{
  "best_metric": 1.319568157196045,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.2259248799774075,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011296243998870376,
      "grad_norm": 0.7753930687904358,
      "learning_rate": 5e-06,
      "loss": 1.3228,
      "step": 1
    },
    {
      "epoch": 0.0011296243998870376,
      "eval_loss": 1.5105721950531006,
      "eval_runtime": 40.362,
      "eval_samples_per_second": 36.941,
      "eval_steps_per_second": 18.483,
      "step": 1
    },
    {
      "epoch": 0.0022592487997740753,
      "grad_norm": 0.8180758357048035,
      "learning_rate": 1e-05,
      "loss": 1.2762,
      "step": 2
    },
    {
      "epoch": 0.003388873199661113,
      "grad_norm": 0.8071308732032776,
      "learning_rate": 1.5e-05,
      "loss": 1.3385,
      "step": 3
    },
    {
      "epoch": 0.0045184975995481505,
      "grad_norm": 0.7587137818336487,
      "learning_rate": 2e-05,
      "loss": 1.261,
      "step": 4
    },
    {
      "epoch": 0.005648121999435188,
      "grad_norm": 0.7234963178634644,
      "learning_rate": 2.5e-05,
      "loss": 1.3662,
      "step": 5
    },
    {
      "epoch": 0.006777746399322226,
      "grad_norm": 0.6198193430900574,
      "learning_rate": 3e-05,
      "loss": 1.2883,
      "step": 6
    },
    {
      "epoch": 0.007907370799209263,
      "grad_norm": 0.7176878452301025,
      "learning_rate": 3.5e-05,
      "loss": 1.3894,
      "step": 7
    },
    {
      "epoch": 0.009036995199096301,
      "grad_norm": 0.7299183011054993,
      "learning_rate": 4e-05,
      "loss": 1.3794,
      "step": 8
    },
    {
      "epoch": 0.010166619598983339,
      "grad_norm": 0.8129087090492249,
      "learning_rate": 4.5e-05,
      "loss": 1.6172,
      "step": 9
    },
    {
      "epoch": 0.011296243998870376,
      "grad_norm": 0.6966177225112915,
      "learning_rate": 5e-05,
      "loss": 1.5394,
      "step": 10
    },
    {
      "epoch": 0.012425868398757414,
      "grad_norm": 0.593917727470398,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.5051,
      "step": 11
    },
    {
      "epoch": 0.013555492798644452,
      "grad_norm": 0.6345414519309998,
      "learning_rate": 6e-05,
      "loss": 1.3946,
      "step": 12
    },
    {
      "epoch": 0.014685117198531489,
      "grad_norm": 0.5908218622207642,
      "learning_rate": 6.500000000000001e-05,
      "loss": 1.2472,
      "step": 13
    },
    {
      "epoch": 0.015814741598418527,
      "grad_norm": 0.7010020613670349,
      "learning_rate": 7e-05,
      "loss": 1.2982,
      "step": 14
    },
    {
      "epoch": 0.016944365998305563,
      "grad_norm": 0.6450609564781189,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.3698,
      "step": 15
    },
    {
      "epoch": 0.018073990398192602,
      "grad_norm": 0.6067284345626831,
      "learning_rate": 8e-05,
      "loss": 1.3054,
      "step": 16
    },
    {
      "epoch": 0.019203614798079638,
      "grad_norm": 0.6235974431037903,
      "learning_rate": 8.5e-05,
      "loss": 1.3359,
      "step": 17
    },
    {
      "epoch": 0.020333239197966677,
      "grad_norm": 0.5723970532417297,
      "learning_rate": 9e-05,
      "loss": 1.1914,
      "step": 18
    },
    {
      "epoch": 0.021462863597853713,
      "grad_norm": 0.6569168567657471,
      "learning_rate": 9.5e-05,
      "loss": 1.3764,
      "step": 19
    },
    {
      "epoch": 0.022592487997740753,
      "grad_norm": 0.5826515555381775,
      "learning_rate": 0.0001,
      "loss": 1.3722,
      "step": 20
    },
    {
      "epoch": 0.02372211239762779,
      "grad_norm": 0.5919983983039856,
      "learning_rate": 9.999238475781957e-05,
      "loss": 1.373,
      "step": 21
    },
    {
      "epoch": 0.024851736797514828,
      "grad_norm": 0.6197838187217712,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.2581,
      "step": 22
    },
    {
      "epoch": 0.025981361197401864,
      "grad_norm": 0.6060734987258911,
      "learning_rate": 9.99314767377287e-05,
      "loss": 1.1977,
      "step": 23
    },
    {
      "epoch": 0.027110985597288903,
      "grad_norm": 0.6347526907920837,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.386,
      "step": 24
    },
    {
      "epoch": 0.02824060999717594,
      "grad_norm": 0.5934184789657593,
      "learning_rate": 9.980973490458728e-05,
      "loss": 1.3412,
      "step": 25
    },
    {
      "epoch": 0.029370234397062978,
      "grad_norm": 0.6491274237632751,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.3562,
      "step": 26
    },
    {
      "epoch": 0.030499858796950014,
      "grad_norm": 0.6903626918792725,
      "learning_rate": 9.962730758206611e-05,
      "loss": 1.3562,
      "step": 27
    },
    {
      "epoch": 0.031629483196837054,
      "grad_norm": 0.7540908455848694,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.3998,
      "step": 28
    },
    {
      "epoch": 0.03275910759672409,
      "grad_norm": 0.6868560314178467,
      "learning_rate": 9.938441702975689e-05,
      "loss": 1.2723,
      "step": 29
    },
    {
      "epoch": 0.033888731996611125,
      "grad_norm": 0.6428096294403076,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.2894,
      "step": 30
    },
    {
      "epoch": 0.03501835639649816,
      "grad_norm": 0.6654598116874695,
      "learning_rate": 9.908135917238321e-05,
      "loss": 1.3825,
      "step": 31
    },
    {
      "epoch": 0.036147980796385204,
      "grad_norm": 0.5971237421035767,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.2241,
      "step": 32
    },
    {
      "epoch": 0.03727760519627224,
      "grad_norm": 0.631828248500824,
      "learning_rate": 9.871850323926177e-05,
      "loss": 1.3014,
      "step": 33
    },
    {
      "epoch": 0.038407229596159276,
      "grad_norm": 0.7876980900764465,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.3527,
      "step": 34
    },
    {
      "epoch": 0.03953685399604631,
      "grad_norm": 0.640664279460907,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.4171,
      "step": 35
    },
    {
      "epoch": 0.040666478395933355,
      "grad_norm": 0.7421198487281799,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.484,
      "step": 36
    },
    {
      "epoch": 0.04179610279582039,
      "grad_norm": 0.6958457827568054,
      "learning_rate": 9.781523779815179e-05,
      "loss": 1.4378,
      "step": 37
    },
    {
      "epoch": 0.042925727195707426,
      "grad_norm": 0.6590381264686584,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.5002,
      "step": 38
    },
    {
      "epoch": 0.04405535159559446,
      "grad_norm": 0.7196072340011597,
      "learning_rate": 9.727592877996585e-05,
      "loss": 1.4445,
      "step": 39
    },
    {
      "epoch": 0.045184975995481505,
      "grad_norm": 0.7248729467391968,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.5349,
      "step": 40
    },
    {
      "epoch": 0.04631460039536854,
      "grad_norm": 0.7737204432487488,
      "learning_rate": 9.667902132486009e-05,
      "loss": 1.6072,
      "step": 41
    },
    {
      "epoch": 0.04744422479525558,
      "grad_norm": 0.7752717733383179,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.6188,
      "step": 42
    },
    {
      "epoch": 0.04857384919514261,
      "grad_norm": 0.7292576432228088,
      "learning_rate": 9.602524267262203e-05,
      "loss": 1.5521,
      "step": 43
    },
    {
      "epoch": 0.049703473595029656,
      "grad_norm": 0.7644132971763611,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.5837,
      "step": 44
    },
    {
      "epoch": 0.05083309799491669,
      "grad_norm": 0.7484924793243408,
      "learning_rate": 9.53153893518325e-05,
      "loss": 1.5187,
      "step": 45
    },
    {
      "epoch": 0.05196272239480373,
      "grad_norm": 0.9397721290588379,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.5828,
      "step": 46
    },
    {
      "epoch": 0.05309234679469076,
      "grad_norm": 0.9622107148170471,
      "learning_rate": 9.45503262094184e-05,
      "loss": 1.6111,
      "step": 47
    },
    {
      "epoch": 0.054221971194577806,
      "grad_norm": 0.9806091785430908,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.7055,
      "step": 48
    },
    {
      "epoch": 0.05535159559446484,
      "grad_norm": 1.1626667976379395,
      "learning_rate": 9.373098535696979e-05,
      "loss": 1.5926,
      "step": 49
    },
    {
      "epoch": 0.05648121999435188,
      "grad_norm": 1.882086157798767,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.6546,
      "step": 50
    },
    {
      "epoch": 0.05648121999435188,
      "eval_loss": 1.432480812072754,
      "eval_runtime": 40.2883,
      "eval_samples_per_second": 37.008,
      "eval_steps_per_second": 18.517,
      "step": 50
    },
    {
      "epoch": 0.057610844394238914,
      "grad_norm": 6.058037281036377,
      "learning_rate": 9.285836503510562e-05,
      "loss": 1.3163,
      "step": 51
    },
    {
      "epoch": 0.058740468794125957,
      "grad_norm": 4.502705097198486,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.3347,
      "step": 52
    },
    {
      "epoch": 0.05987009319401299,
      "grad_norm": 2.17488694190979,
      "learning_rate": 9.193352839727121e-05,
      "loss": 1.2591,
      "step": 53
    },
    {
      "epoch": 0.06099971759390003,
      "grad_norm": 0.9344148635864258,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.3128,
      "step": 54
    },
    {
      "epoch": 0.062129341993787064,
      "grad_norm": 0.6633459329605103,
      "learning_rate": 9.09576022144496e-05,
      "loss": 1.2463,
      "step": 55
    },
    {
      "epoch": 0.06325896639367411,
      "grad_norm": 0.5168513655662537,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.4022,
      "step": 56
    },
    {
      "epoch": 0.06438859079356114,
      "grad_norm": 0.4739576280117035,
      "learning_rate": 8.993177550236464e-05,
      "loss": 1.4488,
      "step": 57
    },
    {
      "epoch": 0.06551821519344818,
      "grad_norm": 0.47201716899871826,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.4155,
      "step": 58
    },
    {
      "epoch": 0.06664783959333521,
      "grad_norm": 0.5001115202903748,
      "learning_rate": 8.885729807284856e-05,
      "loss": 1.4252,
      "step": 59
    },
    {
      "epoch": 0.06777746399322225,
      "grad_norm": 0.5142220258712769,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.5093,
      "step": 60
    },
    {
      "epoch": 0.06890708839310929,
      "grad_norm": 0.5015035271644592,
      "learning_rate": 8.773547901113862e-05,
      "loss": 1.4912,
      "step": 61
    },
    {
      "epoch": 0.07003671279299632,
      "grad_norm": 0.46737051010131836,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.1751,
      "step": 62
    },
    {
      "epoch": 0.07116633719288337,
      "grad_norm": 0.4706385135650635,
      "learning_rate": 8.656768508095853e-05,
      "loss": 1.3106,
      "step": 63
    },
    {
      "epoch": 0.07229596159277041,
      "grad_norm": 0.45581290125846863,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.1907,
      "step": 64
    },
    {
      "epoch": 0.07342558599265744,
      "grad_norm": 0.46465736627578735,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.1932,
      "step": 65
    },
    {
      "epoch": 0.07455521039254448,
      "grad_norm": 0.48178812861442566,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.2628,
      "step": 66
    },
    {
      "epoch": 0.07568483479243152,
      "grad_norm": 0.4830457270145416,
      "learning_rate": 8.409991800312493e-05,
      "loss": 1.2991,
      "step": 67
    },
    {
      "epoch": 0.07681445919231855,
      "grad_norm": 0.462005615234375,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.1688,
      "step": 68
    },
    {
      "epoch": 0.07794408359220559,
      "grad_norm": 0.458380788564682,
      "learning_rate": 8.280295144952536e-05,
      "loss": 1.1544,
      "step": 69
    },
    {
      "epoch": 0.07907370799209262,
      "grad_norm": 0.4663032591342926,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.2183,
      "step": 70
    },
    {
      "epoch": 0.08020333239197967,
      "grad_norm": 0.46658870577812195,
      "learning_rate": 8.146601955249188e-05,
      "loss": 1.1824,
      "step": 71
    },
    {
      "epoch": 0.08133295679186671,
      "grad_norm": 0.481890469789505,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.3568,
      "step": 72
    },
    {
      "epoch": 0.08246258119175374,
      "grad_norm": 0.47948282957077026,
      "learning_rate": 8.009075115760243e-05,
      "loss": 1.3212,
      "step": 73
    },
    {
      "epoch": 0.08359220559164078,
      "grad_norm": 0.48503363132476807,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.3575,
      "step": 74
    },
    {
      "epoch": 0.08472182999152782,
      "grad_norm": 0.4890155792236328,
      "learning_rate": 7.86788218175523e-05,
      "loss": 1.2868,
      "step": 75
    },
    {
      "epoch": 0.08585145439141485,
      "grad_norm": 0.509662389755249,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.2104,
      "step": 76
    },
    {
      "epoch": 0.08698107879130189,
      "grad_norm": 0.5349501371383667,
      "learning_rate": 7.723195175075136e-05,
      "loss": 1.261,
      "step": 77
    },
    {
      "epoch": 0.08811070319118892,
      "grad_norm": 0.4927584230899811,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.2917,
      "step": 78
    },
    {
      "epoch": 0.08924032759107597,
      "grad_norm": 0.5024597644805908,
      "learning_rate": 7.575190374550272e-05,
      "loss": 1.3051,
      "step": 79
    },
    {
      "epoch": 0.09036995199096301,
      "grad_norm": 0.506453812122345,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.2326,
      "step": 80
    },
    {
      "epoch": 0.09149957639085005,
      "grad_norm": 0.5375275015830994,
      "learning_rate": 7.424048101231686e-05,
      "loss": 1.2622,
      "step": 81
    },
    {
      "epoch": 0.09262920079073708,
      "grad_norm": 0.5495799779891968,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.3801,
      "step": 82
    },
    {
      "epoch": 0.09375882519062412,
      "grad_norm": 0.5337545871734619,
      "learning_rate": 7.269952498697734e-05,
      "loss": 1.265,
      "step": 83
    },
    {
      "epoch": 0.09488844959051115,
      "grad_norm": 0.617557168006897,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.4319,
      "step": 84
    },
    {
      "epoch": 0.09601807399039819,
      "grad_norm": 0.5542303919792175,
      "learning_rate": 7.113091308703498e-05,
      "loss": 1.3273,
      "step": 85
    },
    {
      "epoch": 0.09714769839028523,
      "grad_norm": 0.6230977177619934,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.4884,
      "step": 86
    },
    {
      "epoch": 0.09827732279017226,
      "grad_norm": 0.6454778909683228,
      "learning_rate": 6.953655642446368e-05,
      "loss": 1.4153,
      "step": 87
    },
    {
      "epoch": 0.09940694719005931,
      "grad_norm": 0.6431711912155151,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.4105,
      "step": 88
    },
    {
      "epoch": 0.10053657158994635,
      "grad_norm": 0.6007747054100037,
      "learning_rate": 6.7918397477265e-05,
      "loss": 1.5489,
      "step": 89
    },
    {
      "epoch": 0.10166619598983338,
      "grad_norm": 0.7283254861831665,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.5462,
      "step": 90
    },
    {
      "epoch": 0.10279582038972042,
      "grad_norm": 0.6557906270027161,
      "learning_rate": 6.627840772285784e-05,
      "loss": 1.4465,
      "step": 91
    },
    {
      "epoch": 0.10392544478960745,
      "grad_norm": 0.6841725707054138,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.5167,
      "step": 92
    },
    {
      "epoch": 0.10505506918949449,
      "grad_norm": 0.6644818782806396,
      "learning_rate": 6.461858523613684e-05,
      "loss": 1.5386,
      "step": 93
    },
    {
      "epoch": 0.10618469358938153,
      "grad_norm": 0.7009238004684448,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.5738,
      "step": 94
    },
    {
      "epoch": 0.10731431798926856,
      "grad_norm": 0.8302545547485352,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.6512,
      "step": 95
    },
    {
      "epoch": 0.10844394238915561,
      "grad_norm": 0.8315028548240662,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.5656,
      "step": 96
    },
    {
      "epoch": 0.10957356678904265,
      "grad_norm": 0.8375591039657593,
      "learning_rate": 6.124755271719325e-05,
      "loss": 1.6308,
      "step": 97
    },
    {
      "epoch": 0.11070319118892968,
      "grad_norm": 0.9466162323951721,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.5572,
      "step": 98
    },
    {
      "epoch": 0.11183281558881672,
      "grad_norm": 1.0481469631195068,
      "learning_rate": 5.9540449768827246e-05,
      "loss": 1.5684,
      "step": 99
    },
    {
      "epoch": 0.11296243998870376,
      "grad_norm": 1.371314525604248,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.4859,
      "step": 100
    },
    {
      "epoch": 0.11296243998870376,
      "eval_loss": 1.3735841512680054,
      "eval_runtime": 40.2716,
      "eval_samples_per_second": 37.024,
      "eval_steps_per_second": 18.524,
      "step": 100
    },
    {
      "epoch": 0.11409206438859079,
      "grad_norm": 1.4661117792129517,
      "learning_rate": 5.782172325201155e-05,
      "loss": 1.2823,
      "step": 101
    },
    {
      "epoch": 0.11522168878847783,
      "grad_norm": 1.2689025402069092,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.2338,
      "step": 102
    },
    {
      "epoch": 0.11635131318836486,
      "grad_norm": 0.728518009185791,
      "learning_rate": 5.6093467170257374e-05,
      "loss": 1.3032,
      "step": 103
    },
    {
      "epoch": 0.11748093758825191,
      "grad_norm": 0.5547231435775757,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.2473,
      "step": 104
    },
    {
      "epoch": 0.11861056198813895,
      "grad_norm": 0.5641574263572693,
      "learning_rate": 5.435778713738292e-05,
      "loss": 1.4354,
      "step": 105
    },
    {
      "epoch": 0.11974018638802598,
      "grad_norm": 0.47582149505615234,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.3457,
      "step": 106
    },
    {
      "epoch": 0.12086981078791302,
      "grad_norm": 0.45510634779930115,
      "learning_rate": 5.26167978121472e-05,
      "loss": 1.5321,
      "step": 107
    },
    {
      "epoch": 0.12199943518780006,
      "grad_norm": 0.4705533981323242,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.39,
      "step": 108
    },
    {
      "epoch": 0.12312905958768709,
      "grad_norm": 0.5092720985412598,
      "learning_rate": 5.0872620321864185e-05,
      "loss": 1.4614,
      "step": 109
    },
    {
      "epoch": 0.12425868398757413,
      "grad_norm": 0.4724782705307007,
      "learning_rate": 5e-05,
      "loss": 1.5284,
      "step": 110
    },
    {
      "epoch": 0.12538830838746118,
      "grad_norm": 0.4754285216331482,
      "learning_rate": 4.912737967813583e-05,
      "loss": 1.4385,
      "step": 111
    },
    {
      "epoch": 0.12651793278734821,
      "grad_norm": 0.4652653932571411,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.2717,
      "step": 112
    },
    {
      "epoch": 0.12764755718723525,
      "grad_norm": 0.46366190910339355,
      "learning_rate": 4.738320218785281e-05,
      "loss": 1.0826,
      "step": 113
    },
    {
      "epoch": 0.12877718158712229,
      "grad_norm": 0.5129349827766418,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.12,
      "step": 114
    },
    {
      "epoch": 0.12990680598700932,
      "grad_norm": 0.5288143754005432,
      "learning_rate": 4.564221286261709e-05,
      "loss": 1.2204,
      "step": 115
    },
    {
      "epoch": 0.13103643038689636,
      "grad_norm": 0.48036372661590576,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.1622,
      "step": 116
    },
    {
      "epoch": 0.1321660547867834,
      "grad_norm": 0.5082106590270996,
      "learning_rate": 4.390653282974264e-05,
      "loss": 1.1976,
      "step": 117
    },
    {
      "epoch": 0.13329567918667043,
      "grad_norm": 0.46712690591812134,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.1619,
      "step": 118
    },
    {
      "epoch": 0.13442530358655747,
      "grad_norm": 0.476954847574234,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 1.2585,
      "step": 119
    },
    {
      "epoch": 0.1355549279864445,
      "grad_norm": 0.5237648487091064,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.232,
      "step": 120
    },
    {
      "epoch": 0.13668455238633154,
      "grad_norm": 0.5067607760429382,
      "learning_rate": 4.045955023117276e-05,
      "loss": 1.1094,
      "step": 121
    },
    {
      "epoch": 0.13781417678621857,
      "grad_norm": 0.49429094791412354,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.1623,
      "step": 122
    },
    {
      "epoch": 0.1389438011861056,
      "grad_norm": 0.4955546259880066,
      "learning_rate": 3.875244728280676e-05,
      "loss": 1.3095,
      "step": 123
    },
    {
      "epoch": 0.14007342558599264,
      "grad_norm": 0.5102877616882324,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.3287,
      "step": 124
    },
    {
      "epoch": 0.1412030499858797,
      "grad_norm": 0.5063963532447815,
      "learning_rate": 3.705904774487396e-05,
      "loss": 1.3784,
      "step": 125
    },
    {
      "epoch": 0.14233267438576674,
      "grad_norm": 0.5107027292251587,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.3058,
      "step": 126
    },
    {
      "epoch": 0.14346229878565378,
      "grad_norm": 0.5037428140640259,
      "learning_rate": 3.5381414763863166e-05,
      "loss": 1.3713,
      "step": 127
    },
    {
      "epoch": 0.14459192318554082,
      "grad_norm": 0.5251663327217102,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.2503,
      "step": 128
    },
    {
      "epoch": 0.14572154758542785,
      "grad_norm": 0.5187826156616211,
      "learning_rate": 3.372159227714218e-05,
      "loss": 1.2749,
      "step": 129
    },
    {
      "epoch": 0.1468511719853149,
      "grad_norm": 0.5050429105758667,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.2933,
      "step": 130
    },
    {
      "epoch": 0.14798079638520192,
      "grad_norm": 0.5002557039260864,
      "learning_rate": 3.2081602522734986e-05,
      "loss": 1.3044,
      "step": 131
    },
    {
      "epoch": 0.14911042078508896,
      "grad_norm": 0.5536271929740906,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.2421,
      "step": 132
    },
    {
      "epoch": 0.150240045184976,
      "grad_norm": 0.5174810290336609,
      "learning_rate": 3.046344357553632e-05,
      "loss": 1.3492,
      "step": 133
    },
    {
      "epoch": 0.15136966958486303,
      "grad_norm": 0.5379897356033325,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.2034,
      "step": 134
    },
    {
      "epoch": 0.15249929398475007,
      "grad_norm": 0.536281943321228,
      "learning_rate": 2.886908691296504e-05,
      "loss": 1.3215,
      "step": 135
    },
    {
      "epoch": 0.1536289183846371,
      "grad_norm": 0.566135585308075,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.4021,
      "step": 136
    },
    {
      "epoch": 0.15475854278452414,
      "grad_norm": 0.5772363543510437,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 1.4305,
      "step": 137
    },
    {
      "epoch": 0.15588816718441117,
      "grad_norm": 0.5848212242126465,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.3881,
      "step": 138
    },
    {
      "epoch": 0.1570177915842982,
      "grad_norm": 0.5845930576324463,
      "learning_rate": 2.575951898768315e-05,
      "loss": 1.3913,
      "step": 139
    },
    {
      "epoch": 0.15814741598418525,
      "grad_norm": 0.6087456345558167,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.483,
      "step": 140
    },
    {
      "epoch": 0.15927704038407228,
      "grad_norm": 0.6329395771026611,
      "learning_rate": 2.4248096254497288e-05,
      "loss": 1.6086,
      "step": 141
    },
    {
      "epoch": 0.16040666478395935,
      "grad_norm": 0.625912070274353,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.4864,
      "step": 142
    },
    {
      "epoch": 0.16153628918384638,
      "grad_norm": 0.6695480346679688,
      "learning_rate": 2.2768048249248648e-05,
      "loss": 1.5817,
      "step": 143
    },
    {
      "epoch": 0.16266591358373342,
      "grad_norm": 0.6978421211242676,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.4269,
      "step": 144
    },
    {
      "epoch": 0.16379553798362045,
      "grad_norm": 0.7641833424568176,
      "learning_rate": 2.132117818244771e-05,
      "loss": 1.6088,
      "step": 145
    },
    {
      "epoch": 0.1649251623835075,
      "grad_norm": 0.7974191308021545,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.6181,
      "step": 146
    },
    {
      "epoch": 0.16605478678339453,
      "grad_norm": 0.8420169949531555,
      "learning_rate": 1.9909248842397584e-05,
      "loss": 1.6132,
      "step": 147
    },
    {
      "epoch": 0.16718441118328156,
      "grad_norm": 0.9237271547317505,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.6012,
      "step": 148
    },
    {
      "epoch": 0.1683140355831686,
      "grad_norm": 1.0851755142211914,
      "learning_rate": 1.8533980447508137e-05,
      "loss": 1.5464,
      "step": 149
    },
    {
      "epoch": 0.16944365998305563,
      "grad_norm": 1.4369741678237915,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.6628,
      "step": 150
    },
    {
      "epoch": 0.16944365998305563,
      "eval_loss": 1.3262138366699219,
      "eval_runtime": 40.2556,
      "eval_samples_per_second": 37.038,
      "eval_steps_per_second": 18.532,
      "step": 150
    },
    {
      "epoch": 0.17057328438294267,
      "grad_norm": 0.49124306440353394,
      "learning_rate": 1.7197048550474643e-05,
      "loss": 1.1202,
      "step": 151
    },
    {
      "epoch": 0.1717029087828297,
      "grad_norm": 0.49520358443260193,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.0911,
      "step": 152
    },
    {
      "epoch": 0.17283253318271674,
      "grad_norm": 0.5354013442993164,
      "learning_rate": 1.5900081996875083e-05,
      "loss": 1.1471,
      "step": 153
    },
    {
      "epoch": 0.17396215758260378,
      "grad_norm": 0.5129944086074829,
      "learning_rate": 1.526708147705013e-05,
      "loss": 1.1208,
      "step": 154
    },
    {
      "epoch": 0.1750917819824908,
      "grad_norm": 0.5371606349945068,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.3178,
      "step": 155
    },
    {
      "epoch": 0.17622140638237785,
      "grad_norm": 0.5366075038909912,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.2092,
      "step": 156
    },
    {
      "epoch": 0.17735103078226488,
      "grad_norm": 0.4913759231567383,
      "learning_rate": 1.3432314919041478e-05,
      "loss": 1.2554,
      "step": 157
    },
    {
      "epoch": 0.17848065518215195,
      "grad_norm": 0.5127617716789246,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 1.2579,
      "step": 158
    },
    {
      "epoch": 0.17961027958203898,
      "grad_norm": 0.5036717057228088,
      "learning_rate": 1.22645209888614e-05,
      "loss": 1.4016,
      "step": 159
    },
    {
      "epoch": 0.18073990398192602,
      "grad_norm": 0.5216149091720581,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.5803,
      "step": 160
    },
    {
      "epoch": 0.18186952838181306,
      "grad_norm": 0.48862171173095703,
      "learning_rate": 1.1142701927151456e-05,
      "loss": 1.6153,
      "step": 161
    },
    {
      "epoch": 0.1829991527817001,
      "grad_norm": 0.4505916237831116,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.2068,
      "step": 162
    },
    {
      "epoch": 0.18412877718158713,
      "grad_norm": 0.45799902081489563,
      "learning_rate": 1.006822449763537e-05,
      "loss": 1.1012,
      "step": 163
    },
    {
      "epoch": 0.18525840158147416,
      "grad_norm": 0.4590914845466614,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.4007,
      "step": 164
    },
    {
      "epoch": 0.1863880259813612,
      "grad_norm": 0.45719221234321594,
      "learning_rate": 9.042397785550405e-06,
      "loss": 1.1544,
      "step": 165
    },
    {
      "epoch": 0.18751765038124824,
      "grad_norm": 0.4638376832008362,
      "learning_rate": 8.548121372247918e-06,
      "loss": 1.239,
      "step": 166
    },
    {
      "epoch": 0.18864727478113527,
      "grad_norm": 0.46072113513946533,
      "learning_rate": 8.066471602728803e-06,
      "loss": 1.1042,
      "step": 167
    },
    {
      "epoch": 0.1897768991810223,
      "grad_norm": 0.46630680561065674,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.2823,
      "step": 168
    },
    {
      "epoch": 0.19090652358090934,
      "grad_norm": 0.4737482964992523,
      "learning_rate": 7.1416349648943894e-06,
      "loss": 1.1277,
      "step": 169
    },
    {
      "epoch": 0.19203614798079638,
      "grad_norm": 0.47641873359680176,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.3215,
      "step": 170
    },
    {
      "epoch": 0.19316577238068341,
      "grad_norm": 0.4705416262149811,
      "learning_rate": 6.269014643030213e-06,
      "loss": 1.2017,
      "step": 171
    },
    {
      "epoch": 0.19429539678057045,
      "grad_norm": 0.457199364900589,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.1297,
      "step": 172
    },
    {
      "epoch": 0.1954250211804575,
      "grad_norm": 0.48403260111808777,
      "learning_rate": 5.449673790581611e-06,
      "loss": 1.2075,
      "step": 173
    },
    {
      "epoch": 0.19655464558034452,
      "grad_norm": 0.550743818283081,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.1915,
      "step": 174
    },
    {
      "epoch": 0.1976842699802316,
      "grad_norm": 0.4766872823238373,
      "learning_rate": 4.684610648167503e-06,
      "loss": 1.2107,
      "step": 175
    },
    {
      "epoch": 0.19881389438011862,
      "grad_norm": 0.5021941065788269,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.1426,
      "step": 176
    },
    {
      "epoch": 0.19994351878000566,
      "grad_norm": 0.50191730260849,
      "learning_rate": 3.974757327377981e-06,
      "loss": 1.2193,
      "step": 177
    },
    {
      "epoch": 0.2010731431798927,
      "grad_norm": 0.47928962111473083,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 1.1489,
      "step": 178
    },
    {
      "epoch": 0.20220276757977973,
      "grad_norm": 0.503311038017273,
      "learning_rate": 3.3209786751399187e-06,
      "loss": 1.2737,
      "step": 179
    },
    {
      "epoch": 0.20333239197966677,
      "grad_norm": 0.5053710341453552,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.2481,
      "step": 180
    },
    {
      "epoch": 0.2044620163795538,
      "grad_norm": 0.5147269368171692,
      "learning_rate": 2.724071220034158e-06,
      "loss": 1.3417,
      "step": 181
    },
    {
      "epoch": 0.20559164077944084,
      "grad_norm": 0.5732929706573486,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.3868,
      "step": 182
    },
    {
      "epoch": 0.20672126517932787,
      "grad_norm": 0.527452290058136,
      "learning_rate": 2.1847622018482283e-06,
      "loss": 1.3027,
      "step": 183
    },
    {
      "epoch": 0.2078508895792149,
      "grad_norm": 0.5416896343231201,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.2545,
      "step": 184
    },
    {
      "epoch": 0.20898051397910195,
      "grad_norm": 0.5731329321861267,
      "learning_rate": 1.70370868554659e-06,
      "loss": 1.3079,
      "step": 185
    },
    {
      "epoch": 0.21011013837898898,
      "grad_norm": 0.5883909463882446,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 1.5006,
      "step": 186
    },
    {
      "epoch": 0.21123976277887602,
      "grad_norm": 0.5972925424575806,
      "learning_rate": 1.2814967607382432e-06,
      "loss": 1.3674,
      "step": 187
    },
    {
      "epoch": 0.21236938717876305,
      "grad_norm": 0.5583184957504272,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.2725,
      "step": 188
    },
    {
      "epoch": 0.2134990115786501,
      "grad_norm": 0.5782355070114136,
      "learning_rate": 9.186408276168013e-07,
      "loss": 1.3732,
      "step": 189
    },
    {
      "epoch": 0.21462863597853712,
      "grad_norm": 0.6027134656906128,
      "learning_rate": 7.596123493895991e-07,
      "loss": 1.5277,
      "step": 190
    },
    {
      "epoch": 0.21575826037842416,
      "grad_norm": 0.6360686421394348,
      "learning_rate": 6.15582970243117e-07,
      "loss": 1.4427,
      "step": 191
    },
    {
      "epoch": 0.21688788477831122,
      "grad_norm": 0.6561896204948425,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.4844,
      "step": 192
    },
    {
      "epoch": 0.21801750917819826,
      "grad_norm": 0.721521258354187,
      "learning_rate": 3.7269241793390085e-07,
      "loss": 1.4888,
      "step": 193
    },
    {
      "epoch": 0.2191471335780853,
      "grad_norm": 0.7198924422264099,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 1.5454,
      "step": 194
    },
    {
      "epoch": 0.22027675797797233,
      "grad_norm": 0.7584518194198608,
      "learning_rate": 1.9026509541272275e-07,
      "loss": 1.4405,
      "step": 195
    },
    {
      "epoch": 0.22140638237785937,
      "grad_norm": 0.8175909519195557,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.5323,
      "step": 196
    },
    {
      "epoch": 0.2225360067777464,
      "grad_norm": 0.8695264458656311,
      "learning_rate": 6.852326227130834e-08,
      "loss": 1.6161,
      "step": 197
    },
    {
      "epoch": 0.22366563117763344,
      "grad_norm": 0.9309313893318176,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.5374,
      "step": 198
    },
    {
      "epoch": 0.22479525557752048,
      "grad_norm": 1.1391574144363403,
      "learning_rate": 7.615242180436522e-09,
      "loss": 1.5431,
      "step": 199
    },
    {
      "epoch": 0.2259248799774075,
      "grad_norm": 1.4460625648498535,
      "learning_rate": 0.0,
      "loss": 1.5086,
      "step": 200
    },
    {
      "epoch": 0.2259248799774075,
      "eval_loss": 1.319568157196045,
      "eval_runtime": 40.3772,
      "eval_samples_per_second": 36.927,
      "eval_steps_per_second": 18.476,
      "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": 1.9070030400454656e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}