{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 20,
  "global_step": 348,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0,
      "eval_accuracy": 0.7376237623762376,
      "eval_f1": 0.11666666666666667,
      "eval_loss": 0.595770537853241,
      "eval_precision": 0.5,
      "eval_recall": 0.0660377358490566,
      "eval_runtime": 16.1893,
      "eval_samples_per_second": 6.548,
      "eval_steps_per_second": 0.247,
      "step": 0
    },
    {
      "epoch": 0.0028735632183908046,
      "grad_norm": 1.7269402742385864,
      "learning_rate": 5.714285714285715e-07,
      "loss": 0.7755,
      "step": 1
    },
    {
      "epoch": 0.005747126436781609,
      "grad_norm": 1.7528263330459595,
      "learning_rate": 1.142857142857143e-06,
      "loss": 0.7738,
      "step": 2
    },
    {
      "epoch": 0.008620689655172414,
      "grad_norm": 1.903218150138855,
      "learning_rate": 1.7142857142857145e-06,
      "loss": 0.7635,
      "step": 3
    },
    {
      "epoch": 0.011494252873563218,
      "grad_norm": 2.011042833328247,
      "learning_rate": 2.285714285714286e-06,
      "loss": 0.7872,
      "step": 4
    },
    {
      "epoch": 0.014367816091954023,
      "grad_norm": 1.8846079111099243,
      "learning_rate": 2.8571428571428573e-06,
      "loss": 0.7811,
      "step": 5
    },
    {
      "epoch": 0.017241379310344827,
      "grad_norm": 1.7371026277542114,
      "learning_rate": 3.428571428571429e-06,
      "loss": 0.7517,
      "step": 6
    },
    {
      "epoch": 0.020114942528735632,
      "grad_norm": 1.8430122137069702,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.7732,
      "step": 7
    },
    {
      "epoch": 0.022988505747126436,
      "grad_norm": 1.683440923690796,
      "learning_rate": 4.571428571428572e-06,
      "loss": 0.738,
      "step": 8
    },
    {
      "epoch": 0.02586206896551724,
      "grad_norm": 1.8083072900772095,
      "learning_rate": 5.142857142857142e-06,
      "loss": 0.739,
      "step": 9
    },
    {
      "epoch": 0.028735632183908046,
      "grad_norm": 1.8509185314178467,
      "learning_rate": 5.7142857142857145e-06,
      "loss": 0.7536,
      "step": 10
    },
    {
      "epoch": 0.031609195402298854,
      "grad_norm": 1.948458194732666,
      "learning_rate": 6.285714285714286e-06,
      "loss": 0.7414,
      "step": 11
    },
    {
      "epoch": 0.034482758620689655,
      "grad_norm": 1.6882693767547607,
      "learning_rate": 6.857142857142858e-06,
      "loss": 0.7356,
      "step": 12
    },
    {
      "epoch": 0.03735632183908046,
      "grad_norm": 1.7302439212799072,
      "learning_rate": 7.428571428571429e-06,
      "loss": 0.727,
      "step": 13
    },
    {
      "epoch": 0.040229885057471264,
      "grad_norm": 1.6159391403198242,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.7069,
      "step": 14
    },
    {
      "epoch": 0.04310344827586207,
      "grad_norm": 1.63016939163208,
      "learning_rate": 8.571428571428571e-06,
      "loss": 0.6835,
      "step": 15
    },
    {
      "epoch": 0.04597701149425287,
      "grad_norm": 1.506463646888733,
      "learning_rate": 9.142857142857144e-06,
      "loss": 0.7347,
      "step": 16
    },
    {
      "epoch": 0.04885057471264368,
      "grad_norm": 1.412893295288086,
      "learning_rate": 9.714285714285715e-06,
      "loss": 0.702,
      "step": 17
    },
    {
      "epoch": 0.05172413793103448,
      "grad_norm": 1.5896869897842407,
      "learning_rate": 1.0285714285714285e-05,
      "loss": 0.6948,
      "step": 18
    },
    {
      "epoch": 0.05459770114942529,
      "grad_norm": 1.4004888534545898,
      "learning_rate": 1.0857142857142858e-05,
      "loss": 0.6604,
      "step": 19
    },
    {
      "epoch": 0.05747126436781609,
      "grad_norm": 1.3640953302383423,
      "learning_rate": 1.1428571428571429e-05,
      "loss": 0.6819,
      "step": 20
    },
    {
      "epoch": 0.05747126436781609,
      "eval_accuracy": 0.745049504950495,
      "eval_f1": 0.13445378151260504,
      "eval_loss": 0.569399356842041,
      "eval_precision": 0.6153846153846154,
      "eval_recall": 0.07547169811320754,
      "eval_runtime": 17.731,
      "eval_samples_per_second": 5.978,
      "eval_steps_per_second": 0.226,
      "step": 20
    },
    {
      "epoch": 0.0603448275862069,
      "grad_norm": 1.487462043762207,
      "learning_rate": 1.2e-05,
      "loss": 0.6763,
      "step": 21
    },
    {
      "epoch": 0.06321839080459771,
      "grad_norm": 1.291784405708313,
      "learning_rate": 1.2571428571428572e-05,
      "loss": 0.6705,
      "step": 22
    },
    {
      "epoch": 0.06609195402298851,
      "grad_norm": 1.1527869701385498,
      "learning_rate": 1.3142857142857145e-05,
      "loss": 0.6183,
      "step": 23
    },
    {
      "epoch": 0.06896551724137931,
      "grad_norm": 1.1266508102416992,
      "learning_rate": 1.3714285714285716e-05,
      "loss": 0.609,
      "step": 24
    },
    {
      "epoch": 0.07183908045977011,
      "grad_norm": 1.2343026399612427,
      "learning_rate": 1.4285714285714287e-05,
      "loss": 0.619,
      "step": 25
    },
    {
      "epoch": 0.07471264367816093,
      "grad_norm": 1.1558549404144287,
      "learning_rate": 1.4857142857142858e-05,
      "loss": 0.6031,
      "step": 26
    },
    {
      "epoch": 0.07758620689655173,
      "grad_norm": 1.0646226406097412,
      "learning_rate": 1.542857142857143e-05,
      "loss": 0.584,
      "step": 27
    },
    {
      "epoch": 0.08045977011494253,
      "grad_norm": 0.975098729133606,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.5594,
      "step": 28
    },
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 1.0657261610031128,
      "learning_rate": 1.6571428571428574e-05,
      "loss": 0.567,
      "step": 29
    },
    {
      "epoch": 0.08620689655172414,
      "grad_norm": 0.872745156288147,
      "learning_rate": 1.7142857142857142e-05,
      "loss": 0.5435,
      "step": 30
    },
    {
      "epoch": 0.08908045977011494,
      "grad_norm": 0.8025686144828796,
      "learning_rate": 1.7714285714285717e-05,
      "loss": 0.537,
      "step": 31
    },
    {
      "epoch": 0.09195402298850575,
      "grad_norm": 0.8637747764587402,
      "learning_rate": 1.8285714285714288e-05,
      "loss": 0.541,
      "step": 32
    },
    {
      "epoch": 0.09482758620689655,
      "grad_norm": 1.0375990867614746,
      "learning_rate": 1.885714285714286e-05,
      "loss": 0.5199,
      "step": 33
    },
    {
      "epoch": 0.09770114942528736,
      "grad_norm": 0.9441830515861511,
      "learning_rate": 1.942857142857143e-05,
      "loss": 0.5388,
      "step": 34
    },
    {
      "epoch": 0.10057471264367816,
      "grad_norm": 0.8663190603256226,
      "learning_rate": 2e-05,
      "loss": 0.5268,
      "step": 35
    },
    {
      "epoch": 0.10344827586206896,
      "grad_norm": 0.9546361565589905,
      "learning_rate": 1.9999496293646753e-05,
      "loss": 0.5381,
      "step": 36
    },
    {
      "epoch": 0.10632183908045977,
      "grad_norm": 0.7847493290901184,
      "learning_rate": 1.999798522533102e-05,
      "loss": 0.5131,
      "step": 37
    },
    {
      "epoch": 0.10919540229885058,
      "grad_norm": 0.8559457659721375,
      "learning_rate": 1.9995466947279753e-05,
      "loss": 0.4771,
      "step": 38
    },
    {
      "epoch": 0.11206896551724138,
      "grad_norm": 0.9539210796356201,
      "learning_rate": 1.9991941713187477e-05,
      "loss": 0.4833,
      "step": 39
    },
    {
      "epoch": 0.11494252873563218,
      "grad_norm": 1.2878869771957397,
      "learning_rate": 1.9987409878190752e-05,
      "loss": 0.4789,
      "step": 40
    },
    {
      "epoch": 0.11494252873563218,
      "eval_accuracy": 0.754950495049505,
      "eval_f1": 0.5857740585774058,
      "eval_loss": 0.47763171792030334,
      "eval_precision": 0.5263157894736842,
      "eval_recall": 0.660377358490566,
      "eval_runtime": 17.3231,
      "eval_samples_per_second": 6.119,
      "eval_steps_per_second": 0.231,
      "step": 40
    },
    {
      "epoch": 0.11781609195402298,
      "grad_norm": 1.0973199605941772,
      "learning_rate": 1.99818718988324e-05,
      "loss": 0.4739,
      "step": 41
    },
    {
      "epoch": 0.1206896551724138,
      "grad_norm": 0.8685905337333679,
      "learning_rate": 1.9975328333015497e-05,
      "loss": 0.4639,
      "step": 42
    },
    {
      "epoch": 0.1235632183908046,
      "grad_norm": 0.7956727147102356,
      "learning_rate": 1.9967779839947172e-05,
      "loss": 0.475,
      "step": 43
    },
    {
      "epoch": 0.12643678160919541,
      "grad_norm": 0.9125760197639465,
      "learning_rate": 1.9959227180072216e-05,
      "loss": 0.4166,
      "step": 44
    },
    {
      "epoch": 0.12931034482758622,
      "grad_norm": 0.8798947930335999,
      "learning_rate": 1.9949671214996448e-05,
      "loss": 0.4689,
      "step": 45
    },
    {
      "epoch": 0.13218390804597702,
      "grad_norm": 0.7233872413635254,
      "learning_rate": 1.993911290739993e-05,
      "loss": 0.4416,
      "step": 46
    },
    {
      "epoch": 0.13505747126436782,
      "grad_norm": 0.7250576615333557,
      "learning_rate": 1.992755332093999e-05,
      "loss": 0.3968,
      "step": 47
    },
    {
      "epoch": 0.13793103448275862,
      "grad_norm": 1.153190016746521,
      "learning_rate": 1.9914993620144055e-05,
      "loss": 0.4316,
      "step": 48
    },
    {
      "epoch": 0.14080459770114942,
      "grad_norm": 0.8170616626739502,
      "learning_rate": 1.990143507029234e-05,
      "loss": 0.4398,
      "step": 49
    },
    {
      "epoch": 0.14367816091954022,
      "grad_norm": 0.8207669854164124,
      "learning_rate": 1.9886879037290385e-05,
      "loss": 0.4042,
      "step": 50
    },
    {
      "epoch": 0.14655172413793102,
      "grad_norm": 0.7794085144996643,
      "learning_rate": 1.9871326987531453e-05,
      "loss": 0.3656,
      "step": 51
    },
    {
      "epoch": 0.14942528735632185,
      "grad_norm": 0.8606981635093689,
      "learning_rate": 1.98547804877488e-05,
      "loss": 0.3982,
      "step": 52
    },
    {
      "epoch": 0.15229885057471265,
      "grad_norm": 0.8829456567764282,
      "learning_rate": 1.983724120485783e-05,
      "loss": 0.4397,
      "step": 53
    },
    {
      "epoch": 0.15517241379310345,
      "grad_norm": 0.6965311765670776,
      "learning_rate": 1.9818710905788195e-05,
      "loss": 0.3995,
      "step": 54
    },
    {
      "epoch": 0.15804597701149425,
      "grad_norm": 1.190281867980957,
      "learning_rate": 1.9799191457305767e-05,
      "loss": 0.412,
      "step": 55
    },
    {
      "epoch": 0.16091954022988506,
      "grad_norm": 1.1659263372421265,
      "learning_rate": 1.977868482582459e-05,
      "loss": 0.3629,
      "step": 56
    },
    {
      "epoch": 0.16379310344827586,
      "grad_norm": 0.9981995820999146,
      "learning_rate": 1.9757193077208776e-05,
      "loss": 0.4309,
      "step": 57
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 0.9343249201774597,
      "learning_rate": 1.9734718376564386e-05,
      "loss": 0.3732,
      "step": 58
    },
    {
      "epoch": 0.16954022988505746,
      "grad_norm": 1.1614587306976318,
      "learning_rate": 1.9711262988021322e-05,
      "loss": 0.4035,
      "step": 59
    },
    {
      "epoch": 0.1724137931034483,
      "grad_norm": 1.0494896173477173,
      "learning_rate": 1.968682927450523e-05,
      "loss": 0.4108,
      "step": 60
    },
    {
      "epoch": 0.1724137931034483,
      "eval_accuracy": 0.8044554455445545,
      "eval_f1": 0.6255924170616114,
      "eval_loss": 0.40430542826652527,
      "eval_precision": 0.6285714285714286,
      "eval_recall": 0.6226415094339622,
      "eval_runtime": 17.0915,
      "eval_samples_per_second": 6.202,
      "eval_steps_per_second": 0.234,
      "step": 60
    },
    {
      "epoch": 0.1752873563218391,
      "grad_norm": 0.9192970991134644,
      "learning_rate": 1.9661419697499455e-05,
      "loss": 0.3989,
      "step": 61
    },
    {
      "epoch": 0.1781609195402299,
      "grad_norm": 0.999806821346283,
      "learning_rate": 1.9635036816797072e-05,
      "loss": 0.4099,
      "step": 62
    },
    {
      "epoch": 0.1810344827586207,
      "grad_norm": 1.073845624923706,
      "learning_rate": 1.960768329024301e-05,
      "loss": 0.3862,
      "step": 63
    },
    {
      "epoch": 0.1839080459770115,
      "grad_norm": 1.1665489673614502,
      "learning_rate": 1.957936187346628e-05,
      "loss": 0.3551,
      "step": 64
    },
    {
      "epoch": 0.1867816091954023,
      "grad_norm": 1.0729217529296875,
      "learning_rate": 1.955007541960241e-05,
      "loss": 0.4163,
      "step": 65
    },
    {
      "epoch": 0.1896551724137931,
      "grad_norm": 1.194051742553711,
      "learning_rate": 1.9519826879005964e-05,
      "loss": 0.4146,
      "step": 66
    },
    {
      "epoch": 0.1925287356321839,
      "grad_norm": 1.5440024137496948,
      "learning_rate": 1.948861929895336e-05,
      "loss": 0.4091,
      "step": 67
    },
    {
      "epoch": 0.19540229885057472,
      "grad_norm": 1.1414806842803955,
      "learning_rate": 1.945645582333587e-05,
      "loss": 0.3836,
      "step": 68
    },
    {
      "epoch": 0.19827586206896552,
      "grad_norm": 1.4426944255828857,
      "learning_rate": 1.9423339692342885e-05,
      "loss": 0.3825,
      "step": 69
    },
    {
      "epoch": 0.20114942528735633,
      "grad_norm": 1.102241039276123,
      "learning_rate": 1.9389274242135528e-05,
      "loss": 0.355,
      "step": 70
    },
    {
      "epoch": 0.20402298850574713,
      "grad_norm": 1.8680758476257324,
      "learning_rate": 1.9354262904510544e-05,
      "loss": 0.407,
      "step": 71
    },
    {
      "epoch": 0.20689655172413793,
      "grad_norm": 1.2773621082305908,
      "learning_rate": 1.9318309206554567e-05,
      "loss": 0.35,
      "step": 72
    },
    {
      "epoch": 0.20977011494252873,
      "grad_norm": 1.063806414604187,
      "learning_rate": 1.9281416770288806e-05,
      "loss": 0.3602,
      "step": 73
    },
    {
      "epoch": 0.21264367816091953,
      "grad_norm": 1.1581475734710693,
      "learning_rate": 1.924358931230418e-05,
      "loss": 0.345,
      "step": 74
    },
    {
      "epoch": 0.21551724137931033,
      "grad_norm": 1.524601697921753,
      "learning_rate": 1.920483064338687e-05,
      "loss": 0.3571,
      "step": 75
    },
    {
      "epoch": 0.21839080459770116,
      "grad_norm": 1.7578339576721191,
      "learning_rate": 1.9165144668134426e-05,
      "loss": 0.3739,
      "step": 76
    },
    {
      "epoch": 0.22126436781609196,
      "grad_norm": 2.7177462577819824,
      "learning_rate": 1.9124535384562423e-05,
      "loss": 0.3796,
      "step": 77
    },
    {
      "epoch": 0.22413793103448276,
      "grad_norm": 2.676715850830078,
      "learning_rate": 1.9083006883701688e-05,
      "loss": 0.3738,
      "step": 78
    },
    {
      "epoch": 0.22701149425287356,
      "grad_norm": 1.5852210521697998,
      "learning_rate": 1.904056334918617e-05,
      "loss": 0.3082,
      "step": 79
    },
    {
      "epoch": 0.22988505747126436,
      "grad_norm": 1.1979814767837524,
      "learning_rate": 1.8997209056831462e-05,
      "loss": 0.3486,
      "step": 80
    },
    {
      "epoch": 0.22988505747126436,
      "eval_accuracy": 0.8366336633663366,
      "eval_f1": 0.6826923076923077,
      "eval_loss": 0.37516123056411743,
      "eval_precision": 0.696078431372549,
      "eval_recall": 0.6698113207547169,
      "eval_runtime": 16.3429,
      "eval_samples_per_second": 6.486,
      "eval_steps_per_second": 0.245,
      "step": 80
    },
    {
      "epoch": 0.23275862068965517,
      "grad_norm": 1.432535171508789,
      "learning_rate": 1.8952948374204066e-05,
      "loss": 0.4083,
      "step": 81
    },
    {
      "epoch": 0.23563218390804597,
      "grad_norm": 1.1334880590438843,
      "learning_rate": 1.8907785760181392e-05,
      "loss": 0.3422,
      "step": 82
    },
    {
      "epoch": 0.23850574712643677,
      "grad_norm": 1.8673022985458374,
      "learning_rate": 1.8861725764502557e-05,
      "loss": 0.3871,
      "step": 83
    },
    {
      "epoch": 0.2413793103448276,
      "grad_norm": 1.3424856662750244,
      "learning_rate": 1.881477302731006e-05,
      "loss": 0.3595,
      "step": 84
    },
    {
      "epoch": 0.2442528735632184,
      "grad_norm": 1.7336989641189575,
      "learning_rate": 1.87669322786823e-05,
      "loss": 0.3578,
      "step": 85
    },
    {
      "epoch": 0.2471264367816092,
      "grad_norm": 1.203000545501709,
      "learning_rate": 1.8718208338157082e-05,
      "loss": 0.3601,
      "step": 86
    },
    {
      "epoch": 0.25,
      "grad_norm": 1.185094952583313,
      "learning_rate": 1.866860611424609e-05,
      "loss": 0.3307,
      "step": 87
    },
    {
      "epoch": 0.25287356321839083,
      "grad_norm": 2.083695888519287,
      "learning_rate": 1.8618130603940386e-05,
      "loss": 0.3123,
      "step": 88
    },
    {
      "epoch": 0.2557471264367816,
      "grad_norm": 1.6941533088684082,
      "learning_rate": 1.856678689220701e-05,
      "loss": 0.3294,
      "step": 89
    },
    {
      "epoch": 0.25862068965517243,
      "grad_norm": 2.76645565032959,
      "learning_rate": 1.851458015147673e-05,
      "loss": 0.3773,
      "step": 90
    },
    {
      "epoch": 0.2614942528735632,
      "grad_norm": 1.9406121969223022,
      "learning_rate": 1.846151564112294e-05,
      "loss": 0.309,
      "step": 91
    },
    {
      "epoch": 0.26436781609195403,
      "grad_norm": 1.4476113319396973,
      "learning_rate": 1.840759870693184e-05,
      "loss": 0.3724,
      "step": 92
    },
    {
      "epoch": 0.2672413793103448,
      "grad_norm": 1.4683369398117065,
      "learning_rate": 1.8352834780563888e-05,
      "loss": 0.3712,
      "step": 93
    },
    {
      "epoch": 0.27011494252873564,
      "grad_norm": 1.5984596014022827,
      "learning_rate": 1.8297229379006614e-05,
      "loss": 0.277,
      "step": 94
    },
    {
      "epoch": 0.27298850574712646,
      "grad_norm": 1.4368345737457275,
      "learning_rate": 1.8240788104018824e-05,
      "loss": 0.337,
      "step": 95
    },
    {
      "epoch": 0.27586206896551724,
      "grad_norm": 3.34250545501709,
      "learning_rate": 1.8183516641566278e-05,
      "loss": 0.315,
      "step": 96
    },
    {
      "epoch": 0.27873563218390807,
      "grad_norm": 1.4906728267669678,
      "learning_rate": 1.8125420761248878e-05,
      "loss": 0.3778,
      "step": 97
    },
    {
      "epoch": 0.28160919540229884,
      "grad_norm": 1.4306960105895996,
      "learning_rate": 1.806650631571943e-05,
      "loss": 0.354,
      "step": 98
    },
    {
      "epoch": 0.28448275862068967,
      "grad_norm": 1.657739281654358,
      "learning_rate": 1.8006779240094024e-05,
      "loss": 0.2976,
      "step": 99
    },
    {
      "epoch": 0.28735632183908044,
      "grad_norm": 1.2605433464050293,
      "learning_rate": 1.7946245551354156e-05,
      "loss": 0.2936,
      "step": 100
    },
    {
      "epoch": 0.28735632183908044,
      "eval_accuracy": 0.8465346534653465,
      "eval_f1": 0.7047619047619048,
      "eval_loss": 0.36498525738716125,
      "eval_precision": 0.7115384615384616,
      "eval_recall": 0.6981132075471698,
      "eval_runtime": 16.9232,
      "eval_samples_per_second": 6.264,
      "eval_steps_per_second": 0.236,
      "step": 100
    },
    {
      "epoch": 0.29022988505747127,
      "grad_norm": 1.783969759941101,
      "learning_rate": 1.7884911347740556e-05,
      "loss": 0.3322,
      "step": 101
    },
    {
      "epoch": 0.29310344827586204,
      "grad_norm": 1.9220962524414062,
      "learning_rate": 1.782278280813882e-05,
      "loss": 0.3557,
      "step": 102
    },
    {
      "epoch": 0.2959770114942529,
      "grad_norm": 1.7961769104003906,
      "learning_rate": 1.775986619145697e-05,
      "loss": 0.3441,
      "step": 103
    },
    {
      "epoch": 0.2988505747126437,
      "grad_norm": 1.325335144996643,
      "learning_rate": 1.7696167835994927e-05,
      "loss": 0.2601,
      "step": 104
    },
    {
      "epoch": 0.3017241379310345,
      "grad_norm": 2.1230311393737793,
      "learning_rate": 1.7631694158805945e-05,
      "loss": 0.2815,
      "step": 105
    },
    {
      "epoch": 0.3045977011494253,
      "grad_norm": 1.645026445388794,
      "learning_rate": 1.7566451655050197e-05,
      "loss": 0.2929,
      "step": 106
    },
    {
      "epoch": 0.3074712643678161,
      "grad_norm": 1.973618745803833,
      "learning_rate": 1.7500446897340408e-05,
      "loss": 0.3183,
      "step": 107
    },
    {
      "epoch": 0.3103448275862069,
      "grad_norm": 2.0839297771453857,
      "learning_rate": 1.7433686535079736e-05,
      "loss": 0.3313,
      "step": 108
    },
    {
      "epoch": 0.3132183908045977,
      "grad_norm": 1.5320701599121094,
      "learning_rate": 1.736617729379191e-05,
      "loss": 0.3313,
      "step": 109
    },
    {
      "epoch": 0.3160919540229885,
      "grad_norm": 1.7821077108383179,
      "learning_rate": 1.7297925974443675e-05,
      "loss": 0.2894,
      "step": 110
    },
    {
      "epoch": 0.31896551724137934,
      "grad_norm": 4.908563613891602,
      "learning_rate": 1.7228939452759666e-05,
      "loss": 0.3629,
      "step": 111
    },
    {
      "epoch": 0.3218390804597701,
      "grad_norm": 1.7529722452163696,
      "learning_rate": 1.7159224678529734e-05,
      "loss": 0.2838,
      "step": 112
    },
    {
      "epoch": 0.32471264367816094,
      "grad_norm": 1.8097668886184692,
      "learning_rate": 1.7088788674908817e-05,
      "loss": 0.3322,
      "step": 113
    },
    {
      "epoch": 0.3275862068965517,
      "grad_norm": 1.8676601648330688,
      "learning_rate": 1.7017638537709426e-05,
      "loss": 0.3174,
      "step": 114
    },
    {
      "epoch": 0.33045977011494254,
      "grad_norm": 2.841519594192505,
      "learning_rate": 1.6945781434686783e-05,
      "loss": 0.3643,
      "step": 115
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 2.4998703002929688,
      "learning_rate": 1.6873224604816753e-05,
      "loss": 0.3433,
      "step": 116
    },
    {
      "epoch": 0.33620689655172414,
      "grad_norm": 3.173900842666626,
      "learning_rate": 1.679997535756657e-05,
      "loss": 0.2841,
      "step": 117
    },
    {
      "epoch": 0.3390804597701149,
      "grad_norm": 1.547804594039917,
      "learning_rate": 1.672604107215848e-05,
      "loss": 0.271,
      "step": 118
    },
    {
      "epoch": 0.34195402298850575,
      "grad_norm": 2.0458803176879883,
      "learning_rate": 1.6651429196826337e-05,
      "loss": 0.3898,
      "step": 119
    },
    {
      "epoch": 0.3448275862068966,
      "grad_norm": 2.486851930618286,
      "learning_rate": 1.6576147248065268e-05,
      "loss": 0.3788,
      "step": 120
    },
    {
      "epoch": 0.3448275862068966,
      "eval_accuracy": 0.8465346534653465,
      "eval_f1": 0.7232142857142857,
      "eval_loss": 0.3579418361186981,
      "eval_precision": 0.6864406779661016,
      "eval_recall": 0.7641509433962265,
      "eval_runtime": 16.6895,
      "eval_samples_per_second": 6.351,
      "eval_steps_per_second": 0.24,
      "step": 120
    },
    {
      "epoch": 0.34770114942528735,
      "grad_norm": 3.0074172019958496,
      "learning_rate": 1.6500202809874446e-05,
      "loss": 0.3359,
      "step": 121
    },
    {
      "epoch": 0.3505747126436782,
      "grad_norm": 2.094373941421509,
      "learning_rate": 1.6423603532993074e-05,
      "loss": 0.3083,
      "step": 122
    },
    {
      "epoch": 0.35344827586206895,
      "grad_norm": 2.355056047439575,
      "learning_rate": 1.634635713412964e-05,
      "loss": 0.3232,
      "step": 123
    },
    {
      "epoch": 0.3563218390804598,
      "grad_norm": 1.80659019947052,
      "learning_rate": 1.626847139518452e-05,
      "loss": 0.354,
      "step": 124
    },
    {
      "epoch": 0.35919540229885055,
      "grad_norm": 2.1440465450286865,
      "learning_rate": 1.618995416246601e-05,
      "loss": 0.3586,
      "step": 125
    },
    {
      "epoch": 0.3620689655172414,
      "grad_norm": 2.291161060333252,
      "learning_rate": 1.6110813345899914e-05,
      "loss": 0.3136,
      "step": 126
    },
    {
      "epoch": 0.3649425287356322,
      "grad_norm": 2.135361433029175,
      "learning_rate": 1.6031056918232642e-05,
      "loss": 0.2973,
      "step": 127
    },
    {
      "epoch": 0.367816091954023,
      "grad_norm": 2.186067819595337,
      "learning_rate": 1.595069291422807e-05,
      "loss": 0.2909,
      "step": 128
    },
    {
      "epoch": 0.3706896551724138,
      "grad_norm": 1.5670075416564941,
      "learning_rate": 1.586972942985807e-05,
      "loss": 0.2791,
      "step": 129
    },
    {
      "epoch": 0.3735632183908046,
      "grad_norm": 1.6675617694854736,
      "learning_rate": 1.5788174621486936e-05,
      "loss": 0.2841,
      "step": 130
    },
    {
      "epoch": 0.3764367816091954,
      "grad_norm": 1.3991848230361938,
      "learning_rate": 1.570603670504969e-05,
      "loss": 0.2608,
      "step": 131
    },
    {
      "epoch": 0.3793103448275862,
      "grad_norm": 1.75133216381073,
      "learning_rate": 1.5623323955224404e-05,
      "loss": 0.3213,
      "step": 132
    },
    {
      "epoch": 0.382183908045977,
      "grad_norm": 1.7024160623550415,
      "learning_rate": 1.5540044704598588e-05,
      "loss": 0.2968,
      "step": 133
    },
    {
      "epoch": 0.3850574712643678,
      "grad_norm": 1.8097691535949707,
      "learning_rate": 1.5456207342829777e-05,
      "loss": 0.3661,
      "step": 134
    },
    {
      "epoch": 0.3879310344827586,
      "grad_norm": 1.6681524515151978,
      "learning_rate": 1.5371820315800316e-05,
      "loss": 0.3056,
      "step": 135
    },
    {
      "epoch": 0.39080459770114945,
      "grad_norm": 1.9756441116333008,
      "learning_rate": 1.5286892124766546e-05,
      "loss": 0.2813,
      "step": 136
    },
    {
      "epoch": 0.3936781609195402,
      "grad_norm": 1.3441747426986694,
      "learning_rate": 1.5201431325502332e-05,
      "loss": 0.3127,
      "step": 137
    },
    {
      "epoch": 0.39655172413793105,
      "grad_norm": 2.295041561126709,
      "learning_rate": 1.5115446527437193e-05,
      "loss": 0.3027,
      "step": 138
    },
    {
      "epoch": 0.3994252873563218,
      "grad_norm": 1.4709759950637817,
      "learning_rate": 1.5028946392788934e-05,
      "loss": 0.29,
      "step": 139
    },
    {
      "epoch": 0.40229885057471265,
      "grad_norm": 2.2504360675811768,
      "learning_rate": 1.4941939635691036e-05,
      "loss": 0.3918,
      "step": 140
    },
    {
      "epoch": 0.40229885057471265,
      "eval_accuracy": 0.8564356435643564,
      "eval_f1": 0.7156862745098039,
      "eval_loss": 0.34828001260757446,
      "eval_precision": 0.7448979591836735,
      "eval_recall": 0.6886792452830188,
      "eval_runtime": 16.5108,
      "eval_samples_per_second": 6.42,
      "eval_steps_per_second": 0.242,
      "step": 140
    },
    {
      "epoch": 0.4051724137931034,
      "grad_norm": 3.2703957557678223,
      "learning_rate": 1.4854435021314766e-05,
      "loss": 0.3954,
      "step": 141
    },
    {
      "epoch": 0.40804597701149425,
      "grad_norm": 1.358782172203064,
      "learning_rate": 1.4766441364986162e-05,
      "loss": 0.2476,
      "step": 142
    },
    {
      "epoch": 0.4109195402298851,
      "grad_norm": 2.7630207538604736,
      "learning_rate": 1.467796753129797e-05,
      "loss": 0.3169,
      "step": 143
    },
    {
      "epoch": 0.41379310344827586,
      "grad_norm": 3.527498960494995,
      "learning_rate": 1.4589022433216616e-05,
      "loss": 0.3287,
      "step": 144
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 3.0622334480285645,
      "learning_rate": 1.4499615031184297e-05,
      "loss": 0.3051,
      "step": 145
    },
    {
      "epoch": 0.41954022988505746,
      "grad_norm": 2.6105074882507324,
      "learning_rate": 1.4409754332216303e-05,
      "loss": 0.345,
      "step": 146
    },
    {
      "epoch": 0.4224137931034483,
      "grad_norm": 1.8759511709213257,
      "learning_rate": 1.431944938899363e-05,
      "loss": 0.3423,
      "step": 147
    },
    {
      "epoch": 0.42528735632183906,
      "grad_norm": 2.0953996181488037,
      "learning_rate": 1.4228709298950998e-05,
      "loss": 0.2682,
      "step": 148
    },
    {
      "epoch": 0.4281609195402299,
      "grad_norm": 2.999065637588501,
      "learning_rate": 1.4137543203360382e-05,
      "loss": 0.2718,
      "step": 149
    },
    {
      "epoch": 0.43103448275862066,
      "grad_norm": 3.0114426612854004,
      "learning_rate": 1.4045960286410093e-05,
      "loss": 0.3252,
      "step": 150
    },
    {
      "epoch": 0.4339080459770115,
      "grad_norm": 1.6611913442611694,
      "learning_rate": 1.395396977427955e-05,
      "loss": 0.3173,
      "step": 151
    },
    {
      "epoch": 0.4367816091954023,
      "grad_norm": 3.4530274868011475,
      "learning_rate": 1.3861580934209832e-05,
      "loss": 0.3197,
      "step": 152
    },
    {
      "epoch": 0.4396551724137931,
      "grad_norm": 1.6431101560592651,
      "learning_rate": 1.376880307357009e-05,
      "loss": 0.2665,
      "step": 153
    },
    {
      "epoch": 0.4425287356321839,
      "grad_norm": 1.4682122468948364,
      "learning_rate": 1.3675645538919884e-05,
      "loss": 0.2553,
      "step": 154
    },
    {
      "epoch": 0.4454022988505747,
      "grad_norm": 1.7914024591445923,
      "learning_rate": 1.3582117715067628e-05,
      "loss": 0.3186,
      "step": 155
    },
    {
      "epoch": 0.4482758620689655,
      "grad_norm": 3.978621482849121,
      "learning_rate": 1.3488229024125142e-05,
      "loss": 0.3317,
      "step": 156
    },
    {
      "epoch": 0.4511494252873563,
      "grad_norm": 2.1504433155059814,
      "learning_rate": 1.3393988924558445e-05,
      "loss": 0.2656,
      "step": 157
    },
    {
      "epoch": 0.4540229885057471,
      "grad_norm": 4.017497539520264,
      "learning_rate": 1.3299406910234917e-05,
      "loss": 0.3267,
      "step": 158
    },
    {
      "epoch": 0.45689655172413796,
      "grad_norm": 2.058147668838501,
      "learning_rate": 1.3204492509466862e-05,
      "loss": 0.3041,
      "step": 159
    },
    {
      "epoch": 0.45977011494252873,
      "grad_norm": 3.0126659870147705,
      "learning_rate": 1.3109255284051615e-05,
      "loss": 0.3386,
      "step": 160
    },
    {
      "epoch": 0.45977011494252873,
      "eval_accuracy": 0.8613861386138614,
      "eval_f1": 0.7454545454545455,
      "eval_loss": 0.3409002423286438,
      "eval_precision": 0.7192982456140351,
      "eval_recall": 0.7735849056603774,
      "eval_runtime": 16.4366,
      "eval_samples_per_second": 6.449,
      "eval_steps_per_second": 0.243,
      "step": 160
    },
    {
      "epoch": 0.46264367816091956,
      "grad_norm": 1.375235915184021,
      "learning_rate": 1.3013704828308276e-05,
      "loss": 0.2718,
      "step": 161
    },
    {
      "epoch": 0.46551724137931033,
      "grad_norm": 2.28141450881958,
      "learning_rate": 1.2917850768111171e-05,
      "loss": 0.3097,
      "step": 162
    },
    {
      "epoch": 0.46839080459770116,
      "grad_norm": 2.1331875324249268,
      "learning_rate": 1.282170275992012e-05,
      "loss": 0.3447,
      "step": 163
    },
    {
      "epoch": 0.47126436781609193,
      "grad_norm": 3.9664528369903564,
      "learning_rate": 1.2725270489807637e-05,
      "loss": 0.3458,
      "step": 164
    },
    {
      "epoch": 0.47413793103448276,
      "grad_norm": 2.637589454650879,
      "learning_rate": 1.2628563672483147e-05,
      "loss": 0.3498,
      "step": 165
    },
    {
      "epoch": 0.47701149425287354,
      "grad_norm": 1.7771785259246826,
      "learning_rate": 1.2531592050314308e-05,
      "loss": 0.3353,
      "step": 166
    },
    {
      "epoch": 0.47988505747126436,
      "grad_norm": 1.6429569721221924,
      "learning_rate": 1.2434365392345553e-05,
      "loss": 0.2804,
      "step": 167
    },
    {
      "epoch": 0.4827586206896552,
      "grad_norm": 1.9945698976516724,
      "learning_rate": 1.2336893493313946e-05,
      "loss": 0.347,
      "step": 168
    },
    {
      "epoch": 0.48563218390804597,
      "grad_norm": 2.3335530757904053,
      "learning_rate": 1.223918617266245e-05,
      "loss": 0.37,
      "step": 169
    },
    {
      "epoch": 0.4885057471264368,
      "grad_norm": 1.9151017665863037,
      "learning_rate": 1.2141253273550698e-05,
      "loss": 0.3417,
      "step": 170
    },
    {
      "epoch": 0.49137931034482757,
      "grad_norm": 1.794220209121704,
      "learning_rate": 1.2043104661863386e-05,
      "loss": 0.2711,
      "step": 171
    },
    {
      "epoch": 0.4942528735632184,
      "grad_norm": 1.82223641872406,
      "learning_rate": 1.1944750225216363e-05,
      "loss": 0.2617,
      "step": 172
    },
    {
      "epoch": 0.49712643678160917,
      "grad_norm": 1.7924405336380005,
      "learning_rate": 1.1846199871960557e-05,
      "loss": 0.3443,
      "step": 173
    },
    {
      "epoch": 0.5,
      "grad_norm": 2.017181158065796,
      "learning_rate": 1.1747463530183781e-05,
      "loss": 0.3273,
      "step": 174
    },
    {
      "epoch": 0.5028735632183908,
      "grad_norm": 2.3940911293029785,
      "learning_rate": 1.1648551146710557e-05,
      "loss": 0.2886,
      "step": 175
    },
    {
      "epoch": 0.5057471264367817,
      "grad_norm": 2.536769151687622,
      "learning_rate": 1.1549472686100079e-05,
      "loss": 0.3829,
      "step": 176
    },
    {
      "epoch": 0.5086206896551724,
      "grad_norm": 2.0255250930786133,
      "learning_rate": 1.145023812964237e-05,
      "loss": 0.2845,
      "step": 177
    },
    {
      "epoch": 0.5114942528735632,
      "grad_norm": 1.8499056100845337,
      "learning_rate": 1.1350857474352734e-05,
      "loss": 0.2946,
      "step": 178
    },
    {
      "epoch": 0.514367816091954,
      "grad_norm": 1.5355702638626099,
      "learning_rate": 1.1251340731964664e-05,
      "loss": 0.2655,
      "step": 179
    },
    {
      "epoch": 0.5172413793103449,
      "grad_norm": 2.2017929553985596,
      "learning_rate": 1.1151697927921242e-05,
      "loss": 0.2864,
      "step": 180
    },
    {
      "epoch": 0.5172413793103449,
      "eval_accuracy": 0.8663366336633663,
      "eval_f1": 0.7428571428571429,
      "eval_loss": 0.3256542682647705,
      "eval_precision": 0.75,
      "eval_recall": 0.7358490566037735,
      "eval_runtime": 16.3561,
      "eval_samples_per_second": 6.481,
      "eval_steps_per_second": 0.245,
      "step": 180
    },
    {
      "epoch": 0.5201149425287356,
      "grad_norm": 3.028022527694702,
      "learning_rate": 1.1051939100365154e-05,
      "loss": 0.2546,
      "step": 181
    },
    {
      "epoch": 0.5229885057471264,
      "grad_norm": 1.8325839042663574,
      "learning_rate": 1.0952074299127451e-05,
      "loss": 0.2807,
      "step": 182
    },
    {
      "epoch": 0.5258620689655172,
      "grad_norm": 2.084076166152954,
      "learning_rate": 1.0852113584715103e-05,
      "loss": 0.2824,
      "step": 183
    },
    {
      "epoch": 0.5287356321839081,
      "grad_norm": 1.8526941537857056,
      "learning_rate": 1.0752067027297486e-05,
      "loss": 0.3213,
      "step": 184
    },
    {
      "epoch": 0.5316091954022989,
      "grad_norm": 2.2813260555267334,
      "learning_rate": 1.065194470569193e-05,
      "loss": 0.3035,
      "step": 185
    },
    {
      "epoch": 0.5344827586206896,
      "grad_norm": 1.8730769157409668,
      "learning_rate": 1.0551756706348331e-05,
      "loss": 0.3384,
      "step": 186
    },
    {
      "epoch": 0.5373563218390804,
      "grad_norm": 1.9777038097381592,
      "learning_rate": 1.0451513122333042e-05,
      "loss": 0.3276,
      "step": 187
    },
    {
      "epoch": 0.5402298850574713,
      "grad_norm": 1.998000144958496,
      "learning_rate": 1.035122405231209e-05,
      "loss": 0.2696,
      "step": 188
    },
    {
      "epoch": 0.5431034482758621,
      "grad_norm": 2.426605224609375,
      "learning_rate": 1.0250899599533833e-05,
      "loss": 0.308,
      "step": 189
    },
    {
      "epoch": 0.5459770114942529,
      "grad_norm": 2.758247137069702,
      "learning_rate": 1.0150549870811108e-05,
      "loss": 0.4087,
      "step": 190
    },
    {
      "epoch": 0.5488505747126436,
      "grad_norm": 2.1188836097717285,
      "learning_rate": 1.0050184975503104e-05,
      "loss": 0.3134,
      "step": 191
    },
    {
      "epoch": 0.5517241379310345,
      "grad_norm": 3.110748767852783,
      "learning_rate": 9.949815024496901e-06,
      "loss": 0.3494,
      "step": 192
    },
    {
      "epoch": 0.5545977011494253,
      "grad_norm": 3.41999888420105,
      "learning_rate": 9.849450129188895e-06,
      "loss": 0.2797,
      "step": 193
    },
    {
      "epoch": 0.5574712643678161,
      "grad_norm": 5.591911792755127,
      "learning_rate": 9.74910040046617e-06,
      "loss": 0.319,
      "step": 194
    },
    {
      "epoch": 0.5603448275862069,
      "grad_norm": 2.3159942626953125,
      "learning_rate": 9.648775947687914e-06,
      "loss": 0.2842,
      "step": 195
    },
    {
      "epoch": 0.5632183908045977,
      "grad_norm": 1.9389662742614746,
      "learning_rate": 9.548486877666963e-06,
      "loss": 0.299,
      "step": 196
    },
    {
      "epoch": 0.5660919540229885,
      "grad_norm": 2.335818290710449,
      "learning_rate": 9.448243293651676e-06,
      "loss": 0.2969,
      "step": 197
    },
    {
      "epoch": 0.5689655172413793,
      "grad_norm": 2.423042058944702,
      "learning_rate": 9.348055294308074e-06,
      "loss": 0.3088,
      "step": 198
    },
    {
      "epoch": 0.5718390804597702,
      "grad_norm": 1.7627313137054443,
      "learning_rate": 9.247932972702514e-06,
      "loss": 0.2935,
      "step": 199
    },
    {
      "epoch": 0.5747126436781609,
      "grad_norm": 2.063535690307617,
      "learning_rate": 9.147886415284903e-06,
      "loss": 0.2581,
      "step": 200
    },
    {
      "epoch": 0.5747126436781609,
      "eval_accuracy": 0.8663366336633663,
      "eval_f1": 0.7476635514018691,
      "eval_loss": 0.32225465774536133,
      "eval_precision": 0.7407407407407407,
      "eval_recall": 0.7547169811320755,
      "eval_runtime": 16.3493,
      "eval_samples_per_second": 6.483,
      "eval_steps_per_second": 0.245,
      "step": 200
    },
    {
      "epoch": 0.5775862068965517,
      "grad_norm": 2.6798720359802246,
      "learning_rate": 9.047925700872552e-06,
      "loss": 0.3089,
      "step": 201
    },
    {
      "epoch": 0.5804597701149425,
      "grad_norm": 1.8285130262374878,
      "learning_rate": 8.948060899634846e-06,
      "loss": 0.2951,
      "step": 202
    },
    {
      "epoch": 0.5833333333333334,
      "grad_norm": 1.8588842153549194,
      "learning_rate": 8.848302072078762e-06,
      "loss": 0.2872,
      "step": 203
    },
    {
      "epoch": 0.5862068965517241,
      "grad_norm": 1.7378156185150146,
      "learning_rate": 8.748659268035339e-06,
      "loss": 0.2731,
      "step": 204
    },
    {
      "epoch": 0.5890804597701149,
      "grad_norm": 2.0161514282226562,
      "learning_rate": 8.649142525647271e-06,
      "loss": 0.3388,
      "step": 205
    },
    {
      "epoch": 0.5919540229885057,
      "grad_norm": 2.865183115005493,
      "learning_rate": 8.549761870357633e-06,
      "loss": 0.3414,
      "step": 206
    },
    {
      "epoch": 0.5948275862068966,
      "grad_norm": 2.0526323318481445,
      "learning_rate": 8.450527313899923e-06,
      "loss": 0.2896,
      "step": 207
    },
    {
      "epoch": 0.5977011494252874,
      "grad_norm": 1.859277367591858,
      "learning_rate": 8.351448853289448e-06,
      "loss": 0.3396,
      "step": 208
    },
    {
      "epoch": 0.6005747126436781,
      "grad_norm": 1.6364465951919556,
      "learning_rate": 8.25253646981622e-06,
      "loss": 0.3009,
      "step": 209
    },
    {
      "epoch": 0.603448275862069,
      "grad_norm": 1.590421438217163,
      "learning_rate": 8.153800128039441e-06,
      "loss": 0.2851,
      "step": 210
    },
    {
      "epoch": 0.6063218390804598,
      "grad_norm": 2.336608648300171,
      "learning_rate": 8.05524977478364e-06,
      "loss": 0.3176,
      "step": 211
    },
    {
      "epoch": 0.6091954022988506,
      "grad_norm": 2.3211328983306885,
      "learning_rate": 7.956895338136618e-06,
      "loss": 0.3106,
      "step": 212
    },
    {
      "epoch": 0.6120689655172413,
      "grad_norm": 2.7813518047332764,
      "learning_rate": 7.858746726449309e-06,
      "loss": 0.3136,
      "step": 213
    },
    {
      "epoch": 0.6149425287356322,
      "grad_norm": 1.71042799949646,
      "learning_rate": 7.760813827337555e-06,
      "loss": 0.2486,
      "step": 214
    },
    {
      "epoch": 0.617816091954023,
      "grad_norm": 2.9381296634674072,
      "learning_rate": 7.663106506686057e-06,
      "loss": 0.3015,
      "step": 215
    },
    {
      "epoch": 0.6206896551724138,
      "grad_norm": 1.7143189907073975,
      "learning_rate": 7.565634607654453e-06,
      "loss": 0.2992,
      "step": 216
    },
    {
      "epoch": 0.6235632183908046,
      "grad_norm": 3.923569679260254,
      "learning_rate": 7.468407949685695e-06,
      "loss": 0.3573,
      "step": 217
    },
    {
      "epoch": 0.6264367816091954,
      "grad_norm": 2.183392286300659,
      "learning_rate": 7.371436327516854e-06,
      "loss": 0.3268,
      "step": 218
    },
    {
      "epoch": 0.6293103448275862,
      "grad_norm": 2.3036110401153564,
      "learning_rate": 7.274729510192367e-06,
      "loss": 0.3112,
      "step": 219
    },
    {
      "epoch": 0.632183908045977,
      "grad_norm": 2.291121006011963,
      "learning_rate": 7.1782972400798825e-06,
      "loss": 0.3373,
      "step": 220
    },
    {
      "epoch": 0.632183908045977,
      "eval_accuracy": 0.8663366336633663,
      "eval_f1": 0.7428571428571429,
      "eval_loss": 0.3174149990081787,
      "eval_precision": 0.75,
      "eval_recall": 0.7358490566037735,
      "eval_runtime": 16.8275,
      "eval_samples_per_second": 6.299,
      "eval_steps_per_second": 0.238,
      "step": 220
    },
    {
      "epoch": 0.6350574712643678,
      "grad_norm": 2.0122501850128174,
      "learning_rate": 7.082149231888833e-06,
      "loss": 0.2819,
      "step": 221
    },
    {
      "epoch": 0.6379310344827587,
      "grad_norm": 3.282517194747925,
      "learning_rate": 6.986295171691727e-06,
      "loss": 0.3298,
      "step": 222
    },
    {
      "epoch": 0.6408045977011494,
      "grad_norm": 2.086409091949463,
      "learning_rate": 6.890744715948388e-06,
      "loss": 0.3012,
      "step": 223
    },
    {
      "epoch": 0.6436781609195402,
      "grad_norm": 1.70159912109375,
      "learning_rate": 6.795507490533142e-06,
      "loss": 0.2959,
      "step": 224
    },
    {
      "epoch": 0.646551724137931,
      "grad_norm": 2.0289723873138428,
      "learning_rate": 6.700593089765086e-06,
      "loss": 0.3425,
      "step": 225
    },
    {
      "epoch": 0.6494252873563219,
      "grad_norm": 1.884710669517517,
      "learning_rate": 6.606011075441556e-06,
      "loss": 0.3204,
      "step": 226
    },
    {
      "epoch": 0.6522988505747126,
      "grad_norm": 1.501484751701355,
      "learning_rate": 6.511770975874862e-06,
      "loss": 0.2775,
      "step": 227
    },
    {
      "epoch": 0.6551724137931034,
      "grad_norm": 2.8411877155303955,
      "learning_rate": 6.417882284932373e-06,
      "loss": 0.2738,
      "step": 228
    },
    {
      "epoch": 0.6580459770114943,
      "grad_norm": 1.941379427909851,
      "learning_rate": 6.324354461080121e-06,
      "loss": 0.2666,
      "step": 229
    },
    {
      "epoch": 0.6609195402298851,
      "grad_norm": 1.8048228025436401,
      "learning_rate": 6.231196926429913e-06,
      "loss": 0.2855,
      "step": 230
    },
    {
      "epoch": 0.6637931034482759,
      "grad_norm": 3.2040340900421143,
      "learning_rate": 6.138419065790169e-06,
      "loss": 0.3079,
      "step": 231
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 2.1029903888702393,
      "learning_rate": 6.046030225720456e-06,
      "loss": 0.2396,
      "step": 232
    },
    {
      "epoch": 0.6695402298850575,
      "grad_norm": 1.9636800289154053,
      "learning_rate": 5.95403971358991e-06,
      "loss": 0.2626,
      "step": 233
    },
    {
      "epoch": 0.6724137931034483,
      "grad_norm": 2.6405386924743652,
      "learning_rate": 5.86245679663962e-06,
      "loss": 0.3551,
      "step": 234
    },
    {
      "epoch": 0.6752873563218391,
      "grad_norm": 1.5251939296722412,
      "learning_rate": 5.7712907010490036e-06,
      "loss": 0.2533,
      "step": 235
    },
    {
      "epoch": 0.6781609195402298,
      "grad_norm": 2.1209423542022705,
      "learning_rate": 5.680550611006372e-06,
      "loss": 0.3079,
      "step": 236
    },
    {
      "epoch": 0.6810344827586207,
      "grad_norm": 2.9804978370666504,
      "learning_rate": 5.590245667783701e-06,
      "loss": 0.2793,
      "step": 237
    },
    {
      "epoch": 0.6839080459770115,
      "grad_norm": 1.8401639461517334,
      "learning_rate": 5.5003849688157075e-06,
      "loss": 0.3312,
      "step": 238
    },
    {
      "epoch": 0.6867816091954023,
      "grad_norm": 2.289094924926758,
      "learning_rate": 5.4109775667833866e-06,
      "loss": 0.3053,
      "step": 239
    },
    {
      "epoch": 0.6896551724137931,
      "grad_norm": 2.153110980987549,
      "learning_rate": 5.322032468702037e-06,
      "loss": 0.3006,
      "step": 240
    },
    {
      "epoch": 0.6896551724137931,
      "eval_accuracy": 0.8564356435643564,
      "eval_f1": 0.7289719626168224,
      "eval_loss": 0.3172420263290405,
      "eval_precision": 0.7222222222222222,
      "eval_recall": 0.7358490566037735,
      "eval_runtime": 16.2806,
      "eval_samples_per_second": 6.511,
      "eval_steps_per_second": 0.246,
      "step": 240
    },
    {
      "epoch": 0.6925287356321839,
      "grad_norm": 1.8454641103744507,
      "learning_rate": 5.233558635013842e-06,
      "loss": 0.3068,
      "step": 241
    },
    {
      "epoch": 0.6954022988505747,
      "grad_norm": 1.8107268810272217,
      "learning_rate": 5.145564978685234e-06,
      "loss": 0.2948,
      "step": 242
    },
    {
      "epoch": 0.6982758620689655,
      "grad_norm": 3.891240358352661,
      "learning_rate": 5.058060364308965e-06,
      "loss": 0.3284,
      "step": 243
    },
    {
      "epoch": 0.7011494252873564,
      "grad_norm": 2.919726610183716,
      "learning_rate": 4.971053607211069e-06,
      "loss": 0.3849,
      "step": 244
    },
    {
      "epoch": 0.7040229885057471,
      "grad_norm": 2.58359432220459,
      "learning_rate": 4.884553472562809e-06,
      "loss": 0.3178,
      "step": 245
    },
    {
      "epoch": 0.7068965517241379,
      "grad_norm": 2.011887550354004,
      "learning_rate": 4.7985686744976714e-06,
      "loss": 0.2861,
      "step": 246
    },
    {
      "epoch": 0.7097701149425287,
      "grad_norm": 2.8338310718536377,
      "learning_rate": 4.713107875233459e-06,
      "loss": 0.3335,
      "step": 247
    },
    {
      "epoch": 0.7126436781609196,
      "grad_norm": 2.3909761905670166,
      "learning_rate": 4.628179684199685e-06,
      "loss": 0.3075,
      "step": 248
    },
    {
      "epoch": 0.7155172413793104,
      "grad_norm": 2.0963563919067383,
      "learning_rate": 4.543792657170228e-06,
      "loss": 0.3073,
      "step": 249
    },
    {
      "epoch": 0.7183908045977011,
      "grad_norm": 2.0717861652374268,
      "learning_rate": 4.459955295401415e-06,
      "loss": 0.2974,
      "step": 250
    },
    {
      "epoch": 0.7212643678160919,
      "grad_norm": 2.0259382724761963,
      "learning_rate": 4.376676044775601e-06,
      "loss": 0.319,
      "step": 251
    },
    {
      "epoch": 0.7241379310344828,
      "grad_norm": 1.5886821746826172,
      "learning_rate": 4.293963294950313e-06,
      "loss": 0.2938,
      "step": 252
    },
    {
      "epoch": 0.7270114942528736,
      "grad_norm": 3.442382335662842,
      "learning_rate": 4.211825378513066e-06,
      "loss": 0.3855,
      "step": 253
    },
    {
      "epoch": 0.7298850574712644,
      "grad_norm": 1.693603515625,
      "learning_rate": 4.130270570141931e-06,
      "loss": 0.3354,
      "step": 254
    },
    {
      "epoch": 0.7327586206896551,
      "grad_norm": 2.258274555206299,
      "learning_rate": 4.0493070857719305e-06,
      "loss": 0.3418,
      "step": 255
    },
    {
      "epoch": 0.735632183908046,
      "grad_norm": 1.6936811208724976,
      "learning_rate": 3.968943081767358e-06,
      "loss": 0.2287,
      "step": 256
    },
    {
      "epoch": 0.7385057471264368,
      "grad_norm": 2.4249556064605713,
      "learning_rate": 3.889186654100089e-06,
      "loss": 0.2983,
      "step": 257
    },
    {
      "epoch": 0.7413793103448276,
      "grad_norm": 1.6004093885421753,
      "learning_rate": 3.81004583753399e-06,
      "loss": 0.3394,
      "step": 258
    },
    {
      "epoch": 0.7442528735632183,
      "grad_norm": 1.6185859441757202,
      "learning_rate": 3.7315286048154862e-06,
      "loss": 0.2784,
      "step": 259
    },
    {
      "epoch": 0.7471264367816092,
      "grad_norm": 2.6173603534698486,
      "learning_rate": 3.6536428658703594e-06,
      "loss": 0.3157,
      "step": 260
    },
    {
      "epoch": 0.7471264367816092,
      "eval_accuracy": 0.8638613861386139,
      "eval_f1": 0.7441860465116279,
      "eval_loss": 0.31433796882629395,
      "eval_precision": 0.7339449541284404,
      "eval_recall": 0.7547169811320755,
      "eval_runtime": 16.814,
      "eval_samples_per_second": 6.304,
      "eval_steps_per_second": 0.238,
      "step": 260
    },
    {
      "epoch": 0.75,
      "grad_norm": 2.565181016921997,
      "learning_rate": 3.576396467006925e-06,
      "loss": 0.3084,
      "step": 261
    },
    {
      "epoch": 0.7528735632183908,
      "grad_norm": 1.734839677810669,
      "learning_rate": 3.4997971901255588e-06,
      "loss": 0.2717,
      "step": 262
    },
    {
      "epoch": 0.7557471264367817,
      "grad_norm": 2.3014395236968994,
      "learning_rate": 3.4238527519347353e-06,
      "loss": 0.2926,
      "step": 263
    },
    {
      "epoch": 0.7586206896551724,
      "grad_norm": 2.2998158931732178,
      "learning_rate": 3.3485708031736698e-06,
      "loss": 0.2919,
      "step": 264
    },
    {
      "epoch": 0.7614942528735632,
      "grad_norm": 1.628414273262024,
      "learning_rate": 3.2739589278415252e-06,
      "loss": 0.2951,
      "step": 265
    },
    {
      "epoch": 0.764367816091954,
      "grad_norm": 1.8661236763000488,
      "learning_rate": 3.2000246424334315e-06,
      "loss": 0.2859,
      "step": 266
    },
    {
      "epoch": 0.7672413793103449,
      "grad_norm": 1.9966816902160645,
      "learning_rate": 3.1267753951832523e-06,
      "loss": 0.3339,
      "step": 267
    },
    {
      "epoch": 0.7701149425287356,
      "grad_norm": 2.3552565574645996,
      "learning_rate": 3.0542185653132216e-06,
      "loss": 0.2443,
      "step": 268
    },
    {
      "epoch": 0.7729885057471264,
      "grad_norm": 2.6835176944732666,
      "learning_rate": 2.982361462290575e-06,
      "loss": 0.3595,
      "step": 269
    },
    {
      "epoch": 0.7758620689655172,
      "grad_norm": 2.2720601558685303,
      "learning_rate": 2.9112113250911844e-06,
      "loss": 0.3284,
      "step": 270
    },
    {
      "epoch": 0.7787356321839081,
      "grad_norm": 2.1442339420318604,
      "learning_rate": 2.8407753214702694e-06,
      "loss": 0.3026,
      "step": 271
    },
    {
      "epoch": 0.7816091954022989,
      "grad_norm": 2.52978253364563,
      "learning_rate": 2.7710605472403373e-06,
      "loss": 0.2599,
      "step": 272
    },
    {
      "epoch": 0.7844827586206896,
      "grad_norm": 2.584745168685913,
      "learning_rate": 2.702074025556327e-06,
      "loss": 0.3211,
      "step": 273
    },
    {
      "epoch": 0.7873563218390804,
      "grad_norm": 1.9318722486495972,
      "learning_rate": 2.6338227062080924e-06,
      "loss": 0.2654,
      "step": 274
    },
    {
      "epoch": 0.7902298850574713,
      "grad_norm": 2.129678726196289,
      "learning_rate": 2.566313464920265e-06,
      "loss": 0.2944,
      "step": 275
    },
    {
      "epoch": 0.7931034482758621,
      "grad_norm": 2.0152359008789062,
      "learning_rate": 2.4995531026595952e-06,
      "loss": 0.2912,
      "step": 276
    },
    {
      "epoch": 0.7959770114942529,
      "grad_norm": 2.8792333602905273,
      "learning_rate": 2.4335483449498053e-06,
      "loss": 0.2315,
      "step": 277
    },
    {
      "epoch": 0.7988505747126436,
      "grad_norm": 2.067209482192993,
      "learning_rate": 2.3683058411940563e-06,
      "loss": 0.299,
      "step": 278
    },
    {
      "epoch": 0.8017241379310345,
      "grad_norm": 2.9557700157165527,
      "learning_rate": 2.3038321640050763e-06,
      "loss": 0.3056,
      "step": 279
    },
    {
      "epoch": 0.8045977011494253,
      "grad_norm": 2.989224910736084,
      "learning_rate": 2.2401338085430326e-06,
      "loss": 0.291,
      "step": 280
    },
    {
      "epoch": 0.8045977011494253,
      "eval_accuracy": 0.8638613861386139,
      "eval_f1": 0.7441860465116279,
      "eval_loss": 0.313725084066391,
      "eval_precision": 0.7339449541284404,
      "eval_recall": 0.7547169811320755,
      "eval_runtime": 16.9214,
      "eval_samples_per_second": 6.264,
      "eval_steps_per_second": 0.236,
      "step": 280
    },
    {
      "epoch": 0.8074712643678161,
      "grad_norm": 1.7180490493774414,
      "learning_rate": 2.177217191861183e-06,
      "loss": 0.2469,
      "step": 281
    },
    {
      "epoch": 0.8103448275862069,
      "grad_norm": 2.1826789379119873,
      "learning_rate": 2.115088652259446e-06,
      "loss": 0.3332,
      "step": 282
    },
    {
      "epoch": 0.8132183908045977,
      "grad_norm": 1.5366544723510742,
      "learning_rate": 2.053754448645846e-06,
      "loss": 0.228,
      "step": 283
    },
    {
      "epoch": 0.8160919540229885,
      "grad_norm": 2.2642948627471924,
      "learning_rate": 1.9932207599059782e-06,
      "loss": 0.2885,
      "step": 284
    },
    {
      "epoch": 0.8189655172413793,
      "grad_norm": 1.702837347984314,
      "learning_rate": 1.933493684280574e-06,
      "loss": 0.2484,
      "step": 285
    },
    {
      "epoch": 0.8218390804597702,
      "grad_norm": 2.2830252647399902,
      "learning_rate": 1.8745792387511241e-06,
      "loss": 0.299,
      "step": 286
    },
    {
      "epoch": 0.8247126436781609,
      "grad_norm": 2.5294742584228516,
      "learning_rate": 1.8164833584337216e-06,
      "loss": 0.28,
      "step": 287
    },
    {
      "epoch": 0.8275862068965517,
      "grad_norm": 2.3175997734069824,
      "learning_rate": 1.75921189598118e-06,
      "loss": 0.3008,
      "step": 288
    },
    {
      "epoch": 0.8304597701149425,
      "grad_norm": 2.312864065170288,
      "learning_rate": 1.7027706209933903e-06,
      "loss": 0.3326,
      "step": 289
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 1.6961781978607178,
      "learning_rate": 1.6471652194361131e-06,
      "loss": 0.2999,
      "step": 290
    },
    {
      "epoch": 0.8362068965517241,
      "grad_norm": 2.65458607673645,
      "learning_rate": 1.5924012930681643e-06,
      "loss": 0.3208,
      "step": 291
    },
    {
      "epoch": 0.8390804597701149,
      "grad_norm": 4.437558174133301,
      "learning_rate": 1.5384843588770626e-06,
      "loss": 0.344,
      "step": 292
    },
    {
      "epoch": 0.8419540229885057,
      "grad_norm": 2.285850763320923,
      "learning_rate": 1.4854198485232696e-06,
      "loss": 0.2467,
      "step": 293
    },
    {
      "epoch": 0.8448275862068966,
      "grad_norm": 2.915544033050537,
      "learning_rate": 1.433213107792991e-06,
      "loss": 0.3635,
      "step": 294
    },
    {
      "epoch": 0.8477011494252874,
      "grad_norm": 2.448625087738037,
      "learning_rate": 1.3818693960596186e-06,
      "loss": 0.3344,
      "step": 295
    },
    {
      "epoch": 0.8505747126436781,
      "grad_norm": 2.1480016708374023,
      "learning_rate": 1.3313938857539133e-06,
      "loss": 0.2828,
      "step": 296
    },
    {
      "epoch": 0.853448275862069,
      "grad_norm": 2.444200277328491,
      "learning_rate": 1.2817916618429194e-06,
      "loss": 0.3014,
      "step": 297
    },
    {
      "epoch": 0.8563218390804598,
      "grad_norm": 2.8024673461914062,
      "learning_rate": 1.2330677213177034e-06,
      "loss": 0.2614,
      "step": 298
    },
    {
      "epoch": 0.8591954022988506,
      "grad_norm": 3.5111196041107178,
      "learning_rate": 1.1852269726899423e-06,
      "loss": 0.3055,
      "step": 299
    },
    {
      "epoch": 0.8620689655172413,
      "grad_norm": 1.937780737876892,
      "learning_rate": 1.138274235497443e-06,
      "loss": 0.2578,
      "step": 300
    },
    {
      "epoch": 0.8620689655172413,
      "eval_accuracy": 0.8638613861386139,
      "eval_f1": 0.7441860465116279,
      "eval_loss": 0.31676626205444336,
      "eval_precision": 0.7339449541284404,
      "eval_recall": 0.7547169811320755,
      "eval_runtime": 16.8256,
      "eval_samples_per_second": 6.3,
      "eval_steps_per_second": 0.238,
      "step": 300
    },
    {
      "epoch": 0.8649425287356322,
      "grad_norm": 1.617297649383545,
      "learning_rate": 1.0922142398186097e-06,
      "loss": 0.2681,
      "step": 301
    },
    {
      "epoch": 0.867816091954023,
      "grad_norm": 2.8231587409973145,
      "learning_rate": 1.0470516257959351e-06,
      "loss": 0.2958,
      "step": 302
    },
    {
      "epoch": 0.8706896551724138,
      "grad_norm": 1.7231059074401855,
      "learning_rate": 1.00279094316854e-06,
      "loss": 0.2739,
      "step": 303
    },
    {
      "epoch": 0.8735632183908046,
      "grad_norm": 2.3094263076782227,
      "learning_rate": 9.594366508138352e-07,
      "loss": 0.3014,
      "step": 304
    },
    {
      "epoch": 0.8764367816091954,
      "grad_norm": 2.9980764389038086,
      "learning_rate": 9.169931162983137e-07,
      "loss": 0.2781,
      "step": 305
    },
    {
      "epoch": 0.8793103448275862,
      "grad_norm": 2.005481243133545,
      "learning_rate": 8.754646154375801e-07,
      "loss": 0.2592,
      "step": 306
    },
    {
      "epoch": 0.882183908045977,
      "grad_norm": 2.7463858127593994,
      "learning_rate": 8.348553318655795e-07,
      "loss": 0.3159,
      "step": 307
    },
    {
      "epoch": 0.8850574712643678,
      "grad_norm": 2.01882266998291,
      "learning_rate": 7.951693566131325e-07,
      "loss": 0.3136,
      "step": 308
    },
    {
      "epoch": 0.8879310344827587,
      "grad_norm": 1.7923675775527954,
      "learning_rate": 7.564106876958188e-07,
      "loss": 0.2936,
      "step": 309
    },
    {
      "epoch": 0.8908045977011494,
      "grad_norm": 2.2415239810943604,
      "learning_rate": 7.185832297111939e-07,
      "loss": 0.3882,
      "step": 310
    },
    {
      "epoch": 0.8936781609195402,
      "grad_norm": 1.7161551713943481,
      "learning_rate": 6.816907934454353e-07,
      "loss": 0.2533,
      "step": 311
    },
    {
      "epoch": 0.896551724137931,
      "grad_norm": 2.019099712371826,
      "learning_rate": 6.457370954894582e-07,
      "loss": 0.2335,
      "step": 312
    },
    {
      "epoch": 0.8994252873563219,
      "grad_norm": 2.187922477722168,
      "learning_rate": 6.107257578644721e-07,
      "loss": 0.2695,
      "step": 313
    },
    {
      "epoch": 0.9022988505747126,
      "grad_norm": 1.7923535108566284,
      "learning_rate": 5.766603076571164e-07,
      "loss": 0.2652,
      "step": 314
    },
    {
      "epoch": 0.9051724137931034,
      "grad_norm": 1.9885005950927734,
      "learning_rate": 5.43544176664137e-07,
      "loss": 0.2851,
      "step": 315
    },
    {
      "epoch": 0.9080459770114943,
      "grad_norm": 1.9837305545806885,
      "learning_rate": 5.113807010466432e-07,
      "loss": 0.2884,
      "step": 316
    },
    {
      "epoch": 0.9109195402298851,
      "grad_norm": 2.307769536972046,
      "learning_rate": 4.801731209940375e-07,
      "loss": 0.2827,
      "step": 317
    },
    {
      "epoch": 0.9137931034482759,
      "grad_norm": 2.077484130859375,
      "learning_rate": 4.499245803975927e-07,
      "loss": 0.2686,
      "step": 318
    },
    {
      "epoch": 0.9166666666666666,
      "grad_norm": 2.722639799118042,
      "learning_rate": 4.206381265337189e-07,
      "loss": 0.301,
      "step": 319
    },
    {
      "epoch": 0.9195402298850575,
      "grad_norm": 2.3338513374328613,
      "learning_rate": 3.9231670975699354e-07,
      "loss": 0.3223,
      "step": 320
    },
    {
      "epoch": 0.9195402298850575,
      "eval_accuracy": 0.8613861386138614,
      "eval_f1": 0.7407407407407407,
      "eval_loss": 0.3157050609588623,
      "eval_precision": 0.7272727272727273,
      "eval_recall": 0.7547169811320755,
      "eval_runtime": 16.7717,
      "eval_samples_per_second": 6.32,
      "eval_steps_per_second": 0.238,
      "step": 320
    },
    {
      "epoch": 0.9224137931034483,
      "grad_norm": 3.109226942062378,
      "learning_rate": 3.649631832029288e-07,
      "loss": 0.3366,
      "step": 321
    },
    {
      "epoch": 0.9252873563218391,
      "grad_norm": 1.830435872077942,
      "learning_rate": 3.385803025005463e-07,
      "loss": 0.277,
      "step": 322
    },
    {
      "epoch": 0.9281609195402298,
      "grad_norm": 2.406721591949463,
      "learning_rate": 3.1317072549477246e-07,
      "loss": 0.3517,
      "step": 323
    },
    {
      "epoch": 0.9310344827586207,
      "grad_norm": 2.0932199954986572,
      "learning_rate": 2.887370119786792e-07,
      "loss": 0.2832,
      "step": 324
    },
    {
      "epoch": 0.9339080459770115,
      "grad_norm": 2.193326473236084,
      "learning_rate": 2.6528162343561593e-07,
      "loss": 0.3269,
      "step": 325
    },
    {
      "epoch": 0.9367816091954023,
      "grad_norm": 2.217686653137207,
      "learning_rate": 2.4280692279122554e-07,
      "loss": 0.2642,
      "step": 326
    },
    {
      "epoch": 0.9396551724137931,
      "grad_norm": 1.9883277416229248,
      "learning_rate": 2.2131517417540937e-07,
      "loss": 0.2929,
      "step": 327
    },
    {
      "epoch": 0.9425287356321839,
      "grad_norm": 2.0583817958831787,
      "learning_rate": 2.00808542694233e-07,
      "loss": 0.2886,
      "step": 328
    },
    {
      "epoch": 0.9454022988505747,
      "grad_norm": 1.7167632579803467,
      "learning_rate": 1.8128909421180506e-07,
      "loss": 0.2528,
      "step": 329
    },
    {
      "epoch": 0.9482758620689655,
      "grad_norm": 1.9056061506271362,
      "learning_rate": 1.6275879514217052e-07,
      "loss": 0.3133,
      "step": 330
    },
    {
      "epoch": 0.9511494252873564,
      "grad_norm": 2.4173924922943115,
      "learning_rate": 1.4521951225120345e-07,
      "loss": 0.3712,
      "step": 331
    },
    {
      "epoch": 0.9540229885057471,
      "grad_norm": 1.6717036962509155,
      "learning_rate": 1.2867301246854757e-07,
      "loss": 0.2764,
      "step": 332
    },
    {
      "epoch": 0.9568965517241379,
      "grad_norm": 1.7265243530273438,
      "learning_rate": 1.1312096270961525e-07,
      "loss": 0.2683,
      "step": 333
    },
    {
      "epoch": 0.9597701149425287,
      "grad_norm": 1.933962345123291,
      "learning_rate": 9.856492970766296e-08,
      "loss": 0.3035,
      "step": 334
    },
    {
      "epoch": 0.9626436781609196,
      "grad_norm": 1.7811708450317383,
      "learning_rate": 8.50063798559475e-08,
      "loss": 0.2747,
      "step": 335
    },
    {
      "epoch": 0.9655172413793104,
      "grad_norm": 2.420718193054199,
      "learning_rate": 7.244667906001202e-08,
      "loss": 0.2595,
      "step": 336
    },
    {
      "epoch": 0.9683908045977011,
      "grad_norm": 2.360978841781616,
      "learning_rate": 6.088709260007153e-08,
      "loss": 0.2845,
      "step": 337
    },
    {
      "epoch": 0.9712643678160919,
      "grad_norm": 1.8564136028289795,
      "learning_rate": 5.032878500355498e-08,
      "loss": 0.2868,
      "step": 338
    },
    {
      "epoch": 0.9741379310344828,
      "grad_norm": 3.320560932159424,
      "learning_rate": 4.07728199277857e-08,
      "loss": 0.298,
      "step": 339
    },
    {
      "epoch": 0.9770114942528736,
      "grad_norm": 3.1737234592437744,
      "learning_rate": 3.2220160052828245e-08,
      "loss": 0.3448,
      "step": 340
    },
    {
      "epoch": 0.9770114942528736,
      "eval_accuracy": 0.8613861386138614,
      "eval_f1": 0.7407407407407407,
      "eval_loss": 0.31532150506973267,
      "eval_precision": 0.7272727272727273,
      "eval_recall": 0.7547169811320755,
      "eval_runtime": 17.2915,
      "eval_samples_per_second": 6.13,
      "eval_steps_per_second": 0.231,
      "step": 340
    },
    {
      "epoch": 0.9798850574712644,
      "grad_norm": 1.8069976568222046,
      "learning_rate": 2.467166698450485e-08,
      "loss": 0.2825,
      "step": 341
    },
    {
      "epoch": 0.9827586206896551,
      "grad_norm": 2.923757314682007,
      "learning_rate": 1.812810116760044e-08,
      "loss": 0.2836,
      "step": 342
    },
    {
      "epoch": 0.985632183908046,
      "grad_norm": 3.138817310333252,
      "learning_rate": 1.2590121809247235e-08,
      "loss": 0.3312,
      "step": 343
    },
    {
      "epoch": 0.9885057471264368,
      "grad_norm": 1.6502025127410889,
      "learning_rate": 8.05828681252452e-09,
      "loss": 0.2625,
      "step": 344
    },
    {
      "epoch": 0.9913793103448276,
      "grad_norm": 2.4544200897216797,
      "learning_rate": 4.5330527202480656e-09,
      "loss": 0.3451,
      "step": 345
    },
    {
      "epoch": 0.9942528735632183,
      "grad_norm": 1.9814451932907104,
      "learning_rate": 2.014774668979147e-09,
      "loss": 0.2715,
      "step": 346
    },
    {
      "epoch": 0.9971264367816092,
      "grad_norm": 2.851459503173828,
      "learning_rate": 5.037063532498109e-10,
      "loss": 0.3053,
      "step": 347
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.8435858488082886,
      "learning_rate": 0.0,
      "loss": 0.2909,
      "step": 348
    }
  ],
  "logging_steps": 1,
  "max_steps": 348,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1002361050405274e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}