{
  "best_metric": 0.08230920881032944,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.052171644711099516,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00026085822355549756,
      "grad_norm": 2.889893054962158,
      "learning_rate": 1.004e-05,
      "loss": 0.4277,
      "step": 1
    },
    {
      "epoch": 0.00026085822355549756,
      "eval_loss": 0.12571461498737335,
      "eval_runtime": 355.2992,
      "eval_samples_per_second": 4.543,
      "eval_steps_per_second": 1.137,
      "step": 1
    },
    {
      "epoch": 0.0005217164471109951,
      "grad_norm": 2.151228666305542,
      "learning_rate": 2.008e-05,
      "loss": 0.4676,
      "step": 2
    },
    {
      "epoch": 0.0007825746706664928,
      "grad_norm": 1.6503167152404785,
      "learning_rate": 3.012e-05,
      "loss": 0.4041,
      "step": 3
    },
    {
      "epoch": 0.0010434328942219902,
      "grad_norm": 1.666961908340454,
      "learning_rate": 4.016e-05,
      "loss": 0.4058,
      "step": 4
    },
    {
      "epoch": 0.001304291117777488,
      "grad_norm": 3.217031478881836,
      "learning_rate": 5.02e-05,
      "loss": 0.3677,
      "step": 5
    },
    {
      "epoch": 0.0015651493413329856,
      "grad_norm": 1.9754326343536377,
      "learning_rate": 6.024e-05,
      "loss": 0.3753,
      "step": 6
    },
    {
      "epoch": 0.0018260075648884831,
      "grad_norm": 1.1739203929901123,
      "learning_rate": 7.028e-05,
      "loss": 0.4414,
      "step": 7
    },
    {
      "epoch": 0.0020868657884439805,
      "grad_norm": 0.9883484840393066,
      "learning_rate": 8.032e-05,
      "loss": 0.3682,
      "step": 8
    },
    {
      "epoch": 0.0023477240119994785,
      "grad_norm": 1.0638494491577148,
      "learning_rate": 9.036000000000001e-05,
      "loss": 0.4203,
      "step": 9
    },
    {
      "epoch": 0.002608582235554976,
      "grad_norm": 1.1801265478134155,
      "learning_rate": 0.0001004,
      "loss": 0.4001,
      "step": 10
    },
    {
      "epoch": 0.0028694404591104736,
      "grad_norm": 1.0033977031707764,
      "learning_rate": 9.987157894736842e-05,
      "loss": 0.3808,
      "step": 11
    },
    {
      "epoch": 0.003130298682665971,
      "grad_norm": 1.0454702377319336,
      "learning_rate": 9.934315789473684e-05,
      "loss": 0.3992,
      "step": 12
    },
    {
      "epoch": 0.0033911569062214687,
      "grad_norm": 0.9567103981971741,
      "learning_rate": 9.881473684210525e-05,
      "loss": 0.4369,
      "step": 13
    },
    {
      "epoch": 0.0036520151297769663,
      "grad_norm": 0.9078320860862732,
      "learning_rate": 9.828631578947369e-05,
      "loss": 0.3368,
      "step": 14
    },
    {
      "epoch": 0.003912873353332464,
      "grad_norm": 1.067278265953064,
      "learning_rate": 9.77578947368421e-05,
      "loss": 0.362,
      "step": 15
    },
    {
      "epoch": 0.004173731576887961,
      "grad_norm": 1.1500056982040405,
      "learning_rate": 9.722947368421052e-05,
      "loss": 0.3707,
      "step": 16
    },
    {
      "epoch": 0.004434589800443459,
      "grad_norm": 0.9279374480247498,
      "learning_rate": 9.670105263157895e-05,
      "loss": 0.3435,
      "step": 17
    },
    {
      "epoch": 0.004695448023998957,
      "grad_norm": 0.8641620874404907,
      "learning_rate": 9.617263157894737e-05,
      "loss": 0.3694,
      "step": 18
    },
    {
      "epoch": 0.004956306247554454,
      "grad_norm": 0.9377633929252625,
      "learning_rate": 9.564421052631579e-05,
      "loss": 0.3506,
      "step": 19
    },
    {
      "epoch": 0.005217164471109952,
      "grad_norm": 0.8363476991653442,
      "learning_rate": 9.511578947368421e-05,
      "loss": 0.3899,
      "step": 20
    },
    {
      "epoch": 0.005478022694665449,
      "grad_norm": 0.913992702960968,
      "learning_rate": 9.458736842105264e-05,
      "loss": 0.3662,
      "step": 21
    },
    {
      "epoch": 0.005738880918220947,
      "grad_norm": 1.1835615634918213,
      "learning_rate": 9.405894736842106e-05,
      "loss": 0.4134,
      "step": 22
    },
    {
      "epoch": 0.005999739141776444,
      "grad_norm": 0.8820966482162476,
      "learning_rate": 9.353052631578947e-05,
      "loss": 0.3832,
      "step": 23
    },
    {
      "epoch": 0.006260597365331942,
      "grad_norm": 1.1732457876205444,
      "learning_rate": 9.300210526315789e-05,
      "loss": 0.3671,
      "step": 24
    },
    {
      "epoch": 0.0065214555888874395,
      "grad_norm": 1.1374287605285645,
      "learning_rate": 9.247368421052631e-05,
      "loss": 0.1064,
      "step": 25
    },
    {
      "epoch": 0.0067823138124429375,
      "grad_norm": 0.8893991112709045,
      "learning_rate": 9.194526315789473e-05,
      "loss": 0.0371,
      "step": 26
    },
    {
      "epoch": 0.007043172035998435,
      "grad_norm": 6.425418376922607,
      "learning_rate": 9.141684210526316e-05,
      "loss": 0.0351,
      "step": 27
    },
    {
      "epoch": 0.007304030259553933,
      "grad_norm": 2.917386770248413,
      "learning_rate": 9.088842105263158e-05,
      "loss": 0.0259,
      "step": 28
    },
    {
      "epoch": 0.00756488848310943,
      "grad_norm": 2.889286756515503,
      "learning_rate": 9.036000000000001e-05,
      "loss": 0.0523,
      "step": 29
    },
    {
      "epoch": 0.007825746706664928,
      "grad_norm": 1.3778408765792847,
      "learning_rate": 8.983157894736843e-05,
      "loss": 0.0113,
      "step": 30
    },
    {
      "epoch": 0.008086604930220426,
      "grad_norm": 1.199445128440857,
      "learning_rate": 8.930315789473684e-05,
      "loss": 0.0075,
      "step": 31
    },
    {
      "epoch": 0.008347463153775922,
      "grad_norm": 1.0043731927871704,
      "learning_rate": 8.877473684210526e-05,
      "loss": 0.0058,
      "step": 32
    },
    {
      "epoch": 0.00860832137733142,
      "grad_norm": 0.047168854624032974,
      "learning_rate": 8.824631578947368e-05,
      "loss": 0.0005,
      "step": 33
    },
    {
      "epoch": 0.008869179600886918,
      "grad_norm": 0.5005334615707397,
      "learning_rate": 8.771789473684211e-05,
      "loss": 0.0045,
      "step": 34
    },
    {
      "epoch": 0.009130037824442416,
      "grad_norm": 8.737451553344727,
      "learning_rate": 8.718947368421053e-05,
      "loss": 0.0441,
      "step": 35
    },
    {
      "epoch": 0.009390896047997914,
      "grad_norm": 1.570122241973877,
      "learning_rate": 8.666105263157895e-05,
      "loss": 0.0158,
      "step": 36
    },
    {
      "epoch": 0.00965175427155341,
      "grad_norm": 2.2240395545959473,
      "learning_rate": 8.613263157894737e-05,
      "loss": 0.0246,
      "step": 37
    },
    {
      "epoch": 0.009912612495108908,
      "grad_norm": 1.170030117034912,
      "learning_rate": 8.560421052631578e-05,
      "loss": 0.0105,
      "step": 38
    },
    {
      "epoch": 0.010173470718664406,
      "grad_norm": 1.453275442123413,
      "learning_rate": 8.50757894736842e-05,
      "loss": 0.013,
      "step": 39
    },
    {
      "epoch": 0.010434328942219904,
      "grad_norm": 1.6023317575454712,
      "learning_rate": 8.454736842105263e-05,
      "loss": 0.0142,
      "step": 40
    },
    {
      "epoch": 0.0106951871657754,
      "grad_norm": 2.5300304889678955,
      "learning_rate": 8.401894736842106e-05,
      "loss": 0.0245,
      "step": 41
    },
    {
      "epoch": 0.010956045389330898,
      "grad_norm": 1.3093210458755493,
      "learning_rate": 8.349052631578948e-05,
      "loss": 0.0071,
      "step": 42
    },
    {
      "epoch": 0.011216903612886396,
      "grad_norm": 3.7948031425476074,
      "learning_rate": 8.29621052631579e-05,
      "loss": 0.0053,
      "step": 43
    },
    {
      "epoch": 0.011477761836441894,
      "grad_norm": 0.5037760138511658,
      "learning_rate": 8.243368421052632e-05,
      "loss": 0.0034,
      "step": 44
    },
    {
      "epoch": 0.01173862005999739,
      "grad_norm": 0.3311668634414673,
      "learning_rate": 8.190526315789474e-05,
      "loss": 0.0029,
      "step": 45
    },
    {
      "epoch": 0.011999478283552889,
      "grad_norm": 0.4485372006893158,
      "learning_rate": 8.137684210526315e-05,
      "loss": 0.0017,
      "step": 46
    },
    {
      "epoch": 0.012260336507108387,
      "grad_norm": 1.304323434829712,
      "learning_rate": 8.084842105263157e-05,
      "loss": 0.0034,
      "step": 47
    },
    {
      "epoch": 0.012521194730663885,
      "grad_norm": 0.24832318723201752,
      "learning_rate": 8.032e-05,
      "loss": 0.0019,
      "step": 48
    },
    {
      "epoch": 0.012782052954219381,
      "grad_norm": 1.1616764068603516,
      "learning_rate": 7.979157894736842e-05,
      "loss": 0.0031,
      "step": 49
    },
    {
      "epoch": 0.013042911177774879,
      "grad_norm": 4.977385997772217,
      "learning_rate": 7.926315789473684e-05,
      "loss": 0.012,
      "step": 50
    },
    {
      "epoch": 0.013042911177774879,
      "eval_loss": 0.26625388860702515,
      "eval_runtime": 357.7191,
      "eval_samples_per_second": 4.512,
      "eval_steps_per_second": 1.129,
      "step": 50
    },
    {
      "epoch": 0.013303769401330377,
      "grad_norm": 21.080076217651367,
      "learning_rate": 7.873473684210526e-05,
      "loss": 0.898,
      "step": 51
    },
    {
      "epoch": 0.013564627624885875,
      "grad_norm": 7.187935829162598,
      "learning_rate": 7.820631578947369e-05,
      "loss": 0.6007,
      "step": 52
    },
    {
      "epoch": 0.013825485848441373,
      "grad_norm": 2.1182901859283447,
      "learning_rate": 7.76778947368421e-05,
      "loss": 0.4358,
      "step": 53
    },
    {
      "epoch": 0.01408634407199687,
      "grad_norm": 1.093733310699463,
      "learning_rate": 7.714947368421052e-05,
      "loss": 0.347,
      "step": 54
    },
    {
      "epoch": 0.014347202295552367,
      "grad_norm": 0.9055514931678772,
      "learning_rate": 7.662105263157896e-05,
      "loss": 0.3856,
      "step": 55
    },
    {
      "epoch": 0.014608060519107865,
      "grad_norm": 0.8669521808624268,
      "learning_rate": 7.609263157894737e-05,
      "loss": 0.3701,
      "step": 56
    },
    {
      "epoch": 0.014868918742663363,
      "grad_norm": 0.9830688238143921,
      "learning_rate": 7.556421052631579e-05,
      "loss": 0.4053,
      "step": 57
    },
    {
      "epoch": 0.01512977696621886,
      "grad_norm": 0.7812885046005249,
      "learning_rate": 7.503578947368421e-05,
      "loss": 0.354,
      "step": 58
    },
    {
      "epoch": 0.015390635189774357,
      "grad_norm": 0.7740699648857117,
      "learning_rate": 7.450736842105263e-05,
      "loss": 0.3165,
      "step": 59
    },
    {
      "epoch": 0.015651493413329855,
      "grad_norm": 0.7680047750473022,
      "learning_rate": 7.397894736842105e-05,
      "loss": 0.3313,
      "step": 60
    },
    {
      "epoch": 0.01591235163688535,
      "grad_norm": 0.8641350269317627,
      "learning_rate": 7.345052631578948e-05,
      "loss": 0.3395,
      "step": 61
    },
    {
      "epoch": 0.01617320986044085,
      "grad_norm": 1.396049976348877,
      "learning_rate": 7.29221052631579e-05,
      "loss": 0.3642,
      "step": 62
    },
    {
      "epoch": 0.016434068083996348,
      "grad_norm": 0.8436359763145447,
      "learning_rate": 7.239368421052631e-05,
      "loss": 0.3378,
      "step": 63
    },
    {
      "epoch": 0.016694926307551844,
      "grad_norm": 0.8464940786361694,
      "learning_rate": 7.186526315789474e-05,
      "loss": 0.3668,
      "step": 64
    },
    {
      "epoch": 0.016955784531107344,
      "grad_norm": 0.725881040096283,
      "learning_rate": 7.133684210526316e-05,
      "loss": 0.3661,
      "step": 65
    },
    {
      "epoch": 0.01721664275466284,
      "grad_norm": 0.6846409440040588,
      "learning_rate": 7.080842105263158e-05,
      "loss": 0.3638,
      "step": 66
    },
    {
      "epoch": 0.01747750097821834,
      "grad_norm": 0.7216416001319885,
      "learning_rate": 7.028e-05,
      "loss": 0.3635,
      "step": 67
    },
    {
      "epoch": 0.017738359201773836,
      "grad_norm": 0.6579917073249817,
      "learning_rate": 6.975157894736843e-05,
      "loss": 0.356,
      "step": 68
    },
    {
      "epoch": 0.017999217425329332,
      "grad_norm": 0.8300607204437256,
      "learning_rate": 6.922315789473685e-05,
      "loss": 0.362,
      "step": 69
    },
    {
      "epoch": 0.018260075648884832,
      "grad_norm": 0.8601360321044922,
      "learning_rate": 6.869473684210527e-05,
      "loss": 0.3178,
      "step": 70
    },
    {
      "epoch": 0.018520933872440328,
      "grad_norm": 1.229761004447937,
      "learning_rate": 6.816631578947368e-05,
      "loss": 0.3038,
      "step": 71
    },
    {
      "epoch": 0.018781792095995828,
      "grad_norm": 0.8368088603019714,
      "learning_rate": 6.76378947368421e-05,
      "loss": 0.3394,
      "step": 72
    },
    {
      "epoch": 0.019042650319551324,
      "grad_norm": 0.76348876953125,
      "learning_rate": 6.710947368421052e-05,
      "loss": 0.3273,
      "step": 73
    },
    {
      "epoch": 0.01930350854310682,
      "grad_norm": 0.8756521344184875,
      "learning_rate": 6.658105263157894e-05,
      "loss": 0.3483,
      "step": 74
    },
    {
      "epoch": 0.01956436676666232,
      "grad_norm": 1.1323158740997314,
      "learning_rate": 6.605263157894737e-05,
      "loss": 0.1971,
      "step": 75
    },
    {
      "epoch": 0.019825224990217816,
      "grad_norm": 0.7796782851219177,
      "learning_rate": 6.55242105263158e-05,
      "loss": 0.0966,
      "step": 76
    },
    {
      "epoch": 0.020086083213773313,
      "grad_norm": 0.6780573725700378,
      "learning_rate": 6.499578947368422e-05,
      "loss": 0.0203,
      "step": 77
    },
    {
      "epoch": 0.020346941437328812,
      "grad_norm": 23.24646759033203,
      "learning_rate": 6.446736842105264e-05,
      "loss": 0.2551,
      "step": 78
    },
    {
      "epoch": 0.02060779966088431,
      "grad_norm": 8.683259010314941,
      "learning_rate": 6.393894736842105e-05,
      "loss": 0.0885,
      "step": 79
    },
    {
      "epoch": 0.02086865788443981,
      "grad_norm": 0.6611659526824951,
      "learning_rate": 6.341052631578947e-05,
      "loss": 0.0034,
      "step": 80
    },
    {
      "epoch": 0.021129516107995305,
      "grad_norm": 0.1200755164027214,
      "learning_rate": 6.288210526315789e-05,
      "loss": 0.0004,
      "step": 81
    },
    {
      "epoch": 0.0213903743315508,
      "grad_norm": 1.164768934249878,
      "learning_rate": 6.235368421052632e-05,
      "loss": 0.0091,
      "step": 82
    },
    {
      "epoch": 0.0216512325551063,
      "grad_norm": 0.17707791924476624,
      "learning_rate": 6.182526315789474e-05,
      "loss": 0.0013,
      "step": 83
    },
    {
      "epoch": 0.021912090778661797,
      "grad_norm": 0.21379932761192322,
      "learning_rate": 6.129684210526316e-05,
      "loss": 0.0013,
      "step": 84
    },
    {
      "epoch": 0.022172949002217297,
      "grad_norm": 1.1995000839233398,
      "learning_rate": 6.076842105263158e-05,
      "loss": 0.0081,
      "step": 85
    },
    {
      "epoch": 0.022433807225772793,
      "grad_norm": 0.3035678565502167,
      "learning_rate": 6.024e-05,
      "loss": 0.0008,
      "step": 86
    },
    {
      "epoch": 0.02269466544932829,
      "grad_norm": 0.014499887824058533,
      "learning_rate": 5.971157894736842e-05,
      "loss": 0.0002,
      "step": 87
    },
    {
      "epoch": 0.02295552367288379,
      "grad_norm": 1.4160069227218628,
      "learning_rate": 5.9183157894736835e-05,
      "loss": 0.0115,
      "step": 88
    },
    {
      "epoch": 0.023216381896439285,
      "grad_norm": 1.5838091373443604,
      "learning_rate": 5.8654736842105267e-05,
      "loss": 0.0009,
      "step": 89
    },
    {
      "epoch": 0.02347724011999478,
      "grad_norm": 2.2831833362579346,
      "learning_rate": 5.8126315789473684e-05,
      "loss": 0.0095,
      "step": 90
    },
    {
      "epoch": 0.02373809834355028,
      "grad_norm": 1.3635400533676147,
      "learning_rate": 5.759789473684211e-05,
      "loss": 0.0018,
      "step": 91
    },
    {
      "epoch": 0.023998956567105777,
      "grad_norm": 0.0419996902346611,
      "learning_rate": 5.706947368421053e-05,
      "loss": 0.0002,
      "step": 92
    },
    {
      "epoch": 0.024259814790661277,
      "grad_norm": 0.029113048687577248,
      "learning_rate": 5.6541052631578945e-05,
      "loss": 0.0003,
      "step": 93
    },
    {
      "epoch": 0.024520673014216773,
      "grad_norm": 1.1532421112060547,
      "learning_rate": 5.601263157894736e-05,
      "loss": 0.0072,
      "step": 94
    },
    {
      "epoch": 0.02478153123777227,
      "grad_norm": 0.03277314826846123,
      "learning_rate": 5.5484210526315794e-05,
      "loss": 0.0004,
      "step": 95
    },
    {
      "epoch": 0.02504238946132777,
      "grad_norm": 0.19502609968185425,
      "learning_rate": 5.495578947368421e-05,
      "loss": 0.0008,
      "step": 96
    },
    {
      "epoch": 0.025303247684883266,
      "grad_norm": 1.1677289009094238,
      "learning_rate": 5.442736842105264e-05,
      "loss": 0.0045,
      "step": 97
    },
    {
      "epoch": 0.025564105908438762,
      "grad_norm": 0.24581104516983032,
      "learning_rate": 5.3898947368421055e-05,
      "loss": 0.0016,
      "step": 98
    },
    {
      "epoch": 0.02582496413199426,
      "grad_norm": 2.174943685531616,
      "learning_rate": 5.337052631578947e-05,
      "loss": 0.0116,
      "step": 99
    },
    {
      "epoch": 0.026085822355549758,
      "grad_norm": 0.24700959026813507,
      "learning_rate": 5.284210526315789e-05,
      "loss": 0.0014,
      "step": 100
    },
    {
      "epoch": 0.026085822355549758,
      "eval_loss": 0.12110025435686111,
      "eval_runtime": 358.6905,
      "eval_samples_per_second": 4.5,
      "eval_steps_per_second": 1.126,
      "step": 100
    },
    {
      "epoch": 0.026346680579105258,
      "grad_norm": 5.076243877410889,
      "learning_rate": 5.231368421052631e-05,
      "loss": 0.4922,
      "step": 101
    },
    {
      "epoch": 0.026607538802660754,
      "grad_norm": 1.472834825515747,
      "learning_rate": 5.178526315789474e-05,
      "loss": 0.3784,
      "step": 102
    },
    {
      "epoch": 0.02686839702621625,
      "grad_norm": 0.9007657766342163,
      "learning_rate": 5.1256842105263165e-05,
      "loss": 0.381,
      "step": 103
    },
    {
      "epoch": 0.02712925524977175,
      "grad_norm": 0.9710745215415955,
      "learning_rate": 5.072842105263158e-05,
      "loss": 0.3776,
      "step": 104
    },
    {
      "epoch": 0.027390113473327246,
      "grad_norm": 0.6388360857963562,
      "learning_rate": 5.02e-05,
      "loss": 0.3505,
      "step": 105
    },
    {
      "epoch": 0.027650971696882746,
      "grad_norm": 0.8697831034660339,
      "learning_rate": 4.967157894736842e-05,
      "loss": 0.3618,
      "step": 106
    },
    {
      "epoch": 0.027911829920438242,
      "grad_norm": 0.6823816895484924,
      "learning_rate": 4.914315789473684e-05,
      "loss": 0.3559,
      "step": 107
    },
    {
      "epoch": 0.02817268814399374,
      "grad_norm": 0.6802661418914795,
      "learning_rate": 4.861473684210526e-05,
      "loss": 0.3502,
      "step": 108
    },
    {
      "epoch": 0.028433546367549238,
      "grad_norm": 0.7415322065353394,
      "learning_rate": 4.8086315789473686e-05,
      "loss": 0.3634,
      "step": 109
    },
    {
      "epoch": 0.028694404591104734,
      "grad_norm": 0.7177245020866394,
      "learning_rate": 4.7557894736842104e-05,
      "loss": 0.3371,
      "step": 110
    },
    {
      "epoch": 0.02895526281466023,
      "grad_norm": 0.7753718495368958,
      "learning_rate": 4.702947368421053e-05,
      "loss": 0.3397,
      "step": 111
    },
    {
      "epoch": 0.02921612103821573,
      "grad_norm": 0.6841831207275391,
      "learning_rate": 4.6501052631578946e-05,
      "loss": 0.3363,
      "step": 112
    },
    {
      "epoch": 0.029476979261771227,
      "grad_norm": 0.7129581570625305,
      "learning_rate": 4.5972631578947364e-05,
      "loss": 0.3124,
      "step": 113
    },
    {
      "epoch": 0.029737837485326726,
      "grad_norm": 0.6826345324516296,
      "learning_rate": 4.544421052631579e-05,
      "loss": 0.3518,
      "step": 114
    },
    {
      "epoch": 0.029998695708882223,
      "grad_norm": 0.7089869976043701,
      "learning_rate": 4.4915789473684213e-05,
      "loss": 0.3721,
      "step": 115
    },
    {
      "epoch": 0.03025955393243772,
      "grad_norm": 0.7004755139350891,
      "learning_rate": 4.438736842105263e-05,
      "loss": 0.3917,
      "step": 116
    },
    {
      "epoch": 0.03052041215599322,
      "grad_norm": 0.705506443977356,
      "learning_rate": 4.3858947368421056e-05,
      "loss": 0.3312,
      "step": 117
    },
    {
      "epoch": 0.030781270379548715,
      "grad_norm": 0.6989331841468811,
      "learning_rate": 4.3330526315789474e-05,
      "loss": 0.3982,
      "step": 118
    },
    {
      "epoch": 0.031042128603104215,
      "grad_norm": 0.6170200705528259,
      "learning_rate": 4.280210526315789e-05,
      "loss": 0.346,
      "step": 119
    },
    {
      "epoch": 0.03130298682665971,
      "grad_norm": 1.072172999382019,
      "learning_rate": 4.2273684210526317e-05,
      "loss": 0.3726,
      "step": 120
    },
    {
      "epoch": 0.03156384505021521,
      "grad_norm": 0.754610002040863,
      "learning_rate": 4.174526315789474e-05,
      "loss": 0.3519,
      "step": 121
    },
    {
      "epoch": 0.0318247032737707,
      "grad_norm": 0.9958357810974121,
      "learning_rate": 4.121684210526316e-05,
      "loss": 0.2739,
      "step": 122
    },
    {
      "epoch": 0.03208556149732621,
      "grad_norm": 0.8653532266616821,
      "learning_rate": 4.068842105263158e-05,
      "loss": 0.155,
      "step": 123
    },
    {
      "epoch": 0.0323464197208817,
      "grad_norm": 1.0545744895935059,
      "learning_rate": 4.016e-05,
      "loss": 0.0706,
      "step": 124
    },
    {
      "epoch": 0.0326072779444372,
      "grad_norm": 0.9402056932449341,
      "learning_rate": 3.963157894736842e-05,
      "loss": 0.0434,
      "step": 125
    },
    {
      "epoch": 0.032868136167992695,
      "grad_norm": 0.894481897354126,
      "learning_rate": 3.9103157894736844e-05,
      "loss": 0.0202,
      "step": 126
    },
    {
      "epoch": 0.03312899439154819,
      "grad_norm": 0.7376012206077576,
      "learning_rate": 3.857473684210526e-05,
      "loss": 0.0084,
      "step": 127
    },
    {
      "epoch": 0.03338985261510369,
      "grad_norm": 1.427925705909729,
      "learning_rate": 3.804631578947369e-05,
      "loss": 0.0072,
      "step": 128
    },
    {
      "epoch": 0.03365071083865919,
      "grad_norm": 0.9831644296646118,
      "learning_rate": 3.7517894736842105e-05,
      "loss": 0.0031,
      "step": 129
    },
    {
      "epoch": 0.03391156906221469,
      "grad_norm": 0.8595508337020874,
      "learning_rate": 3.698947368421052e-05,
      "loss": 0.0033,
      "step": 130
    },
    {
      "epoch": 0.034172427285770184,
      "grad_norm": 0.06450106203556061,
      "learning_rate": 3.646105263157895e-05,
      "loss": 0.0004,
      "step": 131
    },
    {
      "epoch": 0.03443328550932568,
      "grad_norm": 0.9597758650779724,
      "learning_rate": 3.593263157894737e-05,
      "loss": 0.0023,
      "step": 132
    },
    {
      "epoch": 0.034694143732881176,
      "grad_norm": 0.7004671692848206,
      "learning_rate": 3.540421052631579e-05,
      "loss": 0.0111,
      "step": 133
    },
    {
      "epoch": 0.03495500195643668,
      "grad_norm": 0.9372411966323853,
      "learning_rate": 3.4875789473684215e-05,
      "loss": 0.004,
      "step": 134
    },
    {
      "epoch": 0.035215860179992176,
      "grad_norm": 0.9186482429504395,
      "learning_rate": 3.434736842105263e-05,
      "loss": 0.0082,
      "step": 135
    },
    {
      "epoch": 0.03547671840354767,
      "grad_norm": 0.7771823406219482,
      "learning_rate": 3.381894736842105e-05,
      "loss": 0.0077,
      "step": 136
    },
    {
      "epoch": 0.03573757662710317,
      "grad_norm": 0.15932439267635345,
      "learning_rate": 3.329052631578947e-05,
      "loss": 0.0013,
      "step": 137
    },
    {
      "epoch": 0.035998434850658664,
      "grad_norm": 1.1858546733856201,
      "learning_rate": 3.27621052631579e-05,
      "loss": 0.003,
      "step": 138
    },
    {
      "epoch": 0.03625929307421417,
      "grad_norm": 1.5219371318817139,
      "learning_rate": 3.223368421052632e-05,
      "loss": 0.0174,
      "step": 139
    },
    {
      "epoch": 0.036520151297769664,
      "grad_norm": 0.7560831904411316,
      "learning_rate": 3.1705263157894736e-05,
      "loss": 0.0028,
      "step": 140
    },
    {
      "epoch": 0.03678100952132516,
      "grad_norm": 2.4772675037384033,
      "learning_rate": 3.117684210526316e-05,
      "loss": 0.0093,
      "step": 141
    },
    {
      "epoch": 0.037041867744880656,
      "grad_norm": 0.05707191303372383,
      "learning_rate": 3.064842105263158e-05,
      "loss": 0.0004,
      "step": 142
    },
    {
      "epoch": 0.03730272596843615,
      "grad_norm": 0.03188670799136162,
      "learning_rate": 3.012e-05,
      "loss": 0.0003,
      "step": 143
    },
    {
      "epoch": 0.037563584191991656,
      "grad_norm": 0.041902583092451096,
      "learning_rate": 2.9591578947368418e-05,
      "loss": 0.0004,
      "step": 144
    },
    {
      "epoch": 0.03782444241554715,
      "grad_norm": 1.0179723501205444,
      "learning_rate": 2.9063157894736842e-05,
      "loss": 0.0087,
      "step": 145
    },
    {
      "epoch": 0.03808530063910265,
      "grad_norm": 1.2331745624542236,
      "learning_rate": 2.8534736842105264e-05,
      "loss": 0.0101,
      "step": 146
    },
    {
      "epoch": 0.038346158862658145,
      "grad_norm": 0.06799151748418808,
      "learning_rate": 2.800631578947368e-05,
      "loss": 0.0008,
      "step": 147
    },
    {
      "epoch": 0.03860701708621364,
      "grad_norm": 0.06529802829027176,
      "learning_rate": 2.7477894736842106e-05,
      "loss": 0.0007,
      "step": 148
    },
    {
      "epoch": 0.03886787530976914,
      "grad_norm": 2.640516757965088,
      "learning_rate": 2.6949473684210527e-05,
      "loss": 0.011,
      "step": 149
    },
    {
      "epoch": 0.03912873353332464,
      "grad_norm": 0.2220402956008911,
      "learning_rate": 2.6421052631578945e-05,
      "loss": 0.0021,
      "step": 150
    },
    {
      "epoch": 0.03912873353332464,
      "eval_loss": 0.12124448269605637,
      "eval_runtime": 357.9478,
      "eval_samples_per_second": 4.509,
      "eval_steps_per_second": 1.129,
      "step": 150
    },
    {
      "epoch": 0.039389591756880137,
      "grad_norm": 3.797510862350464,
      "learning_rate": 2.589263157894737e-05,
      "loss": 0.5013,
      "step": 151
    },
    {
      "epoch": 0.03965044998043563,
      "grad_norm": 3.3140711784362793,
      "learning_rate": 2.536421052631579e-05,
      "loss": 0.4598,
      "step": 152
    },
    {
      "epoch": 0.03991130820399113,
      "grad_norm": 1.1835687160491943,
      "learning_rate": 2.483578947368421e-05,
      "loss": 0.3732,
      "step": 153
    },
    {
      "epoch": 0.040172166427546625,
      "grad_norm": 0.5971368551254272,
      "learning_rate": 2.430736842105263e-05,
      "loss": 0.3361,
      "step": 154
    },
    {
      "epoch": 0.04043302465110213,
      "grad_norm": 0.7615634799003601,
      "learning_rate": 2.3778947368421052e-05,
      "loss": 0.317,
      "step": 155
    },
    {
      "epoch": 0.040693882874657625,
      "grad_norm": 0.589562177658081,
      "learning_rate": 2.3250526315789473e-05,
      "loss": 0.3424,
      "step": 156
    },
    {
      "epoch": 0.04095474109821312,
      "grad_norm": 0.5603517293930054,
      "learning_rate": 2.2722105263157894e-05,
      "loss": 0.3523,
      "step": 157
    },
    {
      "epoch": 0.04121559932176862,
      "grad_norm": 0.6157901883125305,
      "learning_rate": 2.2193684210526316e-05,
      "loss": 0.3667,
      "step": 158
    },
    {
      "epoch": 0.041476457545324114,
      "grad_norm": 0.5660136342048645,
      "learning_rate": 2.1665263157894737e-05,
      "loss": 0.2797,
      "step": 159
    },
    {
      "epoch": 0.04173731576887962,
      "grad_norm": 0.5905348658561707,
      "learning_rate": 2.1136842105263158e-05,
      "loss": 0.3196,
      "step": 160
    },
    {
      "epoch": 0.04199817399243511,
      "grad_norm": 0.6353060603141785,
      "learning_rate": 2.060842105263158e-05,
      "loss": 0.3449,
      "step": 161
    },
    {
      "epoch": 0.04225903221599061,
      "grad_norm": 0.6922320127487183,
      "learning_rate": 2.008e-05,
      "loss": 0.3504,
      "step": 162
    },
    {
      "epoch": 0.042519890439546106,
      "grad_norm": 0.5601292252540588,
      "learning_rate": 1.9551578947368422e-05,
      "loss": 0.3378,
      "step": 163
    },
    {
      "epoch": 0.0427807486631016,
      "grad_norm": 0.5565058588981628,
      "learning_rate": 1.9023157894736843e-05,
      "loss": 0.3541,
      "step": 164
    },
    {
      "epoch": 0.043041606886657105,
      "grad_norm": 0.5381285548210144,
      "learning_rate": 1.849473684210526e-05,
      "loss": 0.2956,
      "step": 165
    },
    {
      "epoch": 0.0433024651102126,
      "grad_norm": 0.8170627951622009,
      "learning_rate": 1.7966315789473686e-05,
      "loss": 0.3399,
      "step": 166
    },
    {
      "epoch": 0.0435633233337681,
      "grad_norm": 0.7445321083068848,
      "learning_rate": 1.7437894736842107e-05,
      "loss": 0.3516,
      "step": 167
    },
    {
      "epoch": 0.043824181557323594,
      "grad_norm": 0.6222259998321533,
      "learning_rate": 1.6909473684210525e-05,
      "loss": 0.3152,
      "step": 168
    },
    {
      "epoch": 0.04408503978087909,
      "grad_norm": 0.6484302878379822,
      "learning_rate": 1.638105263157895e-05,
      "loss": 0.3919,
      "step": 169
    },
    {
      "epoch": 0.04434589800443459,
      "grad_norm": 0.6885114908218384,
      "learning_rate": 1.5852631578947368e-05,
      "loss": 0.3483,
      "step": 170
    },
    {
      "epoch": 0.04460675622799009,
      "grad_norm": 0.6635403633117676,
      "learning_rate": 1.532421052631579e-05,
      "loss": 0.2702,
      "step": 171
    },
    {
      "epoch": 0.044867614451545586,
      "grad_norm": 0.7835387587547302,
      "learning_rate": 1.4795789473684209e-05,
      "loss": 0.3227,
      "step": 172
    },
    {
      "epoch": 0.04512847267510108,
      "grad_norm": 0.6229288578033447,
      "learning_rate": 1.4267368421052632e-05,
      "loss": 0.288,
      "step": 173
    },
    {
      "epoch": 0.04538933089865658,
      "grad_norm": 0.7214296460151672,
      "learning_rate": 1.3738947368421053e-05,
      "loss": 0.358,
      "step": 174
    },
    {
      "epoch": 0.045650189122212075,
      "grad_norm": 0.6343803405761719,
      "learning_rate": 1.3210526315789473e-05,
      "loss": 0.1716,
      "step": 175
    },
    {
      "epoch": 0.04591104734576758,
      "grad_norm": 0.470270037651062,
      "learning_rate": 1.2682105263157896e-05,
      "loss": 0.0489,
      "step": 176
    },
    {
      "epoch": 0.046171905569323074,
      "grad_norm": 0.3558203876018524,
      "learning_rate": 1.2153684210526315e-05,
      "loss": 0.0174,
      "step": 177
    },
    {
      "epoch": 0.04643276379287857,
      "grad_norm": 0.4911562502384186,
      "learning_rate": 1.1625263157894737e-05,
      "loss": 0.0214,
      "step": 178
    },
    {
      "epoch": 0.046693622016434067,
      "grad_norm": 0.5593497157096863,
      "learning_rate": 1.1096842105263158e-05,
      "loss": 0.022,
      "step": 179
    },
    {
      "epoch": 0.04695448023998956,
      "grad_norm": 0.4090302288532257,
      "learning_rate": 1.0568421052631579e-05,
      "loss": 0.0197,
      "step": 180
    },
    {
      "epoch": 0.047215338463545066,
      "grad_norm": 0.44141674041748047,
      "learning_rate": 1.004e-05,
      "loss": 0.013,
      "step": 181
    },
    {
      "epoch": 0.04747619668710056,
      "grad_norm": 0.38881024718284607,
      "learning_rate": 9.511578947368422e-06,
      "loss": 0.0129,
      "step": 182
    },
    {
      "epoch": 0.04773705491065606,
      "grad_norm": 0.3517584502696991,
      "learning_rate": 8.983157894736843e-06,
      "loss": 0.013,
      "step": 183
    },
    {
      "epoch": 0.047997913134211555,
      "grad_norm": 0.30295777320861816,
      "learning_rate": 8.454736842105263e-06,
      "loss": 0.0068,
      "step": 184
    },
    {
      "epoch": 0.04825877135776705,
      "grad_norm": 0.22888092696666718,
      "learning_rate": 7.926315789473684e-06,
      "loss": 0.0032,
      "step": 185
    },
    {
      "epoch": 0.048519629581322554,
      "grad_norm": 0.24423319101333618,
      "learning_rate": 7.397894736842104e-06,
      "loss": 0.0032,
      "step": 186
    },
    {
      "epoch": 0.04878048780487805,
      "grad_norm": 0.5701403021812439,
      "learning_rate": 6.8694736842105265e-06,
      "loss": 0.004,
      "step": 187
    },
    {
      "epoch": 0.04904134602843355,
      "grad_norm": 0.7065002918243408,
      "learning_rate": 6.341052631578948e-06,
      "loss": 0.005,
      "step": 188
    },
    {
      "epoch": 0.04930220425198904,
      "grad_norm": 0.642783522605896,
      "learning_rate": 5.812631578947368e-06,
      "loss": 0.004,
      "step": 189
    },
    {
      "epoch": 0.04956306247554454,
      "grad_norm": 0.04088672995567322,
      "learning_rate": 5.2842105263157896e-06,
      "loss": 0.0003,
      "step": 190
    },
    {
      "epoch": 0.04982392069910004,
      "grad_norm": 0.6026747822761536,
      "learning_rate": 4.755789473684211e-06,
      "loss": 0.0056,
      "step": 191
    },
    {
      "epoch": 0.05008477892265554,
      "grad_norm": 0.15268850326538086,
      "learning_rate": 4.227368421052631e-06,
      "loss": 0.0015,
      "step": 192
    },
    {
      "epoch": 0.050345637146211035,
      "grad_norm": 0.20319561660289764,
      "learning_rate": 3.698947368421052e-06,
      "loss": 0.0008,
      "step": 193
    },
    {
      "epoch": 0.05060649536976653,
      "grad_norm": 0.938482403755188,
      "learning_rate": 3.170526315789474e-06,
      "loss": 0.0017,
      "step": 194
    },
    {
      "epoch": 0.05086735359332203,
      "grad_norm": 0.10921061784029007,
      "learning_rate": 2.6421052631578948e-06,
      "loss": 0.0004,
      "step": 195
    },
    {
      "epoch": 0.051128211816877524,
      "grad_norm": 0.25236430764198303,
      "learning_rate": 2.1136842105263157e-06,
      "loss": 0.002,
      "step": 196
    },
    {
      "epoch": 0.05138907004043303,
      "grad_norm": 0.3114216923713684,
      "learning_rate": 1.585263157894737e-06,
      "loss": 0.0012,
      "step": 197
    },
    {
      "epoch": 0.05164992826398852,
      "grad_norm": 0.4255119264125824,
      "learning_rate": 1.0568421052631578e-06,
      "loss": 0.0071,
      "step": 198
    },
    {
      "epoch": 0.05191078648754402,
      "grad_norm": 0.18521125614643097,
      "learning_rate": 5.284210526315789e-07,
      "loss": 0.0005,
      "step": 199
    },
    {
      "epoch": 0.052171644711099516,
      "grad_norm": 2.783665180206299,
      "learning_rate": 0.0,
      "loss": 0.0279,
      "step": 200
    },
    {
      "epoch": 0.052171644711099516,
      "eval_loss": 0.08230920881032944,
      "eval_runtime": 357.6332,
      "eval_samples_per_second": 4.513,
      "eval_steps_per_second": 1.13,
      "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": 1.3057871528853504e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}