{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9852216748768474,
  "eval_steps": 500,
  "global_step": 202,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04926108374384237,
      "grad_norm": 108.0,
      "learning_rate": 2.52589e-06,
      "logits/chosen": 0.06021759659051895,
      "logits/rejected": -0.009350213222205639,
      "logps/chosen": -714.9625244140625,
      "logps/rejected": -992.0533447265625,
      "loss": 0.6838,
      "rewards/accuracies": 0.366666704416275,
      "rewards/chosen": 0.011166826821863651,
      "rewards/margins": 0.022149886935949326,
      "rewards/rejected": -0.010983060114085674,
      "step": 5
    },
    {
      "epoch": 0.09852216748768473,
      "grad_norm": 73.5,
      "learning_rate": 5.6832524999999995e-06,
      "logits/chosen": 0.045873817056417465,
      "logits/rejected": 0.003844240214675665,
      "logps/chosen": -671.487060546875,
      "logps/rejected": -1002.9957885742188,
      "loss": 0.5469,
      "rewards/accuracies": 0.8999999761581421,
      "rewards/chosen": 0.0998205691576004,
      "rewards/margins": 0.3382015824317932,
      "rewards/rejected": -0.2383810579776764,
      "step": 10
    },
    {
      "epoch": 0.1477832512315271,
      "grad_norm": 30.625,
      "learning_rate": 8.840615e-06,
      "logits/chosen": -0.023920465260744095,
      "logits/rejected": 0.042549438774585724,
      "logps/chosen": -677.3431396484375,
      "logps/rejected": -989.5335693359375,
      "loss": 0.2497,
      "rewards/accuracies": 0.98333340883255,
      "rewards/chosen": 0.3677126467227936,
      "rewards/margins": 1.4746158123016357,
      "rewards/rejected": -1.106903076171875,
      "step": 15
    },
    {
      "epoch": 0.19704433497536947,
      "grad_norm": 3.71875,
      "learning_rate": 1.19979775e-05,
      "logits/chosen": 0.008176160976290703,
      "logits/rejected": 0.018394723534584045,
      "logps/chosen": -703.6475830078125,
      "logps/rejected": -1041.759765625,
      "loss": 0.0449,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.787887454032898,
      "rewards/margins": 4.096963405609131,
      "rewards/rejected": -3.3090755939483643,
      "step": 20
    },
    {
      "epoch": 0.24630541871921183,
      "grad_norm": 12.5,
      "learning_rate": 1.5155340000000002e-05,
      "logits/chosen": -0.024350730702280998,
      "logits/rejected": 0.03716661036014557,
      "logps/chosen": -717.7275390625,
      "logps/rejected": -1072.546630859375,
      "loss": 0.0161,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.2740657329559326,
      "rewards/margins": 7.921713829040527,
      "rewards/rejected": -6.647648811340332,
      "step": 25
    },
    {
      "epoch": 0.2955665024630542,
      "grad_norm": 0.2109375,
      "learning_rate": 1.8312702500000002e-05,
      "logits/chosen": 0.02022477611899376,
      "logits/rejected": -0.005769997835159302,
      "logps/chosen": -672.1201171875,
      "logps/rejected": -1118.390380859375,
      "loss": 0.0009,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.8031457662582397,
      "rewards/margins": 12.140481948852539,
      "rewards/rejected": -10.337335586547852,
      "step": 30
    },
    {
      "epoch": 0.3448275862068966,
      "grad_norm": 8.6875,
      "learning_rate": 2.1470065e-05,
      "logits/chosen": 0.0037163645029067993,
      "logits/rejected": -0.027010012418031693,
      "logps/chosen": -665.9528198242188,
      "logps/rejected": -1054.0537109375,
      "loss": 0.0097,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.6622908115386963,
      "rewards/margins": 13.775215148925781,
      "rewards/rejected": -12.112924575805664,
      "step": 35
    },
    {
      "epoch": 0.39408866995073893,
      "grad_norm": 4.53125,
      "learning_rate": 2.2092428004483083e-05,
      "logits/chosen": 0.0688682422041893,
      "logits/rejected": 0.05512089654803276,
      "logps/chosen": -715.6795654296875,
      "logps/rejected": -1175.619140625,
      "loss": 0.0022,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 2.4531707763671875,
      "rewards/margins": 15.8966703414917,
      "rewards/rejected": -13.443501472473145,
      "step": 40
    },
    {
      "epoch": 0.4433497536945813,
      "grad_norm": 0.0022735595703125,
      "learning_rate": 2.205545499586072e-05,
      "logits/chosen": -0.025104057043790817,
      "logits/rejected": -0.059289705008268356,
      "logps/chosen": -683.1431884765625,
      "logps/rejected": -1164.0970458984375,
      "loss": 0.0002,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 2.8538169860839844,
      "rewards/margins": 16.61087989807129,
      "rewards/rejected": -13.757061958312988,
      "step": 45
    },
    {
      "epoch": 0.49261083743842365,
      "grad_norm": 0.5078125,
      "learning_rate": 2.1990176011484834e-05,
      "logits/chosen": 0.06939034163951874,
      "logits/rejected": -0.03862878680229187,
      "logps/chosen": -663.315185546875,
      "logps/rejected": -1101.8394775390625,
      "loss": 0.0012,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 2.704948663711548,
      "rewards/margins": 16.27048110961914,
      "rewards/rejected": -13.565534591674805,
      "step": 50
    },
    {
      "epoch": 0.541871921182266,
      "grad_norm": 1.09375,
      "learning_rate": 2.1896815242896443e-05,
      "logits/chosen": -0.07729315012693405,
      "logits/rejected": -0.07702396810054779,
      "logps/chosen": -613.7337036132812,
      "logps/rejected": -1092.618408203125,
      "loss": 0.0014,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 2.867260694503784,
      "rewards/margins": 16.498395919799805,
      "rewards/rejected": -13.631135940551758,
      "step": 55
    },
    {
      "epoch": 0.5911330049261084,
      "grad_norm": 0.002410888671875,
      "learning_rate": 2.1775693324596527e-05,
      "logits/chosen": -0.03670992702245712,
      "logits/rejected": -0.035895608365535736,
      "logps/chosen": -666.19970703125,
      "logps/rejected": -1143.6500244140625,
      "loss": 0.0005,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.211841583251953,
      "rewards/margins": 17.307846069335938,
      "rewards/rejected": -14.0960054397583,
      "step": 60
    },
    {
      "epoch": 0.6403940886699507,
      "grad_norm": 0.001922607421875,
      "learning_rate": 2.1627226232871688e-05,
      "logits/chosen": -0.031517110764980316,
      "logits/rejected": -0.16813872754573822,
      "logps/chosen": -728.2982177734375,
      "logps/rejected": -1131.3756103515625,
      "loss": 0.0001,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.4621803760528564,
      "rewards/margins": 17.45178985595703,
      "rewards/rejected": -13.98961067199707,
      "step": 65
    },
    {
      "epoch": 0.6896551724137931,
      "grad_norm": 0.11474609375,
      "learning_rate": 2.1451923857181784e-05,
      "logits/chosen": -0.003007475985214114,
      "logits/rejected": -0.1008603423833847,
      "logps/chosen": -675.1759033203125,
      "logps/rejected": -1094.3150634765625,
      "loss": 0.0007,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.4204094409942627,
      "rewards/margins": 16.498920440673828,
      "rewards/rejected": -13.078511238098145,
      "step": 70
    },
    {
      "epoch": 0.7389162561576355,
      "grad_norm": 0.302734375,
      "learning_rate": 2.12503882490159e-05,
      "logits/chosen": -0.08852293342351913,
      "logits/rejected": -0.10156140476465225,
      "logps/chosen": -670.6781005859375,
      "logps/rejected": -1148.835693359375,
      "loss": 0.0003,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.3611931800842285,
      "rewards/margins": 16.560178756713867,
      "rewards/rejected": -13.198987007141113,
      "step": 75
    },
    {
      "epoch": 0.7881773399014779,
      "grad_norm": 0.29296875,
      "learning_rate": 2.1023311554230692e-05,
      "logits/chosen": 0.0469479113817215,
      "logits/rejected": -0.06342597305774689,
      "logps/chosen": -684.2789916992188,
      "logps/rejected": -1146.1676025390625,
      "loss": 0.0002,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.4045166969299316,
      "rewards/margins": 16.89340591430664,
      "rewards/rejected": -13.488889694213867,
      "step": 80
    },
    {
      "epoch": 0.8374384236453202,
      "grad_norm": 0.1240234375,
      "learning_rate": 2.0771473635972312e-05,
      "logits/chosen": -0.07357874512672424,
      "logits/rejected": -0.06026272848248482,
      "logps/chosen": -642.2686767578125,
      "logps/rejected": -1190.205810546875,
      "loss": 0.0001,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.354203701019287,
      "rewards/margins": 17.001527786254883,
      "rewards/rejected": -13.647323608398438,
      "step": 85
    },
    {
      "epoch": 0.8866995073891626,
      "grad_norm": 0.060302734375,
      "learning_rate": 2.0495739396345457e-05,
      "logits/chosen": -0.08571887761354446,
      "logits/rejected": -0.1507987231016159,
      "logps/chosen": -629.473388671875,
      "logps/rejected": -1103.9293212890625,
      "loss": 0.0003,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.417731761932373,
      "rewards/margins": 17.251663208007812,
      "rewards/rejected": -13.833930969238281,
      "step": 90
    },
    {
      "epoch": 0.9359605911330049,
      "grad_norm": 0.0128173828125,
      "learning_rate": 2.01970558060281e-05,
      "logits/chosen": -0.027310481294989586,
      "logits/rejected": -0.04605848342180252,
      "logps/chosen": -725.526611328125,
      "logps/rejected": -1180.865478515625,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.788097858428955,
      "rewards/margins": 17.4461727142334,
      "rewards/rejected": -13.658073425292969,
      "step": 95
    },
    {
      "epoch": 0.9852216748768473,
      "grad_norm": 0.004241943359375,
      "learning_rate": 1.9876448652033145e-05,
      "logits/chosen": -0.12386312335729599,
      "logits/rejected": -0.10513818264007568,
      "logps/chosen": -615.34033203125,
      "logps/rejected": -1112.7601318359375,
      "loss": 0.001,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.5329208374023438,
      "rewards/margins": 16.703248977661133,
      "rewards/rejected": -13.170324325561523,
      "step": 100
    },
    {
      "epoch": 0.9950738916256158,
      "eval_logits/chosen": -0.11170963197946548,
      "eval_logits/rejected": -0.11342550069093704,
      "eval_logps/chosen": -621.7440795898438,
      "eval_logps/rejected": -1078.06591796875,
      "eval_loss": 0.00033413898199796677,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/chosen": 3.6759870052337646,
      "eval_rewards/margins": 16.46457862854004,
      "eval_rewards/rejected": -12.788591384887695,
      "eval_runtime": 16.5627,
      "eval_samples_per_second": 12.075,
      "eval_steps_per_second": 12.075,
      "step": 101
    },
    {
      "epoch": 1.0295566502463054,
      "grad_norm": 0.006683349609375,
      "learning_rate": 1.9535019014786414e-05,
      "logits/chosen": -0.06293856352567673,
      "logits/rejected": -0.09947305917739868,
      "logps/chosen": -672.5732421875,
      "logps/rejected": -1174.2159423828125,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.6842219829559326,
      "rewards/margins": 17.364566802978516,
      "rewards/rejected": -13.680344581604004,
      "step": 105
    },
    {
      "epoch": 1.0788177339901477,
      "grad_norm": 0.0015106201171875,
      "learning_rate": 1.9173939486619933e-05,
      "logits/chosen": -0.05223611742258072,
      "logits/rejected": -0.10244528949260712,
      "logps/chosen": -647.3909912109375,
      "logps/rejected": -1189.0113525390625,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 4.147972583770752,
      "rewards/margins": 17.80228614807129,
      "rewards/rejected": -13.654312133789062,
      "step": 110
    },
    {
      "epoch": 1.1280788177339902,
      "grad_norm": 0.01220703125,
      "learning_rate": 1.8794450144667584e-05,
      "logits/chosen": -0.03947216272354126,
      "logits/rejected": -0.12559063732624054,
      "logps/chosen": -772.1909790039062,
      "logps/rejected": -1098.6795654296875,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 4.7596025466918945,
      "rewards/margins": 18.306901931762695,
      "rewards/rejected": -13.547297477722168,
      "step": 115
    },
    {
      "epoch": 1.1773399014778325,
      "grad_norm": 0.000743865966796875,
      "learning_rate": 1.839785429199364e-05,
      "logits/chosen": -0.0065459804609417915,
      "logits/rejected": -0.1465989649295807,
      "logps/chosen": -711.794189453125,
      "logps/rejected": -1193.7640380859375,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 4.160403251647949,
      "rewards/margins": 18.479259490966797,
      "rewards/rejected": -14.318857192993164,
      "step": 120
    },
    {
      "epoch": 1.2266009852216748,
      "grad_norm": 0.003936767578125,
      "learning_rate": 1.7985513981580707e-05,
      "logits/chosen": -0.0810680016875267,
      "logits/rejected": -0.14764997363090515,
      "logps/chosen": -656.9730224609375,
      "logps/rejected": -1095.385986328125,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.6672158241271973,
      "rewards/margins": 17.432126998901367,
      "rewards/rejected": -13.764910697937012,
      "step": 125
    },
    {
      "epoch": 1.2758620689655173,
      "grad_norm": 0.0162353515625,
      "learning_rate": 1.7558845338549242e-05,
      "logits/chosen": -0.07523246854543686,
      "logits/rejected": -0.25009721517562866,
      "logps/chosen": -668.7523193359375,
      "logps/rejected": -1086.5867919921875,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 4.281540393829346,
      "rewards/margins": 17.89385986328125,
      "rewards/rejected": -13.61231803894043,
      "step": 130
    },
    {
      "epoch": 1.3251231527093597,
      "grad_norm": 0.002838134765625,
      "learning_rate": 1.711931369667393e-05,
      "logits/chosen": -0.1100362166762352,
      "logits/rejected": -0.200296089053154,
      "logps/chosen": -666.0404052734375,
      "logps/rejected": -1082.836669921875,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.762917995452881,
      "rewards/margins": 17.2962703704834,
      "rewards/rejected": -13.533352851867676,
      "step": 135
    },
    {
      "epoch": 1.374384236453202,
      "grad_norm": 0.0068359375,
      "learning_rate": 1.666842856589978e-05,
      "logits/chosen": -0.11170603334903717,
      "logits/rejected": -0.11424056440591812,
      "logps/chosen": -634.7129516601562,
      "logps/rejected": -1162.6055908203125,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.8669981956481934,
      "rewards/margins": 17.46556854248047,
      "rewards/rejected": -13.59857177734375,
      "step": 140
    },
    {
      "epoch": 1.4236453201970443,
      "grad_norm": 0.0010833740234375,
      "learning_rate": 1.6207738448141366e-05,
      "logits/chosen": -0.07618793845176697,
      "logits/rejected": -0.1659926474094391,
      "logps/chosen": -629.3489379882812,
      "logps/rejected": -1141.2314453125,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.594289779663086,
      "rewards/margins": 17.63915252685547,
      "rewards/rejected": -14.044862747192383,
      "step": 145
    },
    {
      "epoch": 1.4729064039408866,
      "grad_norm": 0.0028839111328125,
      "learning_rate": 1.573882551916961e-05,
      "logits/chosen": -0.1288968324661255,
      "logits/rejected": -0.11787639558315277,
      "logps/chosen": -682.9420166015625,
      "logps/rejected": -1165.747802734375,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.8218026161193848,
      "rewards/margins": 17.532339096069336,
      "rewards/rejected": -13.710535049438477,
      "step": 150
    },
    {
      "epoch": 1.522167487684729,
      "grad_norm": 0.0712890625,
      "learning_rate": 1.5263300194850375e-05,
      "logits/chosen": -0.14020918309688568,
      "logits/rejected": -0.17282378673553467,
      "logps/chosen": -562.5584716796875,
      "logps/rejected": -1065.2425537109375,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.819398880004883,
      "rewards/margins": 16.870691299438477,
      "rewards/rejected": -13.051290512084961,
      "step": 155
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 0.01177978515625,
      "learning_rate": 1.478279560039646e-05,
      "logits/chosen": 0.0017956334631890059,
      "logits/rejected": -0.04993182793259621,
      "logps/chosen": -631.7723388671875,
      "logps/rejected": -1118.0230712890625,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.4135658740997314,
      "rewards/margins": 16.631460189819336,
      "rewards/rejected": -13.217893600463867,
      "step": 160
    },
    {
      "epoch": 1.6206896551724137,
      "grad_norm": 0.0032806396484375,
      "learning_rate": 1.429896196162745e-05,
      "logits/chosen": -0.10030888020992279,
      "logits/rejected": -0.0873989462852478,
      "logps/chosen": -593.56884765625,
      "logps/rejected": -1196.1925048828125,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 4.140743255615234,
      "rewards/margins": 18.093753814697266,
      "rewards/rejected": -13.953012466430664,
      "step": 165
    },
    {
      "epoch": 1.6699507389162562,
      "grad_norm": 0.004180908203125,
      "learning_rate": 1.3813460937500001e-05,
      "logits/chosen": -0.022314613685011864,
      "logits/rejected": -0.1113683357834816,
      "logps/chosen": -704.1790771484375,
      "logps/rejected": -1212.56103515625,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.9814553260803223,
      "rewards/margins": 18.219303131103516,
      "rewards/rejected": -14.237849235534668,
      "step": 170
    },
    {
      "epoch": 1.7192118226600985,
      "grad_norm": 0.0185546875,
      "learning_rate": 1.332795991337255e-05,
      "logits/chosen": -0.0795547217130661,
      "logits/rejected": -0.18906092643737793,
      "logps/chosen": -714.6734619140625,
      "logps/rejected": -1112.668212890625,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 4.523798942565918,
      "rewards/margins": 18.23130989074707,
      "rewards/rejected": -13.70750904083252,
      "step": 175
    },
    {
      "epoch": 1.7684729064039408,
      "grad_norm": 0.000331878662109375,
      "learning_rate": 1.2844126274603544e-05,
      "logits/chosen": -0.04283156991004944,
      "logits/rejected": -0.11096321046352386,
      "logps/chosen": -729.1672973632812,
      "logps/rejected": -1158.585205078125,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 4.16518497467041,
      "rewards/margins": 17.872875213623047,
      "rewards/rejected": -13.707687377929688,
      "step": 180
    },
    {
      "epoch": 1.8177339901477834,
      "grad_norm": 0.005584716796875,
      "learning_rate": 1.2363621680149627e-05,
      "logits/chosen": 0.017648298293352127,
      "logits/rejected": -0.08744337409734726,
      "logps/chosen": -655.9172973632812,
      "logps/rejected": -1120.0281982421875,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.544255495071411,
      "rewards/margins": 17.05453109741211,
      "rewards/rejected": -13.510274887084961,
      "step": 185
    },
    {
      "epoch": 1.8669950738916257,
      "grad_norm": 0.00147247314453125,
      "learning_rate": 1.1888096355830394e-05,
      "logits/chosen": -0.009853709489107132,
      "logits/rejected": -0.07630355656147003,
      "logps/chosen": -641.5875244140625,
      "logps/rejected": -1153.7431640625,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.8983428478240967,
      "rewards/margins": 17.25222396850586,
      "rewards/rejected": -13.353883743286133,
      "step": 190
    },
    {
      "epoch": 1.916256157635468,
      "grad_norm": 0.040771484375,
      "learning_rate": 1.1419183426858638e-05,
      "logits/chosen": -0.11551934480667114,
      "logits/rejected": -0.1467764675617218,
      "logps/chosen": -606.7501220703125,
      "logps/rejected": -1105.7303466796875,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 4.016844749450684,
      "rewards/margins": 17.583324432373047,
      "rewards/rejected": -13.56648063659668,
      "step": 195
    },
    {
      "epoch": 1.9655172413793105,
      "grad_norm": 0.029541015625,
      "learning_rate": 1.0958493309100225e-05,
      "logits/chosen": -0.050420112907886505,
      "logits/rejected": -0.09584550559520721,
      "logps/chosen": -662.5157470703125,
      "logps/rejected": -1182.98486328125,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 4.08192253112793,
      "rewards/margins": 18.255043029785156,
      "rewards/rejected": -14.173120498657227,
      "step": 200
    },
    {
      "epoch": 1.9852216748768474,
      "eval_logits/chosen": -0.11707988381385803,
      "eval_logits/rejected": -0.12201124429702759,
      "eval_logps/chosen": -621.3673706054688,
      "eval_logps/rejected": -1078.1207275390625,
      "eval_loss": 0.00028668390586972237,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/chosen": 3.7136542797088623,
      "eval_rewards/margins": 16.507728576660156,
      "eval_rewards/rejected": -12.794075012207031,
      "eval_runtime": 17.6249,
      "eval_samples_per_second": 11.348,
      "eval_steps_per_second": 11.348,
      "step": 202
    }
  ],
  "logging_steps": 5,
  "max_steps": 303,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 12,
  "trial_name": null,
  "trial_params": null
}