{
  "best_metric": 0.7306569218635559,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.13110455588331696,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006555227794165847,
      "grad_norm": 0.22842250764369965,
      "learning_rate": 5e-06,
      "loss": 0.8465,
      "step": 1
    },
    {
      "epoch": 0.0006555227794165847,
      "eval_loss": 1.0142732858657837,
      "eval_runtime": 197.9179,
      "eval_samples_per_second": 12.985,
      "eval_steps_per_second": 6.493,
      "step": 1
    },
    {
      "epoch": 0.0013110455588331695,
      "grad_norm": 0.27400991320610046,
      "learning_rate": 1e-05,
      "loss": 0.9051,
      "step": 2
    },
    {
      "epoch": 0.0019665683382497543,
      "grad_norm": 0.33582624793052673,
      "learning_rate": 1.5e-05,
      "loss": 0.9245,
      "step": 3
    },
    {
      "epoch": 0.002622091117666339,
      "grad_norm": 0.32972264289855957,
      "learning_rate": 2e-05,
      "loss": 0.9183,
      "step": 4
    },
    {
      "epoch": 0.0032776138970829235,
      "grad_norm": 0.2700183093547821,
      "learning_rate": 2.5e-05,
      "loss": 0.8971,
      "step": 5
    },
    {
      "epoch": 0.003933136676499509,
      "grad_norm": 0.28573429584503174,
      "learning_rate": 3e-05,
      "loss": 0.9398,
      "step": 6
    },
    {
      "epoch": 0.004588659455916093,
      "grad_norm": 0.2986675798892975,
      "learning_rate": 3.5e-05,
      "loss": 0.9268,
      "step": 7
    },
    {
      "epoch": 0.005244182235332678,
      "grad_norm": 0.26939091086387634,
      "learning_rate": 4e-05,
      "loss": 0.9701,
      "step": 8
    },
    {
      "epoch": 0.0058997050147492625,
      "grad_norm": 0.27459952235221863,
      "learning_rate": 4.5e-05,
      "loss": 0.9129,
      "step": 9
    },
    {
      "epoch": 0.006555227794165847,
      "grad_norm": 0.26461517810821533,
      "learning_rate": 5e-05,
      "loss": 0.9423,
      "step": 10
    },
    {
      "epoch": 0.007210750573582432,
      "grad_norm": 0.24099130928516388,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.9111,
      "step": 11
    },
    {
      "epoch": 0.007866273352999017,
      "grad_norm": 0.21931226551532745,
      "learning_rate": 6e-05,
      "loss": 0.8694,
      "step": 12
    },
    {
      "epoch": 0.008521796132415601,
      "grad_norm": 0.24747370183467865,
      "learning_rate": 6.500000000000001e-05,
      "loss": 0.8581,
      "step": 13
    },
    {
      "epoch": 0.009177318911832186,
      "grad_norm": 0.24438594281673431,
      "learning_rate": 7e-05,
      "loss": 0.8736,
      "step": 14
    },
    {
      "epoch": 0.00983284169124877,
      "grad_norm": 0.2534273862838745,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.806,
      "step": 15
    },
    {
      "epoch": 0.010488364470665356,
      "grad_norm": 0.26051220297813416,
      "learning_rate": 8e-05,
      "loss": 0.862,
      "step": 16
    },
    {
      "epoch": 0.011143887250081941,
      "grad_norm": 0.2706455588340759,
      "learning_rate": 8.5e-05,
      "loss": 0.862,
      "step": 17
    },
    {
      "epoch": 0.011799410029498525,
      "grad_norm": 0.24733135104179382,
      "learning_rate": 9e-05,
      "loss": 0.835,
      "step": 18
    },
    {
      "epoch": 0.01245493280891511,
      "grad_norm": 0.27589109539985657,
      "learning_rate": 9.5e-05,
      "loss": 0.8309,
      "step": 19
    },
    {
      "epoch": 0.013110455588331694,
      "grad_norm": 0.2654259502887726,
      "learning_rate": 0.0001,
      "loss": 0.8368,
      "step": 20
    },
    {
      "epoch": 0.01376597836774828,
      "grad_norm": 0.2543870806694031,
      "learning_rate": 9.999238475781957e-05,
      "loss": 0.8086,
      "step": 21
    },
    {
      "epoch": 0.014421501147164863,
      "grad_norm": 0.24969661235809326,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.8061,
      "step": 22
    },
    {
      "epoch": 0.015077023926581449,
      "grad_norm": 0.2561767101287842,
      "learning_rate": 9.99314767377287e-05,
      "loss": 0.855,
      "step": 23
    },
    {
      "epoch": 0.015732546705998034,
      "grad_norm": 0.22675134241580963,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.8125,
      "step": 24
    },
    {
      "epoch": 0.01638806948541462,
      "grad_norm": 0.2459305375814438,
      "learning_rate": 9.980973490458728e-05,
      "loss": 0.8065,
      "step": 25
    },
    {
      "epoch": 0.017043592264831202,
      "grad_norm": 0.2415834218263626,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.7935,
      "step": 26
    },
    {
      "epoch": 0.017699115044247787,
      "grad_norm": 0.23889082670211792,
      "learning_rate": 9.962730758206611e-05,
      "loss": 0.8356,
      "step": 27
    },
    {
      "epoch": 0.018354637823664373,
      "grad_norm": 0.24053475260734558,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.8135,
      "step": 28
    },
    {
      "epoch": 0.01901016060308096,
      "grad_norm": 0.22948268055915833,
      "learning_rate": 9.938441702975689e-05,
      "loss": 0.816,
      "step": 29
    },
    {
      "epoch": 0.01966568338249754,
      "grad_norm": 0.2485935240983963,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.7616,
      "step": 30
    },
    {
      "epoch": 0.020321206161914126,
      "grad_norm": 0.2558572292327881,
      "learning_rate": 9.908135917238321e-05,
      "loss": 0.7875,
      "step": 31
    },
    {
      "epoch": 0.02097672894133071,
      "grad_norm": 0.2514430582523346,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.7731,
      "step": 32
    },
    {
      "epoch": 0.021632251720747297,
      "grad_norm": 0.25761303305625916,
      "learning_rate": 9.871850323926177e-05,
      "loss": 0.8322,
      "step": 33
    },
    {
      "epoch": 0.022287774500163882,
      "grad_norm": 0.26310867071151733,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.7961,
      "step": 34
    },
    {
      "epoch": 0.022943297279580464,
      "grad_norm": 0.26123255491256714,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.7747,
      "step": 35
    },
    {
      "epoch": 0.02359882005899705,
      "grad_norm": 0.256563276052475,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.7796,
      "step": 36
    },
    {
      "epoch": 0.024254342838413635,
      "grad_norm": 0.272085964679718,
      "learning_rate": 9.781523779815179e-05,
      "loss": 0.76,
      "step": 37
    },
    {
      "epoch": 0.02490986561783022,
      "grad_norm": 0.2578217387199402,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.7897,
      "step": 38
    },
    {
      "epoch": 0.025565388397246803,
      "grad_norm": 0.26427558064460754,
      "learning_rate": 9.727592877996585e-05,
      "loss": 0.7607,
      "step": 39
    },
    {
      "epoch": 0.02622091117666339,
      "grad_norm": 0.2925783097743988,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.8141,
      "step": 40
    },
    {
      "epoch": 0.026876433956079974,
      "grad_norm": 0.26159489154815674,
      "learning_rate": 9.667902132486009e-05,
      "loss": 0.7314,
      "step": 41
    },
    {
      "epoch": 0.02753195673549656,
      "grad_norm": 0.29255083203315735,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.7743,
      "step": 42
    },
    {
      "epoch": 0.028187479514913145,
      "grad_norm": 0.2994762659072876,
      "learning_rate": 9.602524267262203e-05,
      "loss": 0.7554,
      "step": 43
    },
    {
      "epoch": 0.028843002294329727,
      "grad_norm": 0.3325808644294739,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.7631,
      "step": 44
    },
    {
      "epoch": 0.029498525073746312,
      "grad_norm": 0.2953774034976959,
      "learning_rate": 9.53153893518325e-05,
      "loss": 0.7917,
      "step": 45
    },
    {
      "epoch": 0.030154047853162898,
      "grad_norm": 0.42029112577438354,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.805,
      "step": 46
    },
    {
      "epoch": 0.030809570632579483,
      "grad_norm": 0.3243456184864044,
      "learning_rate": 9.45503262094184e-05,
      "loss": 0.735,
      "step": 47
    },
    {
      "epoch": 0.03146509341199607,
      "grad_norm": 0.3843507170677185,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.7965,
      "step": 48
    },
    {
      "epoch": 0.032120616191412654,
      "grad_norm": 0.6134610176086426,
      "learning_rate": 9.373098535696979e-05,
      "loss": 0.7454,
      "step": 49
    },
    {
      "epoch": 0.03277613897082924,
      "grad_norm": 1.1139791011810303,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.7828,
      "step": 50
    },
    {
      "epoch": 0.03277613897082924,
      "eval_loss": 0.8404982686042786,
      "eval_runtime": 199.8195,
      "eval_samples_per_second": 12.862,
      "eval_steps_per_second": 6.431,
      "step": 50
    },
    {
      "epoch": 0.03343166175024582,
      "grad_norm": 0.4332141876220703,
      "learning_rate": 9.285836503510562e-05,
      "loss": 0.8933,
      "step": 51
    },
    {
      "epoch": 0.034087184529662404,
      "grad_norm": 0.44742506742477417,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.862,
      "step": 52
    },
    {
      "epoch": 0.03474270730907899,
      "grad_norm": 0.40047910809516907,
      "learning_rate": 9.193352839727121e-05,
      "loss": 0.8256,
      "step": 53
    },
    {
      "epoch": 0.035398230088495575,
      "grad_norm": 0.23541966080665588,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.7841,
      "step": 54
    },
    {
      "epoch": 0.03605375286791216,
      "grad_norm": 0.19308950006961823,
      "learning_rate": 9.09576022144496e-05,
      "loss": 0.7482,
      "step": 55
    },
    {
      "epoch": 0.036709275647328746,
      "grad_norm": 0.18649353086948395,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.7752,
      "step": 56
    },
    {
      "epoch": 0.03736479842674533,
      "grad_norm": 0.17265942692756653,
      "learning_rate": 8.993177550236464e-05,
      "loss": 0.7913,
      "step": 57
    },
    {
      "epoch": 0.03802032120616192,
      "grad_norm": 0.19148337841033936,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.8175,
      "step": 58
    },
    {
      "epoch": 0.0386758439855785,
      "grad_norm": 0.19986121356487274,
      "learning_rate": 8.885729807284856e-05,
      "loss": 0.7991,
      "step": 59
    },
    {
      "epoch": 0.03933136676499508,
      "grad_norm": 0.1891452968120575,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.7911,
      "step": 60
    },
    {
      "epoch": 0.039986889544411666,
      "grad_norm": 0.20013684034347534,
      "learning_rate": 8.773547901113862e-05,
      "loss": 0.8004,
      "step": 61
    },
    {
      "epoch": 0.04064241232382825,
      "grad_norm": 0.19894744455814362,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.8009,
      "step": 62
    },
    {
      "epoch": 0.04129793510324484,
      "grad_norm": 0.19562208652496338,
      "learning_rate": 8.656768508095853e-05,
      "loss": 0.8368,
      "step": 63
    },
    {
      "epoch": 0.04195345788266142,
      "grad_norm": 0.20086877048015594,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.7889,
      "step": 64
    },
    {
      "epoch": 0.04260898066207801,
      "grad_norm": 0.1950705349445343,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.7739,
      "step": 65
    },
    {
      "epoch": 0.043264503441494594,
      "grad_norm": 0.19534240663051605,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.7864,
      "step": 66
    },
    {
      "epoch": 0.04392002622091118,
      "grad_norm": 0.2013138234615326,
      "learning_rate": 8.409991800312493e-05,
      "loss": 0.812,
      "step": 67
    },
    {
      "epoch": 0.044575549000327765,
      "grad_norm": 0.2195879966020584,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.8219,
      "step": 68
    },
    {
      "epoch": 0.04523107177974434,
      "grad_norm": 0.2001798003911972,
      "learning_rate": 8.280295144952536e-05,
      "loss": 0.7529,
      "step": 69
    },
    {
      "epoch": 0.04588659455916093,
      "grad_norm": 0.20293432474136353,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.7348,
      "step": 70
    },
    {
      "epoch": 0.046542117338577514,
      "grad_norm": 0.21200138330459595,
      "learning_rate": 8.146601955249188e-05,
      "loss": 0.7952,
      "step": 71
    },
    {
      "epoch": 0.0471976401179941,
      "grad_norm": 0.20770512521266937,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.7719,
      "step": 72
    },
    {
      "epoch": 0.047853162897410685,
      "grad_norm": 0.21342378854751587,
      "learning_rate": 8.009075115760243e-05,
      "loss": 0.732,
      "step": 73
    },
    {
      "epoch": 0.04850868567682727,
      "grad_norm": 0.21674242615699768,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.7664,
      "step": 74
    },
    {
      "epoch": 0.049164208456243856,
      "grad_norm": 0.21934330463409424,
      "learning_rate": 7.86788218175523e-05,
      "loss": 0.7895,
      "step": 75
    },
    {
      "epoch": 0.04981973123566044,
      "grad_norm": 0.21142475306987762,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.7869,
      "step": 76
    },
    {
      "epoch": 0.05047525401507703,
      "grad_norm": 0.22337253391742706,
      "learning_rate": 7.723195175075136e-05,
      "loss": 0.776,
      "step": 77
    },
    {
      "epoch": 0.051130776794493606,
      "grad_norm": 0.2339678853750229,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.7705,
      "step": 78
    },
    {
      "epoch": 0.05178629957391019,
      "grad_norm": 0.22793947160243988,
      "learning_rate": 7.575190374550272e-05,
      "loss": 0.7324,
      "step": 79
    },
    {
      "epoch": 0.05244182235332678,
      "grad_norm": 0.22728127241134644,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.7373,
      "step": 80
    },
    {
      "epoch": 0.05309734513274336,
      "grad_norm": 0.22513455152511597,
      "learning_rate": 7.424048101231686e-05,
      "loss": 0.7097,
      "step": 81
    },
    {
      "epoch": 0.05375286791215995,
      "grad_norm": 0.22638094425201416,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.7263,
      "step": 82
    },
    {
      "epoch": 0.05440839069157653,
      "grad_norm": 0.24754472076892853,
      "learning_rate": 7.269952498697734e-05,
      "loss": 0.7598,
      "step": 83
    },
    {
      "epoch": 0.05506391347099312,
      "grad_norm": 0.24551862478256226,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.7759,
      "step": 84
    },
    {
      "epoch": 0.055719436250409704,
      "grad_norm": 0.25020939111709595,
      "learning_rate": 7.113091308703498e-05,
      "loss": 0.7318,
      "step": 85
    },
    {
      "epoch": 0.05637495902982629,
      "grad_norm": 0.25986289978027344,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.7429,
      "step": 86
    },
    {
      "epoch": 0.05703048180924287,
      "grad_norm": 0.283760130405426,
      "learning_rate": 6.953655642446368e-05,
      "loss": 0.7437,
      "step": 87
    },
    {
      "epoch": 0.057686004588659454,
      "grad_norm": 0.2627193331718445,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.7394,
      "step": 88
    },
    {
      "epoch": 0.05834152736807604,
      "grad_norm": 0.26023104786872864,
      "learning_rate": 6.7918397477265e-05,
      "loss": 0.7423,
      "step": 89
    },
    {
      "epoch": 0.058997050147492625,
      "grad_norm": 0.2716743052005768,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.7866,
      "step": 90
    },
    {
      "epoch": 0.05965257292690921,
      "grad_norm": 0.26850956678390503,
      "learning_rate": 6.627840772285784e-05,
      "loss": 0.739,
      "step": 91
    },
    {
      "epoch": 0.060308095706325796,
      "grad_norm": 0.2863216698169708,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.712,
      "step": 92
    },
    {
      "epoch": 0.06096361848574238,
      "grad_norm": 0.2597072422504425,
      "learning_rate": 6.461858523613684e-05,
      "loss": 0.7251,
      "step": 93
    },
    {
      "epoch": 0.061619141265158967,
      "grad_norm": 0.27403563261032104,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.7818,
      "step": 94
    },
    {
      "epoch": 0.06227466404457555,
      "grad_norm": 0.28989920020103455,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.7917,
      "step": 95
    },
    {
      "epoch": 0.06293018682399214,
      "grad_norm": 0.3043973445892334,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.7424,
      "step": 96
    },
    {
      "epoch": 0.06358570960340872,
      "grad_norm": 0.35575154423713684,
      "learning_rate": 6.124755271719325e-05,
      "loss": 0.7037,
      "step": 97
    },
    {
      "epoch": 0.06424123238282531,
      "grad_norm": 0.3839647173881531,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.7422,
      "step": 98
    },
    {
      "epoch": 0.06489675516224189,
      "grad_norm": 0.3971020579338074,
      "learning_rate": 5.9540449768827246e-05,
      "loss": 0.7345,
      "step": 99
    },
    {
      "epoch": 0.06555227794165848,
      "grad_norm": 0.8090072274208069,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.7107,
      "step": 100
    },
    {
      "epoch": 0.06555227794165848,
      "eval_loss": 0.7711856961250305,
      "eval_runtime": 199.7476,
      "eval_samples_per_second": 12.866,
      "eval_steps_per_second": 6.433,
      "step": 100
    },
    {
      "epoch": 0.06620780072107506,
      "grad_norm": 0.2854394018650055,
      "learning_rate": 5.782172325201155e-05,
      "loss": 0.806,
      "step": 101
    },
    {
      "epoch": 0.06686332350049164,
      "grad_norm": 0.2501490116119385,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.766,
      "step": 102
    },
    {
      "epoch": 0.06751884627990823,
      "grad_norm": 0.2460934966802597,
      "learning_rate": 5.6093467170257374e-05,
      "loss": 0.7838,
      "step": 103
    },
    {
      "epoch": 0.06817436905932481,
      "grad_norm": 0.21523185074329376,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.723,
      "step": 104
    },
    {
      "epoch": 0.0688298918387414,
      "grad_norm": 0.18155883252620697,
      "learning_rate": 5.435778713738292e-05,
      "loss": 0.7721,
      "step": 105
    },
    {
      "epoch": 0.06948541461815798,
      "grad_norm": 0.17506293952465057,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.7722,
      "step": 106
    },
    {
      "epoch": 0.07014093739757457,
      "grad_norm": 0.1855786293745041,
      "learning_rate": 5.26167978121472e-05,
      "loss": 0.7588,
      "step": 107
    },
    {
      "epoch": 0.07079646017699115,
      "grad_norm": 0.18874594569206238,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.7552,
      "step": 108
    },
    {
      "epoch": 0.07145198295640774,
      "grad_norm": 0.18815328180789948,
      "learning_rate": 5.0872620321864185e-05,
      "loss": 0.7624,
      "step": 109
    },
    {
      "epoch": 0.07210750573582432,
      "grad_norm": 0.19321073591709137,
      "learning_rate": 5e-05,
      "loss": 0.7655,
      "step": 110
    },
    {
      "epoch": 0.0727630285152409,
      "grad_norm": 0.19126199185848236,
      "learning_rate": 4.912737967813583e-05,
      "loss": 0.7148,
      "step": 111
    },
    {
      "epoch": 0.07341855129465749,
      "grad_norm": 0.1977165937423706,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.7435,
      "step": 112
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 0.20759083330631256,
      "learning_rate": 4.738320218785281e-05,
      "loss": 0.7297,
      "step": 113
    },
    {
      "epoch": 0.07472959685349066,
      "grad_norm": 0.21419835090637207,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.7835,
      "step": 114
    },
    {
      "epoch": 0.07538511963290724,
      "grad_norm": 0.2073257565498352,
      "learning_rate": 4.564221286261709e-05,
      "loss": 0.7402,
      "step": 115
    },
    {
      "epoch": 0.07604064241232383,
      "grad_norm": 0.20203441381454468,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.767,
      "step": 116
    },
    {
      "epoch": 0.07669616519174041,
      "grad_norm": 0.20654654502868652,
      "learning_rate": 4.390653282974264e-05,
      "loss": 0.7574,
      "step": 117
    },
    {
      "epoch": 0.077351687971157,
      "grad_norm": 0.2055203914642334,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.7623,
      "step": 118
    },
    {
      "epoch": 0.07800721075057358,
      "grad_norm": 0.20675183832645416,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.753,
      "step": 119
    },
    {
      "epoch": 0.07866273352999016,
      "grad_norm": 0.21456296741962433,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.7794,
      "step": 120
    },
    {
      "epoch": 0.07931825630940675,
      "grad_norm": 0.21291404962539673,
      "learning_rate": 4.045955023117276e-05,
      "loss": 0.7853,
      "step": 121
    },
    {
      "epoch": 0.07997377908882333,
      "grad_norm": 0.21847602725028992,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.777,
      "step": 122
    },
    {
      "epoch": 0.08062930186823992,
      "grad_norm": 0.21636834740638733,
      "learning_rate": 3.875244728280676e-05,
      "loss": 0.7493,
      "step": 123
    },
    {
      "epoch": 0.0812848246476565,
      "grad_norm": 0.21808314323425293,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.7649,
      "step": 124
    },
    {
      "epoch": 0.0819403474270731,
      "grad_norm": 0.22126802802085876,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.7338,
      "step": 125
    },
    {
      "epoch": 0.08259587020648967,
      "grad_norm": 0.22322940826416016,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.7689,
      "step": 126
    },
    {
      "epoch": 0.08325139298590627,
      "grad_norm": 0.2250346690416336,
      "learning_rate": 3.5381414763863166e-05,
      "loss": 0.7212,
      "step": 127
    },
    {
      "epoch": 0.08390691576532285,
      "grad_norm": 0.2389887422323227,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.7524,
      "step": 128
    },
    {
      "epoch": 0.08456243854473942,
      "grad_norm": 0.2435750961303711,
      "learning_rate": 3.372159227714218e-05,
      "loss": 0.7743,
      "step": 129
    },
    {
      "epoch": 0.08521796132415602,
      "grad_norm": 0.22282806038856506,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.7025,
      "step": 130
    },
    {
      "epoch": 0.0858734841035726,
      "grad_norm": 0.23607531189918518,
      "learning_rate": 3.2081602522734986e-05,
      "loss": 0.7981,
      "step": 131
    },
    {
      "epoch": 0.08652900688298919,
      "grad_norm": 0.24423764646053314,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.7636,
      "step": 132
    },
    {
      "epoch": 0.08718452966240577,
      "grad_norm": 0.2365090698003769,
      "learning_rate": 3.046344357553632e-05,
      "loss": 0.7201,
      "step": 133
    },
    {
      "epoch": 0.08784005244182236,
      "grad_norm": 0.237791508436203,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.7025,
      "step": 134
    },
    {
      "epoch": 0.08849557522123894,
      "grad_norm": 0.2471911460161209,
      "learning_rate": 2.886908691296504e-05,
      "loss": 0.745,
      "step": 135
    },
    {
      "epoch": 0.08915109800065553,
      "grad_norm": 0.24586082994937897,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.7251,
      "step": 136
    },
    {
      "epoch": 0.08980662078007211,
      "grad_norm": 0.2511478662490845,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 0.7601,
      "step": 137
    },
    {
      "epoch": 0.09046214355948869,
      "grad_norm": 0.24248506128787994,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.7078,
      "step": 138
    },
    {
      "epoch": 0.09111766633890528,
      "grad_norm": 0.26230138540267944,
      "learning_rate": 2.575951898768315e-05,
      "loss": 0.7117,
      "step": 139
    },
    {
      "epoch": 0.09177318911832186,
      "grad_norm": 0.26975852251052856,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.7202,
      "step": 140
    },
    {
      "epoch": 0.09242871189773845,
      "grad_norm": 0.27416229248046875,
      "learning_rate": 2.4248096254497288e-05,
      "loss": 0.7577,
      "step": 141
    },
    {
      "epoch": 0.09308423467715503,
      "grad_norm": 0.2665165364742279,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.7151,
      "step": 142
    },
    {
      "epoch": 0.09373975745657162,
      "grad_norm": 0.2814359962940216,
      "learning_rate": 2.2768048249248648e-05,
      "loss": 0.7466,
      "step": 143
    },
    {
      "epoch": 0.0943952802359882,
      "grad_norm": 0.3412998616695404,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.7975,
      "step": 144
    },
    {
      "epoch": 0.09505080301540479,
      "grad_norm": 0.30855631828308105,
      "learning_rate": 2.132117818244771e-05,
      "loss": 0.7205,
      "step": 145
    },
    {
      "epoch": 0.09570632579482137,
      "grad_norm": 0.27196890115737915,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.7026,
      "step": 146
    },
    {
      "epoch": 0.09636184857423795,
      "grad_norm": 0.31602856516838074,
      "learning_rate": 1.9909248842397584e-05,
      "loss": 0.7064,
      "step": 147
    },
    {
      "epoch": 0.09701737135365454,
      "grad_norm": 0.3314160704612732,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.7897,
      "step": 148
    },
    {
      "epoch": 0.09767289413307112,
      "grad_norm": 0.39607930183410645,
      "learning_rate": 1.8533980447508137e-05,
      "loss": 0.704,
      "step": 149
    },
    {
      "epoch": 0.09832841691248771,
      "grad_norm": 1.1761752367019653,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.7426,
      "step": 150
    },
    {
      "epoch": 0.09832841691248771,
      "eval_loss": 0.7386060357093811,
      "eval_runtime": 498.5167,
      "eval_samples_per_second": 5.155,
      "eval_steps_per_second": 2.578,
      "step": 150
    },
    {
      "epoch": 0.09898393969190429,
      "grad_norm": 0.15368381142616272,
      "learning_rate": 1.7197048550474643e-05,
      "loss": 0.7585,
      "step": 151
    },
    {
      "epoch": 0.09963946247132088,
      "grad_norm": 0.160555899143219,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.7376,
      "step": 152
    },
    {
      "epoch": 0.10029498525073746,
      "grad_norm": 0.18000783026218414,
      "learning_rate": 1.5900081996875083e-05,
      "loss": 0.7138,
      "step": 153
    },
    {
      "epoch": 0.10095050803015405,
      "grad_norm": 0.17999839782714844,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.7574,
      "step": 154
    },
    {
      "epoch": 0.10160603080957063,
      "grad_norm": 0.18467019498348236,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.7512,
      "step": 155
    },
    {
      "epoch": 0.10226155358898721,
      "grad_norm": 0.20621947944164276,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.7504,
      "step": 156
    },
    {
      "epoch": 0.1029170763684038,
      "grad_norm": 0.20901134610176086,
      "learning_rate": 1.3432314919041478e-05,
      "loss": 0.7748,
      "step": 157
    },
    {
      "epoch": 0.10357259914782038,
      "grad_norm": 0.20796838402748108,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.7558,
      "step": 158
    },
    {
      "epoch": 0.10422812192723697,
      "grad_norm": 0.20482483506202698,
      "learning_rate": 1.22645209888614e-05,
      "loss": 0.7357,
      "step": 159
    },
    {
      "epoch": 0.10488364470665355,
      "grad_norm": 0.21744480729103088,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.7119,
      "step": 160
    },
    {
      "epoch": 0.10553916748607015,
      "grad_norm": 0.21816715598106384,
      "learning_rate": 1.1142701927151456e-05,
      "loss": 0.7637,
      "step": 161
    },
    {
      "epoch": 0.10619469026548672,
      "grad_norm": 0.21218472719192505,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.7927,
      "step": 162
    },
    {
      "epoch": 0.10685021304490332,
      "grad_norm": 0.21583938598632812,
      "learning_rate": 1.006822449763537e-05,
      "loss": 0.7786,
      "step": 163
    },
    {
      "epoch": 0.1075057358243199,
      "grad_norm": 0.21331270039081573,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.7391,
      "step": 164
    },
    {
      "epoch": 0.10816125860373647,
      "grad_norm": 0.2049589604139328,
      "learning_rate": 9.042397785550405e-06,
      "loss": 0.7331,
      "step": 165
    },
    {
      "epoch": 0.10881678138315307,
      "grad_norm": 0.23487131297588348,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.7442,
      "step": 166
    },
    {
      "epoch": 0.10947230416256964,
      "grad_norm": 0.2134774923324585,
      "learning_rate": 8.066471602728803e-06,
      "loss": 0.7466,
      "step": 167
    },
    {
      "epoch": 0.11012782694198624,
      "grad_norm": 0.22224828600883484,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.7183,
      "step": 168
    },
    {
      "epoch": 0.11078334972140282,
      "grad_norm": 0.2176111936569214,
      "learning_rate": 7.1416349648943894e-06,
      "loss": 0.6985,
      "step": 169
    },
    {
      "epoch": 0.11143887250081941,
      "grad_norm": 0.20548199117183685,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.7697,
      "step": 170
    },
    {
      "epoch": 0.11209439528023599,
      "grad_norm": 0.19867375493049622,
      "learning_rate": 6.269014643030213e-06,
      "loss": 0.713,
      "step": 171
    },
    {
      "epoch": 0.11274991805965258,
      "grad_norm": 0.20385012030601501,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.7301,
      "step": 172
    },
    {
      "epoch": 0.11340544083906916,
      "grad_norm": 0.22076192498207092,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.7329,
      "step": 173
    },
    {
      "epoch": 0.11406096361848574,
      "grad_norm": 0.2200993299484253,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.6823,
      "step": 174
    },
    {
      "epoch": 0.11471648639790233,
      "grad_norm": 0.2180580049753189,
      "learning_rate": 4.684610648167503e-06,
      "loss": 0.7202,
      "step": 175
    },
    {
      "epoch": 0.11537200917731891,
      "grad_norm": 0.22774535417556763,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.7674,
      "step": 176
    },
    {
      "epoch": 0.1160275319567355,
      "grad_norm": 0.2176027148962021,
      "learning_rate": 3.974757327377981e-06,
      "loss": 0.707,
      "step": 177
    },
    {
      "epoch": 0.11668305473615208,
      "grad_norm": 0.22468215227127075,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.728,
      "step": 178
    },
    {
      "epoch": 0.11733857751556867,
      "grad_norm": 0.22399358451366425,
      "learning_rate": 3.3209786751399187e-06,
      "loss": 0.7462,
      "step": 179
    },
    {
      "epoch": 0.11799410029498525,
      "grad_norm": 0.21534043550491333,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.6924,
      "step": 180
    },
    {
      "epoch": 0.11864962307440184,
      "grad_norm": 0.22705651819705963,
      "learning_rate": 2.724071220034158e-06,
      "loss": 0.7357,
      "step": 181
    },
    {
      "epoch": 0.11930514585381842,
      "grad_norm": 0.23129010200500488,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.7104,
      "step": 182
    },
    {
      "epoch": 0.119960668633235,
      "grad_norm": 0.22510115802288055,
      "learning_rate": 2.1847622018482283e-06,
      "loss": 0.7323,
      "step": 183
    },
    {
      "epoch": 0.12061619141265159,
      "grad_norm": 0.23414209485054016,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.6943,
      "step": 184
    },
    {
      "epoch": 0.12127171419206817,
      "grad_norm": 0.2462332546710968,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.7141,
      "step": 185
    },
    {
      "epoch": 0.12192723697148476,
      "grad_norm": 0.24228835105895996,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.7375,
      "step": 186
    },
    {
      "epoch": 0.12258275975090134,
      "grad_norm": 0.23694011569023132,
      "learning_rate": 1.2814967607382432e-06,
      "loss": 0.6983,
      "step": 187
    },
    {
      "epoch": 0.12323828253031793,
      "grad_norm": 0.2774541974067688,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.7515,
      "step": 188
    },
    {
      "epoch": 0.12389380530973451,
      "grad_norm": 0.26081380248069763,
      "learning_rate": 9.186408276168013e-07,
      "loss": 0.6847,
      "step": 189
    },
    {
      "epoch": 0.1245493280891511,
      "grad_norm": 0.26271530985832214,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.7219,
      "step": 190
    },
    {
      "epoch": 0.1252048508685677,
      "grad_norm": 0.3054777979850769,
      "learning_rate": 6.15582970243117e-07,
      "loss": 0.764,
      "step": 191
    },
    {
      "epoch": 0.12586037364798427,
      "grad_norm": 0.27839982509613037,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.7349,
      "step": 192
    },
    {
      "epoch": 0.12651589642740085,
      "grad_norm": 0.27662938833236694,
      "learning_rate": 3.7269241793390085e-07,
      "loss": 0.7232,
      "step": 193
    },
    {
      "epoch": 0.12717141920681743,
      "grad_norm": 0.2891337275505066,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.7421,
      "step": 194
    },
    {
      "epoch": 0.127826941986234,
      "grad_norm": 0.29528573155403137,
      "learning_rate": 1.9026509541272275e-07,
      "loss": 0.7403,
      "step": 195
    },
    {
      "epoch": 0.12848246476565062,
      "grad_norm": 0.3769616484642029,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.7436,
      "step": 196
    },
    {
      "epoch": 0.1291379875450672,
      "grad_norm": 0.31551793217658997,
      "learning_rate": 6.852326227130834e-08,
      "loss": 0.6736,
      "step": 197
    },
    {
      "epoch": 0.12979351032448377,
      "grad_norm": 0.3691118657588959,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.6901,
      "step": 198
    },
    {
      "epoch": 0.13044903310390035,
      "grad_norm": 0.40889638662338257,
      "learning_rate": 7.615242180436522e-09,
      "loss": 0.7847,
      "step": 199
    },
    {
      "epoch": 0.13110455588331696,
      "grad_norm": 0.5048396587371826,
      "learning_rate": 0.0,
      "loss": 0.6559,
      "step": 200
    },
    {
      "epoch": 0.13110455588331696,
      "eval_loss": 0.7306569218635559,
      "eval_runtime": 497.501,
      "eval_samples_per_second": 5.166,
      "eval_steps_per_second": 2.583,
      "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": 2.6709961332699955e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}