{
  "best_metric": 0.3821594715118408,
  "best_model_checkpoint": "classify-google-augment-3/checkpoint-4950",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 4950,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.015151515151515152,
      "grad_norm": 12.085535049438477,
      "learning_rate": 2.3232323232323234e-06,
      "loss": 2.4513,
      "step": 25
    },
    {
      "epoch": 0.030303030303030304,
      "grad_norm": 10.15959358215332,
      "learning_rate": 4.848484848484849e-06,
      "loss": 2.234,
      "step": 50
    },
    {
      "epoch": 0.045454545454545456,
      "grad_norm": 12.21349048614502,
      "learning_rate": 7.3737373737373745e-06,
      "loss": 1.9342,
      "step": 75
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 13.986493110656738,
      "learning_rate": 9.898989898989899e-06,
      "loss": 1.7956,
      "step": 100
    },
    {
      "epoch": 0.07575757575757576,
      "grad_norm": 13.179245948791504,
      "learning_rate": 1.2424242424242424e-05,
      "loss": 1.7165,
      "step": 125
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 15.372575759887695,
      "learning_rate": 1.494949494949495e-05,
      "loss": 1.519,
      "step": 150
    },
    {
      "epoch": 0.10606060606060606,
      "grad_norm": 9.555817604064941,
      "learning_rate": 1.7474747474747475e-05,
      "loss": 1.4716,
      "step": 175
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 14.15468692779541,
      "learning_rate": 2e-05,
      "loss": 1.5611,
      "step": 200
    },
    {
      "epoch": 0.13636363636363635,
      "grad_norm": 9.72482681274414,
      "learning_rate": 2.2525252525252528e-05,
      "loss": 1.3692,
      "step": 225
    },
    {
      "epoch": 0.15151515151515152,
      "grad_norm": 11.219098091125488,
      "learning_rate": 2.505050505050505e-05,
      "loss": 1.3761,
      "step": 250
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 14.293442726135254,
      "learning_rate": 2.7575757575757578e-05,
      "loss": 1.5677,
      "step": 275
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 12.68210506439209,
      "learning_rate": 3.01010101010101e-05,
      "loss": 1.4212,
      "step": 300
    },
    {
      "epoch": 0.19696969696969696,
      "grad_norm": 10.856423377990723,
      "learning_rate": 3.2626262626262624e-05,
      "loss": 1.3204,
      "step": 325
    },
    {
      "epoch": 0.21212121212121213,
      "grad_norm": 11.644044876098633,
      "learning_rate": 3.515151515151515e-05,
      "loss": 1.3228,
      "step": 350
    },
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 7.3117356300354,
      "learning_rate": 3.767676767676768e-05,
      "loss": 1.4005,
      "step": 375
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 12.309542655944824,
      "learning_rate": 4.0202020202020204e-05,
      "loss": 1.2739,
      "step": 400
    },
    {
      "epoch": 0.25757575757575757,
      "grad_norm": 11.981978416442871,
      "learning_rate": 4.2727272727272724e-05,
      "loss": 1.3082,
      "step": 425
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 8.469183921813965,
      "learning_rate": 4.525252525252526e-05,
      "loss": 1.1932,
      "step": 450
    },
    {
      "epoch": 0.2878787878787879,
      "grad_norm": 13.018028259277344,
      "learning_rate": 4.7777777777777784e-05,
      "loss": 1.2612,
      "step": 475
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 11.944835662841797,
      "learning_rate": 4.9966329966329964e-05,
      "loss": 1.3266,
      "step": 500
    },
    {
      "epoch": 0.3181818181818182,
      "grad_norm": 11.489705085754395,
      "learning_rate": 4.968574635241302e-05,
      "loss": 1.3537,
      "step": 525
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 14.265945434570312,
      "learning_rate": 4.940516273849607e-05,
      "loss": 1.4162,
      "step": 550
    },
    {
      "epoch": 0.3484848484848485,
      "grad_norm": 10.913326263427734,
      "learning_rate": 4.912457912457913e-05,
      "loss": 1.0754,
      "step": 575
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 7.5248236656188965,
      "learning_rate": 4.884399551066218e-05,
      "loss": 1.3724,
      "step": 600
    },
    {
      "epoch": 0.3787878787878788,
      "grad_norm": 9.98138427734375,
      "learning_rate": 4.856341189674523e-05,
      "loss": 1.184,
      "step": 625
    },
    {
      "epoch": 0.3939393939393939,
      "grad_norm": 9.07705307006836,
      "learning_rate": 4.828282828282829e-05,
      "loss": 1.0418,
      "step": 650
    },
    {
      "epoch": 0.4090909090909091,
      "grad_norm": 8.512435913085938,
      "learning_rate": 4.800224466891134e-05,
      "loss": 1.1425,
      "step": 675
    },
    {
      "epoch": 0.42424242424242425,
      "grad_norm": 13.559457778930664,
      "learning_rate": 4.7721661054994394e-05,
      "loss": 1.4285,
      "step": 700
    },
    {
      "epoch": 0.4393939393939394,
      "grad_norm": 7.820692539215088,
      "learning_rate": 4.7441077441077445e-05,
      "loss": 1.1221,
      "step": 725
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 6.074573040008545,
      "learning_rate": 4.7160493827160495e-05,
      "loss": 0.9862,
      "step": 750
    },
    {
      "epoch": 0.4696969696969697,
      "grad_norm": 6.816392421722412,
      "learning_rate": 4.687991021324355e-05,
      "loss": 1.1894,
      "step": 775
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 9.136533737182617,
      "learning_rate": 4.65993265993266e-05,
      "loss": 1.0674,
      "step": 800
    },
    {
      "epoch": 0.5,
      "grad_norm": 8.841058731079102,
      "learning_rate": 4.631874298540965e-05,
      "loss": 1.0798,
      "step": 825
    },
    {
      "epoch": 0.5151515151515151,
      "grad_norm": 10.076774597167969,
      "learning_rate": 4.60381593714927e-05,
      "loss": 1.0903,
      "step": 850
    },
    {
      "epoch": 0.5303030303030303,
      "grad_norm": 13.101428985595703,
      "learning_rate": 4.575757575757576e-05,
      "loss": 1.0672,
      "step": 875
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 10.879769325256348,
      "learning_rate": 4.547699214365882e-05,
      "loss": 1.005,
      "step": 900
    },
    {
      "epoch": 0.5606060606060606,
      "grad_norm": 5.972232341766357,
      "learning_rate": 4.519640852974186e-05,
      "loss": 1.026,
      "step": 925
    },
    {
      "epoch": 0.5757575757575758,
      "grad_norm": 12.992452621459961,
      "learning_rate": 4.491582491582492e-05,
      "loss": 1.0436,
      "step": 950
    },
    {
      "epoch": 0.5909090909090909,
      "grad_norm": 11.431863784790039,
      "learning_rate": 4.463524130190797e-05,
      "loss": 1.006,
      "step": 975
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 13.05385971069336,
      "learning_rate": 4.4354657687991025e-05,
      "loss": 1.1255,
      "step": 1000
    },
    {
      "epoch": 0.6212121212121212,
      "grad_norm": 9.93174934387207,
      "learning_rate": 4.4074074074074076e-05,
      "loss": 1.0457,
      "step": 1025
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 14.331412315368652,
      "learning_rate": 4.3793490460157126e-05,
      "loss": 0.997,
      "step": 1050
    },
    {
      "epoch": 0.6515151515151515,
      "grad_norm": 11.081893920898438,
      "learning_rate": 4.351290684624018e-05,
      "loss": 0.999,
      "step": 1075
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 8.453628540039062,
      "learning_rate": 4.3232323232323234e-05,
      "loss": 1.0695,
      "step": 1100
    },
    {
      "epoch": 0.6818181818181818,
      "grad_norm": 8.907005310058594,
      "learning_rate": 4.295173961840629e-05,
      "loss": 0.967,
      "step": 1125
    },
    {
      "epoch": 0.696969696969697,
      "grad_norm": 10.75546646118164,
      "learning_rate": 4.267115600448934e-05,
      "loss": 1.0517,
      "step": 1150
    },
    {
      "epoch": 0.7121212121212122,
      "grad_norm": 9.127320289611816,
      "learning_rate": 4.239057239057239e-05,
      "loss": 1.0049,
      "step": 1175
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 10.124237060546875,
      "learning_rate": 4.210998877665545e-05,
      "loss": 0.969,
      "step": 1200
    },
    {
      "epoch": 0.7424242424242424,
      "grad_norm": 5.617876052856445,
      "learning_rate": 4.18294051627385e-05,
      "loss": 1.0031,
      "step": 1225
    },
    {
      "epoch": 0.7575757575757576,
      "grad_norm": 11.184277534484863,
      "learning_rate": 4.154882154882155e-05,
      "loss": 1.0209,
      "step": 1250
    },
    {
      "epoch": 0.7727272727272727,
      "grad_norm": 6.545035362243652,
      "learning_rate": 4.12682379349046e-05,
      "loss": 0.8416,
      "step": 1275
    },
    {
      "epoch": 0.7878787878787878,
      "grad_norm": 4.944152355194092,
      "learning_rate": 4.0987654320987657e-05,
      "loss": 1.0029,
      "step": 1300
    },
    {
      "epoch": 0.803030303030303,
      "grad_norm": 8.916969299316406,
      "learning_rate": 4.070707070707071e-05,
      "loss": 0.8808,
      "step": 1325
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 4.9258713722229,
      "learning_rate": 4.0426487093153764e-05,
      "loss": 0.9536,
      "step": 1350
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 11.556329727172852,
      "learning_rate": 4.0145903479236814e-05,
      "loss": 0.937,
      "step": 1375
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 10.06991958618164,
      "learning_rate": 3.9865319865319865e-05,
      "loss": 0.8424,
      "step": 1400
    },
    {
      "epoch": 0.8636363636363636,
      "grad_norm": 8.390497207641602,
      "learning_rate": 3.958473625140292e-05,
      "loss": 0.9453,
      "step": 1425
    },
    {
      "epoch": 0.8787878787878788,
      "grad_norm": 8.02001667022705,
      "learning_rate": 3.930415263748597e-05,
      "loss": 0.8522,
      "step": 1450
    },
    {
      "epoch": 0.8939393939393939,
      "grad_norm": 8.541698455810547,
      "learning_rate": 3.902356902356902e-05,
      "loss": 0.9519,
      "step": 1475
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 7.404212951660156,
      "learning_rate": 3.874298540965208e-05,
      "loss": 0.9692,
      "step": 1500
    },
    {
      "epoch": 0.9242424242424242,
      "grad_norm": 10.684733390808105,
      "learning_rate": 3.846240179573513e-05,
      "loss": 1.0417,
      "step": 1525
    },
    {
      "epoch": 0.9393939393939394,
      "grad_norm": 6.182531833648682,
      "learning_rate": 3.818181818181819e-05,
      "loss": 0.8632,
      "step": 1550
    },
    {
      "epoch": 0.9545454545454546,
      "grad_norm": 8.63337516784668,
      "learning_rate": 3.790123456790123e-05,
      "loss": 0.9318,
      "step": 1575
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 11.64743709564209,
      "learning_rate": 3.762065095398429e-05,
      "loss": 0.8535,
      "step": 1600
    },
    {
      "epoch": 0.9848484848484849,
      "grad_norm": 11.15438461303711,
      "learning_rate": 3.7340067340067345e-05,
      "loss": 0.9558,
      "step": 1625
    },
    {
      "epoch": 1.0,
      "grad_norm": 7.817443370819092,
      "learning_rate": 3.7059483726150395e-05,
      "loss": 0.9244,
      "step": 1650
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7645454545454545,
      "eval_f1_macro": 0.6989492792384068,
      "eval_f1_micro": 0.7645454545454545,
      "eval_f1_weighted": 0.7496986753676582,
      "eval_loss": 0.752944827079773,
      "eval_precision_macro": 0.8012284685903541,
      "eval_precision_micro": 0.7645454545454545,
      "eval_precision_weighted": 0.817408067065806,
      "eval_recall_macro": 0.7035,
      "eval_recall_micro": 0.7645454545454545,
      "eval_recall_weighted": 0.7645454545454545,
      "eval_runtime": 18.9801,
      "eval_samples_per_second": 173.866,
      "eval_steps_per_second": 10.906,
      "step": 1650
    },
    {
      "epoch": 1.0151515151515151,
      "grad_norm": 10.560444831848145,
      "learning_rate": 3.677890011223345e-05,
      "loss": 0.7833,
      "step": 1675
    },
    {
      "epoch": 1.0303030303030303,
      "grad_norm": 4.251949310302734,
      "learning_rate": 3.6498316498316496e-05,
      "loss": 0.7379,
      "step": 1700
    },
    {
      "epoch": 1.0454545454545454,
      "grad_norm": 10.605439186096191,
      "learning_rate": 3.621773288439955e-05,
      "loss": 0.7779,
      "step": 1725
    },
    {
      "epoch": 1.0606060606060606,
      "grad_norm": 7.418851375579834,
      "learning_rate": 3.59371492704826e-05,
      "loss": 0.7347,
      "step": 1750
    },
    {
      "epoch": 1.0757575757575757,
      "grad_norm": 10.209125518798828,
      "learning_rate": 3.565656565656566e-05,
      "loss": 0.8636,
      "step": 1775
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 5.001626491546631,
      "learning_rate": 3.537598204264871e-05,
      "loss": 0.8716,
      "step": 1800
    },
    {
      "epoch": 1.106060606060606,
      "grad_norm": 5.035640239715576,
      "learning_rate": 3.509539842873176e-05,
      "loss": 0.7529,
      "step": 1825
    },
    {
      "epoch": 1.121212121212121,
      "grad_norm": 7.653929710388184,
      "learning_rate": 3.481481481481482e-05,
      "loss": 0.8541,
      "step": 1850
    },
    {
      "epoch": 1.1363636363636362,
      "grad_norm": 11.623481750488281,
      "learning_rate": 3.453423120089787e-05,
      "loss": 0.8159,
      "step": 1875
    },
    {
      "epoch": 1.1515151515151516,
      "grad_norm": 9.897392272949219,
      "learning_rate": 3.425364758698092e-05,
      "loss": 0.5642,
      "step": 1900
    },
    {
      "epoch": 1.1666666666666667,
      "grad_norm": 8.24569320678711,
      "learning_rate": 3.3973063973063976e-05,
      "loss": 1.0238,
      "step": 1925
    },
    {
      "epoch": 1.1818181818181819,
      "grad_norm": 6.044914245605469,
      "learning_rate": 3.3692480359147026e-05,
      "loss": 0.8917,
      "step": 1950
    },
    {
      "epoch": 1.196969696969697,
      "grad_norm": 5.3622002601623535,
      "learning_rate": 3.3411896745230084e-05,
      "loss": 0.7951,
      "step": 1975
    },
    {
      "epoch": 1.2121212121212122,
      "grad_norm": 8.479634284973145,
      "learning_rate": 3.3131313131313134e-05,
      "loss": 0.9219,
      "step": 2000
    },
    {
      "epoch": 1.2272727272727273,
      "grad_norm": 10.730965614318848,
      "learning_rate": 3.2850729517396184e-05,
      "loss": 0.6391,
      "step": 2025
    },
    {
      "epoch": 1.2424242424242424,
      "grad_norm": 2.901815891265869,
      "learning_rate": 3.2570145903479235e-05,
      "loss": 0.7946,
      "step": 2050
    },
    {
      "epoch": 1.2575757575757576,
      "grad_norm": 7.174593448638916,
      "learning_rate": 3.228956228956229e-05,
      "loss": 0.7458,
      "step": 2075
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 5.743284702301025,
      "learning_rate": 3.200897867564535e-05,
      "loss": 0.8514,
      "step": 2100
    },
    {
      "epoch": 1.2878787878787878,
      "grad_norm": 5.6034464836120605,
      "learning_rate": 3.172839506172839e-05,
      "loss": 0.5711,
      "step": 2125
    },
    {
      "epoch": 1.303030303030303,
      "grad_norm": 6.2251996994018555,
      "learning_rate": 3.144781144781145e-05,
      "loss": 0.8115,
      "step": 2150
    },
    {
      "epoch": 1.3181818181818181,
      "grad_norm": 6.7410078048706055,
      "learning_rate": 3.11672278338945e-05,
      "loss": 0.7262,
      "step": 2175
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 5.232451438903809,
      "learning_rate": 3.088664421997756e-05,
      "loss": 0.7573,
      "step": 2200
    },
    {
      "epoch": 1.3484848484848486,
      "grad_norm": 4.0043439865112305,
      "learning_rate": 3.060606060606061e-05,
      "loss": 0.9982,
      "step": 2225
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 8.409883499145508,
      "learning_rate": 3.0325476992143658e-05,
      "loss": 0.7902,
      "step": 2250
    },
    {
      "epoch": 1.378787878787879,
      "grad_norm": 8.475225448608398,
      "learning_rate": 3.004489337822671e-05,
      "loss": 0.8343,
      "step": 2275
    },
    {
      "epoch": 1.393939393939394,
      "grad_norm": 4.989223480224609,
      "learning_rate": 2.976430976430977e-05,
      "loss": 0.8126,
      "step": 2300
    },
    {
      "epoch": 1.4090909090909092,
      "grad_norm": 5.526180267333984,
      "learning_rate": 2.9483726150392822e-05,
      "loss": 0.6589,
      "step": 2325
    },
    {
      "epoch": 1.4242424242424243,
      "grad_norm": 7.382469177246094,
      "learning_rate": 2.920314253647587e-05,
      "loss": 0.7384,
      "step": 2350
    },
    {
      "epoch": 1.4393939393939394,
      "grad_norm": 5.158092498779297,
      "learning_rate": 2.8922558922558923e-05,
      "loss": 0.6578,
      "step": 2375
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 4.976596832275391,
      "learning_rate": 2.8641975308641977e-05,
      "loss": 0.8378,
      "step": 2400
    },
    {
      "epoch": 1.4696969696969697,
      "grad_norm": 9.176383018493652,
      "learning_rate": 2.836139169472503e-05,
      "loss": 0.7935,
      "step": 2425
    },
    {
      "epoch": 1.4848484848484849,
      "grad_norm": 10.877906799316406,
      "learning_rate": 2.808080808080808e-05,
      "loss": 0.8241,
      "step": 2450
    },
    {
      "epoch": 1.5,
      "grad_norm": 12.3035249710083,
      "learning_rate": 2.7800224466891134e-05,
      "loss": 0.8298,
      "step": 2475
    },
    {
      "epoch": 1.5151515151515151,
      "grad_norm": 7.093743324279785,
      "learning_rate": 2.7519640852974188e-05,
      "loss": 0.7239,
      "step": 2500
    },
    {
      "epoch": 1.5303030303030303,
      "grad_norm": 14.64828872680664,
      "learning_rate": 2.7239057239057242e-05,
      "loss": 0.7086,
      "step": 2525
    },
    {
      "epoch": 1.5454545454545454,
      "grad_norm": 5.189187526702881,
      "learning_rate": 2.6958473625140296e-05,
      "loss": 0.7458,
      "step": 2550
    },
    {
      "epoch": 1.5606060606060606,
      "grad_norm": 7.915388107299805,
      "learning_rate": 2.6677890011223346e-05,
      "loss": 0.765,
      "step": 2575
    },
    {
      "epoch": 1.5757575757575757,
      "grad_norm": 5.491411209106445,
      "learning_rate": 2.63973063973064e-05,
      "loss": 0.8382,
      "step": 2600
    },
    {
      "epoch": 1.5909090909090908,
      "grad_norm": 10.231388092041016,
      "learning_rate": 2.6116722783389453e-05,
      "loss": 0.6905,
      "step": 2625
    },
    {
      "epoch": 1.606060606060606,
      "grad_norm": 4.599724769592285,
      "learning_rate": 2.5836139169472507e-05,
      "loss": 0.7544,
      "step": 2650
    },
    {
      "epoch": 1.621212121212121,
      "grad_norm": 9.038063049316406,
      "learning_rate": 2.5555555555555554e-05,
      "loss": 0.5843,
      "step": 2675
    },
    {
      "epoch": 1.6363636363636362,
      "grad_norm": 7.875892639160156,
      "learning_rate": 2.5274971941638608e-05,
      "loss": 0.7318,
      "step": 2700
    },
    {
      "epoch": 1.6515151515151514,
      "grad_norm": 7.997163772583008,
      "learning_rate": 2.499438832772166e-05,
      "loss": 0.6789,
      "step": 2725
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 12.051643371582031,
      "learning_rate": 2.4725028058361395e-05,
      "loss": 0.8427,
      "step": 2750
    },
    {
      "epoch": 1.6818181818181817,
      "grad_norm": 18.78903579711914,
      "learning_rate": 2.4444444444444445e-05,
      "loss": 0.7387,
      "step": 2775
    },
    {
      "epoch": 1.696969696969697,
      "grad_norm": 5.628903865814209,
      "learning_rate": 2.41638608305275e-05,
      "loss": 0.6316,
      "step": 2800
    },
    {
      "epoch": 1.7121212121212122,
      "grad_norm": 6.309241771697998,
      "learning_rate": 2.388327721661055e-05,
      "loss": 0.6701,
      "step": 2825
    },
    {
      "epoch": 1.7272727272727273,
      "grad_norm": 6.3270392417907715,
      "learning_rate": 2.3602693602693603e-05,
      "loss": 0.5524,
      "step": 2850
    },
    {
      "epoch": 1.7424242424242424,
      "grad_norm": 3.400372266769409,
      "learning_rate": 2.3322109988776656e-05,
      "loss": 0.6322,
      "step": 2875
    },
    {
      "epoch": 1.7575757575757576,
      "grad_norm": 10.937955856323242,
      "learning_rate": 2.304152637485971e-05,
      "loss": 0.5497,
      "step": 2900
    },
    {
      "epoch": 1.7727272727272727,
      "grad_norm": 9.74146842956543,
      "learning_rate": 2.2760942760942764e-05,
      "loss": 0.7272,
      "step": 2925
    },
    {
      "epoch": 1.7878787878787878,
      "grad_norm": 24.714502334594727,
      "learning_rate": 2.2480359147025814e-05,
      "loss": 0.7961,
      "step": 2950
    },
    {
      "epoch": 1.803030303030303,
      "grad_norm": 3.8761136531829834,
      "learning_rate": 2.2199775533108868e-05,
      "loss": 0.6801,
      "step": 2975
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 5.883018493652344,
      "learning_rate": 2.191919191919192e-05,
      "loss": 0.7082,
      "step": 3000
    },
    {
      "epoch": 1.8333333333333335,
      "grad_norm": 7.082830905914307,
      "learning_rate": 2.1638608305274975e-05,
      "loss": 0.5892,
      "step": 3025
    },
    {
      "epoch": 1.8484848484848486,
      "grad_norm": 10.057491302490234,
      "learning_rate": 2.1358024691358026e-05,
      "loss": 0.7226,
      "step": 3050
    },
    {
      "epoch": 1.8636363636363638,
      "grad_norm": 3.2809817790985107,
      "learning_rate": 2.107744107744108e-05,
      "loss": 0.546,
      "step": 3075
    },
    {
      "epoch": 1.878787878787879,
      "grad_norm": 8.243097305297852,
      "learning_rate": 2.079685746352413e-05,
      "loss": 0.6747,
      "step": 3100
    },
    {
      "epoch": 1.893939393939394,
      "grad_norm": 7.2149457931518555,
      "learning_rate": 2.0516273849607184e-05,
      "loss": 0.6502,
      "step": 3125
    },
    {
      "epoch": 1.9090909090909092,
      "grad_norm": 5.218500137329102,
      "learning_rate": 2.0235690235690234e-05,
      "loss": 0.5866,
      "step": 3150
    },
    {
      "epoch": 1.9242424242424243,
      "grad_norm": 8.202606201171875,
      "learning_rate": 1.995510662177329e-05,
      "loss": 0.7029,
      "step": 3175
    },
    {
      "epoch": 1.9393939393939394,
      "grad_norm": 10.254151344299316,
      "learning_rate": 1.967452300785634e-05,
      "loss": 0.6972,
      "step": 3200
    },
    {
      "epoch": 1.9545454545454546,
      "grad_norm": 3.413534641265869,
      "learning_rate": 1.9393939393939395e-05,
      "loss": 0.6599,
      "step": 3225
    },
    {
      "epoch": 1.9696969696969697,
      "grad_norm": 5.466010570526123,
      "learning_rate": 1.911335578002245e-05,
      "loss": 0.6938,
      "step": 3250
    },
    {
      "epoch": 1.9848484848484849,
      "grad_norm": 4.317994594573975,
      "learning_rate": 1.88327721661055e-05,
      "loss": 0.7309,
      "step": 3275
    },
    {
      "epoch": 2.0,
      "grad_norm": 7.49802303314209,
      "learning_rate": 1.8552188552188553e-05,
      "loss": 0.5147,
      "step": 3300
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8475757575757575,
      "eval_f1_macro": 0.8117394542384239,
      "eval_f1_micro": 0.8475757575757575,
      "eval_f1_weighted": 0.840866356559439,
      "eval_loss": 0.5004541873931885,
      "eval_precision_macro": 0.8356258037544531,
      "eval_precision_micro": 0.8475757575757575,
      "eval_precision_weighted": 0.8505208734646063,
      "eval_recall_macro": 0.8084166666666667,
      "eval_recall_micro": 0.8475757575757575,
      "eval_recall_weighted": 0.8475757575757575,
      "eval_runtime": 18.9039,
      "eval_samples_per_second": 174.567,
      "eval_steps_per_second": 10.95,
      "step": 3300
    },
    {
      "epoch": 2.015151515151515,
      "grad_norm": 4.281924247741699,
      "learning_rate": 1.8271604938271607e-05,
      "loss": 0.4413,
      "step": 3325
    },
    {
      "epoch": 2.0303030303030303,
      "grad_norm": 11.078526496887207,
      "learning_rate": 1.799102132435466e-05,
      "loss": 0.516,
      "step": 3350
    },
    {
      "epoch": 2.0454545454545454,
      "grad_norm": 12.010851860046387,
      "learning_rate": 1.771043771043771e-05,
      "loss": 0.6546,
      "step": 3375
    },
    {
      "epoch": 2.0606060606060606,
      "grad_norm": 6.438499450683594,
      "learning_rate": 1.7429854096520764e-05,
      "loss": 0.6509,
      "step": 3400
    },
    {
      "epoch": 2.0757575757575757,
      "grad_norm": 2.6832661628723145,
      "learning_rate": 1.7149270482603815e-05,
      "loss": 0.6495,
      "step": 3425
    },
    {
      "epoch": 2.090909090909091,
      "grad_norm": 6.37797737121582,
      "learning_rate": 1.686868686868687e-05,
      "loss": 0.6738,
      "step": 3450
    },
    {
      "epoch": 2.106060606060606,
      "grad_norm": 5.069665908813477,
      "learning_rate": 1.6588103254769922e-05,
      "loss": 0.5145,
      "step": 3475
    },
    {
      "epoch": 2.121212121212121,
      "grad_norm": 12.002437591552734,
      "learning_rate": 1.6307519640852976e-05,
      "loss": 0.7411,
      "step": 3500
    },
    {
      "epoch": 2.1363636363636362,
      "grad_norm": 4.099394798278809,
      "learning_rate": 1.6026936026936026e-05,
      "loss": 0.6736,
      "step": 3525
    },
    {
      "epoch": 2.1515151515151514,
      "grad_norm": 11.855905532836914,
      "learning_rate": 1.574635241301908e-05,
      "loss": 0.4738,
      "step": 3550
    },
    {
      "epoch": 2.1666666666666665,
      "grad_norm": 9.715377807617188,
      "learning_rate": 1.5465768799102134e-05,
      "loss": 0.5321,
      "step": 3575
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 10.646961212158203,
      "learning_rate": 1.5185185185185186e-05,
      "loss": 0.5856,
      "step": 3600
    },
    {
      "epoch": 2.196969696969697,
      "grad_norm": 9.710843086242676,
      "learning_rate": 1.490460157126824e-05,
      "loss": 0.6343,
      "step": 3625
    },
    {
      "epoch": 2.212121212121212,
      "grad_norm": 5.35206937789917,
      "learning_rate": 1.4624017957351292e-05,
      "loss": 0.7256,
      "step": 3650
    },
    {
      "epoch": 2.227272727272727,
      "grad_norm": 6.582408428192139,
      "learning_rate": 1.4343434343434345e-05,
      "loss": 0.5843,
      "step": 3675
    },
    {
      "epoch": 2.242424242424242,
      "grad_norm": 11.637269973754883,
      "learning_rate": 1.4062850729517396e-05,
      "loss": 0.5725,
      "step": 3700
    },
    {
      "epoch": 2.257575757575758,
      "grad_norm": 11.256560325622559,
      "learning_rate": 1.378226711560045e-05,
      "loss": 0.5129,
      "step": 3725
    },
    {
      "epoch": 2.2727272727272725,
      "grad_norm": 4.118545055389404,
      "learning_rate": 1.3501683501683501e-05,
      "loss": 0.6303,
      "step": 3750
    },
    {
      "epoch": 2.287878787878788,
      "grad_norm": 8.819905281066895,
      "learning_rate": 1.3221099887766555e-05,
      "loss": 0.4861,
      "step": 3775
    },
    {
      "epoch": 2.303030303030303,
      "grad_norm": 11.89466667175293,
      "learning_rate": 1.2940516273849607e-05,
      "loss": 0.6803,
      "step": 3800
    },
    {
      "epoch": 2.3181818181818183,
      "grad_norm": 14.192046165466309,
      "learning_rate": 1.2659932659932661e-05,
      "loss": 0.6194,
      "step": 3825
    },
    {
      "epoch": 2.3333333333333335,
      "grad_norm": 8.376368522644043,
      "learning_rate": 1.2379349046015713e-05,
      "loss": 0.5394,
      "step": 3850
    },
    {
      "epoch": 2.3484848484848486,
      "grad_norm": 2.375666856765747,
      "learning_rate": 1.2098765432098767e-05,
      "loss": 0.5348,
      "step": 3875
    },
    {
      "epoch": 2.3636363636363638,
      "grad_norm": 6.248928070068359,
      "learning_rate": 1.1818181818181819e-05,
      "loss": 0.6926,
      "step": 3900
    },
    {
      "epoch": 2.378787878787879,
      "grad_norm": 3.3347110748291016,
      "learning_rate": 1.153759820426487e-05,
      "loss": 0.5196,
      "step": 3925
    },
    {
      "epoch": 2.393939393939394,
      "grad_norm": 7.418989658355713,
      "learning_rate": 1.1257014590347924e-05,
      "loss": 0.5975,
      "step": 3950
    },
    {
      "epoch": 2.409090909090909,
      "grad_norm": 17.091835021972656,
      "learning_rate": 1.0976430976430976e-05,
      "loss": 0.5818,
      "step": 3975
    },
    {
      "epoch": 2.4242424242424243,
      "grad_norm": 4.748253345489502,
      "learning_rate": 1.0695847362514029e-05,
      "loss": 0.5008,
      "step": 4000
    },
    {
      "epoch": 2.4393939393939394,
      "grad_norm": 2.7156593799591064,
      "learning_rate": 1.0415263748597082e-05,
      "loss": 0.5977,
      "step": 4025
    },
    {
      "epoch": 2.4545454545454546,
      "grad_norm": 3.704885482788086,
      "learning_rate": 1.0134680134680136e-05,
      "loss": 0.428,
      "step": 4050
    },
    {
      "epoch": 2.4696969696969697,
      "grad_norm": 6.289621829986572,
      "learning_rate": 9.854096520763188e-06,
      "loss": 0.6108,
      "step": 4075
    },
    {
      "epoch": 2.484848484848485,
      "grad_norm": 11.862101554870605,
      "learning_rate": 9.573512906846242e-06,
      "loss": 0.6182,
      "step": 4100
    },
    {
      "epoch": 2.5,
      "grad_norm": 2.4363837242126465,
      "learning_rate": 9.292929292929294e-06,
      "loss": 0.6187,
      "step": 4125
    },
    {
      "epoch": 2.515151515151515,
      "grad_norm": 4.281114101409912,
      "learning_rate": 9.012345679012346e-06,
      "loss": 0.5247,
      "step": 4150
    },
    {
      "epoch": 2.5303030303030303,
      "grad_norm": 7.008238315582275,
      "learning_rate": 8.7317620650954e-06,
      "loss": 0.4063,
      "step": 4175
    },
    {
      "epoch": 2.5454545454545454,
      "grad_norm": 10.460261344909668,
      "learning_rate": 8.451178451178452e-06,
      "loss": 0.4699,
      "step": 4200
    },
    {
      "epoch": 2.5606060606060606,
      "grad_norm": 6.779576301574707,
      "learning_rate": 8.170594837261504e-06,
      "loss": 0.632,
      "step": 4225
    },
    {
      "epoch": 2.5757575757575757,
      "grad_norm": 12.081551551818848,
      "learning_rate": 7.890011223344557e-06,
      "loss": 0.5803,
      "step": 4250
    },
    {
      "epoch": 2.590909090909091,
      "grad_norm": 14.813763618469238,
      "learning_rate": 7.609427609427609e-06,
      "loss": 0.5825,
      "step": 4275
    },
    {
      "epoch": 2.606060606060606,
      "grad_norm": 3.7761809825897217,
      "learning_rate": 7.328843995510662e-06,
      "loss": 0.4587,
      "step": 4300
    },
    {
      "epoch": 2.621212121212121,
      "grad_norm": 2.71801495552063,
      "learning_rate": 7.048260381593716e-06,
      "loss": 0.5465,
      "step": 4325
    },
    {
      "epoch": 2.6363636363636362,
      "grad_norm": 5.783569812774658,
      "learning_rate": 6.767676767676769e-06,
      "loss": 0.5003,
      "step": 4350
    },
    {
      "epoch": 2.6515151515151514,
      "grad_norm": 12.182541847229004,
      "learning_rate": 6.487093153759821e-06,
      "loss": 0.5783,
      "step": 4375
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 12.15306282043457,
      "learning_rate": 6.206509539842874e-06,
      "loss": 0.5159,
      "step": 4400
    },
    {
      "epoch": 2.6818181818181817,
      "grad_norm": 8.337636947631836,
      "learning_rate": 5.925925925925927e-06,
      "loss": 0.4119,
      "step": 4425
    },
    {
      "epoch": 2.6969696969696972,
      "grad_norm": 3.530006170272827,
      "learning_rate": 5.645342312008979e-06,
      "loss": 0.4734,
      "step": 4450
    },
    {
      "epoch": 2.712121212121212,
      "grad_norm": 7.290157794952393,
      "learning_rate": 5.364758698092032e-06,
      "loss": 0.5549,
      "step": 4475
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 6.58420467376709,
      "learning_rate": 5.0841750841750845e-06,
      "loss": 0.4441,
      "step": 4500
    },
    {
      "epoch": 2.742424242424242,
      "grad_norm": 4.345494747161865,
      "learning_rate": 4.803591470258137e-06,
      "loss": 0.48,
      "step": 4525
    },
    {
      "epoch": 2.757575757575758,
      "grad_norm": 10.148066520690918,
      "learning_rate": 4.523007856341189e-06,
      "loss": 0.4423,
      "step": 4550
    },
    {
      "epoch": 2.7727272727272725,
      "grad_norm": 6.80890417098999,
      "learning_rate": 4.242424242424243e-06,
      "loss": 0.4497,
      "step": 4575
    },
    {
      "epoch": 2.787878787878788,
      "grad_norm": 9.686090469360352,
      "learning_rate": 3.961840628507295e-06,
      "loss": 0.3885,
      "step": 4600
    },
    {
      "epoch": 2.8030303030303028,
      "grad_norm": 6.605715274810791,
      "learning_rate": 3.681257014590348e-06,
      "loss": 0.4989,
      "step": 4625
    },
    {
      "epoch": 2.8181818181818183,
      "grad_norm": 5.217257499694824,
      "learning_rate": 3.400673400673401e-06,
      "loss": 0.5379,
      "step": 4650
    },
    {
      "epoch": 2.8333333333333335,
      "grad_norm": 8.507195472717285,
      "learning_rate": 3.1200897867564538e-06,
      "loss": 0.6228,
      "step": 4675
    },
    {
      "epoch": 2.8484848484848486,
      "grad_norm": 5.713125228881836,
      "learning_rate": 2.8395061728395062e-06,
      "loss": 0.4659,
      "step": 4700
    },
    {
      "epoch": 2.8636363636363638,
      "grad_norm": 13.924797058105469,
      "learning_rate": 2.558922558922559e-06,
      "loss": 0.5267,
      "step": 4725
    },
    {
      "epoch": 2.878787878787879,
      "grad_norm": 9.560832023620605,
      "learning_rate": 2.2783389450056116e-06,
      "loss": 0.5839,
      "step": 4750
    },
    {
      "epoch": 2.893939393939394,
      "grad_norm": 4.680112361907959,
      "learning_rate": 1.9977553310886645e-06,
      "loss": 0.3282,
      "step": 4775
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": 3.320807695388794,
      "learning_rate": 1.7171717171717171e-06,
      "loss": 0.4741,
      "step": 4800
    },
    {
      "epoch": 2.9242424242424243,
      "grad_norm": 6.167539119720459,
      "learning_rate": 1.43658810325477e-06,
      "loss": 0.5005,
      "step": 4825
    },
    {
      "epoch": 2.9393939393939394,
      "grad_norm": 6.241283893585205,
      "learning_rate": 1.156004489337823e-06,
      "loss": 0.4634,
      "step": 4850
    },
    {
      "epoch": 2.9545454545454546,
      "grad_norm": 2.0378332138061523,
      "learning_rate": 8.754208754208755e-07,
      "loss": 0.4892,
      "step": 4875
    },
    {
      "epoch": 2.9696969696969697,
      "grad_norm": 8.896339416503906,
      "learning_rate": 5.948372615039282e-07,
      "loss": 0.5611,
      "step": 4900
    },
    {
      "epoch": 2.984848484848485,
      "grad_norm": 2.1297545433044434,
      "learning_rate": 3.1425364758698096e-07,
      "loss": 0.516,
      "step": 4925
    },
    {
      "epoch": 3.0,
      "grad_norm": 10.862909317016602,
      "learning_rate": 3.367003367003367e-08,
      "loss": 0.4453,
      "step": 4950
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.886969696969697,
      "eval_f1_macro": 0.8644630522360383,
      "eval_f1_micro": 0.886969696969697,
      "eval_f1_weighted": 0.8837489529217776,
      "eval_loss": 0.3821594715118408,
      "eval_precision_macro": 0.8700338902181693,
      "eval_precision_micro": 0.886969696969697,
      "eval_precision_weighted": 0.8838390180385471,
      "eval_recall_macro": 0.8628333333333335,
      "eval_recall_micro": 0.886969696969697,
      "eval_recall_weighted": 0.886969696969697,
      "eval_runtime": 18.9146,
      "eval_samples_per_second": 174.469,
      "eval_steps_per_second": 10.944,
      "step": 4950
    }
  ],
  "logging_steps": 25,
  "max_steps": 4950,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.01
      },
      "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": 1.084816011852841e+19,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}