{
  "best_metric": 2.503065347671509,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.06760753824051381,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003380376912025691,
      "grad_norm": 0.10523601621389389,
      "learning_rate": 5e-06,
      "loss": 2.853,
      "step": 1
    },
    {
      "epoch": 0.0003380376912025691,
      "eval_loss": 2.8840956687927246,
      "eval_runtime": 162.3438,
      "eval_samples_per_second": 30.694,
      "eval_steps_per_second": 15.35,
      "step": 1
    },
    {
      "epoch": 0.0006760753824051382,
      "grad_norm": 0.11300719529390335,
      "learning_rate": 1e-05,
      "loss": 2.8731,
      "step": 2
    },
    {
      "epoch": 0.0010141130736077072,
      "grad_norm": 0.1181124895811081,
      "learning_rate": 1.5e-05,
      "loss": 2.7197,
      "step": 3
    },
    {
      "epoch": 0.0013521507648102764,
      "grad_norm": 0.11358941346406937,
      "learning_rate": 2e-05,
      "loss": 2.6189,
      "step": 4
    },
    {
      "epoch": 0.0016901884560128453,
      "grad_norm": 0.12935127317905426,
      "learning_rate": 2.5e-05,
      "loss": 2.7227,
      "step": 5
    },
    {
      "epoch": 0.0020282261472154145,
      "grad_norm": 0.12635090947151184,
      "learning_rate": 3e-05,
      "loss": 2.7281,
      "step": 6
    },
    {
      "epoch": 0.0023662638384179834,
      "grad_norm": 0.12893423438072205,
      "learning_rate": 3.5e-05,
      "loss": 2.7856,
      "step": 7
    },
    {
      "epoch": 0.002704301529620553,
      "grad_norm": 0.13405907154083252,
      "learning_rate": 4e-05,
      "loss": 2.7059,
      "step": 8
    },
    {
      "epoch": 0.0030423392208231217,
      "grad_norm": 0.13030965626239777,
      "learning_rate": 4.5e-05,
      "loss": 2.8557,
      "step": 9
    },
    {
      "epoch": 0.0033803769120256907,
      "grad_norm": 0.12359292060136795,
      "learning_rate": 5e-05,
      "loss": 2.7765,
      "step": 10
    },
    {
      "epoch": 0.00371841460322826,
      "grad_norm": 0.12834692001342773,
      "learning_rate": 5.500000000000001e-05,
      "loss": 2.8538,
      "step": 11
    },
    {
      "epoch": 0.004056452294430829,
      "grad_norm": 0.11821915954351425,
      "learning_rate": 6e-05,
      "loss": 2.8292,
      "step": 12
    },
    {
      "epoch": 0.004394489985633398,
      "grad_norm": 0.11626603454351425,
      "learning_rate": 6.500000000000001e-05,
      "loss": 2.7373,
      "step": 13
    },
    {
      "epoch": 0.004732527676835967,
      "grad_norm": 0.10216615349054337,
      "learning_rate": 7e-05,
      "loss": 2.6357,
      "step": 14
    },
    {
      "epoch": 0.005070565368038536,
      "grad_norm": 0.0992196574807167,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.7112,
      "step": 15
    },
    {
      "epoch": 0.005408603059241106,
      "grad_norm": 0.09023231267929077,
      "learning_rate": 8e-05,
      "loss": 2.6532,
      "step": 16
    },
    {
      "epoch": 0.005746640750443674,
      "grad_norm": 0.09340744465589523,
      "learning_rate": 8.5e-05,
      "loss": 2.6416,
      "step": 17
    },
    {
      "epoch": 0.0060846784416462435,
      "grad_norm": 0.11787692457437515,
      "learning_rate": 9e-05,
      "loss": 2.7012,
      "step": 18
    },
    {
      "epoch": 0.006422716132848813,
      "grad_norm": 0.11715151369571686,
      "learning_rate": 9.5e-05,
      "loss": 2.7406,
      "step": 19
    },
    {
      "epoch": 0.006760753824051381,
      "grad_norm": 0.12233071029186249,
      "learning_rate": 0.0001,
      "loss": 2.708,
      "step": 20
    },
    {
      "epoch": 0.007098791515253951,
      "grad_norm": 0.11601782590150833,
      "learning_rate": 9.999238475781957e-05,
      "loss": 2.7221,
      "step": 21
    },
    {
      "epoch": 0.00743682920645652,
      "grad_norm": 0.10434184968471527,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.7095,
      "step": 22
    },
    {
      "epoch": 0.007774866897659089,
      "grad_norm": 0.10461997240781784,
      "learning_rate": 9.99314767377287e-05,
      "loss": 2.8121,
      "step": 23
    },
    {
      "epoch": 0.008112904588861658,
      "grad_norm": 0.09764059633016586,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.6841,
      "step": 24
    },
    {
      "epoch": 0.008450942280064227,
      "grad_norm": 0.08557726442813873,
      "learning_rate": 9.980973490458728e-05,
      "loss": 2.5819,
      "step": 25
    },
    {
      "epoch": 0.008788979971266797,
      "grad_norm": 0.08187226206064224,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.5487,
      "step": 26
    },
    {
      "epoch": 0.009127017662469365,
      "grad_norm": 0.0848044604063034,
      "learning_rate": 9.962730758206611e-05,
      "loss": 2.5841,
      "step": 27
    },
    {
      "epoch": 0.009465055353671934,
      "grad_norm": 0.09243357181549072,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.5736,
      "step": 28
    },
    {
      "epoch": 0.009803093044874504,
      "grad_norm": 0.10886672139167786,
      "learning_rate": 9.938441702975689e-05,
      "loss": 2.5038,
      "step": 29
    },
    {
      "epoch": 0.010141130736077072,
      "grad_norm": 0.09007382392883301,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.4045,
      "step": 30
    },
    {
      "epoch": 0.010479168427279641,
      "grad_norm": 0.0924578458070755,
      "learning_rate": 9.908135917238321e-05,
      "loss": 2.4872,
      "step": 31
    },
    {
      "epoch": 0.010817206118482211,
      "grad_norm": 0.0975000262260437,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.6115,
      "step": 32
    },
    {
      "epoch": 0.01115524380968478,
      "grad_norm": 0.09270554780960083,
      "learning_rate": 9.871850323926177e-05,
      "loss": 2.4329,
      "step": 33
    },
    {
      "epoch": 0.011493281500887348,
      "grad_norm": 0.10020536929368973,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.5145,
      "step": 34
    },
    {
      "epoch": 0.011831319192089918,
      "grad_norm": 0.09536325931549072,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.5099,
      "step": 35
    },
    {
      "epoch": 0.012169356883292487,
      "grad_norm": 0.09235840290784836,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.4359,
      "step": 36
    },
    {
      "epoch": 0.012507394574495055,
      "grad_norm": 0.10001373291015625,
      "learning_rate": 9.781523779815179e-05,
      "loss": 2.3665,
      "step": 37
    },
    {
      "epoch": 0.012845432265697626,
      "grad_norm": 0.10007135570049286,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.3076,
      "step": 38
    },
    {
      "epoch": 0.013183469956900194,
      "grad_norm": 0.11269430071115494,
      "learning_rate": 9.727592877996585e-05,
      "loss": 2.3814,
      "step": 39
    },
    {
      "epoch": 0.013521507648102763,
      "grad_norm": 0.17496685683727264,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.3701,
      "step": 40
    },
    {
      "epoch": 0.013859545339305333,
      "grad_norm": 0.10990560799837112,
      "learning_rate": 9.667902132486009e-05,
      "loss": 2.3456,
      "step": 41
    },
    {
      "epoch": 0.014197583030507901,
      "grad_norm": 0.12474522739648819,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.2977,
      "step": 42
    },
    {
      "epoch": 0.01453562072171047,
      "grad_norm": 0.14294423162937164,
      "learning_rate": 9.602524267262203e-05,
      "loss": 2.2603,
      "step": 43
    },
    {
      "epoch": 0.01487365841291304,
      "grad_norm": 0.15347222983837128,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.1884,
      "step": 44
    },
    {
      "epoch": 0.015211696104115609,
      "grad_norm": 0.21388979256153107,
      "learning_rate": 9.53153893518325e-05,
      "loss": 2.3148,
      "step": 45
    },
    {
      "epoch": 0.015549733795318177,
      "grad_norm": 0.739169180393219,
      "learning_rate": 9.493970231495835e-05,
      "loss": 2.7314,
      "step": 46
    },
    {
      "epoch": 0.015887771486520746,
      "grad_norm": 0.9878103733062744,
      "learning_rate": 9.45503262094184e-05,
      "loss": 3.0176,
      "step": 47
    },
    {
      "epoch": 0.016225809177723316,
      "grad_norm": 1.23638916015625,
      "learning_rate": 9.414737964294636e-05,
      "loss": 3.5695,
      "step": 48
    },
    {
      "epoch": 0.016563846868925886,
      "grad_norm": 1.0610380172729492,
      "learning_rate": 9.373098535696979e-05,
      "loss": 3.4646,
      "step": 49
    },
    {
      "epoch": 0.016901884560128453,
      "grad_norm": 1.2307878732681274,
      "learning_rate": 9.330127018922194e-05,
      "loss": 4.0786,
      "step": 50
    },
    {
      "epoch": 0.016901884560128453,
      "eval_loss": 2.7397637367248535,
      "eval_runtime": 162.8273,
      "eval_samples_per_second": 30.603,
      "eval_steps_per_second": 15.305,
      "step": 50
    },
    {
      "epoch": 0.017239922251331023,
      "grad_norm": 0.5866208672523499,
      "learning_rate": 9.285836503510562e-05,
      "loss": 2.7651,
      "step": 51
    },
    {
      "epoch": 0.017577959942533593,
      "grad_norm": 0.7429975271224976,
      "learning_rate": 9.24024048078213e-05,
      "loss": 2.842,
      "step": 52
    },
    {
      "epoch": 0.01791599763373616,
      "grad_norm": 0.5988535284996033,
      "learning_rate": 9.193352839727121e-05,
      "loss": 2.6998,
      "step": 53
    },
    {
      "epoch": 0.01825403532493873,
      "grad_norm": 0.3802872598171234,
      "learning_rate": 9.145187862775209e-05,
      "loss": 2.716,
      "step": 54
    },
    {
      "epoch": 0.0185920730161413,
      "grad_norm": 0.24354064464569092,
      "learning_rate": 9.09576022144496e-05,
      "loss": 2.6113,
      "step": 55
    },
    {
      "epoch": 0.018930110707343867,
      "grad_norm": 0.16416750848293304,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.6169,
      "step": 56
    },
    {
      "epoch": 0.019268148398546438,
      "grad_norm": 0.1279710978269577,
      "learning_rate": 8.993177550236464e-05,
      "loss": 2.7098,
      "step": 57
    },
    {
      "epoch": 0.019606186089749008,
      "grad_norm": 0.11319886893033981,
      "learning_rate": 8.940053768033609e-05,
      "loss": 2.6226,
      "step": 58
    },
    {
      "epoch": 0.019944223780951575,
      "grad_norm": 0.10347788780927658,
      "learning_rate": 8.885729807284856e-05,
      "loss": 2.6154,
      "step": 59
    },
    {
      "epoch": 0.020282261472154145,
      "grad_norm": 0.09901144355535507,
      "learning_rate": 8.83022221559489e-05,
      "loss": 2.7105,
      "step": 60
    },
    {
      "epoch": 0.020620299163356715,
      "grad_norm": 0.09612453728914261,
      "learning_rate": 8.773547901113862e-05,
      "loss": 2.5739,
      "step": 61
    },
    {
      "epoch": 0.020958336854559282,
      "grad_norm": 0.09539550542831421,
      "learning_rate": 8.715724127386972e-05,
      "loss": 2.6807,
      "step": 62
    },
    {
      "epoch": 0.021296374545761852,
      "grad_norm": 0.08847247064113617,
      "learning_rate": 8.656768508095853e-05,
      "loss": 2.596,
      "step": 63
    },
    {
      "epoch": 0.021634412236964422,
      "grad_norm": 0.1007726639509201,
      "learning_rate": 8.596699001693255e-05,
      "loss": 2.6731,
      "step": 64
    },
    {
      "epoch": 0.02197244992816699,
      "grad_norm": 0.0899026170372963,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.5884,
      "step": 65
    },
    {
      "epoch": 0.02231048761936956,
      "grad_norm": 0.09400119632482529,
      "learning_rate": 8.473291852294987e-05,
      "loss": 2.5335,
      "step": 66
    },
    {
      "epoch": 0.02264852531057213,
      "grad_norm": 0.08951772004365921,
      "learning_rate": 8.409991800312493e-05,
      "loss": 2.6593,
      "step": 67
    },
    {
      "epoch": 0.022986563001774696,
      "grad_norm": 0.08979274332523346,
      "learning_rate": 8.345653031794292e-05,
      "loss": 2.704,
      "step": 68
    },
    {
      "epoch": 0.023324600692977267,
      "grad_norm": 0.08381976932287216,
      "learning_rate": 8.280295144952536e-05,
      "loss": 2.565,
      "step": 69
    },
    {
      "epoch": 0.023662638384179837,
      "grad_norm": 0.08561103045940399,
      "learning_rate": 8.213938048432697e-05,
      "loss": 2.4998,
      "step": 70
    },
    {
      "epoch": 0.024000676075382404,
      "grad_norm": 0.08922868967056274,
      "learning_rate": 8.146601955249188e-05,
      "loss": 2.5256,
      "step": 71
    },
    {
      "epoch": 0.024338713766584974,
      "grad_norm": 0.09140028059482574,
      "learning_rate": 8.07830737662829e-05,
      "loss": 2.6774,
      "step": 72
    },
    {
      "epoch": 0.024676751457787544,
      "grad_norm": 0.08435528725385666,
      "learning_rate": 8.009075115760243e-05,
      "loss": 2.5338,
      "step": 73
    },
    {
      "epoch": 0.02501478914899011,
      "grad_norm": 0.08592145889997482,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.4624,
      "step": 74
    },
    {
      "epoch": 0.02535282684019268,
      "grad_norm": 0.08802437037229538,
      "learning_rate": 7.86788218175523e-05,
      "loss": 2.5648,
      "step": 75
    },
    {
      "epoch": 0.02569086453139525,
      "grad_norm": 0.08933433890342712,
      "learning_rate": 7.795964517353735e-05,
      "loss": 2.5267,
      "step": 76
    },
    {
      "epoch": 0.026028902222597818,
      "grad_norm": 0.08545012027025223,
      "learning_rate": 7.723195175075136e-05,
      "loss": 2.6728,
      "step": 77
    },
    {
      "epoch": 0.02636693991380039,
      "grad_norm": 0.08358581364154816,
      "learning_rate": 7.649596321166024e-05,
      "loss": 2.4774,
      "step": 78
    },
    {
      "epoch": 0.02670497760500296,
      "grad_norm": 0.08687689155340195,
      "learning_rate": 7.575190374550272e-05,
      "loss": 2.5508,
      "step": 79
    },
    {
      "epoch": 0.027043015296205525,
      "grad_norm": 0.08650659769773483,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.5081,
      "step": 80
    },
    {
      "epoch": 0.027381052987408096,
      "grad_norm": 0.08604317903518677,
      "learning_rate": 7.424048101231686e-05,
      "loss": 2.5027,
      "step": 81
    },
    {
      "epoch": 0.027719090678610666,
      "grad_norm": 0.08907677233219147,
      "learning_rate": 7.347357813929454e-05,
      "loss": 2.4634,
      "step": 82
    },
    {
      "epoch": 0.028057128369813233,
      "grad_norm": 0.08967877179384232,
      "learning_rate": 7.269952498697734e-05,
      "loss": 2.4163,
      "step": 83
    },
    {
      "epoch": 0.028395166061015803,
      "grad_norm": 0.0939180925488472,
      "learning_rate": 7.191855733945387e-05,
      "loss": 2.4759,
      "step": 84
    },
    {
      "epoch": 0.028733203752218373,
      "grad_norm": 0.09361878782510757,
      "learning_rate": 7.113091308703498e-05,
      "loss": 2.387,
      "step": 85
    },
    {
      "epoch": 0.02907124144342094,
      "grad_norm": 0.09520508348941803,
      "learning_rate": 7.033683215379002e-05,
      "loss": 2.4342,
      "step": 86
    },
    {
      "epoch": 0.02940927913462351,
      "grad_norm": 0.09410521388053894,
      "learning_rate": 6.953655642446368e-05,
      "loss": 2.3505,
      "step": 87
    },
    {
      "epoch": 0.02974731682582608,
      "grad_norm": 0.09730350971221924,
      "learning_rate": 6.873032967079561e-05,
      "loss": 2.4134,
      "step": 88
    },
    {
      "epoch": 0.030085354517028647,
      "grad_norm": 0.11176914721727371,
      "learning_rate": 6.7918397477265e-05,
      "loss": 2.2922,
      "step": 89
    },
    {
      "epoch": 0.030423392208231217,
      "grad_norm": 0.10425267368555069,
      "learning_rate": 6.710100716628344e-05,
      "loss": 2.3032,
      "step": 90
    },
    {
      "epoch": 0.030761429899433788,
      "grad_norm": 0.11240172386169434,
      "learning_rate": 6.627840772285784e-05,
      "loss": 2.354,
      "step": 91
    },
    {
      "epoch": 0.031099467590636354,
      "grad_norm": 0.12464030832052231,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.2911,
      "step": 92
    },
    {
      "epoch": 0.031437505281838925,
      "grad_norm": 0.13469967246055603,
      "learning_rate": 6.461858523613684e-05,
      "loss": 2.3911,
      "step": 93
    },
    {
      "epoch": 0.03177554297304149,
      "grad_norm": 0.1728590726852417,
      "learning_rate": 6.378186779084995e-05,
      "loss": 2.2189,
      "step": 94
    },
    {
      "epoch": 0.032113580664244065,
      "grad_norm": 0.20108544826507568,
      "learning_rate": 6.294095225512603e-05,
      "loss": 2.2428,
      "step": 95
    },
    {
      "epoch": 0.03245161835544663,
      "grad_norm": 0.25884371995925903,
      "learning_rate": 6.209609477998338e-05,
      "loss": 2.309,
      "step": 96
    },
    {
      "epoch": 0.0327896560466492,
      "grad_norm": 0.4613964855670929,
      "learning_rate": 6.124755271719325e-05,
      "loss": 2.2025,
      "step": 97
    },
    {
      "epoch": 0.03312769373785177,
      "grad_norm": 0.8054183125495911,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 2.9777,
      "step": 98
    },
    {
      "epoch": 0.03346573142905434,
      "grad_norm": 1.0649651288986206,
      "learning_rate": 5.9540449768827246e-05,
      "loss": 3.2602,
      "step": 99
    },
    {
      "epoch": 0.033803769120256906,
      "grad_norm": 1.2406833171844482,
      "learning_rate": 5.868240888334653e-05,
      "loss": 3.9073,
      "step": 100
    },
    {
      "epoch": 0.033803769120256906,
      "eval_loss": 2.5389018058776855,
      "eval_runtime": 162.6367,
      "eval_samples_per_second": 30.639,
      "eval_steps_per_second": 15.322,
      "step": 100
    },
    {
      "epoch": 0.03414180681145948,
      "grad_norm": 0.12543514370918274,
      "learning_rate": 5.782172325201155e-05,
      "loss": 2.6515,
      "step": 101
    },
    {
      "epoch": 0.034479844502662046,
      "grad_norm": 0.13559122383594513,
      "learning_rate": 5.695865504800327e-05,
      "loss": 2.7056,
      "step": 102
    },
    {
      "epoch": 0.03481788219386461,
      "grad_norm": 0.15086260437965393,
      "learning_rate": 5.6093467170257374e-05,
      "loss": 2.623,
      "step": 103
    },
    {
      "epoch": 0.03515591988506719,
      "grad_norm": 0.16311992704868317,
      "learning_rate": 5.522642316338268e-05,
      "loss": 2.6536,
      "step": 104
    },
    {
      "epoch": 0.035493957576269754,
      "grad_norm": 0.14247645437717438,
      "learning_rate": 5.435778713738292e-05,
      "loss": 2.5373,
      "step": 105
    },
    {
      "epoch": 0.03583199526747232,
      "grad_norm": 0.14667530357837677,
      "learning_rate": 5.348782368720626e-05,
      "loss": 2.5767,
      "step": 106
    },
    {
      "epoch": 0.036170032958674894,
      "grad_norm": 0.14065583050251007,
      "learning_rate": 5.26167978121472e-05,
      "loss": 2.5077,
      "step": 107
    },
    {
      "epoch": 0.03650807064987746,
      "grad_norm": 0.14365576207637787,
      "learning_rate": 5.174497483512506e-05,
      "loss": 2.5648,
      "step": 108
    },
    {
      "epoch": 0.03684610834108003,
      "grad_norm": 0.1457732617855072,
      "learning_rate": 5.0872620321864185e-05,
      "loss": 2.6561,
      "step": 109
    },
    {
      "epoch": 0.0371841460322826,
      "grad_norm": 0.14005421102046967,
      "learning_rate": 5e-05,
      "loss": 2.5391,
      "step": 110
    },
    {
      "epoch": 0.03752218372348517,
      "grad_norm": 0.12205882370471954,
      "learning_rate": 4.912737967813583e-05,
      "loss": 2.5779,
      "step": 111
    },
    {
      "epoch": 0.037860221414687735,
      "grad_norm": 0.1202678307890892,
      "learning_rate": 4.825502516487497e-05,
      "loss": 2.5411,
      "step": 112
    },
    {
      "epoch": 0.03819825910589031,
      "grad_norm": 0.10689626634120941,
      "learning_rate": 4.738320218785281e-05,
      "loss": 2.5778,
      "step": 113
    },
    {
      "epoch": 0.038536296797092875,
      "grad_norm": 0.10453428328037262,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 2.6124,
      "step": 114
    },
    {
      "epoch": 0.03887433448829544,
      "grad_norm": 0.1035134494304657,
      "learning_rate": 4.564221286261709e-05,
      "loss": 2.6176,
      "step": 115
    },
    {
      "epoch": 0.039212372179498016,
      "grad_norm": 0.0994374230504036,
      "learning_rate": 4.477357683661734e-05,
      "loss": 2.5362,
      "step": 116
    },
    {
      "epoch": 0.03955040987070058,
      "grad_norm": 0.09687662869691849,
      "learning_rate": 4.390653282974264e-05,
      "loss": 2.546,
      "step": 117
    },
    {
      "epoch": 0.03988844756190315,
      "grad_norm": 0.1032131165266037,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 2.544,
      "step": 118
    },
    {
      "epoch": 0.04022648525310572,
      "grad_norm": 0.09238135069608688,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 2.5745,
      "step": 119
    },
    {
      "epoch": 0.04056452294430829,
      "grad_norm": 0.09466104954481125,
      "learning_rate": 4.131759111665349e-05,
      "loss": 2.5365,
      "step": 120
    },
    {
      "epoch": 0.04090256063551086,
      "grad_norm": 0.09744452685117722,
      "learning_rate": 4.045955023117276e-05,
      "loss": 2.568,
      "step": 121
    },
    {
      "epoch": 0.04124059832671343,
      "grad_norm": 0.095356784760952,
      "learning_rate": 3.960441545911204e-05,
      "loss": 2.5054,
      "step": 122
    },
    {
      "epoch": 0.041578636017916,
      "grad_norm": 0.09819884598255157,
      "learning_rate": 3.875244728280676e-05,
      "loss": 2.51,
      "step": 123
    },
    {
      "epoch": 0.041916673709118564,
      "grad_norm": 0.09662871062755585,
      "learning_rate": 3.790390522001662e-05,
      "loss": 2.6494,
      "step": 124
    },
    {
      "epoch": 0.04225471140032114,
      "grad_norm": 0.09809296578168869,
      "learning_rate": 3.705904774487396e-05,
      "loss": 2.6305,
      "step": 125
    },
    {
      "epoch": 0.042592749091523704,
      "grad_norm": 0.09920753538608551,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 2.4887,
      "step": 126
    },
    {
      "epoch": 0.04293078678272627,
      "grad_norm": 0.09396395087242126,
      "learning_rate": 3.5381414763863166e-05,
      "loss": 2.4469,
      "step": 127
    },
    {
      "epoch": 0.043268824473928845,
      "grad_norm": 0.10174640268087387,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 2.5329,
      "step": 128
    },
    {
      "epoch": 0.04360686216513141,
      "grad_norm": 0.0986228957772255,
      "learning_rate": 3.372159227714218e-05,
      "loss": 2.5181,
      "step": 129
    },
    {
      "epoch": 0.04394489985633398,
      "grad_norm": 0.10053939372301102,
      "learning_rate": 3.289899283371657e-05,
      "loss": 2.4012,
      "step": 130
    },
    {
      "epoch": 0.04428293754753655,
      "grad_norm": 0.10566799342632294,
      "learning_rate": 3.2081602522734986e-05,
      "loss": 2.4489,
      "step": 131
    },
    {
      "epoch": 0.04462097523873912,
      "grad_norm": 0.10213074833154678,
      "learning_rate": 3.12696703292044e-05,
      "loss": 2.502,
      "step": 132
    },
    {
      "epoch": 0.044959012929941686,
      "grad_norm": 0.1079111322760582,
      "learning_rate": 3.046344357553632e-05,
      "loss": 2.4545,
      "step": 133
    },
    {
      "epoch": 0.04529705062114426,
      "grad_norm": 0.10515129566192627,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 2.3398,
      "step": 134
    },
    {
      "epoch": 0.045635088312346826,
      "grad_norm": 0.1130945011973381,
      "learning_rate": 2.886908691296504e-05,
      "loss": 2.5233,
      "step": 135
    },
    {
      "epoch": 0.04597312600354939,
      "grad_norm": 0.11503010243177414,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 2.5065,
      "step": 136
    },
    {
      "epoch": 0.04631116369475197,
      "grad_norm": 0.11939393728971481,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 2.3705,
      "step": 137
    },
    {
      "epoch": 0.046649201385954533,
      "grad_norm": 0.11583313345909119,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 2.3557,
      "step": 138
    },
    {
      "epoch": 0.0469872390771571,
      "grad_norm": 0.11651947349309921,
      "learning_rate": 2.575951898768315e-05,
      "loss": 2.4014,
      "step": 139
    },
    {
      "epoch": 0.047325276768359674,
      "grad_norm": 0.13216450810432434,
      "learning_rate": 2.500000000000001e-05,
      "loss": 2.2894,
      "step": 140
    },
    {
      "epoch": 0.04766331445956224,
      "grad_norm": 0.1305103302001953,
      "learning_rate": 2.4248096254497288e-05,
      "loss": 2.2655,
      "step": 141
    },
    {
      "epoch": 0.04800135215076481,
      "grad_norm": 0.13988003134727478,
      "learning_rate": 2.350403678833976e-05,
      "loss": 2.3382,
      "step": 142
    },
    {
      "epoch": 0.04833938984196738,
      "grad_norm": 0.15006910264492035,
      "learning_rate": 2.2768048249248648e-05,
      "loss": 2.2201,
      "step": 143
    },
    {
      "epoch": 0.04867742753316995,
      "grad_norm": 0.1915428787469864,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 2.282,
      "step": 144
    },
    {
      "epoch": 0.049015465224372515,
      "grad_norm": 0.23334573209285736,
      "learning_rate": 2.132117818244771e-05,
      "loss": 2.2407,
      "step": 145
    },
    {
      "epoch": 0.04935350291557509,
      "grad_norm": 0.3686174154281616,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.3498,
      "step": 146
    },
    {
      "epoch": 0.049691540606777655,
      "grad_norm": 0.5592883229255676,
      "learning_rate": 1.9909248842397584e-05,
      "loss": 2.7735,
      "step": 147
    },
    {
      "epoch": 0.05002957829798022,
      "grad_norm": 0.5878916382789612,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 2.653,
      "step": 148
    },
    {
      "epoch": 0.050367615989182796,
      "grad_norm": 0.7976477146148682,
      "learning_rate": 1.8533980447508137e-05,
      "loss": 3.2429,
      "step": 149
    },
    {
      "epoch": 0.05070565368038536,
      "grad_norm": 1.0811750888824463,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 3.204,
      "step": 150
    },
    {
      "epoch": 0.05070565368038536,
      "eval_loss": 2.506248950958252,
      "eval_runtime": 162.644,
      "eval_samples_per_second": 30.637,
      "eval_steps_per_second": 15.322,
      "step": 150
    },
    {
      "epoch": 0.05104369137158793,
      "grad_norm": 0.074004627764225,
      "learning_rate": 1.7197048550474643e-05,
      "loss": 2.7227,
      "step": 151
    },
    {
      "epoch": 0.0513817290627905,
      "grad_norm": 0.07234673947095871,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 2.5232,
      "step": 152
    },
    {
      "epoch": 0.05171976675399307,
      "grad_norm": 0.07369707524776459,
      "learning_rate": 1.5900081996875083e-05,
      "loss": 2.659,
      "step": 153
    },
    {
      "epoch": 0.052057804445195636,
      "grad_norm": 0.07989693433046341,
      "learning_rate": 1.526708147705013e-05,
      "loss": 2.6055,
      "step": 154
    },
    {
      "epoch": 0.05239584213639821,
      "grad_norm": 0.07991430908441544,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.5445,
      "step": 155
    },
    {
      "epoch": 0.05273387982760078,
      "grad_norm": 0.08781698346138,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 2.6015,
      "step": 156
    },
    {
      "epoch": 0.053071917518803344,
      "grad_norm": 0.0825238898396492,
      "learning_rate": 1.3432314919041478e-05,
      "loss": 2.5479,
      "step": 157
    },
    {
      "epoch": 0.05340995521000592,
      "grad_norm": 0.07822147756814957,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 2.5229,
      "step": 158
    },
    {
      "epoch": 0.053747992901208484,
      "grad_norm": 0.07933247089385986,
      "learning_rate": 1.22645209888614e-05,
      "loss": 2.5495,
      "step": 159
    },
    {
      "epoch": 0.05408603059241105,
      "grad_norm": 0.08545535802841187,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 2.6076,
      "step": 160
    },
    {
      "epoch": 0.054424068283613625,
      "grad_norm": 0.08676018565893173,
      "learning_rate": 1.1142701927151456e-05,
      "loss": 2.6037,
      "step": 161
    },
    {
      "epoch": 0.05476210597481619,
      "grad_norm": 0.09296593815088272,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 2.6491,
      "step": 162
    },
    {
      "epoch": 0.05510014366601876,
      "grad_norm": 0.08331656455993652,
      "learning_rate": 1.006822449763537e-05,
      "loss": 2.4742,
      "step": 163
    },
    {
      "epoch": 0.05543818135722133,
      "grad_norm": 0.08637680113315582,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.6467,
      "step": 164
    },
    {
      "epoch": 0.0557762190484239,
      "grad_norm": 0.0850832536816597,
      "learning_rate": 9.042397785550405e-06,
      "loss": 2.5635,
      "step": 165
    },
    {
      "epoch": 0.056114256739626465,
      "grad_norm": 0.09275282919406891,
      "learning_rate": 8.548121372247918e-06,
      "loss": 2.5468,
      "step": 166
    },
    {
      "epoch": 0.05645229443082904,
      "grad_norm": 0.09009023755788803,
      "learning_rate": 8.066471602728803e-06,
      "loss": 2.4651,
      "step": 167
    },
    {
      "epoch": 0.056790332122031606,
      "grad_norm": 0.09028450399637222,
      "learning_rate": 7.597595192178702e-06,
      "loss": 2.5726,
      "step": 168
    },
    {
      "epoch": 0.05712836981323417,
      "grad_norm": 0.08400668948888779,
      "learning_rate": 7.1416349648943894e-06,
      "loss": 2.4748,
      "step": 169
    },
    {
      "epoch": 0.057466407504436746,
      "grad_norm": 0.08592666685581207,
      "learning_rate": 6.698729810778065e-06,
      "loss": 2.4492,
      "step": 170
    },
    {
      "epoch": 0.05780444519563931,
      "grad_norm": 0.08860240876674652,
      "learning_rate": 6.269014643030213e-06,
      "loss": 2.6181,
      "step": 171
    },
    {
      "epoch": 0.05814248288684188,
      "grad_norm": 0.08713769167661667,
      "learning_rate": 5.852620357053651e-06,
      "loss": 2.4715,
      "step": 172
    },
    {
      "epoch": 0.058480520578044454,
      "grad_norm": 0.08633475005626678,
      "learning_rate": 5.449673790581611e-06,
      "loss": 2.5371,
      "step": 173
    },
    {
      "epoch": 0.05881855826924702,
      "grad_norm": 0.09059322625398636,
      "learning_rate": 5.060297685041659e-06,
      "loss": 2.5911,
      "step": 174
    },
    {
      "epoch": 0.05915659596044959,
      "grad_norm": 0.08804945647716522,
      "learning_rate": 4.684610648167503e-06,
      "loss": 2.5121,
      "step": 175
    },
    {
      "epoch": 0.05949463365165216,
      "grad_norm": 0.0910625234246254,
      "learning_rate": 4.322727117869951e-06,
      "loss": 2.5346,
      "step": 176
    },
    {
      "epoch": 0.05983267134285473,
      "grad_norm": 0.09178397804498672,
      "learning_rate": 3.974757327377981e-06,
      "loss": 2.583,
      "step": 177
    },
    {
      "epoch": 0.060170709034057294,
      "grad_norm": 0.0911891981959343,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 2.4937,
      "step": 178
    },
    {
      "epoch": 0.06050874672525987,
      "grad_norm": 0.09039957821369171,
      "learning_rate": 3.3209786751399187e-06,
      "loss": 2.4119,
      "step": 179
    },
    {
      "epoch": 0.060846784416462435,
      "grad_norm": 0.09597639739513397,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 2.3971,
      "step": 180
    },
    {
      "epoch": 0.061184822107665,
      "grad_norm": 0.09821389615535736,
      "learning_rate": 2.724071220034158e-06,
      "loss": 2.4921,
      "step": 181
    },
    {
      "epoch": 0.061522859798867575,
      "grad_norm": 0.09597838670015335,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 2.4565,
      "step": 182
    },
    {
      "epoch": 0.06186089749007014,
      "grad_norm": 0.09808821231126785,
      "learning_rate": 2.1847622018482283e-06,
      "loss": 2.4119,
      "step": 183
    },
    {
      "epoch": 0.06219893518127271,
      "grad_norm": 0.10516849160194397,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 2.4429,
      "step": 184
    },
    {
      "epoch": 0.06253697287247528,
      "grad_norm": 0.10354617983102798,
      "learning_rate": 1.70370868554659e-06,
      "loss": 2.4067,
      "step": 185
    },
    {
      "epoch": 0.06287501056367785,
      "grad_norm": 0.11714711040258408,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 2.3115,
      "step": 186
    },
    {
      "epoch": 0.06321304825488042,
      "grad_norm": 0.10734293609857559,
      "learning_rate": 1.2814967607382432e-06,
      "loss": 2.3398,
      "step": 187
    },
    {
      "epoch": 0.06355108594608298,
      "grad_norm": 0.11610043793916702,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 2.4179,
      "step": 188
    },
    {
      "epoch": 0.06388912363728556,
      "grad_norm": 0.12529993057250977,
      "learning_rate": 9.186408276168013e-07,
      "loss": 2.3229,
      "step": 189
    },
    {
      "epoch": 0.06422716132848813,
      "grad_norm": 0.1205725371837616,
      "learning_rate": 7.596123493895991e-07,
      "loss": 2.3116,
      "step": 190
    },
    {
      "epoch": 0.0645651990196907,
      "grad_norm": 0.1311439573764801,
      "learning_rate": 6.15582970243117e-07,
      "loss": 2.357,
      "step": 191
    },
    {
      "epoch": 0.06490323671089326,
      "grad_norm": 0.1364409327507019,
      "learning_rate": 4.865965629214819e-07,
      "loss": 2.3083,
      "step": 192
    },
    {
      "epoch": 0.06524127440209583,
      "grad_norm": 0.16119834780693054,
      "learning_rate": 3.7269241793390085e-07,
      "loss": 2.2713,
      "step": 193
    },
    {
      "epoch": 0.0655793120932984,
      "grad_norm": 0.17283137142658234,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 2.2942,
      "step": 194
    },
    {
      "epoch": 0.06591734978450098,
      "grad_norm": 0.207033172249794,
      "learning_rate": 1.9026509541272275e-07,
      "loss": 2.2575,
      "step": 195
    },
    {
      "epoch": 0.06625538747570354,
      "grad_norm": 0.28731778264045715,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 2.2415,
      "step": 196
    },
    {
      "epoch": 0.06659342516690611,
      "grad_norm": 0.5070729851722717,
      "learning_rate": 6.852326227130834e-08,
      "loss": 2.4135,
      "step": 197
    },
    {
      "epoch": 0.06693146285810868,
      "grad_norm": 0.46098220348358154,
      "learning_rate": 3.04586490452119e-08,
      "loss": 2.586,
      "step": 198
    },
    {
      "epoch": 0.06726950054931125,
      "grad_norm": 0.5361522436141968,
      "learning_rate": 7.615242180436522e-09,
      "loss": 2.6058,
      "step": 199
    },
    {
      "epoch": 0.06760753824051381,
      "grad_norm": 0.7800777554512024,
      "learning_rate": 0.0,
      "loss": 2.9973,
      "step": 200
    },
    {
      "epoch": 0.06760753824051381,
      "eval_loss": 2.503065347671509,
      "eval_runtime": 162.8737,
      "eval_samples_per_second": 30.594,
      "eval_steps_per_second": 15.3,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.651170610846106e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}