{
  "best_metric": 10.353182792663574,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.34315760343157603,
  "eval_steps": 100,
  "global_step": 155,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0022139200221392,
      "grad_norm": 0.015347130596637726,
      "learning_rate": 2e-05,
      "loss": 10.3793,
      "step": 1
    },
    {
      "epoch": 0.0022139200221392,
      "eval_loss": 10.376798629760742,
      "eval_runtime": 4.6374,
      "eval_samples_per_second": 328.199,
      "eval_steps_per_second": 82.157,
      "step": 1
    },
    {
      "epoch": 0.0044278400442784,
      "grad_norm": 0.018048662692308426,
      "learning_rate": 4e-05,
      "loss": 10.3775,
      "step": 2
    },
    {
      "epoch": 0.006641760066417601,
      "grad_norm": 0.022233936935663223,
      "learning_rate": 6e-05,
      "loss": 10.3768,
      "step": 3
    },
    {
      "epoch": 0.0088556800885568,
      "grad_norm": 0.019449712708592415,
      "learning_rate": 8e-05,
      "loss": 10.3786,
      "step": 4
    },
    {
      "epoch": 0.011069600110696002,
      "grad_norm": 0.020489409565925598,
      "learning_rate": 0.0001,
      "loss": 10.3764,
      "step": 5
    },
    {
      "epoch": 0.013283520132835201,
      "grad_norm": 0.021540051326155663,
      "learning_rate": 0.00012,
      "loss": 10.3786,
      "step": 6
    },
    {
      "epoch": 0.0154974401549744,
      "grad_norm": 0.018246637657284737,
      "learning_rate": 0.00014,
      "loss": 10.3767,
      "step": 7
    },
    {
      "epoch": 0.0177113601771136,
      "grad_norm": 0.01636139489710331,
      "learning_rate": 0.00016,
      "loss": 10.3764,
      "step": 8
    },
    {
      "epoch": 0.019925280199252802,
      "grad_norm": 0.019374892115592957,
      "learning_rate": 0.00018,
      "loss": 10.3768,
      "step": 9
    },
    {
      "epoch": 0.022139200221392003,
      "grad_norm": 0.02034880220890045,
      "learning_rate": 0.0002,
      "loss": 10.3765,
      "step": 10
    },
    {
      "epoch": 0.0243531202435312,
      "grad_norm": 0.01910431496798992,
      "learning_rate": 0.00019997652980184843,
      "loss": 10.3751,
      "step": 11
    },
    {
      "epoch": 0.026567040265670402,
      "grad_norm": 0.020900217816233635,
      "learning_rate": 0.0001999061302243977,
      "loss": 10.3766,
      "step": 12
    },
    {
      "epoch": 0.028780960287809604,
      "grad_norm": 0.01849156990647316,
      "learning_rate": 0.00019978883431348845,
      "loss": 10.378,
      "step": 13
    },
    {
      "epoch": 0.0309948803099488,
      "grad_norm": 0.018774129450321198,
      "learning_rate": 0.00019962469712828614,
      "loss": 10.3779,
      "step": 14
    },
    {
      "epoch": 0.033208800332088007,
      "grad_norm": 0.021555211395025253,
      "learning_rate": 0.00019941379571543596,
      "loss": 10.3781,
      "step": 15
    },
    {
      "epoch": 0.0354227203542272,
      "grad_norm": 0.021058112382888794,
      "learning_rate": 0.00019915622907289694,
      "loss": 10.3764,
      "step": 16
    },
    {
      "epoch": 0.0376366403763664,
      "grad_norm": 0.025353940203785896,
      "learning_rate": 0.00019885211810347184,
      "loss": 10.3754,
      "step": 17
    },
    {
      "epoch": 0.039850560398505604,
      "grad_norm": 0.023140626028180122,
      "learning_rate": 0.00019850160555805486,
      "loss": 10.376,
      "step": 18
    },
    {
      "epoch": 0.042064480420644805,
      "grad_norm": 0.022708751261234283,
      "learning_rate": 0.00019810485596862392,
      "loss": 10.3754,
      "step": 19
    },
    {
      "epoch": 0.044278400442784006,
      "grad_norm": 0.02649092860519886,
      "learning_rate": 0.00019766205557100868,
      "loss": 10.3751,
      "step": 20
    },
    {
      "epoch": 0.04649232046492321,
      "grad_norm": 0.026685183867812157,
      "learning_rate": 0.00019717341221747056,
      "loss": 10.3743,
      "step": 21
    },
    {
      "epoch": 0.0487062404870624,
      "grad_norm": 0.030229078605771065,
      "learning_rate": 0.00019663915527913625,
      "loss": 10.3754,
      "step": 22
    },
    {
      "epoch": 0.050920160509201604,
      "grad_norm": 0.025011839345097542,
      "learning_rate": 0.00019605953553832988,
      "loss": 10.3762,
      "step": 23
    },
    {
      "epoch": 0.053134080531340805,
      "grad_norm": 0.03366699442267418,
      "learning_rate": 0.00019543482507085482,
      "loss": 10.3732,
      "step": 24
    },
    {
      "epoch": 0.055348000553480006,
      "grad_norm": 0.031245626509189606,
      "learning_rate": 0.00019476531711828027,
      "loss": 10.3732,
      "step": 25
    },
    {
      "epoch": 0.05756192057561921,
      "grad_norm": 0.033843208104372025,
      "learning_rate": 0.0001940513259502924,
      "loss": 10.3746,
      "step": 26
    },
    {
      "epoch": 0.05977584059775841,
      "grad_norm": 0.031005628407001495,
      "learning_rate": 0.0001932931867171751,
      "loss": 10.3757,
      "step": 27
    },
    {
      "epoch": 0.0619897606198976,
      "grad_norm": 0.04169201850891113,
      "learning_rate": 0.0001924912552924889,
      "loss": 10.3723,
      "step": 28
    },
    {
      "epoch": 0.06420368064203681,
      "grad_norm": 0.04145209118723869,
      "learning_rate": 0.00019164590810602262,
      "loss": 10.3726,
      "step": 29
    },
    {
      "epoch": 0.06641760066417601,
      "grad_norm": 0.04390417039394379,
      "learning_rate": 0.00019075754196709572,
      "loss": 10.3735,
      "step": 30
    },
    {
      "epoch": 0.0686315206863152,
      "grad_norm": 0.04278510808944702,
      "learning_rate": 0.00018982657387829445,
      "loss": 10.3715,
      "step": 31
    },
    {
      "epoch": 0.0708454407084544,
      "grad_norm": 0.042029816657304764,
      "learning_rate": 0.00018885344083972914,
      "loss": 10.3736,
      "step": 32
    },
    {
      "epoch": 0.0730593607305936,
      "grad_norm": 0.04833783209323883,
      "learning_rate": 0.00018783859964390464,
      "loss": 10.3727,
      "step": 33
    },
    {
      "epoch": 0.0752732807527328,
      "grad_norm": 0.04858450964093208,
      "learning_rate": 0.00018678252666130013,
      "loss": 10.3711,
      "step": 34
    },
    {
      "epoch": 0.077487200774872,
      "grad_norm": 0.05063305422663689,
      "learning_rate": 0.00018568571761675893,
      "loss": 10.3696,
      "step": 35
    },
    {
      "epoch": 0.07970112079701121,
      "grad_norm": 0.05562438815832138,
      "learning_rate": 0.0001845486873567932,
      "loss": 10.3704,
      "step": 36
    },
    {
      "epoch": 0.08191504081915041,
      "grad_norm": 0.06275998800992966,
      "learning_rate": 0.00018337196960791302,
      "loss": 10.3701,
      "step": 37
    },
    {
      "epoch": 0.08412896084128961,
      "grad_norm": 0.06581102311611176,
      "learning_rate": 0.00018215611672609317,
      "loss": 10.3701,
      "step": 38
    },
    {
      "epoch": 0.08634288086342881,
      "grad_norm": 0.06170434504747391,
      "learning_rate": 0.00018090169943749476,
      "loss": 10.3693,
      "step": 39
    },
    {
      "epoch": 0.08855680088556801,
      "grad_norm": 0.06494265049695969,
      "learning_rate": 0.00017960930657056438,
      "loss": 10.3718,
      "step": 40
    },
    {
      "epoch": 0.09077072090770721,
      "grad_norm": 0.06664866209030151,
      "learning_rate": 0.00017827954477963557,
      "loss": 10.3714,
      "step": 41
    },
    {
      "epoch": 0.09298464092984642,
      "grad_norm": 0.05908958986401558,
      "learning_rate": 0.0001769130382601629,
      "loss": 10.3683,
      "step": 42
    },
    {
      "epoch": 0.0951985609519856,
      "grad_norm": 0.07850487530231476,
      "learning_rate": 0.00017551042845572208,
      "loss": 10.366,
      "step": 43
    },
    {
      "epoch": 0.0974124809741248,
      "grad_norm": 0.07899674773216248,
      "learning_rate": 0.00017407237375691392,
      "loss": 10.3679,
      "step": 44
    },
    {
      "epoch": 0.099626400996264,
      "grad_norm": 0.08278781175613403,
      "learning_rate": 0.0001725995491923131,
      "loss": 10.3674,
      "step": 45
    },
    {
      "epoch": 0.10184032101840321,
      "grad_norm": 0.07795372605323792,
      "learning_rate": 0.00017109264611160708,
      "loss": 10.3658,
      "step": 46
    },
    {
      "epoch": 0.10405424104054241,
      "grad_norm": 0.06829465925693512,
      "learning_rate": 0.00016955237186107387,
      "loss": 10.3658,
      "step": 47
    },
    {
      "epoch": 0.10626816106268161,
      "grad_norm": 0.08101464062929153,
      "learning_rate": 0.0001679794494515508,
      "loss": 10.3642,
      "step": 48
    },
    {
      "epoch": 0.10848208108482081,
      "grad_norm": 0.08278671652078629,
      "learning_rate": 0.00016637461721905045,
      "loss": 10.3651,
      "step": 49
    },
    {
      "epoch": 0.11069600110696001,
      "grad_norm": 0.07952283322811127,
      "learning_rate": 0.00016473862847818277,
      "loss": 10.3637,
      "step": 50
    },
    {
      "epoch": 0.11290992112909921,
      "grad_norm": 0.08242182433605194,
      "learning_rate": 0.00016307225116854622,
      "loss": 10.3645,
      "step": 51
    },
    {
      "epoch": 0.11512384115123842,
      "grad_norm": 0.08912307769060135,
      "learning_rate": 0.00016137626749425377,
      "loss": 10.3624,
      "step": 52
    },
    {
      "epoch": 0.11733776117337762,
      "grad_norm": 0.07046646624803543,
      "learning_rate": 0.00015965147355676343,
      "loss": 10.3622,
      "step": 53
    },
    {
      "epoch": 0.11955168119551682,
      "grad_norm": 0.08123268932104111,
      "learning_rate": 0.0001578986789811849,
      "loss": 10.3636,
      "step": 54
    },
    {
      "epoch": 0.121765601217656,
      "grad_norm": 0.07835382968187332,
      "learning_rate": 0.00015611870653623825,
      "loss": 10.3637,
      "step": 55
    },
    {
      "epoch": 0.1239795212397952,
      "grad_norm": 0.0735471174120903,
      "learning_rate": 0.00015431239174804328,
      "loss": 10.3604,
      "step": 56
    },
    {
      "epoch": 0.1261934412619344,
      "grad_norm": 0.0726391151547432,
      "learning_rate": 0.00015248058250792008,
      "loss": 10.3613,
      "step": 57
    },
    {
      "epoch": 0.12840736128407362,
      "grad_norm": 0.07755741477012634,
      "learning_rate": 0.0001506241386743854,
      "loss": 10.3579,
      "step": 58
    },
    {
      "epoch": 0.1306212813062128,
      "grad_norm": 0.06758265197277069,
      "learning_rate": 0.00014874393166953192,
      "loss": 10.3583,
      "step": 59
    },
    {
      "epoch": 0.13283520132835203,
      "grad_norm": 0.06026022881269455,
      "learning_rate": 0.00014684084406997903,
      "loss": 10.3587,
      "step": 60
    },
    {
      "epoch": 0.1350491213504912,
      "grad_norm": 0.06415611505508423,
      "learning_rate": 0.00014491576919258792,
      "loss": 10.3574,
      "step": 61
    },
    {
      "epoch": 0.1372630413726304,
      "grad_norm": 0.054800305515527725,
      "learning_rate": 0.0001429696106751352,
      "loss": 10.3607,
      "step": 62
    },
    {
      "epoch": 0.13947696139476962,
      "grad_norm": 0.056575533002614975,
      "learning_rate": 0.0001410032820521416,
      "loss": 10.3583,
      "step": 63
    },
    {
      "epoch": 0.1416908814169088,
      "grad_norm": 0.05453406646847725,
      "learning_rate": 0.00013901770632605547,
      "loss": 10.3581,
      "step": 64
    },
    {
      "epoch": 0.14390480143904802,
      "grad_norm": 0.052836980670690536,
      "learning_rate": 0.00013701381553399145,
      "loss": 10.3553,
      "step": 65
    },
    {
      "epoch": 0.1461187214611872,
      "grad_norm": 0.06288017332553864,
      "learning_rate": 0.00013499255031022885,
      "loss": 10.3575,
      "step": 66
    },
    {
      "epoch": 0.14833264148332642,
      "grad_norm": 0.05181482061743736,
      "learning_rate": 0.00013295485944467405,
      "loss": 10.3561,
      "step": 67
    },
    {
      "epoch": 0.1505465615054656,
      "grad_norm": 0.04769117385149002,
      "learning_rate": 0.00013090169943749476,
      "loss": 10.3588,
      "step": 68
    },
    {
      "epoch": 0.15276048152760482,
      "grad_norm": 0.05283131077885628,
      "learning_rate": 0.0001288340340501351,
      "loss": 10.3577,
      "step": 69
    },
    {
      "epoch": 0.154974401549744,
      "grad_norm": 0.053591929376125336,
      "learning_rate": 0.00012675283385292212,
      "loss": 10.3542,
      "step": 70
    },
    {
      "epoch": 0.15718832157188323,
      "grad_norm": 0.053562965244054794,
      "learning_rate": 0.00012465907576947622,
      "loss": 10.3554,
      "step": 71
    },
    {
      "epoch": 0.15940224159402241,
      "grad_norm": 0.04689027741551399,
      "learning_rate": 0.00012255374261813944,
      "loss": 10.3555,
      "step": 72
    },
    {
      "epoch": 0.16161616161616163,
      "grad_norm": 0.05137080326676369,
      "learning_rate": 0.0001204378226506365,
      "loss": 10.3579,
      "step": 73
    },
    {
      "epoch": 0.16383008163830082,
      "grad_norm": 0.04621529206633568,
      "learning_rate": 0.00011831230908818563,
      "loss": 10.3556,
      "step": 74
    },
    {
      "epoch": 0.16604400166044,
      "grad_norm": 0.04236424341797829,
      "learning_rate": 0.0001161781996552765,
      "loss": 10.3562,
      "step": 75
    },
    {
      "epoch": 0.16825792168257922,
      "grad_norm": 0.046798307448625565,
      "learning_rate": 0.00011403649611133444,
      "loss": 10.3537,
      "step": 76
    },
    {
      "epoch": 0.1704718417047184,
      "grad_norm": 0.040729619562625885,
      "learning_rate": 0.00011188820378049065,
      "loss": 10.3543,
      "step": 77
    },
    {
      "epoch": 0.17268576172685762,
      "grad_norm": 0.03752255439758301,
      "learning_rate": 0.00010973433107967902,
      "loss": 10.3547,
      "step": 78
    },
    {
      "epoch": 0.1748996817489968,
      "grad_norm": 0.04051700234413147,
      "learning_rate": 0.00010757588904528106,
      "loss": 10.355,
      "step": 79
    },
    {
      "epoch": 0.17711360177113603,
      "grad_norm": 0.04239342361688614,
      "learning_rate": 0.00010541389085854176,
      "loss": 10.3547,
      "step": 80
    },
    {
      "epoch": 0.1793275217932752,
      "grad_norm": 0.04204672947525978,
      "learning_rate": 0.00010324935136997806,
      "loss": 10.3569,
      "step": 81
    },
    {
      "epoch": 0.18154144181541443,
      "grad_norm": 0.031643904745578766,
      "learning_rate": 0.000101083286623004,
      "loss": 10.3562,
      "step": 82
    },
    {
      "epoch": 0.18375536183755362,
      "grad_norm": 0.038713809102773666,
      "learning_rate": 9.891671337699602e-05,
      "loss": 10.3554,
      "step": 83
    },
    {
      "epoch": 0.18596928185969283,
      "grad_norm": 0.046824660152196884,
      "learning_rate": 9.675064863002196e-05,
      "loss": 10.3561,
      "step": 84
    },
    {
      "epoch": 0.18818320188183202,
      "grad_norm": 0.039098598062992096,
      "learning_rate": 9.458610914145826e-05,
      "loss": 10.3546,
      "step": 85
    },
    {
      "epoch": 0.1903971219039712,
      "grad_norm": 0.04264703765511513,
      "learning_rate": 9.242411095471897e-05,
      "loss": 10.3542,
      "step": 86
    },
    {
      "epoch": 0.19261104192611042,
      "grad_norm": 0.04310859739780426,
      "learning_rate": 9.026566892032105e-05,
      "loss": 10.3552,
      "step": 87
    },
    {
      "epoch": 0.1948249619482496,
      "grad_norm": 0.039878156036138535,
      "learning_rate": 8.811179621950936e-05,
      "loss": 10.3576,
      "step": 88
    },
    {
      "epoch": 0.19703888197038882,
      "grad_norm": 0.038004275411367416,
      "learning_rate": 8.596350388866558e-05,
      "loss": 10.3547,
      "step": 89
    },
    {
      "epoch": 0.199252801992528,
      "grad_norm": 0.04718531668186188,
      "learning_rate": 8.382180034472353e-05,
      "loss": 10.3557,
      "step": 90
    },
    {
      "epoch": 0.20146672201466723,
      "grad_norm": 0.04298553988337517,
      "learning_rate": 8.168769091181438e-05,
      "loss": 10.3555,
      "step": 91
    },
    {
      "epoch": 0.20368064203680641,
      "grad_norm": 0.029132699593901634,
      "learning_rate": 7.956217734936353e-05,
      "loss": 10.3531,
      "step": 92
    },
    {
      "epoch": 0.20589456205894563,
      "grad_norm": 0.03928364813327789,
      "learning_rate": 7.744625738186059e-05,
      "loss": 10.3556,
      "step": 93
    },
    {
      "epoch": 0.20810848208108482,
      "grad_norm": 0.046986378729343414,
      "learning_rate": 7.534092423052381e-05,
      "loss": 10.3545,
      "step": 94
    },
    {
      "epoch": 0.21032240210322403,
      "grad_norm": 0.03824040666222572,
      "learning_rate": 7.324716614707793e-05,
      "loss": 10.3551,
      "step": 95
    },
    {
      "epoch": 0.21253632212536322,
      "grad_norm": 0.02702680043876171,
      "learning_rate": 7.116596594986494e-05,
      "loss": 10.3572,
      "step": 96
    },
    {
      "epoch": 0.21475024214750243,
      "grad_norm": 0.026534808799624443,
      "learning_rate": 6.909830056250527e-05,
      "loss": 10.3535,
      "step": 97
    },
    {
      "epoch": 0.21696416216964162,
      "grad_norm": 0.03434290364384651,
      "learning_rate": 6.704514055532597e-05,
      "loss": 10.3522,
      "step": 98
    },
    {
      "epoch": 0.2191780821917808,
      "grad_norm": 0.037764888256788254,
      "learning_rate": 6.500744968977116e-05,
      "loss": 10.3555,
      "step": 99
    },
    {
      "epoch": 0.22139200221392002,
      "grad_norm": 0.03366897255182266,
      "learning_rate": 6.298618446600856e-05,
      "loss": 10.3527,
      "step": 100
    },
    {
      "epoch": 0.22139200221392002,
      "eval_loss": 10.353182792663574,
      "eval_runtime": 4.6374,
      "eval_samples_per_second": 328.204,
      "eval_steps_per_second": 82.159,
      "step": 100
    },
    {
      "epoch": 0.2236059222360592,
      "grad_norm": 0.03327897563576698,
      "learning_rate": 6.0982293673944544e-05,
      "loss": 10.3556,
      "step": 101
    },
    {
      "epoch": 0.22581984225819843,
      "grad_norm": 0.03691767901182175,
      "learning_rate": 5.899671794785839e-05,
      "loss": 10.3553,
      "step": 102
    },
    {
      "epoch": 0.22803376228033762,
      "grad_norm": 0.030172044411301613,
      "learning_rate": 5.703038932486484e-05,
      "loss": 10.3542,
      "step": 103
    },
    {
      "epoch": 0.23024768230247683,
      "grad_norm": 0.021300997585058212,
      "learning_rate": 5.5084230807412126e-05,
      "loss": 10.3543,
      "step": 104
    },
    {
      "epoch": 0.23246160232461602,
      "grad_norm": 0.03279775753617287,
      "learning_rate": 5.3159155930021e-05,
      "loss": 10.3539,
      "step": 105
    },
    {
      "epoch": 0.23467552234675523,
      "grad_norm": 0.02924364060163498,
      "learning_rate": 5.12560683304681e-05,
      "loss": 10.3543,
      "step": 106
    },
    {
      "epoch": 0.23688944236889442,
      "grad_norm": 0.03262259438633919,
      "learning_rate": 4.9375861325614606e-05,
      "loss": 10.355,
      "step": 107
    },
    {
      "epoch": 0.23910336239103364,
      "grad_norm": 0.034073278307914734,
      "learning_rate": 4.751941749207995e-05,
      "loss": 10.357,
      "step": 108
    },
    {
      "epoch": 0.24131728241317282,
      "grad_norm": 0.03489963710308075,
      "learning_rate": 4.5687608251956714e-05,
      "loss": 10.355,
      "step": 109
    },
    {
      "epoch": 0.243531202435312,
      "grad_norm": 0.02581014297902584,
      "learning_rate": 4.388129346376178e-05,
      "loss": 10.3537,
      "step": 110
    },
    {
      "epoch": 0.24574512245745123,
      "grad_norm": 0.023335812613368034,
      "learning_rate": 4.210132101881516e-05,
      "loss": 10.3553,
      "step": 111
    },
    {
      "epoch": 0.2479590424795904,
      "grad_norm": 0.03612133115530014,
      "learning_rate": 4.034852644323661e-05,
      "loss": 10.3534,
      "step": 112
    },
    {
      "epoch": 0.2501729625017296,
      "grad_norm": 0.02821163646876812,
      "learning_rate": 3.862373250574626e-05,
      "loss": 10.3556,
      "step": 113
    },
    {
      "epoch": 0.2523868825238688,
      "grad_norm": 0.0300295390188694,
      "learning_rate": 3.6927748831453836e-05,
      "loss": 10.3551,
      "step": 114
    },
    {
      "epoch": 0.25460080254600803,
      "grad_norm": 0.025033898651599884,
      "learning_rate": 3.5261371521817244e-05,
      "loss": 10.3525,
      "step": 115
    },
    {
      "epoch": 0.25681472256814725,
      "grad_norm": 0.02417595498263836,
      "learning_rate": 3.3625382780949574e-05,
      "loss": 10.3542,
      "step": 116
    },
    {
      "epoch": 0.2590286425902864,
      "grad_norm": 0.02323267050087452,
      "learning_rate": 3.202055054844921e-05,
      "loss": 10.3521,
      "step": 117
    },
    {
      "epoch": 0.2612425626124256,
      "grad_norm": 0.026705941185355186,
      "learning_rate": 3.0447628138926156e-05,
      "loss": 10.3536,
      "step": 118
    },
    {
      "epoch": 0.26345648263456484,
      "grad_norm": 0.033880215138196945,
      "learning_rate": 2.890735388839295e-05,
      "loss": 10.3554,
      "step": 119
    },
    {
      "epoch": 0.26567040265670405,
      "grad_norm": 0.029678767547011375,
      "learning_rate": 2.7400450807686938e-05,
      "loss": 10.353,
      "step": 120
    },
    {
      "epoch": 0.2678843226788432,
      "grad_norm": 0.02781762182712555,
      "learning_rate": 2.59276262430861e-05,
      "loss": 10.3553,
      "step": 121
    },
    {
      "epoch": 0.2700982427009824,
      "grad_norm": 0.027942579239606857,
      "learning_rate": 2.4489571544277945e-05,
      "loss": 10.3556,
      "step": 122
    },
    {
      "epoch": 0.27231216272312164,
      "grad_norm": 0.02813226915895939,
      "learning_rate": 2.308696173983711e-05,
      "loss": 10.3528,
      "step": 123
    },
    {
      "epoch": 0.2745260827452608,
      "grad_norm": 0.030037103220820427,
      "learning_rate": 2.1720455220364444e-05,
      "loss": 10.353,
      "step": 124
    },
    {
      "epoch": 0.2767400027674,
      "grad_norm": 0.030153660103678703,
      "learning_rate": 2.0390693429435627e-05,
      "loss": 10.3552,
      "step": 125
    },
    {
      "epoch": 0.27895392278953923,
      "grad_norm": 0.037454936653375626,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 10.3531,
      "step": 126
    },
    {
      "epoch": 0.28116784281167845,
      "grad_norm": 0.029572051018476486,
      "learning_rate": 1.784388327390687e-05,
      "loss": 10.3504,
      "step": 127
    },
    {
      "epoch": 0.2833817628338176,
      "grad_norm": 0.027182403951883316,
      "learning_rate": 1.6628030392087e-05,
      "loss": 10.3504,
      "step": 128
    },
    {
      "epoch": 0.2855956828559568,
      "grad_norm": 0.03518354520201683,
      "learning_rate": 1.5451312643206827e-05,
      "loss": 10.3536,
      "step": 129
    },
    {
      "epoch": 0.28780960287809604,
      "grad_norm": 0.024024929851293564,
      "learning_rate": 1.4314282383241096e-05,
      "loss": 10.3533,
      "step": 130
    },
    {
      "epoch": 0.29002352290023525,
      "grad_norm": 0.020221339538693428,
      "learning_rate": 1.3217473338699859e-05,
      "loss": 10.3521,
      "step": 131
    },
    {
      "epoch": 0.2922374429223744,
      "grad_norm": 0.02575266920030117,
      "learning_rate": 1.2161400356095375e-05,
      "loss": 10.3528,
      "step": 132
    },
    {
      "epoch": 0.29445136294451363,
      "grad_norm": 0.019320376217365265,
      "learning_rate": 1.1146559160270875e-05,
      "loss": 10.3529,
      "step": 133
    },
    {
      "epoch": 0.29666528296665284,
      "grad_norm": 0.022721335291862488,
      "learning_rate": 1.0173426121705576e-05,
      "loss": 10.3534,
      "step": 134
    },
    {
      "epoch": 0.298879202988792,
      "grad_norm": 0.030306054279208183,
      "learning_rate": 9.242458032904311e-06,
      "loss": 10.3529,
      "step": 135
    },
    {
      "epoch": 0.3010931230109312,
      "grad_norm": 0.03088550828397274,
      "learning_rate": 8.354091893977401e-06,
      "loss": 10.3542,
      "step": 136
    },
    {
      "epoch": 0.30330704303307043,
      "grad_norm": 0.02875097282230854,
      "learning_rate": 7.508744707511117e-06,
      "loss": 10.3556,
      "step": 137
    },
    {
      "epoch": 0.30552096305520965,
      "grad_norm": 0.022224275395274162,
      "learning_rate": 6.70681328282492e-06,
      "loss": 10.3536,
      "step": 138
    },
    {
      "epoch": 0.3077348830773488,
      "grad_norm": 0.028994860127568245,
      "learning_rate": 5.948674049707603e-06,
      "loss": 10.3531,
      "step": 139
    },
    {
      "epoch": 0.309948803099488,
      "grad_norm": 0.03301481530070305,
      "learning_rate": 5.2346828817197655e-06,
      "loss": 10.3539,
      "step": 140
    },
    {
      "epoch": 0.31216272312162724,
      "grad_norm": 0.031127754598855972,
      "learning_rate": 4.565174929145188e-06,
      "loss": 10.3541,
      "step": 141
    },
    {
      "epoch": 0.31437664314376645,
      "grad_norm": 0.03324393928050995,
      "learning_rate": 3.940464461670135e-06,
      "loss": 10.3558,
      "step": 142
    },
    {
      "epoch": 0.3165905631659056,
      "grad_norm": 0.025115065276622772,
      "learning_rate": 3.360844720863765e-06,
      "loss": 10.3528,
      "step": 143
    },
    {
      "epoch": 0.31880448318804483,
      "grad_norm": 0.02497878670692444,
      "learning_rate": 2.826587782529444e-06,
      "loss": 10.353,
      "step": 144
    },
    {
      "epoch": 0.32101840321018404,
      "grad_norm": 0.026006096974015236,
      "learning_rate": 2.3379444289913342e-06,
      "loss": 10.3548,
      "step": 145
    },
    {
      "epoch": 0.32323232323232326,
      "grad_norm": 0.028647800907492638,
      "learning_rate": 1.8951440313760837e-06,
      "loss": 10.355,
      "step": 146
    },
    {
      "epoch": 0.3254462432544624,
      "grad_norm": 0.03259943798184395,
      "learning_rate": 1.4983944419451613e-06,
      "loss": 10.3541,
      "step": 147
    },
    {
      "epoch": 0.32766016327660163,
      "grad_norm": 0.033153582364320755,
      "learning_rate": 1.1478818965281911e-06,
      "loss": 10.3529,
      "step": 148
    },
    {
      "epoch": 0.32987408329874085,
      "grad_norm": 0.026517199352383614,
      "learning_rate": 8.437709271030603e-07,
      "loss": 10.3537,
      "step": 149
    },
    {
      "epoch": 0.33208800332088,
      "grad_norm": 0.02658323012292385,
      "learning_rate": 5.862042845640403e-07,
      "loss": 10.3527,
      "step": 150
    },
    {
      "epoch": 0.3343019233430192,
      "grad_norm": 0.024668825790286064,
      "learning_rate": 3.7530287171387843e-07,
      "loss": 10.3539,
      "step": 151
    },
    {
      "epoch": 0.33651584336515844,
      "grad_norm": 0.030534988269209862,
      "learning_rate": 2.1116568651156076e-07,
      "loss": 10.3545,
      "step": 152
    },
    {
      "epoch": 0.33872976338729766,
      "grad_norm": 0.024195190519094467,
      "learning_rate": 9.386977560232879e-08,
      "loss": 10.3539,
      "step": 153
    },
    {
      "epoch": 0.3409436834094368,
      "grad_norm": 0.027664266526699066,
      "learning_rate": 2.347019815158724e-08,
      "loss": 10.3528,
      "step": 154
    },
    {
      "epoch": 0.34315760343157603,
      "grad_norm": 0.03868336230516434,
      "learning_rate": 0.0,
      "loss": 10.3539,
      "step": 155
    }
  ],
  "logging_steps": 1,
  "max_steps": 155,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 64855033774080.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}