05,
      "loss": 0.9177,
      "step": 373
    },
    {
      "epoch": 0.6622399291722001,
      "grad_norm": 0.26074786278382406,
      "learning_rate": 1.3465129999486823e-05,
      "loss": 0.9108,
      "step": 374
    },
    {
      "epoch": 0.6640106241699867,
      "grad_norm": 0.34166971844209293,
      "learning_rate": 1.3337934970001414e-05,
      "loss": 0.9489,
      "step": 375
    },
    {
      "epoch": 0.6657813191677734,
      "grad_norm": 0.384669348430479,
      "learning_rate": 1.3211124620294884e-05,
      "loss": 0.9077,
      "step": 376
    },
    {
      "epoch": 0.66755201416556,
      "grad_norm": 0.44656959237743055,
      "learning_rate": 1.3084703133277992e-05,
      "loss": 0.9916,
      "step": 377
    },
    {
      "epoch": 0.6693227091633466,
      "grad_norm": 0.263818972740591,
      "learning_rate": 1.2958674679034646e-05,
      "loss": 0.8587,
      "step": 378
    },
    {
      "epoch": 0.6710934041611333,
      "grad_norm": 0.25690501055449655,
      "learning_rate": 1.2833043414684339e-05,
      "loss": 1.0814,
      "step": 379
    },
    {
      "epoch": 0.6728640991589199,
      "grad_norm": 0.20408581025726671,
      "learning_rate": 1.2707813484245037e-05,
      "loss": 0.8947,
      "step": 380
    },
    {
      "epoch": 0.6746347941567065,
      "grad_norm": 0.24615392100995462,
      "learning_rate": 1.2582989018496472e-05,
      "loss": 0.9691,
      "step": 381
    },
    {
      "epoch": 0.6764054891544932,
      "grad_norm": 0.28397497308414643,
      "learning_rate": 1.2458574134843925e-05,
      "loss": 1.0128,
      "step": 382
    },
    {
      "epoch": 0.6781761841522798,
      "grad_norm": 0.3852610639836814,
      "learning_rate": 1.2334572937182329e-05,
      "loss": 0.9729,
      "step": 383
    },
    {
      "epoch": 0.6799468791500664,
      "grad_norm": 0.38161111359208505,
      "learning_rate": 1.2210989515761003e-05,
      "loss": 0.9507,
      "step": 384
    },
    {
      "epoch": 0.6817175741478531,
      "grad_norm": 0.5182419669022313,
      "learning_rate": 1.2087827947048667e-05,
      "loss": 0.9718,
      "step": 385
    },
    {
      "epoch": 0.6834882691456396,
      "grad_norm": 0.5099622915103452,
      "learning_rate": 1.1965092293598951e-05,
      "loss": 0.9924,
      "step": 386
    },
    {
      "epoch": 0.6852589641434262,
      "grad_norm": 0.27781844234890757,
      "learning_rate": 1.1842786603916495e-05,
      "loss": 0.9066,
      "step": 387
    },
    {
      "epoch": 0.687029659141213,
      "grad_norm": 0.20293216966460462,
      "learning_rate": 1.1720914912323302e-05,
      "loss": 0.9369,
      "step": 388
    },
    {
      "epoch": 0.6888003541389995,
      "grad_norm": 0.544767063506075,
      "learning_rate": 1.1599481238825716e-05,
      "loss": 0.9818,
      "step": 389
    },
    {
      "epoch": 0.6905710491367862,
      "grad_norm": 0.3500115187080296,
      "learning_rate": 1.14784895889818e-05,
      "loss": 0.908,
      "step": 390
    },
    {
      "epoch": 0.6923417441345728,
      "grad_norm": 0.5829996640341826,
      "learning_rate": 1.1357943953769227e-05,
      "loss": 0.9601,
      "step": 391
    },
    {
      "epoch": 0.6941124391323594,
      "grad_norm": 0.2731875675191534,
      "learning_rate": 1.1237848309453618e-05,
      "loss": 1.0047,
      "step": 392
    },
    {
      "epoch": 0.6958831341301461,
      "grad_norm": 1.0546607854705663,
      "learning_rate": 1.1118206617457402e-05,
      "loss": 1.0119,
      "step": 393
    },
    {
      "epoch": 0.6976538291279327,
      "grad_norm": 0.3640762166703244,
      "learning_rate": 1.0999022824229122e-05,
      "loss": 0.9518,
      "step": 394
    },
    {
      "epoch": 0.6994245241257193,
      "grad_norm": 0.3261765070529957,
      "learning_rate": 1.088030086111327e-05,
      "loss": 0.9647,
      "step": 395
    },
    {
      "epoch": 0.701195219123506,
      "grad_norm": 0.19542279323497083,
      "learning_rate": 1.0762044644220656e-05,
      "loss": 1.0047,
      "step": 396
    },
    {
      "epoch": 0.7029659141212926,
      "grad_norm": 0.40070413656366866,
      "learning_rate": 1.0644258074299107e-05,
      "loss": 0.9321,
      "step": 397
    },
    {
      "epoch": 0.7047366091190792,
      "grad_norm": 0.35993931453802785,
      "learning_rate": 1.052694503660496e-05,
      "loss": 0.9614,
      "step": 398
    },
    {
      "epoch": 0.7065073041168659,
      "grad_norm": 0.4746881107586071,
      "learning_rate": 1.041010940077479e-05,
      "loss": 0.9285,
      "step": 399
    },
    {
      "epoch": 0.7082779991146525,
      "grad_norm": 0.6886690903453301,
      "learning_rate": 1.0293755020697777e-05,
      "loss": 0.9866,
      "step": 400
    },
    {
      "epoch": 0.7100486941124391,
      "grad_norm": 0.5275884272206892,
      "learning_rate": 1.0177885734388662e-05,
      "loss": 0.8553,
      "step": 401
    },
    {
      "epoch": 0.7118193891102258,
      "grad_norm": 0.26269193186007295,
      "learning_rate": 1.0062505363861066e-05,
      "loss": 0.9797,
      "step": 402
    },
    {
      "epoch": 0.7135900841080124,
      "grad_norm": 0.6272983074973808,
      "learning_rate": 9.947617715001447e-06,
      "loss": 0.9484,
      "step": 403
    },
    {
      "epoch": 0.715360779105799,
      "grad_norm": 0.3304251239893632,
      "learning_rate": 9.833226577443567e-06,
      "loss": 0.8561,
      "step": 404
    },
    {
      "epoch": 0.7171314741035857,
      "grad_norm": 2.206676994401497,
      "learning_rate": 9.719335724443483e-06,
      "loss": 0.9953,
      "step": 405
    },
    {
      "epoch": 0.7189021691013723,
      "grad_norm": 0.5709622999741539,
      "learning_rate": 9.605948912755081e-06,
      "loss": 0.999,
      "step": 406
    },
    {
      "epoch": 0.7206728640991589,
      "grad_norm": 0.3738739492153253,
      "learning_rate": 9.493069882506164e-06,
      "loss": 1.004,
      "step": 407
    },
    {
      "epoch": 0.7224435590969456,
      "grad_norm": 0.312291030741623,
      "learning_rate": 9.38070235707508e-06,
      "loss": 0.9254,
      "step": 408
    },
    {
      "epoch": 0.7242142540947322,
      "grad_norm": 0.9184875527933677,
      "learning_rate": 9.268850042967891e-06,
      "loss": 0.8658,
      "step": 409
    },
    {
      "epoch": 0.7259849490925188,
      "grad_norm": 0.5471952042316085,
      "learning_rate": 9.157516629696155e-06,
      "loss": 0.9527,
      "step": 410
    },
    {
      "epoch": 0.7277556440903055,
      "grad_norm": 0.33430559660693876,
      "learning_rate": 9.046705789655142e-06,
      "loss": 0.9527,
      "step": 411
    },
    {
      "epoch": 0.7295263390880921,
      "grad_norm": 0.6477313604328087,
      "learning_rate": 8.936421178002799e-06,
      "loss": 0.9335,
      "step": 412
    },
    {
      "epoch": 0.7312970340858788,
      "grad_norm": 0.42781710304754167,
      "learning_rate": 8.826666432539121e-06,
      "loss": 0.9496,
      "step": 413
    },
    {
      "epoch": 0.7330677290836654,
      "grad_norm": 0.2328978628449917,
      "learning_rate": 8.71744517358613e-06,
      "loss": 0.9491,
      "step": 414
    },
    {
      "epoch": 0.734838424081452,
      "grad_norm": 0.2737211959457202,
      "learning_rate": 8.608761003868553e-06,
      "loss": 0.9686,
      "step": 415
    },
    {
      "epoch": 0.7366091190792387,
      "grad_norm": 0.5497346106452949,
      "learning_rate": 8.500617508394895e-06,
      "loss": 0.9491,
      "step": 416
    },
    {
      "epoch": 0.7383798140770252,
      "grad_norm": 0.46015400476973456,
      "learning_rate": 8.393018254339218e-06,
      "loss": 0.9673,
      "step": 417
    },
    {
      "epoch": 0.7401505090748118,
      "grad_norm": 0.7256467356379981,
      "learning_rate": 8.285966790923483e-06,
      "loss": 0.8839,
      "step": 418
    },
    {
      "epoch": 0.7419212040725985,
      "grad_norm": 0.46732089070528426,
      "learning_rate": 8.179466649300455e-06,
      "loss": 0.9694,
      "step": 419
    },
    {
      "epoch": 0.7436918990703851,
      "grad_norm": 1.300459975489861,
      "learning_rate": 8.073521342437254e-06,
      "loss": 1.0199,
      "step": 420
    },
    {
      "epoch": 0.7454625940681717,
      "grad_norm": 0.43398555270976436,
      "learning_rate": 7.968134364999457e-06,
      "loss": 0.9589,
      "step": 421
    },
    {
      "epoch": 0.7472332890659584,
      "grad_norm": 0.23249455985125458,
      "learning_rate": 7.86330919323583e-06,
      "loss": 0.8944,
      "step": 422
    },
    {
      "epoch": 0.749003984063745,
      "grad_norm": 0.33964976151845105,
      "learning_rate": 7.75904928486365e-06,
      "loss": 1.0333,
      "step": 423
    },
    {
      "epoch": 0.7507746790615316,
      "grad_norm": 0.46966427563505364,
      "learning_rate": 7.65535807895471e-06,
      "loss": 1.0164,
      "step": 424
    },
    {
      "epoch": 0.7525453740593183,
      "grad_norm": 0.2825626217682482,
      "learning_rate": 7.552238995821759e-06,
      "loss": 0.9508,
      "step": 425
    },
    {
      "epoch": 0.7543160690571049,
      "grad_norm": 0.2907540215786789,
      "learning_rate": 7.449695436905821e-06,
      "loss": 0.9621,
      "step": 426
    },
    {
      "epoch": 0.7560867640548915,
      "grad_norm": 0.27417828632129443,
      "learning_rate": 7.3477307846639e-06,
      "loss": 0.9221,
      "step": 427
    },
    {
      "epoch": 0.7578574590526782,
      "grad_norm": 0.28936814659075366,
      "learning_rate": 7.24634840245742e-06,
      "loss": 0.8859,
      "step": 428
    },
    {
      "epoch": 0.7596281540504648,
      "grad_norm": 0.23722434010968263,
      "learning_rate": 7.145551634441338e-06,
      "loss": 0.9851,
      "step": 429
    },
    {
      "epoch": 0.7613988490482514,
      "grad_norm": 0.7415443874567637,
      "learning_rate": 7.045343805453775e-06,
      "loss": 1.0053,
      "step": 430
    },
    {
      "epoch": 0.7631695440460381,
      "grad_norm": 0.2692981503113472,
      "learning_rate": 6.945728220906372e-06,
      "loss": 0.9586,
      "step": 431
    },
    {
      "epoch": 0.7649402390438247,
      "grad_norm": 0.4345108968400207,
      "learning_rate": 6.846708166675251e-06,
      "loss": 0.9186,
      "step": 432
    },
    {
      "epoch": 0.7667109340416113,
      "grad_norm": 0.21330524041717588,
      "learning_rate": 6.748286908992632e-06,
      "loss": 0.8936,
      "step": 433
    },
    {
      "epoch": 0.768481629039398,
      "grad_norm": 0.29514752279468,
      "learning_rate": 6.6504676943390995e-06,
      "loss": 1.0111,
      "step": 434
    },
    {
      "epoch": 0.7702523240371846,
      "grad_norm": 0.358649875266797,
      "learning_rate": 6.553253749336499e-06,
      "loss": 0.9462,
      "step": 435
    },
    {
      "epoch": 0.7720230190349713,
      "grad_norm": 0.2854871463058154,
      "learning_rate": 6.456648280641528e-06,
      "loss": 0.8442,
      "step": 436
    },
    {
      "epoch": 0.7737937140327579,
      "grad_norm": 0.2663044255872368,
      "learning_rate": 6.360654474839933e-06,
      "loss": 1.0495,
      "step": 437
    },
    {
      "epoch": 0.7755644090305445,
      "grad_norm": 0.7837168825478478,
      "learning_rate": 6.265275498341452e-06,
      "loss": 0.9539,
      "step": 438
    },
    {
      "epoch": 0.7773351040283312,
      "grad_norm": 0.2686093631957968,
      "learning_rate": 6.170514497275279e-06,
      "loss": 1.0047,
      "step": 439
    },
    {
      "epoch": 0.7791057990261178,
      "grad_norm": 0.23272524098670316,
      "learning_rate": 6.076374597386392e-06,
      "loss": 0.9597,
      "step": 440
    },
    {
      "epoch": 0.7808764940239044,
      "grad_norm": 0.3949100266889239,
      "learning_rate": 5.98285890393237e-06,
      "loss": 0.9713,
      "step": 441
    },
    {
      "epoch": 0.7826471890216911,
      "grad_norm": 0.24656629929958365,
      "learning_rate": 5.889970501580977e-06,
      "loss": 0.956,
      "step": 442
    },
    {
      "epoch": 0.7844178840194777,
      "grad_norm": 0.4185640519516844,
      "learning_rate": 5.797712454308466e-06,
      "loss": 0.9115,
      "step": 443
    },
    {
      "epoch": 0.7861885790172642,
      "grad_norm": 0.2875571707807097,
      "learning_rate": 5.706087805298449e-06,
      "loss": 0.9881,
      "step": 444
    },
    {
      "epoch": 0.787959274015051,
      "grad_norm": 0.5244651631752031,
      "learning_rate": 5.61509957684154e-06,
      "loss": 0.9747,
      "step": 445
    },
    {
      "epoch": 0.7897299690128375,
      "grad_norm": 0.42557573300534784,
      "learning_rate": 5.524750770235662e-06,
      "loss": 0.9671,
      "step": 446
    },
    {
      "epoch": 0.7915006640106241,
      "grad_norm": 0.3403063358576201,
      "learning_rate": 5.4350443656870695e-06,
      "loss": 0.9006,
      "step": 447
    },
    {
      "epoch": 0.7932713590084108,
      "grad_norm": 0.3545848375026469,
      "learning_rate": 5.3459833222119924e-06,
      "loss": 0.9789,
      "step": 448
    },
    {
      "epoch": 0.7950420540061974,
      "grad_norm": 0.2702441280545906,
      "learning_rate": 5.25757057753907e-06,
      "loss": 0.971,
      "step": 449
    },
    {
      "epoch": 0.796812749003984,
      "grad_norm": 0.4256028123166393,
      "learning_rate": 5.169809048012472e-06,
      "loss": 1.0391,
      "step": 450
    },
    {
      "epoch": 0.7985834440017707,
      "grad_norm": 0.3409754983334487,
      "learning_rate": 5.08270162849562e-06,
      "loss": 0.9281,
      "step": 451
    },
    {
      "epoch": 0.8003541389995573,
      "grad_norm": 0.2571829777876711,
      "learning_rate": 4.996251192275789e-06,
      "loss": 0.8988,
      "step": 452
    },
    {
      "epoch": 0.8021248339973439,
      "grad_norm": 0.6234290041108655,
      "learning_rate": 4.910460590969274e-06,
      "loss": 1.0036,
      "step": 453
    },
    {
      "epoch": 0.8038955289951306,
      "grad_norm": 0.47670650715619023,
      "learning_rate": 4.825332654427339e-06,
      "loss": 0.9825,
      "step": 454
    },
    {
      "epoch": 0.8056662239929172,
      "grad_norm": 0.32461043472972656,
      "learning_rate": 4.740870190642891e-06,
      "loss": 1.034,
      "step": 455
    },
    {
      "epoch": 0.8074369189907038,
      "grad_norm": 0.3013174746233432,
      "learning_rate": 4.657075985657833e-06,
      "loss": 1.0131,
      "step": 456
    },
    {
      "epoch": 0.8092076139884905,
      "grad_norm": 0.41223791824131345,
      "learning_rate": 4.573952803471182e-06,
      "loss": 0.9571,
      "step": 457
    },
    {
      "epoch": 0.8109783089862771,
      "grad_norm": 0.7330514986832135,
      "learning_rate": 4.4915033859478815e-06,
      "loss": 0.9569,
      "step": 458
    },
    {
      "epoch": 0.8127490039840638,
      "grad_norm": 0.27099582026093344,
      "learning_rate": 4.409730452728381e-06,
      "loss": 0.9501,
      "step": 459
    },
    {
      "epoch": 0.8145196989818504,
      "grad_norm": 0.2246385276662406,
      "learning_rate": 4.328636701138899e-06,
      "loss": 1.0713,
      "step": 460
    },
    {
      "epoch": 0.816290393979637,
      "grad_norm": 0.45632255294563046,
      "learning_rate": 4.248224806102491e-06,
      "loss": 0.9979,
      "step": 461
    },
    {
      "epoch": 0.8180610889774237,
      "grad_norm": 0.598542063578142,
      "learning_rate": 4.168497420050757e-06,
      "loss": 0.9919,
      "step": 462
    },
    {
      "epoch": 0.8198317839752103,
      "grad_norm": 1.7508608540398765,
      "learning_rate": 4.0894571728364e-06,
      "loss": 0.9331,
      "step": 463
    },
    {
      "epoch": 0.8216024789729969,
      "grad_norm": 0.3270455931346705,
      "learning_rate": 4.011106671646478e-06,
      "loss": 0.8842,
      "step": 464
    },
    {
      "epoch": 0.8233731739707836,
      "grad_norm": 0.24681677717275213,
      "learning_rate": 3.933448500916348e-06,
      "loss": 0.934,
      "step": 465
    },
    {
      "epoch": 0.8251438689685702,
      "grad_norm": 0.3947600510423621,
      "learning_rate": 3.856485222244502e-06,
      "loss": 0.9595,
      "step": 466
    },
    {
      "epoch": 0.8269145639663568,
      "grad_norm": 0.7370719505718769,
      "learning_rate": 3.7802193743079918e-06,
      "loss": 1.027,
      "step": 467
    },
    {
      "epoch": 0.8286852589641435,
      "grad_norm": 0.357793989722142,
      "learning_rate": 3.7046534727787435e-06,
      "loss": 0.918,
      "step": 468
    },
    {
      "epoch": 0.8304559539619301,
      "grad_norm": 0.6286670399207404,
      "learning_rate": 3.6297900102405467e-06,
      "loss": 0.9995,
      "step": 469
    },
    {
      "epoch": 0.8322266489597167,
      "grad_norm": 0.6413093550089062,
      "learning_rate": 3.5556314561068533e-06,
      "loss": 0.9766,
      "step": 470
    },
    {
      "epoch": 0.8339973439575034,
      "grad_norm": 0.8486411770809245,
      "learning_rate": 3.4821802565393053e-06,
      "loss": 0.9881,
      "step": 471
    },
    {
      "epoch": 0.83576803895529,
      "grad_norm": 0.43986416979221415,
      "learning_rate": 3.409438834367065e-06,
      "loss": 0.9106,
      "step": 472
    },
    {
      "epoch": 0.8375387339530765,
      "grad_norm": 0.31998069815625896,
      "learning_rate": 3.3374095890068846e-06,
      "loss": 0.9306,
      "step": 473
    },
    {
      "epoch": 0.8393094289508632,
      "grad_norm": 0.5296357710405419,
      "learning_rate": 3.266094896383962e-06,
      "loss": 0.8779,
      "step": 474
    },
    {
      "epoch": 0.8410801239486498,
      "grad_norm": 0.4654236060351656,
      "learning_rate": 3.1954971088535706e-06,
      "loss": 0.9674,
      "step": 475
    },
    {
      "epoch": 0.8428508189464364,
      "grad_norm": 0.4154522670434833,
      "learning_rate": 3.125618555123472e-06,
      "loss": 0.9645,
      "step": 476
    },
    {
      "epoch": 0.8446215139442231,
      "grad_norm": 0.9160070478825881,
      "learning_rate": 3.056461540177083e-06,
      "loss": 0.9502,
      "step": 477
    },
    {
      "epoch": 0.8463922089420097,
      "grad_norm": 0.3536481796959227,
      "learning_rate": 2.98802834519748e-06,
      "loss": 0.8523,
      "step": 478
    },
    {
      "epoch": 0.8481629039397963,
      "grad_norm": 0.3228114562787794,
      "learning_rate": 2.9203212274920984e-06,
      "loss": 0.9986,
      "step": 479
    },
    {
      "epoch": 0.849933598937583,
      "grad_norm": 0.3901857580767375,
      "learning_rate": 2.853342420418337e-06,
      "loss": 0.9332,
      "step": 480
    },
    {
      "epoch": 0.8517042939353696,
      "grad_norm": 0.37519558025758587,
      "learning_rate": 2.787094133309848e-06,
      "loss": 0.9699,
      "step": 481
    },
    {
      "epoch": 0.8534749889331562,
      "grad_norm": 0.4209038771302386,
      "learning_rate": 2.721578551403653e-06,
      "loss": 0.9867,
      "step": 482
    },
    {
      "epoch": 0.8552456839309429,
      "grad_norm": 0.7675782000123913,
      "learning_rate": 2.6567978357681102e-06,
      "loss": 0.9338,
      "step": 483
    },
    {
      "epoch": 0.8570163789287295,
      "grad_norm": 0.27806978140256067,
      "learning_rate": 2.5927541232315806e-06,
      "loss": 0.9039,
      "step": 484
    },
    {
      "epoch": 0.8587870739265162,
      "grad_norm": 0.5982381939497643,
      "learning_rate": 2.5294495263119666e-06,
      "loss": 0.9623,
      "step": 485
    },
    {
      "epoch": 0.8605577689243028,
      "grad_norm": 1.6649642174972414,
      "learning_rate": 2.466886133147034e-06,
      "loss": 0.9936,
      "step": 486
    },
    {
      "epoch": 0.8623284639220894,
      "grad_norm": 0.6538153030266359,
      "learning_rate": 2.4050660074255135e-06,
      "loss": 0.9907,
      "step": 487
    },
    {
      "epoch": 0.8640991589198761,
      "grad_norm": 0.3699582859612269,
      "learning_rate": 2.3439911883190503e-06,
      "loss": 0.9716,
      "step": 488
    },
    {
      "epoch": 0.8658698539176627,
      "grad_norm": 0.6471061669967688,
      "learning_rate": 2.283663690414925e-06,
      "loss": 0.9876,
      "step": 489
    },
    {
      "epoch": 0.8676405489154493,
      "grad_norm": 0.21294965791276163,
      "learning_rate": 2.2240855036496146e-06,
      "loss": 0.9821,
      "step": 490
    },
    {
      "epoch": 0.869411243913236,
      "grad_norm": 0.2589511503004552,
      "learning_rate": 2.165258593243133e-06,
      "loss": 0.9316,
      "step": 491
    },
    {
      "epoch": 0.8711819389110226,
      "grad_norm": 0.3497570794795895,
      "learning_rate": 2.1071848996342484e-06,
      "loss": 1.0154,
      "step": 492
    },
    {
      "epoch": 0.8729526339088092,
      "grad_norm": 0.28590947862295407,
      "learning_rate": 2.049866338416409e-06,
      "loss": 0.9934,
      "step": 493
    },
    {
      "epoch": 0.8747233289065959,
      "grad_norm": 0.5042466382531616,
      "learning_rate": 1.993304800274634e-06,
      "loss": 0.9914,
      "step": 494
    },
    {
      "epoch": 0.8764940239043825,
      "grad_norm": 0.40946628962136805,
      "learning_rate": 1.9375021509230927e-06,
      "loss": 0.979,
      "step": 495
    },
    {
      "epoch": 0.8782647189021691,
      "grad_norm": 0.4597347280667509,
      "learning_rate": 1.8824602310435674e-06,
      "loss": 0.9892,
      "step": 496
    },
    {
      "epoch": 0.8800354138999558,
      "grad_norm": 0.5504372685807565,
      "learning_rate": 1.8281808562247788e-06,
      "loss": 0.9088,
      "step": 497
    },
    {
      "epoch": 0.8818061088977424,
      "grad_norm": 0.40897334593160445,
      "learning_rate": 1.7746658169024543e-06,
      "loss": 0.9877,
      "step": 498
    },
    {
      "epoch": 0.883576803895529,
      "grad_norm": 0.5420597055250422,
      "learning_rate": 1.7219168783002838e-06,
      "loss": 0.9675,
      "step": 499
    },
    {
      "epoch": 0.8853474988933157,
      "grad_norm": 0.6048657826046908,
      "learning_rate": 1.6699357803716898e-06,
      "loss": 0.9681,
      "step": 500
    },
    {
      "epoch": 0.8871181938911022,
      "grad_norm": 0.3805164881891378,
      "learning_rate": 1.618724237742461e-06,
      "loss": 0.9335,
      "step": 501
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.3215494192034467,
      "learning_rate": 1.5682839396541415e-06,
      "loss": 0.9699,
      "step": 502
    },
    {
      "epoch": 0.8906595838866755,
      "grad_norm": 1.1461457667757167,
      "learning_rate": 1.5186165499083526e-06,
      "loss": 0.9522,
      "step": 503
    },
    {
      "epoch": 0.8924302788844621,
      "grad_norm": 0.2519571594987118,
      "learning_rate": 1.4697237068119123e-06,
      "loss": 0.9123,
      "step": 504
    },
    {
      "epoch": 0.8942009738822487,
      "grad_norm": 0.979619737438515,
      "learning_rate": 1.4216070231227535e-06,
      "loss": 0.9805,
      "step": 505
    },
    {
      "epoch": 0.8959716688800354,
      "grad_norm": 0.30203677691624176,
      "learning_rate": 1.3742680859967827e-06,
      "loss": 1.0316,
      "step": 506
    },
    {
      "epoch": 0.897742363877822,
      "grad_norm": 0.5151106058121392,
      "learning_rate": 1.327708456935478e-06,
      "loss": 1.0711,
      "step": 507
    },
    {
      "epoch": 0.8995130588756087,
      "grad_norm": 0.5693332200166277,
      "learning_rate": 1.281929671734411e-06,
      "loss": 0.948,
      "step": 508
    },
    {
      "epoch": 0.9012837538733953,
      "grad_norm": 0.26356330901984054,
      "learning_rate": 1.2369332404325751e-06,
      "loss": 0.9706,
      "step": 509
    },
    {
      "epoch": 0.9030544488711819,
      "grad_norm": 0.3546912599090531,
      "learning_rate": 1.192720647262588e-06,
      "loss": 0.9772,
      "step": 510
    },
    {
      "epoch": 0.9048251438689686,
      "grad_norm": 0.4670068279373899,
      "learning_rate": 1.1492933506017184e-06,
      "loss": 1.0675,
      "step": 511
    },
    {
      "epoch": 0.9065958388667552,
      "grad_norm": 0.39738453322852857,
      "learning_rate": 1.1066527829237866e-06,
      "loss": 0.926,
      "step": 512
    },
    {
      "epoch": 0.9083665338645418,
      "grad_norm": 0.42717978126386696,
      "learning_rate": 1.0648003507519183e-06,
      "loss": 1.0222,
      "step": 513
    },
    {
      "epoch": 0.9101372288623285,
      "grad_norm": 0.29654465127258584,
      "learning_rate": 1.0237374346121432e-06,
      "loss": 0.9194,
      "step": 514
    },
    {
      "epoch": 0.9119079238601151,
      "grad_norm": 0.3588015133837428,
      "learning_rate": 9.83465388987867e-07,
      "loss": 0.9814,
      "step": 515
    },
    {
      "epoch": 0.9136786188579017,
      "grad_norm": 0.3423576484057866,
      "learning_rate": 9.439855422751803e-07,
      "loss": 0.9707,
      "step": 516
    },
    {
      "epoch": 0.9154493138556884,
      "grad_norm": 0.354153462047092,
      "learning_rate": 9.0529919673904e-07,
      "loss": 0.9668,
      "step": 517
    },
    {
      "epoch": 0.917220008853475,
      "grad_norm": 0.5284431334842055,
      "learning_rate": 8.674076284703375e-07,
      "loss": 0.9288,
      "step": 518
    },
    {
      "epoch": 0.9189907038512616,
      "grad_norm": 0.30590552595520604,
      "learning_rate": 8.303120873437736e-07,
      "loss": 0.9546,
      "step": 519
    },
    {
      "epoch": 0.9207613988490483,
      "grad_norm": 0.2773895170166225,
      "learning_rate": 7.940137969766531e-07,
      "loss": 0.9562,
      "step": 520
    },
    {
      "epoch": 0.9225320938468349,
      "grad_norm": 0.4133616700791343,
      "learning_rate": 7.585139546885139e-07,
      "loss": 1.0485,
      "step": 521
    },
    {
      "epoch": 0.9243027888446215,
      "grad_norm": 0.2757529520625695,
      "learning_rate": 7.238137314616339e-07,
      "loss": 0.9758,
      "step": 522
    },
    {
      "epoch": 0.9260734838424082,
      "grad_norm": 0.35569844173730036,
      "learning_rate": 6.89914271902406e-07,
      "loss": 0.96,
      "step": 523
    },
    {
      "epoch": 0.9278441788401948,
      "grad_norm": 0.28096066635225186,
      "learning_rate": 6.568166942035853e-07,
      "loss": 0.9684,
      "step": 524
    },
    {
      "epoch": 0.9296148738379814,
      "grad_norm": 0.4528025053265481,
      "learning_rate": 6.245220901074017e-07,
      "loss": 0.9024,
      "step": 525
    },
    {
      "epoch": 0.9313855688357681,
      "grad_norm": 0.26352192815866343,
      "learning_rate": 5.930315248695445e-07,
      "loss": 0.992,
      "step": 526
    },
    {
      "epoch": 0.9331562638335547,
      "grad_norm": 0.39555157694057114,
      "learning_rate": 5.623460372240346e-07,
      "loss": 0.9628,
      "step": 527
    },
    {
      "epoch": 0.9349269588313412,
      "grad_norm": 0.3121622403769059,
      "learning_rate": 5.324666393489525e-07,
      "loss": 0.9988,
      "step": 528
    },
    {
      "epoch": 0.936697653829128,
      "grad_norm": 0.25998114632967384,
      "learning_rate": 5.033943168330557e-07,
      "loss": 0.9854,
      "step": 529
    },
    {
      "epoch": 0.9384683488269145,
      "grad_norm": 0.46999271478502563,
      "learning_rate": 4.751300286432642e-07,
      "loss": 0.9863,
      "step": 530
    },
    {
      "epoch": 0.9402390438247012,
      "grad_norm": 0.2598853615153877,
      "learning_rate": 4.4767470709302927e-07,
      "loss": 1.0105,
      "step": 531
    },
    {
      "epoch": 0.9420097388224878,
      "grad_norm": 0.24037544638017372,
      "learning_rate": 4.210292578115921e-07,
      "loss": 0.9481,
      "step": 532
    },
    {
      "epoch": 0.9437804338202744,
      "grad_norm": 0.26431862871954687,
      "learning_rate": 3.951945597140877e-07,
      "loss": 1.0143,
      "step": 533
    },
    {
      "epoch": 0.9455511288180611,
      "grad_norm": 0.2601938026317066,
      "learning_rate": 3.7017146497257684e-07,
      "loss": 0.9651,
      "step": 534
    },
    {
      "epoch": 0.9473218238158477,
      "grad_norm": 0.4984852661875567,
      "learning_rate": 3.459607989879238e-07,
      "loss": 0.9975,
      "step": 535
    },
    {
      "epoch": 0.9490925188136343,
      "grad_norm": 0.35338866740693625,
      "learning_rate": 3.225633603625711e-07,
      "loss": 0.9553,
      "step": 536
    },
    {
      "epoch": 0.950863213811421,
      "grad_norm": 0.3675518990454959,
      "learning_rate": 2.999799208742021e-07,
      "loss": 0.9729,
      "step": 537
    },
    {
      "epoch": 0.9526339088092076,
      "grad_norm": 0.22309206751160482,
      "learning_rate": 2.782112254502783e-07,
      "loss": 0.9319,
      "step": 538
    },
    {
      "epoch": 0.9544046038069942,
      "grad_norm": 0.29793634544853714,
      "learning_rate": 2.572579921434698e-07,
      "loss": 0.9427,
      "step": 539
    },
    {
      "epoch": 0.9561752988047809,
      "grad_norm": 0.40461771547508135,
      "learning_rate": 2.3712091210797428e-07,
      "loss": 0.9422,
      "step": 540
    },
    {
      "epoch": 0.9579459938025675,
      "grad_norm": 0.41485986367350947,
      "learning_rate": 2.1780064957670487e-07,
      "loss": 0.9144,
      "step": 541
    },
    {
      "epoch": 0.9597166888003541,
      "grad_norm": 0.902094887926934,
      "learning_rate": 1.9929784183939927e-07,
      "loss": 0.9757,
      "step": 542
    },
    {
      "epoch": 0.9614873837981408,
      "grad_norm": 0.31826665847725427,
      "learning_rate": 1.8161309922158643e-07,
      "loss": 0.8741,
      "step": 543
    },
    {
      "epoch": 0.9632580787959274,
      "grad_norm": 0.8635430703869863,
      "learning_rate": 1.6474700506445005e-07,
      "loss": 0.9424,
      "step": 544
    },
    {
      "epoch": 0.965028773793714,
      "grad_norm": 0.7140469585286057,
      "learning_rate": 1.4870011570560226e-07,
      "loss": 1.0257,
      "step": 545
    },
    {
      "epoch": 0.9667994687915007,
      "grad_norm": 0.3779738825006288,
      "learning_rate": 1.3347296046072322e-07,
      "loss": 1.0001,
      "step": 546
    },
    {
      "epoch": 0.9685701637892873,
      "grad_norm": 0.909146825139116,
      "learning_rate": 1.1906604160609181e-07,
      "loss": 1.0091,
      "step": 547
    },
    {
      "epoch": 0.9703408587870739,
      "grad_norm": 0.29609131106488873,
      "learning_rate": 1.0547983436203779e-07,
      "loss": 0.9517,
      "step": 548
    },
    {
      "epoch": 0.9721115537848606,
      "grad_norm": 1.4158544123947736,
      "learning_rate": 9.271478687725709e-08,
      "loss": 1.0357,
      "step": 549
    },
    {
      "epoch": 0.9738822487826472,
      "grad_norm": 0.4057613683729244,
      "learning_rate": 8.077132021402644e-08,
      "loss": 0.9146,
      "step": 550
    },
    {
      "epoch": 0.9756529437804338,
      "grad_norm": 0.6138811918514607,
      "learning_rate": 6.964982833430889e-08,
      "loss": 0.9549,
      "step": 551
    },
    {
      "epoch": 0.9774236387782205,
      "grad_norm": 0.5437675343584231,
      "learning_rate": 5.935067808678085e-08,
      "loss": 1.0645,
      "step": 552
    },
    {
      "epoch": 0.9791943337760071,
      "grad_norm": 0.8752922088956007,
      "learning_rate": 4.9874209194705754e-08,
      "loss": 1.0234,
      "step": 553
    },
    {
      "epoch": 0.9809650287737938,
      "grad_norm": 0.47948811756841286,
      "learning_rate": 4.122073424474571e-08,
      "loss": 0.9671,
      "step": 554
    },
    {
      "epoch": 0.9827357237715804,
      "grad_norm": 0.27393573116974734,
      "learning_rate": 3.339053867664199e-08,
      "loss": 0.9984,
      "step": 555
    },
    {
      "epoch": 0.984506418769367,
      "grad_norm": 0.2837200936351358,
      "learning_rate": 2.638388077380316e-08,
      "loss": 0.96,
      "step": 556
    },
    {
      "epoch": 0.9862771137671537,
      "grad_norm": 0.36043307073388037,
      "learning_rate": 2.0200991654784063e-08,
      "loss": 1.0143,
      "step": 557
    },
    {
      "epoch": 0.9880478087649402,
      "grad_norm": 0.3537153234817886,
      "learning_rate": 1.4842075265658617e-08,
      "loss": 0.8833,
      "step": 558
    },
    {
      "epoch": 0.9898185037627268,
      "grad_norm": 0.8167537355087086,
      "learning_rate": 1.0307308373305735e-08,
      "loss": 0.9781,
      "step": 559
    },
    {
      "epoch": 0.9915891987605135,
      "grad_norm": 0.295363095429904,
      "learning_rate": 6.596840559558448e-09,
      "loss": 0.9778,
      "step": 560
    },
    {
      "epoch": 0.9933598937583001,
      "grad_norm": 0.25913311078811646,
      "learning_rate": 3.7107942162883934e-09,
      "loss": 0.8581,
      "step": 561
    },
    {
      "epoch": 0.9951305887560867,
      "grad_norm": 0.4213853047968374,
      "learning_rate": 1.6492645413590525e-09,
      "loss": 1.0346,
      "step": 562
    },
    {
      "epoch": 0.9969012837538734,
      "grad_norm": 0.38857867496363646,
      "learning_rate": 4.1231953548936943e-10,
      "loss": 0.9974,
      "step": 563
    },
    {
      "epoch": 0.99867197875166,
      "grad_norm": 0.2819711758486504,
      "learning_rate": 0.0,
      "loss": 0.9873,
      "step": 564
    },
    {
      "epoch": 0.99867197875166,
      "step": 564,
      "total_flos": 624769463549952.0,
      "train_loss": 0.9490886049490448,
      "train_runtime": 2900.7495,
      "train_samples_per_second": 49.831,
      "train_steps_per_second": 0.194
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 564,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 624769463549952.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}