{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 2370,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004219409282700422,
      "grad_norm": 3.1438205242156982,
      "learning_rate": 8.438818565400843e-07,
      "loss": 2.5933,
      "step": 1
    },
    {
      "epoch": 0.02109704641350211,
      "grad_norm": 3.45337176322937,
      "learning_rate": 4.219409282700422e-06,
      "loss": 2.5683,
      "step": 5
    },
    {
      "epoch": 0.04219409282700422,
      "grad_norm": 3.8354620933532715,
      "learning_rate": 8.438818565400844e-06,
      "loss": 2.567,
      "step": 10
    },
    {
      "epoch": 0.06329113924050633,
      "grad_norm": 3.2700271606445312,
      "learning_rate": 1.2658227848101267e-05,
      "loss": 2.4327,
      "step": 15
    },
    {
      "epoch": 0.08438818565400844,
      "grad_norm": 3.2498395442962646,
      "learning_rate": 1.6877637130801688e-05,
      "loss": 2.2197,
      "step": 20
    },
    {
      "epoch": 0.10548523206751055,
      "grad_norm": 2.3556034564971924,
      "learning_rate": 2.1097046413502112e-05,
      "loss": 1.8787,
      "step": 25
    },
    {
      "epoch": 0.12658227848101267,
      "grad_norm": 1.5979266166687012,
      "learning_rate": 2.5316455696202533e-05,
      "loss": 1.5467,
      "step": 30
    },
    {
      "epoch": 0.14767932489451477,
      "grad_norm": 1.260302186012268,
      "learning_rate": 2.9535864978902954e-05,
      "loss": 1.4303,
      "step": 35
    },
    {
      "epoch": 0.16877637130801687,
      "grad_norm": 0.5591890811920166,
      "learning_rate": 3.3755274261603375e-05,
      "loss": 1.3705,
      "step": 40
    },
    {
      "epoch": 0.189873417721519,
      "grad_norm": 0.5186863541603088,
      "learning_rate": 3.79746835443038e-05,
      "loss": 1.328,
      "step": 45
    },
    {
      "epoch": 0.2109704641350211,
      "grad_norm": 0.5181670188903809,
      "learning_rate": 4.2194092827004224e-05,
      "loss": 1.2614,
      "step": 50
    },
    {
      "epoch": 0.2320675105485232,
      "grad_norm": 0.5109447240829468,
      "learning_rate": 4.641350210970464e-05,
      "loss": 1.2328,
      "step": 55
    },
    {
      "epoch": 0.25316455696202533,
      "grad_norm": 0.4200008809566498,
      "learning_rate": 5.0632911392405066e-05,
      "loss": 1.1882,
      "step": 60
    },
    {
      "epoch": 0.2742616033755274,
      "grad_norm": 0.37015053629875183,
      "learning_rate": 5.4852320675105484e-05,
      "loss": 1.1461,
      "step": 65
    },
    {
      "epoch": 0.29535864978902954,
      "grad_norm": 0.39964228868484497,
      "learning_rate": 5.907172995780591e-05,
      "loss": 1.1336,
      "step": 70
    },
    {
      "epoch": 0.31645569620253167,
      "grad_norm": 0.3632591962814331,
      "learning_rate": 6.329113924050633e-05,
      "loss": 1.1081,
      "step": 75
    },
    {
      "epoch": 0.33755274261603374,
      "grad_norm": 0.363908588886261,
      "learning_rate": 6.751054852320675e-05,
      "loss": 1.1042,
      "step": 80
    },
    {
      "epoch": 0.35864978902953587,
      "grad_norm": 0.373738557100296,
      "learning_rate": 7.172995780590718e-05,
      "loss": 1.0802,
      "step": 85
    },
    {
      "epoch": 0.379746835443038,
      "grad_norm": 0.3337308168411255,
      "learning_rate": 7.59493670886076e-05,
      "loss": 1.0781,
      "step": 90
    },
    {
      "epoch": 0.4008438818565401,
      "grad_norm": 0.36707767844200134,
      "learning_rate": 8.016877637130802e-05,
      "loss": 1.07,
      "step": 95
    },
    {
      "epoch": 0.4219409282700422,
      "grad_norm": 0.40698128938674927,
      "learning_rate": 8.438818565400845e-05,
      "loss": 1.0672,
      "step": 100
    },
    {
      "epoch": 0.4430379746835443,
      "grad_norm": 0.4015476107597351,
      "learning_rate": 8.860759493670887e-05,
      "loss": 1.0508,
      "step": 105
    },
    {
      "epoch": 0.4641350210970464,
      "grad_norm": 0.3830510675907135,
      "learning_rate": 9.282700421940928e-05,
      "loss": 1.0396,
      "step": 110
    },
    {
      "epoch": 0.48523206751054854,
      "grad_norm": 0.540158748626709,
      "learning_rate": 9.704641350210972e-05,
      "loss": 1.0356,
      "step": 115
    },
    {
      "epoch": 0.5063291139240507,
      "grad_norm": 0.5870048999786377,
      "learning_rate": 0.00010126582278481013,
      "loss": 1.0363,
      "step": 120
    },
    {
      "epoch": 0.5274261603375527,
      "grad_norm": 0.6282536387443542,
      "learning_rate": 0.00010548523206751055,
      "loss": 1.0205,
      "step": 125
    },
    {
      "epoch": 0.5485232067510548,
      "grad_norm": 0.5962668061256409,
      "learning_rate": 0.00010970464135021097,
      "loss": 1.0327,
      "step": 130
    },
    {
      "epoch": 0.569620253164557,
      "grad_norm": 0.44145339727401733,
      "learning_rate": 0.0001139240506329114,
      "loss": 1.0036,
      "step": 135
    },
    {
      "epoch": 0.5907172995780591,
      "grad_norm": 0.3850124776363373,
      "learning_rate": 0.00011814345991561182,
      "loss": 0.9939,
      "step": 140
    },
    {
      "epoch": 0.6118143459915611,
      "grad_norm": 0.45476189255714417,
      "learning_rate": 0.00012236286919831225,
      "loss": 1.01,
      "step": 145
    },
    {
      "epoch": 0.6329113924050633,
      "grad_norm": 0.4156922399997711,
      "learning_rate": 0.00012658227848101267,
      "loss": 1.0046,
      "step": 150
    },
    {
      "epoch": 0.6540084388185654,
      "grad_norm": 0.5297821760177612,
      "learning_rate": 0.00013080168776371308,
      "loss": 0.9885,
      "step": 155
    },
    {
      "epoch": 0.6751054852320675,
      "grad_norm": 0.4995609521865845,
      "learning_rate": 0.0001350210970464135,
      "loss": 0.9885,
      "step": 160
    },
    {
      "epoch": 0.6962025316455697,
      "grad_norm": 0.43320751190185547,
      "learning_rate": 0.00013924050632911395,
      "loss": 0.9818,
      "step": 165
    },
    {
      "epoch": 0.7172995780590717,
      "grad_norm": 0.3719841539859772,
      "learning_rate": 0.00014345991561181436,
      "loss": 0.9739,
      "step": 170
    },
    {
      "epoch": 0.7383966244725738,
      "grad_norm": 0.40309059619903564,
      "learning_rate": 0.00014767932489451478,
      "loss": 0.9646,
      "step": 175
    },
    {
      "epoch": 0.759493670886076,
      "grad_norm": 0.41251224279403687,
      "learning_rate": 0.0001518987341772152,
      "loss": 0.9606,
      "step": 180
    },
    {
      "epoch": 0.7805907172995781,
      "grad_norm": 0.3959939181804657,
      "learning_rate": 0.00015611814345991562,
      "loss": 0.9585,
      "step": 185
    },
    {
      "epoch": 0.8016877637130801,
      "grad_norm": 0.5289701819419861,
      "learning_rate": 0.00016033755274261603,
      "loss": 0.9709,
      "step": 190
    },
    {
      "epoch": 0.8227848101265823,
      "grad_norm": 0.4239669740200043,
      "learning_rate": 0.00016455696202531648,
      "loss": 0.9577,
      "step": 195
    },
    {
      "epoch": 0.8438818565400844,
      "grad_norm": 0.5463127493858337,
      "learning_rate": 0.0001687763713080169,
      "loss": 0.9703,
      "step": 200
    },
    {
      "epoch": 0.8649789029535865,
      "grad_norm": 0.4942500591278076,
      "learning_rate": 0.00017299578059071731,
      "loss": 0.956,
      "step": 205
    },
    {
      "epoch": 0.8860759493670886,
      "grad_norm": 0.361708402633667,
      "learning_rate": 0.00017721518987341773,
      "loss": 0.9598,
      "step": 210
    },
    {
      "epoch": 0.9071729957805907,
      "grad_norm": 0.5146432518959045,
      "learning_rate": 0.00018143459915611815,
      "loss": 0.9606,
      "step": 215
    },
    {
      "epoch": 0.9282700421940928,
      "grad_norm": 0.4746183156967163,
      "learning_rate": 0.00018565400843881857,
      "loss": 0.9255,
      "step": 220
    },
    {
      "epoch": 0.9493670886075949,
      "grad_norm": 0.35139352083206177,
      "learning_rate": 0.00018987341772151899,
      "loss": 0.9452,
      "step": 225
    },
    {
      "epoch": 0.9704641350210971,
      "grad_norm": 0.3744509816169739,
      "learning_rate": 0.00019409282700421943,
      "loss": 0.9388,
      "step": 230
    },
    {
      "epoch": 0.9915611814345991,
      "grad_norm": 0.409365177154541,
      "learning_rate": 0.00019831223628691985,
      "loss": 0.9183,
      "step": 235
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.6516629457473755,
      "eval_runtime": 0.5551,
      "eval_samples_per_second": 3.603,
      "eval_steps_per_second": 1.802,
      "step": 237
    },
    {
      "epoch": 1.0126582278481013,
      "grad_norm": 0.3671579658985138,
      "learning_rate": 0.00019999902382014363,
      "loss": 0.9181,
      "step": 240
    },
    {
      "epoch": 1.0337552742616034,
      "grad_norm": 0.37430304288864136,
      "learning_rate": 0.0001999930583455953,
      "loss": 0.9099,
      "step": 245
    },
    {
      "epoch": 1.0548523206751055,
      "grad_norm": 0.3971017599105835,
      "learning_rate": 0.00019998167004176888,
      "loss": 0.9187,
      "step": 250
    },
    {
      "epoch": 1.0759493670886076,
      "grad_norm": 0.35043320059776306,
      "learning_rate": 0.00019996485952627552,
      "loss": 0.9063,
      "step": 255
    },
    {
      "epoch": 1.0970464135021096,
      "grad_norm": 0.34455016255378723,
      "learning_rate": 0.00019994262771078406,
      "loss": 0.9072,
      "step": 260
    },
    {
      "epoch": 1.1181434599156117,
      "grad_norm": 0.358531653881073,
      "learning_rate": 0.0001999149758009716,
      "loss": 0.916,
      "step": 265
    },
    {
      "epoch": 1.139240506329114,
      "grad_norm": 0.3874802589416504,
      "learning_rate": 0.00019988190529645808,
      "loss": 0.8913,
      "step": 270
    },
    {
      "epoch": 1.160337552742616,
      "grad_norm": 0.3963850736618042,
      "learning_rate": 0.00019984341799072504,
      "loss": 0.9033,
      "step": 275
    },
    {
      "epoch": 1.1814345991561181,
      "grad_norm": 0.485408753156662,
      "learning_rate": 0.0001997995159710182,
      "loss": 0.8965,
      "step": 280
    },
    {
      "epoch": 1.2025316455696202,
      "grad_norm": 0.383575975894928,
      "learning_rate": 0.00019975020161823445,
      "loss": 0.8919,
      "step": 285
    },
    {
      "epoch": 1.2236286919831223,
      "grad_norm": 0.3458747863769531,
      "learning_rate": 0.00019969547760679258,
      "loss": 0.8827,
      "step": 290
    },
    {
      "epoch": 1.2447257383966246,
      "grad_norm": 0.36945974826812744,
      "learning_rate": 0.00019963534690448835,
      "loss": 0.8957,
      "step": 295
    },
    {
      "epoch": 1.2658227848101267,
      "grad_norm": 0.39198634028434753,
      "learning_rate": 0.0001995698127723334,
      "loss": 0.879,
      "step": 300
    },
    {
      "epoch": 1.2869198312236287,
      "grad_norm": 0.36909279227256775,
      "learning_rate": 0.0001994988787643786,
      "loss": 0.9014,
      "step": 305
    },
    {
      "epoch": 1.3080168776371308,
      "grad_norm": 0.3728243112564087,
      "learning_rate": 0.00019942254872752112,
      "loss": 0.891,
      "step": 310
    },
    {
      "epoch": 1.3291139240506329,
      "grad_norm": 0.34412381052970886,
      "learning_rate": 0.00019934082680129586,
      "loss": 0.8744,
      "step": 315
    },
    {
      "epoch": 1.350210970464135,
      "grad_norm": 0.3310409486293793,
      "learning_rate": 0.00019925371741765107,
      "loss": 0.8788,
      "step": 320
    },
    {
      "epoch": 1.371308016877637,
      "grad_norm": 0.3466126620769501,
      "learning_rate": 0.00019916122530070783,
      "loss": 0.8953,
      "step": 325
    },
    {
      "epoch": 1.3924050632911391,
      "grad_norm": 0.3331877291202545,
      "learning_rate": 0.00019906335546650392,
      "loss": 0.8703,
      "step": 330
    },
    {
      "epoch": 1.4135021097046414,
      "grad_norm": 0.37082529067993164,
      "learning_rate": 0.0001989601132227218,
      "loss": 0.8951,
      "step": 335
    },
    {
      "epoch": 1.4345991561181435,
      "grad_norm": 0.3338633179664612,
      "learning_rate": 0.00019885150416840082,
      "loss": 0.8826,
      "step": 340
    },
    {
      "epoch": 1.4556962025316456,
      "grad_norm": 0.32301968336105347,
      "learning_rate": 0.00019873753419363336,
      "loss": 0.8821,
      "step": 345
    },
    {
      "epoch": 1.4767932489451476,
      "grad_norm": 0.3255464732646942,
      "learning_rate": 0.00019861820947924565,
      "loss": 0.87,
      "step": 350
    },
    {
      "epoch": 1.49789029535865,
      "grad_norm": 0.33072352409362793,
      "learning_rate": 0.0001984935364964625,
      "loss": 0.8755,
      "step": 355
    },
    {
      "epoch": 1.518987341772152,
      "grad_norm": 0.39160993695259094,
      "learning_rate": 0.0001983635220065562,
      "loss": 0.861,
      "step": 360
    },
    {
      "epoch": 1.540084388185654,
      "grad_norm": 0.35338205099105835,
      "learning_rate": 0.00019822817306048006,
      "loss": 0.864,
      "step": 365
    },
    {
      "epoch": 1.5611814345991561,
      "grad_norm": 0.30854344367980957,
      "learning_rate": 0.00019808749699848593,
      "loss": 0.8521,
      "step": 370
    },
    {
      "epoch": 1.5822784810126582,
      "grad_norm": 0.3593827188014984,
      "learning_rate": 0.00019794150144972602,
      "loss": 0.8738,
      "step": 375
    },
    {
      "epoch": 1.6033755274261603,
      "grad_norm": 0.30474522709846497,
      "learning_rate": 0.0001977901943318393,
      "loss": 0.8612,
      "step": 380
    },
    {
      "epoch": 1.6244725738396624,
      "grad_norm": 0.3270438611507416,
      "learning_rate": 0.0001976335838505221,
      "loss": 0.8838,
      "step": 385
    },
    {
      "epoch": 1.6455696202531644,
      "grad_norm": 0.3059784471988678,
      "learning_rate": 0.00019747167849908304,
      "loss": 0.8687,
      "step": 390
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.3195934295654297,
      "learning_rate": 0.00019730448705798239,
      "loss": 0.8639,
      "step": 395
    },
    {
      "epoch": 1.6877637130801688,
      "grad_norm": 0.31650060415267944,
      "learning_rate": 0.00019713201859435602,
      "loss": 0.8825,
      "step": 400
    },
    {
      "epoch": 1.7088607594936709,
      "grad_norm": 0.33506250381469727,
      "learning_rate": 0.0001969542824615235,
      "loss": 0.8663,
      "step": 405
    },
    {
      "epoch": 1.729957805907173,
      "grad_norm": 0.3536715805530548,
      "learning_rate": 0.00019677128829848103,
      "loss": 0.8498,
      "step": 410
    },
    {
      "epoch": 1.7510548523206753,
      "grad_norm": 0.35253262519836426,
      "learning_rate": 0.00019658304602937856,
      "loss": 0.8614,
      "step": 415
    },
    {
      "epoch": 1.7721518987341773,
      "grad_norm": 0.3264296054840088,
      "learning_rate": 0.0001963895658629816,
      "loss": 0.8456,
      "step": 420
    },
    {
      "epoch": 1.7932489451476794,
      "grad_norm": 0.32499557733535767,
      "learning_rate": 0.00019619085829211764,
      "loss": 0.8435,
      "step": 425
    },
    {
      "epoch": 1.8143459915611815,
      "grad_norm": 0.31721100211143494,
      "learning_rate": 0.00019598693409310708,
      "loss": 0.8716,
      "step": 430
    },
    {
      "epoch": 1.8354430379746836,
      "grad_norm": 0.31418412923812866,
      "learning_rate": 0.00019577780432517879,
      "loss": 0.859,
      "step": 435
    },
    {
      "epoch": 1.8565400843881856,
      "grad_norm": 0.3075924515724182,
      "learning_rate": 0.0001955634803298703,
      "loss": 0.8573,
      "step": 440
    },
    {
      "epoch": 1.8776371308016877,
      "grad_norm": 0.30187729001045227,
      "learning_rate": 0.00019534397373041285,
      "loss": 0.8381,
      "step": 445
    },
    {
      "epoch": 1.8987341772151898,
      "grad_norm": 0.3083683252334595,
      "learning_rate": 0.00019511929643110097,
      "loss": 0.8536,
      "step": 450
    },
    {
      "epoch": 1.9198312236286919,
      "grad_norm": 0.2972455620765686,
      "learning_rate": 0.0001948894606166468,
      "loss": 0.8487,
      "step": 455
    },
    {
      "epoch": 1.9409282700421941,
      "grad_norm": 0.3294317424297333,
      "learning_rate": 0.00019465447875151946,
      "loss": 0.8485,
      "step": 460
    },
    {
      "epoch": 1.9620253164556962,
      "grad_norm": 0.28597962856292725,
      "learning_rate": 0.00019441436357926892,
      "loss": 0.8608,
      "step": 465
    },
    {
      "epoch": 1.9831223628691983,
      "grad_norm": 0.30924198031425476,
      "learning_rate": 0.00019416912812183498,
      "loss": 0.8583,
      "step": 470
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.629499912261963,
      "eval_runtime": 0.5557,
      "eval_samples_per_second": 3.599,
      "eval_steps_per_second": 1.8,
      "step": 474
    },
    {
      "epoch": 2.0042194092827006,
      "grad_norm": 0.3041239380836487,
      "learning_rate": 0.000193918785678841,
      "loss": 0.8475,
      "step": 475
    },
    {
      "epoch": 2.0253164556962027,
      "grad_norm": 0.31540679931640625,
      "learning_rate": 0.0001936633498268728,
      "loss": 0.8119,
      "step": 480
    },
    {
      "epoch": 2.0464135021097047,
      "grad_norm": 0.3115026652812958,
      "learning_rate": 0.0001934028344187421,
      "loss": 0.8259,
      "step": 485
    },
    {
      "epoch": 2.067510548523207,
      "grad_norm": 0.39703112840652466,
      "learning_rate": 0.00019313725358273548,
      "loss": 0.8041,
      "step": 490
    },
    {
      "epoch": 2.088607594936709,
      "grad_norm": 0.3294001817703247,
      "learning_rate": 0.00019286662172184808,
      "loss": 0.8003,
      "step": 495
    },
    {
      "epoch": 2.109704641350211,
      "grad_norm": 0.3266647160053253,
      "learning_rate": 0.00019259095351300252,
      "loss": 0.8109,
      "step": 500
    },
    {
      "epoch": 2.130801687763713,
      "grad_norm": 0.31092244386672974,
      "learning_rate": 0.0001923102639062529,
      "loss": 0.8212,
      "step": 505
    },
    {
      "epoch": 2.151898734177215,
      "grad_norm": 0.3094409704208374,
      "learning_rate": 0.00019202456812397406,
      "loss": 0.8187,
      "step": 510
    },
    {
      "epoch": 2.172995780590717,
      "grad_norm": 0.32525700330734253,
      "learning_rate": 0.00019173388166003613,
      "loss": 0.8058,
      "step": 515
    },
    {
      "epoch": 2.1940928270042193,
      "grad_norm": 0.296203076839447,
      "learning_rate": 0.00019143822027896406,
      "loss": 0.8037,
      "step": 520
    },
    {
      "epoch": 2.2151898734177213,
      "grad_norm": 0.3076232373714447,
      "learning_rate": 0.0001911376000150828,
      "loss": 0.8208,
      "step": 525
    },
    {
      "epoch": 2.2362869198312234,
      "grad_norm": 0.2956830859184265,
      "learning_rate": 0.0001908320371716478,
      "loss": 0.788,
      "step": 530
    },
    {
      "epoch": 2.257383966244726,
      "grad_norm": 0.3284301161766052,
      "learning_rate": 0.00019052154831996073,
      "loss": 0.7986,
      "step": 535
    },
    {
      "epoch": 2.278481012658228,
      "grad_norm": 0.31620386242866516,
      "learning_rate": 0.00019020615029847072,
      "loss": 0.8049,
      "step": 540
    },
    {
      "epoch": 2.29957805907173,
      "grad_norm": 0.3297165632247925,
      "learning_rate": 0.00018988586021186147,
      "loss": 0.8309,
      "step": 545
    },
    {
      "epoch": 2.320675105485232,
      "grad_norm": 0.2959255874156952,
      "learning_rate": 0.0001895606954301233,
      "loss": 0.7965,
      "step": 550
    },
    {
      "epoch": 2.3417721518987342,
      "grad_norm": 0.3089437782764435,
      "learning_rate": 0.00018923067358761136,
      "loss": 0.7946,
      "step": 555
    },
    {
      "epoch": 2.3628691983122363,
      "grad_norm": 0.30109426379203796,
      "learning_rate": 0.00018889581258208903,
      "loss": 0.8123,
      "step": 560
    },
    {
      "epoch": 2.3839662447257384,
      "grad_norm": 0.32586753368377686,
      "learning_rate": 0.0001885561305737577,
      "loss": 0.8162,
      "step": 565
    },
    {
      "epoch": 2.4050632911392404,
      "grad_norm": 0.3282499611377716,
      "learning_rate": 0.00018821164598427145,
      "loss": 0.8196,
      "step": 570
    },
    {
      "epoch": 2.4261603375527425,
      "grad_norm": 0.3379076421260834,
      "learning_rate": 0.00018786237749573837,
      "loss": 0.816,
      "step": 575
    },
    {
      "epoch": 2.4472573839662446,
      "grad_norm": 0.30591997504234314,
      "learning_rate": 0.00018750834404970718,
      "loss": 0.8015,
      "step": 580
    },
    {
      "epoch": 2.4683544303797467,
      "grad_norm": 0.3031338155269623,
      "learning_rate": 0.00018714956484613995,
      "loss": 0.817,
      "step": 585
    },
    {
      "epoch": 2.489451476793249,
      "grad_norm": 0.3209945261478424,
      "learning_rate": 0.0001867860593423711,
      "loss": 0.8134,
      "step": 590
    },
    {
      "epoch": 2.510548523206751,
      "grad_norm": 0.31199783086776733,
      "learning_rate": 0.000186417847252052,
      "loss": 0.8053,
      "step": 595
    },
    {
      "epoch": 2.5316455696202533,
      "grad_norm": 0.29871612787246704,
      "learning_rate": 0.00018604494854408178,
      "loss": 0.804,
      "step": 600
    },
    {
      "epoch": 2.5527426160337554,
      "grad_norm": 0.31065070629119873,
      "learning_rate": 0.0001856673834415246,
      "loss": 0.8033,
      "step": 605
    },
    {
      "epoch": 2.5738396624472575,
      "grad_norm": 0.2946309447288513,
      "learning_rate": 0.00018528517242051283,
      "loss": 0.8006,
      "step": 610
    },
    {
      "epoch": 2.5949367088607596,
      "grad_norm": 0.2882119119167328,
      "learning_rate": 0.00018489833620913642,
      "loss": 0.8059,
      "step": 615
    },
    {
      "epoch": 2.6160337552742616,
      "grad_norm": 0.31968575716018677,
      "learning_rate": 0.00018450689578631898,
      "loss": 0.8045,
      "step": 620
    },
    {
      "epoch": 2.6371308016877637,
      "grad_norm": 0.3142683804035187,
      "learning_rate": 0.00018411087238068003,
      "loss": 0.8045,
      "step": 625
    },
    {
      "epoch": 2.6582278481012658,
      "grad_norm": 0.3006449043750763,
      "learning_rate": 0.0001837102874693836,
      "loss": 0.8056,
      "step": 630
    },
    {
      "epoch": 2.679324894514768,
      "grad_norm": 0.3158734440803528,
      "learning_rate": 0.0001833051627769736,
      "loss": 0.8275,
      "step": 635
    },
    {
      "epoch": 2.70042194092827,
      "grad_norm": 0.30407387018203735,
      "learning_rate": 0.00018289552027419558,
      "loss": 0.8133,
      "step": 640
    },
    {
      "epoch": 2.721518987341772,
      "grad_norm": 0.3022385835647583,
      "learning_rate": 0.0001824813821768053,
      "loss": 0.8026,
      "step": 645
    },
    {
      "epoch": 2.742616033755274,
      "grad_norm": 0.29126378893852234,
      "learning_rate": 0.00018206277094436377,
      "loss": 0.8075,
      "step": 650
    },
    {
      "epoch": 2.7637130801687766,
      "grad_norm": 0.29224568605422974,
      "learning_rate": 0.00018163970927901937,
      "loss": 0.811,
      "step": 655
    },
    {
      "epoch": 2.7848101265822782,
      "grad_norm": 0.3017180860042572,
      "learning_rate": 0.00018121222012427665,
      "loss": 0.7945,
      "step": 660
    },
    {
      "epoch": 2.8059071729957807,
      "grad_norm": 0.2974776029586792,
      "learning_rate": 0.00018078032666375194,
      "loss": 0.8078,
      "step": 665
    },
    {
      "epoch": 2.827004219409283,
      "grad_norm": 0.2910807430744171,
      "learning_rate": 0.0001803440523199162,
      "loss": 0.7887,
      "step": 670
    },
    {
      "epoch": 2.848101265822785,
      "grad_norm": 0.3062914311885834,
      "learning_rate": 0.0001799034207528247,
      "loss": 0.7928,
      "step": 675
    },
    {
      "epoch": 2.869198312236287,
      "grad_norm": 0.29467758536338806,
      "learning_rate": 0.0001794584558588338,
      "loss": 0.8047,
      "step": 680
    },
    {
      "epoch": 2.890295358649789,
      "grad_norm": 0.32635724544525146,
      "learning_rate": 0.00017900918176930522,
      "loss": 0.8144,
      "step": 685
    },
    {
      "epoch": 2.911392405063291,
      "grad_norm": 0.31900787353515625,
      "learning_rate": 0.00017855562284929718,
      "loss": 0.8089,
      "step": 690
    },
    {
      "epoch": 2.932489451476793,
      "grad_norm": 0.3085595667362213,
      "learning_rate": 0.00017809780369624302,
      "loss": 0.8048,
      "step": 695
    },
    {
      "epoch": 2.9535864978902953,
      "grad_norm": 0.2946968078613281,
      "learning_rate": 0.00017763574913861734,
      "loss": 0.8157,
      "step": 700
    },
    {
      "epoch": 2.9746835443037973,
      "grad_norm": 0.29723235964775085,
      "learning_rate": 0.00017716948423458938,
      "loss": 0.796,
      "step": 705
    },
    {
      "epoch": 2.9957805907173,
      "grad_norm": 0.2712932229042053,
      "learning_rate": 0.00017669903427066424,
      "loss": 0.8179,
      "step": 710
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.6558986902236938,
      "eval_runtime": 0.5507,
      "eval_samples_per_second": 3.632,
      "eval_steps_per_second": 1.816,
      "step": 711
    },
    {
      "epoch": 3.0168776371308015,
      "grad_norm": 0.3356448709964752,
      "learning_rate": 0.0001762244247603113,
      "loss": 0.7628,
      "step": 715
    },
    {
      "epoch": 3.037974683544304,
      "grad_norm": 0.3006523847579956,
      "learning_rate": 0.00017574568144258077,
      "loss": 0.7558,
      "step": 720
    },
    {
      "epoch": 3.059071729957806,
      "grad_norm": 0.30827251076698303,
      "learning_rate": 0.00017526283028070777,
      "loss": 0.7567,
      "step": 725
    },
    {
      "epoch": 3.080168776371308,
      "grad_norm": 0.3096933662891388,
      "learning_rate": 0.00017477589746070417,
      "loss": 0.7581,
      "step": 730
    },
    {
      "epoch": 3.1012658227848102,
      "grad_norm": 0.32005831599235535,
      "learning_rate": 0.00017428490938993862,
      "loss": 0.7549,
      "step": 735
    },
    {
      "epoch": 3.1223628691983123,
      "grad_norm": 0.30930569767951965,
      "learning_rate": 0.00017378989269570437,
      "loss": 0.7702,
      "step": 740
    },
    {
      "epoch": 3.1434599156118144,
      "grad_norm": 0.32762596011161804,
      "learning_rate": 0.0001732908742237752,
      "loss": 0.7471,
      "step": 745
    },
    {
      "epoch": 3.1645569620253164,
      "grad_norm": 0.32086798548698425,
      "learning_rate": 0.00017278788103694943,
      "loss": 0.7618,
      "step": 750
    },
    {
      "epoch": 3.1856540084388185,
      "grad_norm": 0.3558262586593628,
      "learning_rate": 0.00017228094041358248,
      "loss": 0.7764,
      "step": 755
    },
    {
      "epoch": 3.2067510548523206,
      "grad_norm": 0.3397001326084137,
      "learning_rate": 0.0001717700798461074,
      "loss": 0.753,
      "step": 760
    },
    {
      "epoch": 3.2278481012658227,
      "grad_norm": 0.30650395154953003,
      "learning_rate": 0.00017125532703954365,
      "loss": 0.7595,
      "step": 765
    },
    {
      "epoch": 3.2489451476793247,
      "grad_norm": 0.317777156829834,
      "learning_rate": 0.0001707367099099951,
      "loss": 0.7546,
      "step": 770
    },
    {
      "epoch": 3.270042194092827,
      "grad_norm": 0.3183245062828064,
      "learning_rate": 0.00017021425658313565,
      "loss": 0.7633,
      "step": 775
    },
    {
      "epoch": 3.291139240506329,
      "grad_norm": 0.3169344365596771,
      "learning_rate": 0.00016968799539268407,
      "loss": 0.7759,
      "step": 780
    },
    {
      "epoch": 3.3122362869198314,
      "grad_norm": 0.30704858899116516,
      "learning_rate": 0.00016915795487886746,
      "loss": 0.7565,
      "step": 785
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 0.3002530038356781,
      "learning_rate": 0.0001686241637868734,
      "loss": 0.7509,
      "step": 790
    },
    {
      "epoch": 3.3544303797468356,
      "grad_norm": 0.3143273591995239,
      "learning_rate": 0.00016808665106529094,
      "loss": 0.7482,
      "step": 795
    },
    {
      "epoch": 3.3755274261603376,
      "grad_norm": 0.30195352435112,
      "learning_rate": 0.00016754544586454094,
      "loss": 0.762,
      "step": 800
    },
    {
      "epoch": 3.3966244725738397,
      "grad_norm": 0.32630935311317444,
      "learning_rate": 0.00016700057753529484,
      "loss": 0.7637,
      "step": 805
    },
    {
      "epoch": 3.4177215189873418,
      "grad_norm": 0.31649506092071533,
      "learning_rate": 0.0001664520756268832,
      "loss": 0.7577,
      "step": 810
    },
    {
      "epoch": 3.438818565400844,
      "grad_norm": 0.3301686644554138,
      "learning_rate": 0.0001658999698856929,
      "loss": 0.7534,
      "step": 815
    },
    {
      "epoch": 3.459915611814346,
      "grad_norm": 0.3230050802230835,
      "learning_rate": 0.00016534429025355426,
      "loss": 0.7567,
      "step": 820
    },
    {
      "epoch": 3.481012658227848,
      "grad_norm": 0.30652645230293274,
      "learning_rate": 0.00016478506686611697,
      "loss": 0.757,
      "step": 825
    },
    {
      "epoch": 3.50210970464135,
      "grad_norm": 0.32210221886634827,
      "learning_rate": 0.0001642223300512158,
      "loss": 0.7734,
      "step": 830
    },
    {
      "epoch": 3.523206751054852,
      "grad_norm": 0.3032419681549072,
      "learning_rate": 0.00016365611032722604,
      "loss": 0.7519,
      "step": 835
    },
    {
      "epoch": 3.5443037974683547,
      "grad_norm": 0.2990473508834839,
      "learning_rate": 0.00016308643840140828,
      "loss": 0.7579,
      "step": 840
    },
    {
      "epoch": 3.5654008438818563,
      "grad_norm": 0.32090187072753906,
      "learning_rate": 0.000162513345168243,
      "loss": 0.7569,
      "step": 845
    },
    {
      "epoch": 3.586497890295359,
      "grad_norm": 0.3112528920173645,
      "learning_rate": 0.00016193686170775537,
      "loss": 0.7752,
      "step": 850
    },
    {
      "epoch": 3.607594936708861,
      "grad_norm": 0.311675488948822,
      "learning_rate": 0.00016135701928382952,
      "loss": 0.7523,
      "step": 855
    },
    {
      "epoch": 3.628691983122363,
      "grad_norm": 0.316641628742218,
      "learning_rate": 0.000160773849342513,
      "loss": 0.7651,
      "step": 860
    },
    {
      "epoch": 3.649789029535865,
      "grad_norm": 0.32175716757774353,
      "learning_rate": 0.00016018738351031156,
      "loss": 0.7646,
      "step": 865
    },
    {
      "epoch": 3.670886075949367,
      "grad_norm": 0.30499377846717834,
      "learning_rate": 0.00015959765359247388,
      "loss": 0.7654,
      "step": 870
    },
    {
      "epoch": 3.691983122362869,
      "grad_norm": 0.3078381419181824,
      "learning_rate": 0.0001590046915712667,
      "loss": 0.7682,
      "step": 875
    },
    {
      "epoch": 3.7130801687763713,
      "grad_norm": 0.3422172963619232,
      "learning_rate": 0.00015840852960424036,
      "loss": 0.7504,
      "step": 880
    },
    {
      "epoch": 3.7341772151898733,
      "grad_norm": 0.30137816071510315,
      "learning_rate": 0.00015780920002248484,
      "loss": 0.75,
      "step": 885
    },
    {
      "epoch": 3.7552742616033754,
      "grad_norm": 0.31054186820983887,
      "learning_rate": 0.00015720673532887647,
      "loss": 0.7511,
      "step": 890
    },
    {
      "epoch": 3.7763713080168775,
      "grad_norm": 0.3199822008609772,
      "learning_rate": 0.00015660116819631506,
      "loss": 0.7659,
      "step": 895
    },
    {
      "epoch": 3.7974683544303796,
      "grad_norm": 0.30703869462013245,
      "learning_rate": 0.0001559925314659521,
      "loss": 0.7641,
      "step": 900
    },
    {
      "epoch": 3.818565400843882,
      "grad_norm": 0.3145774006843567,
      "learning_rate": 0.00015538085814540962,
      "loss": 0.7589,
      "step": 905
    },
    {
      "epoch": 3.8396624472573837,
      "grad_norm": 0.3188943862915039,
      "learning_rate": 0.00015476618140699034,
      "loss": 0.7615,
      "step": 910
    },
    {
      "epoch": 3.8607594936708862,
      "grad_norm": 0.32847416400909424,
      "learning_rate": 0.00015414853458587833,
      "loss": 0.7569,
      "step": 915
    },
    {
      "epoch": 3.8818565400843883,
      "grad_norm": 0.33269551396369934,
      "learning_rate": 0.00015352795117833145,
      "loss": 0.7539,
      "step": 920
    },
    {
      "epoch": 3.9029535864978904,
      "grad_norm": 0.30027341842651367,
      "learning_rate": 0.00015290446483986472,
      "loss": 0.76,
      "step": 925
    },
    {
      "epoch": 3.9240506329113924,
      "grad_norm": 0.3010607063770294,
      "learning_rate": 0.00015227810938342492,
      "loss": 0.7574,
      "step": 930
    },
    {
      "epoch": 3.9451476793248945,
      "grad_norm": 0.30083900690078735,
      "learning_rate": 0.0001516489187775572,
      "loss": 0.7556,
      "step": 935
    },
    {
      "epoch": 3.9662447257383966,
      "grad_norm": 0.30435124039649963,
      "learning_rate": 0.00015101692714456259,
      "loss": 0.7612,
      "step": 940
    },
    {
      "epoch": 3.9873417721518987,
      "grad_norm": 0.31260964274406433,
      "learning_rate": 0.00015038216875864756,
      "loss": 0.7533,
      "step": 945
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.6894222497940063,
      "eval_runtime": 0.5552,
      "eval_samples_per_second": 3.602,
      "eval_steps_per_second": 1.801,
      "step": 948
    },
    {
      "epoch": 4.008438818565401,
      "grad_norm": 0.3140685558319092,
      "learning_rate": 0.00014974467804406533,
      "loss": 0.749,
      "step": 950
    },
    {
      "epoch": 4.029535864978903,
      "grad_norm": 0.3326011896133423,
      "learning_rate": 0.00014910448957324897,
      "loss": 0.7177,
      "step": 955
    },
    {
      "epoch": 4.050632911392405,
      "grad_norm": 0.32034996151924133,
      "learning_rate": 0.00014846163806493627,
      "loss": 0.7061,
      "step": 960
    },
    {
      "epoch": 4.071729957805907,
      "grad_norm": 0.31769704818725586,
      "learning_rate": 0.00014781615838228715,
      "loss": 0.6986,
      "step": 965
    },
    {
      "epoch": 4.0928270042194095,
      "grad_norm": 0.35571393370628357,
      "learning_rate": 0.00014716808553099286,
      "loss": 0.7042,
      "step": 970
    },
    {
      "epoch": 4.113924050632911,
      "grad_norm": 0.33056944608688354,
      "learning_rate": 0.00014651745465737737,
      "loss": 0.7195,
      "step": 975
    },
    {
      "epoch": 4.135021097046414,
      "grad_norm": 0.35726672410964966,
      "learning_rate": 0.00014586430104649163,
      "loss": 0.7245,
      "step": 980
    },
    {
      "epoch": 4.156118143459915,
      "grad_norm": 0.3273336887359619,
      "learning_rate": 0.0001452086601201997,
      "loss": 0.709,
      "step": 985
    },
    {
      "epoch": 4.177215189873418,
      "grad_norm": 0.33940553665161133,
      "learning_rate": 0.00014455056743525792,
      "loss": 0.7115,
      "step": 990
    },
    {
      "epoch": 4.198312236286919,
      "grad_norm": 0.34996211528778076,
      "learning_rate": 0.00014389005868138658,
      "loss": 0.7078,
      "step": 995
    },
    {
      "epoch": 4.219409282700422,
      "grad_norm": 0.33837664127349854,
      "learning_rate": 0.00014322716967933428,
      "loss": 0.7042,
      "step": 1000
    },
    {
      "epoch": 4.2405063291139244,
      "grad_norm": 0.3329886198043823,
      "learning_rate": 0.0001425619363789354,
      "loss": 0.7212,
      "step": 1005
    },
    {
      "epoch": 4.261603375527426,
      "grad_norm": 0.35570377111434937,
      "learning_rate": 0.00014189439485716053,
      "loss": 0.7088,
      "step": 1010
    },
    {
      "epoch": 4.282700421940929,
      "grad_norm": 0.3659791648387909,
      "learning_rate": 0.00014122458131615975,
      "loss": 0.7023,
      "step": 1015
    },
    {
      "epoch": 4.30379746835443,
      "grad_norm": 0.3362638056278229,
      "learning_rate": 0.00014055253208129938,
      "loss": 0.7138,
      "step": 1020
    },
    {
      "epoch": 4.324894514767933,
      "grad_norm": 0.3303203284740448,
      "learning_rate": 0.00013987828359919222,
      "loss": 0.7085,
      "step": 1025
    },
    {
      "epoch": 4.345991561181434,
      "grad_norm": 0.32455962896347046,
      "learning_rate": 0.00013920187243572057,
      "loss": 0.7142,
      "step": 1030
    },
    {
      "epoch": 4.367088607594937,
      "grad_norm": 0.33820950984954834,
      "learning_rate": 0.00013852333527405346,
      "loss": 0.7198,
      "step": 1035
    },
    {
      "epoch": 4.3881856540084385,
      "grad_norm": 0.3443733751773834,
      "learning_rate": 0.00013784270891265717,
      "loss": 0.7281,
      "step": 1040
    },
    {
      "epoch": 4.409282700421941,
      "grad_norm": 0.3376203179359436,
      "learning_rate": 0.00013716003026329965,
      "loss": 0.7157,
      "step": 1045
    },
    {
      "epoch": 4.430379746835443,
      "grad_norm": 0.3343973159790039,
      "learning_rate": 0.0001364753363490485,
      "loss": 0.7157,
      "step": 1050
    },
    {
      "epoch": 4.451476793248945,
      "grad_norm": 0.32973435521125793,
      "learning_rate": 0.00013578866430226342,
      "loss": 0.7183,
      "step": 1055
    },
    {
      "epoch": 4.472573839662447,
      "grad_norm": 0.3444620370864868,
      "learning_rate": 0.00013510005136258227,
      "loss": 0.7196,
      "step": 1060
    },
    {
      "epoch": 4.493670886075949,
      "grad_norm": 0.33004656434059143,
      "learning_rate": 0.00013440953487490144,
      "loss": 0.7139,
      "step": 1065
    },
    {
      "epoch": 4.514767932489452,
      "grad_norm": 0.3244040608406067,
      "learning_rate": 0.00013371715228735077,
      "loss": 0.7144,
      "step": 1070
    },
    {
      "epoch": 4.5358649789029535,
      "grad_norm": 0.3370364308357239,
      "learning_rate": 0.0001330229411492625,
      "loss": 0.7014,
      "step": 1075
    },
    {
      "epoch": 4.556962025316456,
      "grad_norm": 0.3164542317390442,
      "learning_rate": 0.00013232693910913485,
      "loss": 0.7124,
      "step": 1080
    },
    {
      "epoch": 4.578059071729958,
      "grad_norm": 0.3478745222091675,
      "learning_rate": 0.0001316291839125904,
      "loss": 0.7253,
      "step": 1085
    },
    {
      "epoch": 4.59915611814346,
      "grad_norm": 0.33551761507987976,
      "learning_rate": 0.00013092971340032905,
      "loss": 0.7237,
      "step": 1090
    },
    {
      "epoch": 4.620253164556962,
      "grad_norm": 0.3593490421772003,
      "learning_rate": 0.00013022856550607572,
      "loss": 0.7187,
      "step": 1095
    },
    {
      "epoch": 4.641350210970464,
      "grad_norm": 0.33983170986175537,
      "learning_rate": 0.0001295257782545233,
      "loss": 0.715,
      "step": 1100
    },
    {
      "epoch": 4.662447257383966,
      "grad_norm": 0.3238469064235687,
      "learning_rate": 0.00012882138975927026,
      "loss": 0.7024,
      "step": 1105
    },
    {
      "epoch": 4.6835443037974684,
      "grad_norm": 0.3401734232902527,
      "learning_rate": 0.00012811543822075397,
      "loss": 0.7175,
      "step": 1110
    },
    {
      "epoch": 4.70464135021097,
      "grad_norm": 0.35343295335769653,
      "learning_rate": 0.00012740796192417875,
      "loss": 0.7445,
      "step": 1115
    },
    {
      "epoch": 4.725738396624473,
      "grad_norm": 0.3328774869441986,
      "learning_rate": 0.00012669899923743968,
      "loss": 0.7007,
      "step": 1120
    },
    {
      "epoch": 4.746835443037975,
      "grad_norm": 0.341886967420578,
      "learning_rate": 0.00012598858860904193,
      "loss": 0.7275,
      "step": 1125
    },
    {
      "epoch": 4.767932489451477,
      "grad_norm": 0.33224210143089294,
      "learning_rate": 0.00012527676856601542,
      "loss": 0.7093,
      "step": 1130
    },
    {
      "epoch": 4.789029535864979,
      "grad_norm": 0.3608289062976837,
      "learning_rate": 0.0001245635777118256,
      "loss": 0.7237,
      "step": 1135
    },
    {
      "epoch": 4.810126582278481,
      "grad_norm": 0.3258775472640991,
      "learning_rate": 0.00012384905472427975,
      "loss": 0.7068,
      "step": 1140
    },
    {
      "epoch": 4.831223628691983,
      "grad_norm": 0.3356561064720154,
      "learning_rate": 0.0001231332383534296,
      "loss": 0.7208,
      "step": 1145
    },
    {
      "epoch": 4.852320675105485,
      "grad_norm": 0.32746249437332153,
      "learning_rate": 0.00012241616741946962,
      "loss": 0.7143,
      "step": 1150
    },
    {
      "epoch": 4.8734177215189876,
      "grad_norm": 0.33153674006462097,
      "learning_rate": 0.0001216978808106318,
      "loss": 0.726,
      "step": 1155
    },
    {
      "epoch": 4.894514767932489,
      "grad_norm": 0.33083775639533997,
      "learning_rate": 0.00012097841748107681,
      "loss": 0.7015,
      "step": 1160
    },
    {
      "epoch": 4.915611814345992,
      "grad_norm": 0.3352629542350769,
      "learning_rate": 0.00012025781644878118,
      "loss": 0.7234,
      "step": 1165
    },
    {
      "epoch": 4.936708860759493,
      "grad_norm": 0.3423599898815155,
      "learning_rate": 0.00011953611679342143,
      "loss": 0.733,
      "step": 1170
    },
    {
      "epoch": 4.957805907172996,
      "grad_norm": 0.3402250409126282,
      "learning_rate": 0.00011881335765425473,
      "loss": 0.7187,
      "step": 1175
    },
    {
      "epoch": 4.978902953586498,
      "grad_norm": 0.345759779214859,
      "learning_rate": 0.00011808957822799614,
      "loss": 0.7119,
      "step": 1180
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.3274582326412201,
      "learning_rate": 0.00011736481776669306,
      "loss": 0.716,
      "step": 1185
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.7251324653625488,
      "eval_runtime": 0.554,
      "eval_samples_per_second": 3.61,
      "eval_steps_per_second": 1.805,
      "step": 1185
    },
    {
      "epoch": 5.0210970464135025,
      "grad_norm": 0.36755794286727905,
      "learning_rate": 0.0001166391155755964,
      "loss": 0.6589,
      "step": 1190
    },
    {
      "epoch": 5.042194092827004,
      "grad_norm": 0.3618139624595642,
      "learning_rate": 0.00011591251101102906,
      "loss": 0.6697,
      "step": 1195
    },
    {
      "epoch": 5.063291139240507,
      "grad_norm": 0.38643401861190796,
      "learning_rate": 0.00011518504347825145,
      "loss": 0.661,
      "step": 1200
    },
    {
      "epoch": 5.084388185654008,
      "grad_norm": 0.3515397012233734,
      "learning_rate": 0.00011445675242932457,
      "loss": 0.6455,
      "step": 1205
    },
    {
      "epoch": 5.105485232067511,
      "grad_norm": 0.37624698877334595,
      "learning_rate": 0.00011372767736097039,
      "loss": 0.6628,
      "step": 1210
    },
    {
      "epoch": 5.1265822784810124,
      "grad_norm": 0.3468095660209656,
      "learning_rate": 0.00011299785781242982,
      "loss": 0.6591,
      "step": 1215
    },
    {
      "epoch": 5.147679324894515,
      "grad_norm": 0.3849187195301056,
      "learning_rate": 0.00011226733336331855,
      "loss": 0.6726,
      "step": 1220
    },
    {
      "epoch": 5.168776371308017,
      "grad_norm": 0.36786338686943054,
      "learning_rate": 0.00011153614363148032,
      "loss": 0.6795,
      "step": 1225
    },
    {
      "epoch": 5.189873417721519,
      "grad_norm": 0.35997211933135986,
      "learning_rate": 0.00011080432827083873,
      "loss": 0.676,
      "step": 1230
    },
    {
      "epoch": 5.210970464135021,
      "grad_norm": 0.3702506721019745,
      "learning_rate": 0.00011007192696924638,
      "loss": 0.6734,
      "step": 1235
    },
    {
      "epoch": 5.232067510548523,
      "grad_norm": 0.35727155208587646,
      "learning_rate": 0.00010933897944633265,
      "loss": 0.6719,
      "step": 1240
    },
    {
      "epoch": 5.253164556962025,
      "grad_norm": 0.35158923268318176,
      "learning_rate": 0.0001086055254513497,
      "loss": 0.6572,
      "step": 1245
    },
    {
      "epoch": 5.274261603375527,
      "grad_norm": 0.3676392734050751,
      "learning_rate": 0.00010787160476101668,
      "loss": 0.663,
      "step": 1250
    },
    {
      "epoch": 5.29535864978903,
      "grad_norm": 0.35416457056999207,
      "learning_rate": 0.00010713725717736254,
      "loss": 0.6619,
      "step": 1255
    },
    {
      "epoch": 5.3164556962025316,
      "grad_norm": 0.36827412247657776,
      "learning_rate": 0.00010640252252556759,
      "loss": 0.6861,
      "step": 1260
    },
    {
      "epoch": 5.337552742616034,
      "grad_norm": 0.37270885705947876,
      "learning_rate": 0.00010566744065180368,
      "loss": 0.6842,
      "step": 1265
    },
    {
      "epoch": 5.358649789029536,
      "grad_norm": 0.6396368741989136,
      "learning_rate": 0.00010493205142107312,
      "loss": 0.6648,
      "step": 1270
    },
    {
      "epoch": 5.379746835443038,
      "grad_norm": 0.3901231288909912,
      "learning_rate": 0.00010419639471504682,
      "loss": 0.6682,
      "step": 1275
    },
    {
      "epoch": 5.40084388185654,
      "grad_norm": 0.3932683765888214,
      "learning_rate": 0.0001034605104299016,
      "loss": 0.6715,
      "step": 1280
    },
    {
      "epoch": 5.421940928270042,
      "grad_norm": 0.3795235753059387,
      "learning_rate": 0.00010272443847415615,
      "loss": 0.6826,
      "step": 1285
    },
    {
      "epoch": 5.443037974683544,
      "grad_norm": 0.3844228982925415,
      "learning_rate": 0.00010198821876650701,
      "loss": 0.6624,
      "step": 1290
    },
    {
      "epoch": 5.4641350210970465,
      "grad_norm": 0.37277084589004517,
      "learning_rate": 0.00010125189123366368,
      "loss": 0.6818,
      "step": 1295
    },
    {
      "epoch": 5.485232067510548,
      "grad_norm": 0.3795084059238434,
      "learning_rate": 0.0001005154958081831,
      "loss": 0.6688,
      "step": 1300
    },
    {
      "epoch": 5.506329113924051,
      "grad_norm": 0.37196341156959534,
      "learning_rate": 9.977907242630426e-05,
      "loss": 0.6627,
      "step": 1305
    },
    {
      "epoch": 5.527426160337553,
      "grad_norm": 0.3792167603969574,
      "learning_rate": 9.904266102578231e-05,
      "loss": 0.6768,
      "step": 1310
    },
    {
      "epoch": 5.548523206751055,
      "grad_norm": 0.3688276410102844,
      "learning_rate": 9.830630154372252e-05,
      "loss": 0.6663,
      "step": 1315
    },
    {
      "epoch": 5.569620253164557,
      "grad_norm": 0.3876282870769501,
      "learning_rate": 9.75700339144146e-05,
      "loss": 0.6757,
      "step": 1320
    },
    {
      "epoch": 5.590717299578059,
      "grad_norm": 0.35115256905555725,
      "learning_rate": 9.68338980671669e-05,
      "loss": 0.6846,
      "step": 1325
    },
    {
      "epoch": 5.6118143459915615,
      "grad_norm": 0.3650346100330353,
      "learning_rate": 9.609793392414086e-05,
      "loss": 0.6948,
      "step": 1330
    },
    {
      "epoch": 5.632911392405063,
      "grad_norm": 0.3864571750164032,
      "learning_rate": 9.536218139818614e-05,
      "loss": 0.6712,
      "step": 1335
    },
    {
      "epoch": 5.654008438818566,
      "grad_norm": 0.36888009309768677,
      "learning_rate": 9.462668039067602e-05,
      "loss": 0.6705,
      "step": 1340
    },
    {
      "epoch": 5.675105485232067,
      "grad_norm": 0.36247017979621887,
      "learning_rate": 9.389147078934329e-05,
      "loss": 0.6696,
      "step": 1345
    },
    {
      "epoch": 5.69620253164557,
      "grad_norm": 0.3620111048221588,
      "learning_rate": 9.31565924661172e-05,
      "loss": 0.6686,
      "step": 1350
    },
    {
      "epoch": 5.717299578059071,
      "grad_norm": 0.3552044630050659,
      "learning_rate": 9.242208527496121e-05,
      "loss": 0.6922,
      "step": 1355
    },
    {
      "epoch": 5.738396624472574,
      "grad_norm": 0.36270490288734436,
      "learning_rate": 9.168798904971143e-05,
      "loss": 0.6625,
      "step": 1360
    },
    {
      "epoch": 5.759493670886076,
      "grad_norm": 0.3620161712169647,
      "learning_rate": 9.095434360191642e-05,
      "loss": 0.6684,
      "step": 1365
    },
    {
      "epoch": 5.780590717299578,
      "grad_norm": 0.37736937403678894,
      "learning_rate": 9.02211887186783e-05,
      "loss": 0.6896,
      "step": 1370
    },
    {
      "epoch": 5.80168776371308,
      "grad_norm": 0.4165714979171753,
      "learning_rate": 8.948856416049475e-05,
      "loss": 0.6704,
      "step": 1375
    },
    {
      "epoch": 5.822784810126582,
      "grad_norm": 0.3674893081188202,
      "learning_rate": 8.875650965910279e-05,
      "loss": 0.6871,
      "step": 1380
    },
    {
      "epoch": 5.843881856540085,
      "grad_norm": 0.39419984817504883,
      "learning_rate": 8.802506491532421e-05,
      "loss": 0.6941,
      "step": 1385
    },
    {
      "epoch": 5.864978902953586,
      "grad_norm": 0.3581133782863617,
      "learning_rate": 8.72942695969123e-05,
      "loss": 0.6815,
      "step": 1390
    },
    {
      "epoch": 5.886075949367089,
      "grad_norm": 0.3663847744464874,
      "learning_rate": 8.656416333640066e-05,
      "loss": 0.6792,
      "step": 1395
    },
    {
      "epoch": 5.9071729957805905,
      "grad_norm": 0.39068740606307983,
      "learning_rate": 8.583478572895394e-05,
      "loss": 0.6689,
      "step": 1400
    },
    {
      "epoch": 5.928270042194093,
      "grad_norm": 0.3782387971878052,
      "learning_rate": 8.510617633022044e-05,
      "loss": 0.6825,
      "step": 1405
    },
    {
      "epoch": 5.949367088607595,
      "grad_norm": 0.3802437484264374,
      "learning_rate": 8.437837465418684e-05,
      "loss": 0.669,
      "step": 1410
    },
    {
      "epoch": 5.970464135021097,
      "grad_norm": 0.35812443494796753,
      "learning_rate": 8.365142017103542e-05,
      "loss": 0.6788,
      "step": 1415
    },
    {
      "epoch": 5.991561181434599,
      "grad_norm": 0.36878547072410583,
      "learning_rate": 8.292535230500342e-05,
      "loss": 0.6876,
      "step": 1420
    },
    {
      "epoch": 6.0,
      "eval_loss": 1.782979130744934,
      "eval_runtime": 0.5539,
      "eval_samples_per_second": 3.611,
      "eval_steps_per_second": 1.805,
      "step": 1422
    },
    {
      "epoch": 6.012658227848101,
      "grad_norm": 0.40747499465942383,
      "learning_rate": 8.2200210432245e-05,
      "loss": 0.6326,
      "step": 1425
    },
    {
      "epoch": 6.033755274261603,
      "grad_norm": 0.40314236283302307,
      "learning_rate": 8.147603387869582e-05,
      "loss": 0.6234,
      "step": 1430
    },
    {
      "epoch": 6.0548523206751055,
      "grad_norm": 0.3922586739063263,
      "learning_rate": 8.075286191794025e-05,
      "loss": 0.6238,
      "step": 1435
    },
    {
      "epoch": 6.075949367088608,
      "grad_norm": 0.41105443239212036,
      "learning_rate": 8.003073376908163e-05,
      "loss": 0.6312,
      "step": 1440
    },
    {
      "epoch": 6.09704641350211,
      "grad_norm": 0.3970966339111328,
      "learning_rate": 7.930968859461516e-05,
      "loss": 0.6233,
      "step": 1445
    },
    {
      "epoch": 6.118143459915612,
      "grad_norm": 0.42427581548690796,
      "learning_rate": 7.85897654983041e-05,
      "loss": 0.6348,
      "step": 1450
    },
    {
      "epoch": 6.139240506329114,
      "grad_norm": 0.38989487290382385,
      "learning_rate": 7.787100352305908e-05,
      "loss": 0.6237,
      "step": 1455
    },
    {
      "epoch": 6.160337552742616,
      "grad_norm": 0.4042844772338867,
      "learning_rate": 7.715344164882085e-05,
      "loss": 0.6232,
      "step": 1460
    },
    {
      "epoch": 6.181434599156118,
      "grad_norm": 0.40070950984954834,
      "learning_rate": 7.643711879044612e-05,
      "loss": 0.6173,
      "step": 1465
    },
    {
      "epoch": 6.2025316455696204,
      "grad_norm": 0.40951260924339294,
      "learning_rate": 7.572207379559721e-05,
      "loss": 0.6369,
      "step": 1470
    },
    {
      "epoch": 6.223628691983122,
      "grad_norm": 0.40946945548057556,
      "learning_rate": 7.50083454426354e-05,
      "loss": 0.6267,
      "step": 1475
    },
    {
      "epoch": 6.244725738396625,
      "grad_norm": 0.40567830204963684,
      "learning_rate": 7.429597243851764e-05,
      "loss": 0.616,
      "step": 1480
    },
    {
      "epoch": 6.265822784810126,
      "grad_norm": 0.4094925820827484,
      "learning_rate": 7.358499341669756e-05,
      "loss": 0.6231,
      "step": 1485
    },
    {
      "epoch": 6.286919831223629,
      "grad_norm": 0.396982878446579,
      "learning_rate": 7.287544693503028e-05,
      "loss": 0.6263,
      "step": 1490
    },
    {
      "epoch": 6.308016877637131,
      "grad_norm": 0.41034215688705444,
      "learning_rate": 7.216737147368127e-05,
      "loss": 0.6466,
      "step": 1495
    },
    {
      "epoch": 6.329113924050633,
      "grad_norm": 0.4219072163105011,
      "learning_rate": 7.146080543303965e-05,
      "loss": 0.6479,
      "step": 1500
    },
    {
      "epoch": 6.350210970464135,
      "grad_norm": 0.39759665727615356,
      "learning_rate": 7.075578713163541e-05,
      "loss": 0.6235,
      "step": 1505
    },
    {
      "epoch": 6.371308016877637,
      "grad_norm": 0.4137880504131317,
      "learning_rate": 7.00523548040616e-05,
      "loss": 0.6221,
      "step": 1510
    },
    {
      "epoch": 6.3924050632911396,
      "grad_norm": 0.4084639847278595,
      "learning_rate": 6.935054659890052e-05,
      "loss": 0.633,
      "step": 1515
    },
    {
      "epoch": 6.413502109704641,
      "grad_norm": 0.39727863669395447,
      "learning_rate": 6.865040057665506e-05,
      "loss": 0.6356,
      "step": 1520
    },
    {
      "epoch": 6.434599156118144,
      "grad_norm": 0.4197627007961273,
      "learning_rate": 6.795195470768444e-05,
      "loss": 0.6355,
      "step": 1525
    },
    {
      "epoch": 6.455696202531645,
      "grad_norm": 0.4036734402179718,
      "learning_rate": 6.725524687014514e-05,
      "loss": 0.6367,
      "step": 1530
    },
    {
      "epoch": 6.476793248945148,
      "grad_norm": 0.4073878526687622,
      "learning_rate": 6.656031484793657e-05,
      "loss": 0.6367,
      "step": 1535
    },
    {
      "epoch": 6.4978902953586495,
      "grad_norm": 0.4095742702484131,
      "learning_rate": 6.586719632865198e-05,
      "loss": 0.6292,
      "step": 1540
    },
    {
      "epoch": 6.518987341772152,
      "grad_norm": 0.408542662858963,
      "learning_rate": 6.517592890153476e-05,
      "loss": 0.6312,
      "step": 1545
    },
    {
      "epoch": 6.540084388185654,
      "grad_norm": 0.4064979553222656,
      "learning_rate": 6.448655005543969e-05,
      "loss": 0.6373,
      "step": 1550
    },
    {
      "epoch": 6.561181434599156,
      "grad_norm": 0.4208141565322876,
      "learning_rate": 6.379909717679985e-05,
      "loss": 0.6289,
      "step": 1555
    },
    {
      "epoch": 6.582278481012658,
      "grad_norm": 0.4085118770599365,
      "learning_rate": 6.311360754759923e-05,
      "loss": 0.6289,
      "step": 1560
    },
    {
      "epoch": 6.60337552742616,
      "grad_norm": 0.4019670784473419,
      "learning_rate": 6.243011834335075e-05,
      "loss": 0.639,
      "step": 1565
    },
    {
      "epoch": 6.624472573839663,
      "grad_norm": 0.4115982949733734,
      "learning_rate": 6.17486666310801e-05,
      "loss": 0.6437,
      "step": 1570
    },
    {
      "epoch": 6.6455696202531644,
      "grad_norm": 0.40410783886909485,
      "learning_rate": 6.106928936731571e-05,
      "loss": 0.6439,
      "step": 1575
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 0.3954565227031708,
      "learning_rate": 6.039202339608432e-05,
      "loss": 0.6339,
      "step": 1580
    },
    {
      "epoch": 6.687763713080169,
      "grad_norm": 0.40417176485061646,
      "learning_rate": 5.971690544691294e-05,
      "loss": 0.6238,
      "step": 1585
    },
    {
      "epoch": 6.708860759493671,
      "grad_norm": 0.40106064081192017,
      "learning_rate": 5.90439721328369e-05,
      "loss": 0.6183,
      "step": 1590
    },
    {
      "epoch": 6.729957805907173,
      "grad_norm": 0.3997708261013031,
      "learning_rate": 5.837325994841434e-05,
      "loss": 0.6349,
      "step": 1595
    },
    {
      "epoch": 6.751054852320675,
      "grad_norm": 0.40423154830932617,
      "learning_rate": 5.770480526774693e-05,
      "loss": 0.6319,
      "step": 1600
    },
    {
      "epoch": 6.772151898734177,
      "grad_norm": 0.39728954434394836,
      "learning_rate": 5.7038644342507205e-05,
      "loss": 0.6454,
      "step": 1605
    },
    {
      "epoch": 6.793248945147679,
      "grad_norm": 0.4143037497997284,
      "learning_rate": 5.6374813299972805e-05,
      "loss": 0.6532,
      "step": 1610
    },
    {
      "epoch": 6.814345991561181,
      "grad_norm": 0.4104886054992676,
      "learning_rate": 5.571334814106681e-05,
      "loss": 0.6375,
      "step": 1615
    },
    {
      "epoch": 6.8354430379746836,
      "grad_norm": 0.41742509603500366,
      "learning_rate": 5.505428473840576e-05,
      "loss": 0.6443,
      "step": 1620
    },
    {
      "epoch": 6.856540084388186,
      "grad_norm": 0.4019664227962494,
      "learning_rate": 5.4397658834353895e-05,
      "loss": 0.6207,
      "step": 1625
    },
    {
      "epoch": 6.877637130801688,
      "grad_norm": 0.4325370490550995,
      "learning_rate": 5.3743506039084913e-05,
      "loss": 0.6357,
      "step": 1630
    },
    {
      "epoch": 6.89873417721519,
      "grad_norm": 0.4043619632720947,
      "learning_rate": 5.309186182865076e-05,
      "loss": 0.646,
      "step": 1635
    },
    {
      "epoch": 6.919831223628692,
      "grad_norm": 0.4148579239845276,
      "learning_rate": 5.244276154305758e-05,
      "loss": 0.6417,
      "step": 1640
    },
    {
      "epoch": 6.940928270042194,
      "grad_norm": 0.41201284527778625,
      "learning_rate": 5.179624038434938e-05,
      "loss": 0.6396,
      "step": 1645
    },
    {
      "epoch": 6.962025316455696,
      "grad_norm": 0.4112018644809723,
      "learning_rate": 5.115233341469877e-05,
      "loss": 0.6391,
      "step": 1650
    },
    {
      "epoch": 6.9831223628691985,
      "grad_norm": 0.42246147990226746,
      "learning_rate": 5.0511075554505426e-05,
      "loss": 0.6344,
      "step": 1655
    },
    {
      "epoch": 7.0,
      "eval_loss": 1.8556586503982544,
      "eval_runtime": 0.5548,
      "eval_samples_per_second": 3.605,
      "eval_steps_per_second": 1.802,
      "step": 1659
    },
    {
      "epoch": 7.0042194092827,
      "grad_norm": 0.38922393321990967,
      "learning_rate": 4.987250158050244e-05,
      "loss": 0.6267,
      "step": 1660
    },
    {
      "epoch": 7.025316455696203,
      "grad_norm": 0.4556201100349426,
      "learning_rate": 4.923664612387019e-05,
      "loss": 0.5894,
      "step": 1665
    },
    {
      "epoch": 7.046413502109704,
      "grad_norm": 0.4320254325866699,
      "learning_rate": 4.860354366835825e-05,
      "loss": 0.6007,
      "step": 1670
    },
    {
      "epoch": 7.067510548523207,
      "grad_norm": 0.41525062918663025,
      "learning_rate": 4.7973228548415385e-05,
      "loss": 0.5944,
      "step": 1675
    },
    {
      "epoch": 7.0886075949367084,
      "grad_norm": 0.46430733799934387,
      "learning_rate": 4.734573494732735e-05,
      "loss": 0.5945,
      "step": 1680
    },
    {
      "epoch": 7.109704641350211,
      "grad_norm": 0.421763151884079,
      "learning_rate": 4.6721096895363114e-05,
      "loss": 0.583,
      "step": 1685
    },
    {
      "epoch": 7.1308016877637135,
      "grad_norm": 0.44340547919273376,
      "learning_rate": 4.6099348267929334e-05,
      "loss": 0.6034,
      "step": 1690
    },
    {
      "epoch": 7.151898734177215,
      "grad_norm": 0.4334201216697693,
      "learning_rate": 4.548052278373327e-05,
      "loss": 0.592,
      "step": 1695
    },
    {
      "epoch": 7.172995780590718,
      "grad_norm": 0.4375658631324768,
      "learning_rate": 4.486465400295404e-05,
      "loss": 0.5942,
      "step": 1700
    },
    {
      "epoch": 7.194092827004219,
      "grad_norm": 0.4318469762802124,
      "learning_rate": 4.4251775325422795e-05,
      "loss": 0.6079,
      "step": 1705
    },
    {
      "epoch": 7.215189873417722,
      "grad_norm": 0.4487842619419098,
      "learning_rate": 4.364191998881104e-05,
      "loss": 0.5938,
      "step": 1710
    },
    {
      "epoch": 7.236286919831223,
      "grad_norm": 0.4327734112739563,
      "learning_rate": 4.303512106682849e-05,
      "loss": 0.5965,
      "step": 1715
    },
    {
      "epoch": 7.257383966244726,
      "grad_norm": 0.4447080194950104,
      "learning_rate": 4.243141146742905e-05,
      "loss": 0.5953,
      "step": 1720
    },
    {
      "epoch": 7.2784810126582276,
      "grad_norm": 0.4422175884246826,
      "learning_rate": 4.183082393102636e-05,
      "loss": 0.5849,
      "step": 1725
    },
    {
      "epoch": 7.29957805907173,
      "grad_norm": 0.4476224184036255,
      "learning_rate": 4.1233391028718116e-05,
      "loss": 0.5962,
      "step": 1730
    },
    {
      "epoch": 7.320675105485232,
      "grad_norm": 0.4534938931465149,
      "learning_rate": 4.063914516051984e-05,
      "loss": 0.5838,
      "step": 1735
    },
    {
      "epoch": 7.341772151898734,
      "grad_norm": 0.45842060446739197,
      "learning_rate": 4.004811855360748e-05,
      "loss": 0.6046,
      "step": 1740
    },
    {
      "epoch": 7.362869198312236,
      "grad_norm": 0.43340378999710083,
      "learning_rate": 3.9460343260569964e-05,
      "loss": 0.5972,
      "step": 1745
    },
    {
      "epoch": 7.383966244725738,
      "grad_norm": 0.4477992057800293,
      "learning_rate": 3.887585115767068e-05,
      "loss": 0.6067,
      "step": 1750
    },
    {
      "epoch": 7.405063291139241,
      "grad_norm": 0.44521939754486084,
      "learning_rate": 3.82946739431189e-05,
      "loss": 0.5959,
      "step": 1755
    },
    {
      "epoch": 7.4261603375527425,
      "grad_norm": 0.42936068773269653,
      "learning_rate": 3.771684313535062e-05,
      "loss": 0.5963,
      "step": 1760
    },
    {
      "epoch": 7.447257383966245,
      "grad_norm": 0.45330098271369934,
      "learning_rate": 3.7142390071319454e-05,
      "loss": 0.6001,
      "step": 1765
    },
    {
      "epoch": 7.468354430379747,
      "grad_norm": 0.451648473739624,
      "learning_rate": 3.65713459047969e-05,
      "loss": 0.6104,
      "step": 1770
    },
    {
      "epoch": 7.489451476793249,
      "grad_norm": 0.4406780004501343,
      "learning_rate": 3.60037416046829e-05,
      "loss": 0.5942,
      "step": 1775
    },
    {
      "epoch": 7.510548523206751,
      "grad_norm": 0.4443998634815216,
      "learning_rate": 3.543960795332653e-05,
      "loss": 0.5919,
      "step": 1780
    },
    {
      "epoch": 7.531645569620253,
      "grad_norm": 0.45104894042015076,
      "learning_rate": 3.487897554485628e-05,
      "loss": 0.5995,
      "step": 1785
    },
    {
      "epoch": 7.552742616033755,
      "grad_norm": 0.45314210653305054,
      "learning_rate": 3.43218747835211e-05,
      "loss": 0.587,
      "step": 1790
    },
    {
      "epoch": 7.5738396624472575,
      "grad_norm": 0.4450884163379669,
      "learning_rate": 3.376833588204148e-05,
      "loss": 0.5879,
      "step": 1795
    },
    {
      "epoch": 7.594936708860759,
      "grad_norm": 0.44848042726516724,
      "learning_rate": 3.3218388859970875e-05,
      "loss": 0.598,
      "step": 1800
    },
    {
      "epoch": 7.616033755274262,
      "grad_norm": 0.45061829686164856,
      "learning_rate": 3.2672063542067734e-05,
      "loss": 0.6111,
      "step": 1805
    },
    {
      "epoch": 7.637130801687764,
      "grad_norm": 0.43524765968322754,
      "learning_rate": 3.2129389556678016e-05,
      "loss": 0.6004,
      "step": 1810
    },
    {
      "epoch": 7.658227848101266,
      "grad_norm": 0.46142658591270447,
      "learning_rate": 3.15903963341285e-05,
      "loss": 0.594,
      "step": 1815
    },
    {
      "epoch": 7.679324894514768,
      "grad_norm": 0.45434656739234924,
      "learning_rate": 3.1055113105130506e-05,
      "loss": 0.6002,
      "step": 1820
    },
    {
      "epoch": 7.70042194092827,
      "grad_norm": 0.45925071835517883,
      "learning_rate": 3.052356889919489e-05,
      "loss": 0.5914,
      "step": 1825
    },
    {
      "epoch": 7.7215189873417724,
      "grad_norm": 0.44464772939682007,
      "learning_rate": 2.9995792543057478e-05,
      "loss": 0.6064,
      "step": 1830
    },
    {
      "epoch": 7.742616033755274,
      "grad_norm": 0.44117605686187744,
      "learning_rate": 2.9471812659115917e-05,
      "loss": 0.5993,
      "step": 1835
    },
    {
      "epoch": 7.763713080168777,
      "grad_norm": 0.4454299509525299,
      "learning_rate": 2.895165766387733e-05,
      "loss": 0.5957,
      "step": 1840
    },
    {
      "epoch": 7.784810126582278,
      "grad_norm": 0.4484660029411316,
      "learning_rate": 2.843535576641725e-05,
      "loss": 0.5985,
      "step": 1845
    },
    {
      "epoch": 7.805907172995781,
      "grad_norm": 0.4591384828090668,
      "learning_rate": 2.7922934966849823e-05,
      "loss": 0.6044,
      "step": 1850
    },
    {
      "epoch": 7.827004219409282,
      "grad_norm": 0.4372834861278534,
      "learning_rate": 2.7414423054809302e-05,
      "loss": 0.5958,
      "step": 1855
    },
    {
      "epoch": 7.848101265822785,
      "grad_norm": 0.44407814741134644,
      "learning_rate": 2.690984760794284e-05,
      "loss": 0.5965,
      "step": 1860
    },
    {
      "epoch": 7.869198312236287,
      "grad_norm": 0.44278717041015625,
      "learning_rate": 2.6409235990415026e-05,
      "loss": 0.6062,
      "step": 1865
    },
    {
      "epoch": 7.890295358649789,
      "grad_norm": 0.4526854455471039,
      "learning_rate": 2.591261535142383e-05,
      "loss": 0.6035,
      "step": 1870
    },
    {
      "epoch": 7.911392405063291,
      "grad_norm": 0.4361235499382019,
      "learning_rate": 2.5420012623728208e-05,
      "loss": 0.6041,
      "step": 1875
    },
    {
      "epoch": 7.932489451476793,
      "grad_norm": 0.4319293200969696,
      "learning_rate": 2.4931454522187593e-05,
      "loss": 0.6005,
      "step": 1880
    },
    {
      "epoch": 7.953586497890296,
      "grad_norm": 0.44515419006347656,
      "learning_rate": 2.4446967542313015e-05,
      "loss": 0.614,
      "step": 1885
    },
    {
      "epoch": 7.974683544303797,
      "grad_norm": 0.4468868672847748,
      "learning_rate": 2.3966577958830128e-05,
      "loss": 0.5999,
      "step": 1890
    },
    {
      "epoch": 7.9957805907173,
      "grad_norm": 0.43502089381217957,
      "learning_rate": 2.3490311824254386e-05,
      "loss": 0.591,
      "step": 1895
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.9239612817764282,
      "eval_runtime": 0.555,
      "eval_samples_per_second": 3.604,
      "eval_steps_per_second": 1.802,
      "step": 1896
    },
    {
      "epoch": 8.016877637130802,
      "grad_norm": 0.43088486790657043,
      "learning_rate": 2.3018194967478145e-05,
      "loss": 0.5772,
      "step": 1900
    },
    {
      "epoch": 8.037974683544304,
      "grad_norm": 0.4887051582336426,
      "learning_rate": 2.2550252992369837e-05,
      "loss": 0.5858,
      "step": 1905
    },
    {
      "epoch": 8.059071729957806,
      "grad_norm": 0.46031367778778076,
      "learning_rate": 2.2086511276385556e-05,
      "loss": 0.5698,
      "step": 1910
    },
    {
      "epoch": 8.080168776371307,
      "grad_norm": 0.44916045665740967,
      "learning_rate": 2.1626994969192617e-05,
      "loss": 0.5832,
      "step": 1915
    },
    {
      "epoch": 8.10126582278481,
      "grad_norm": 0.45516934990882874,
      "learning_rate": 2.1171728991305795e-05,
      "loss": 0.5678,
      "step": 1920
    },
    {
      "epoch": 8.122362869198312,
      "grad_norm": 0.4672262668609619,
      "learning_rate": 2.072073803273572e-05,
      "loss": 0.5609,
      "step": 1925
    },
    {
      "epoch": 8.143459915611814,
      "grad_norm": 0.4732205271720886,
      "learning_rate": 2.0274046551649918e-05,
      "loss": 0.5748,
      "step": 1930
    },
    {
      "epoch": 8.164556962025316,
      "grad_norm": 0.4523015022277832,
      "learning_rate": 1.9831678773046424e-05,
      "loss": 0.572,
      "step": 1935
    },
    {
      "epoch": 8.185654008438819,
      "grad_norm": 0.46077847480773926,
      "learning_rate": 1.9393658687439985e-05,
      "loss": 0.5734,
      "step": 1940
    },
    {
      "epoch": 8.20675105485232,
      "grad_norm": 0.48243677616119385,
      "learning_rate": 1.8960010049561028e-05,
      "loss": 0.5749,
      "step": 1945
    },
    {
      "epoch": 8.227848101265822,
      "grad_norm": 0.45998242497444153,
      "learning_rate": 1.8530756377067394e-05,
      "loss": 0.5635,
      "step": 1950
    },
    {
      "epoch": 8.248945147679326,
      "grad_norm": 0.4926050305366516,
      "learning_rate": 1.8105920949268862e-05,
      "loss": 0.5656,
      "step": 1955
    },
    {
      "epoch": 8.270042194092827,
      "grad_norm": 0.44752731919288635,
      "learning_rate": 1.7685526805864727e-05,
      "loss": 0.5713,
      "step": 1960
    },
    {
      "epoch": 8.291139240506329,
      "grad_norm": 0.4773804843425751,
      "learning_rate": 1.7269596745694295e-05,
      "loss": 0.5753,
      "step": 1965
    },
    {
      "epoch": 8.31223628691983,
      "grad_norm": 0.4709602892398834,
      "learning_rate": 1.6858153325500435e-05,
      "loss": 0.5604,
      "step": 1970
    },
    {
      "epoch": 8.333333333333334,
      "grad_norm": 0.46927887201309204,
      "learning_rate": 1.6451218858706374e-05,
      "loss": 0.578,
      "step": 1975
    },
    {
      "epoch": 8.354430379746836,
      "grad_norm": 0.467042475938797,
      "learning_rate": 1.60488154142054e-05,
      "loss": 0.5876,
      "step": 1980
    },
    {
      "epoch": 8.375527426160337,
      "grad_norm": 0.4665224850177765,
      "learning_rate": 1.565096481516427e-05,
      "loss": 0.5727,
      "step": 1985
    },
    {
      "epoch": 8.396624472573839,
      "grad_norm": 0.46915140748023987,
      "learning_rate": 1.5257688637839484e-05,
      "loss": 0.5744,
      "step": 1990
    },
    {
      "epoch": 8.417721518987342,
      "grad_norm": 0.4630158841609955,
      "learning_rate": 1.4869008210407243e-05,
      "loss": 0.5609,
      "step": 1995
    },
    {
      "epoch": 8.438818565400844,
      "grad_norm": 0.46690833568573,
      "learning_rate": 1.4484944611806773e-05,
      "loss": 0.5764,
      "step": 2000
    },
    {
      "epoch": 8.459915611814345,
      "grad_norm": 0.46290239691734314,
      "learning_rate": 1.410551867059724e-05,
      "loss": 0.5817,
      "step": 2005
    },
    {
      "epoch": 8.481012658227849,
      "grad_norm": 0.4760874807834625,
      "learning_rate": 1.3730750963828032e-05,
      "loss": 0.5704,
      "step": 2010
    },
    {
      "epoch": 8.50210970464135,
      "grad_norm": 0.47287824749946594,
      "learning_rate": 1.3360661815922903e-05,
      "loss": 0.574,
      "step": 2015
    },
    {
      "epoch": 8.523206751054852,
      "grad_norm": 0.46598172187805176,
      "learning_rate": 1.2995271297577816e-05,
      "loss": 0.5792,
      "step": 2020
    },
    {
      "epoch": 8.544303797468354,
      "grad_norm": 0.4603840410709381,
      "learning_rate": 1.2634599224672294e-05,
      "loss": 0.5674,
      "step": 2025
    },
    {
      "epoch": 8.565400843881857,
      "grad_norm": 0.48355668783187866,
      "learning_rate": 1.227866515719489e-05,
      "loss": 0.5676,
      "step": 2030
    },
    {
      "epoch": 8.586497890295359,
      "grad_norm": 0.4648090898990631,
      "learning_rate": 1.1927488398182395e-05,
      "loss": 0.5595,
      "step": 2035
    },
    {
      "epoch": 8.60759493670886,
      "grad_norm": 0.47335174679756165,
      "learning_rate": 1.1581087992672935e-05,
      "loss": 0.5743,
      "step": 2040
    },
    {
      "epoch": 8.628691983122362,
      "grad_norm": 0.46940383315086365,
      "learning_rate": 1.1239482726673201e-05,
      "loss": 0.5719,
      "step": 2045
    },
    {
      "epoch": 8.649789029535865,
      "grad_norm": 0.46548011898994446,
      "learning_rate": 1.0902691126139542e-05,
      "loss": 0.5722,
      "step": 2050
    },
    {
      "epoch": 8.670886075949367,
      "grad_norm": 0.4601798355579376,
      "learning_rate": 1.0570731455973414e-05,
      "loss": 0.5752,
      "step": 2055
    },
    {
      "epoch": 8.691983122362869,
      "grad_norm": 0.47531968355178833,
      "learning_rate": 1.024362171903065e-05,
      "loss": 0.5833,
      "step": 2060
    },
    {
      "epoch": 8.713080168776372,
      "grad_norm": 0.46817246079444885,
      "learning_rate": 9.921379655145313e-06,
      "loss": 0.5716,
      "step": 2065
    },
    {
      "epoch": 8.734177215189874,
      "grad_norm": 0.47469767928123474,
      "learning_rate": 9.604022740167495e-06,
      "loss": 0.5825,
      "step": 2070
    },
    {
      "epoch": 8.755274261603375,
      "grad_norm": 0.4739144444465637,
      "learning_rate": 9.29156818501561e-06,
      "loss": 0.5669,
      "step": 2075
    },
    {
      "epoch": 8.776371308016877,
      "grad_norm": 0.5070598721504211,
      "learning_rate": 8.984032934743026e-06,
      "loss": 0.5797,
      "step": 2080
    },
    {
      "epoch": 8.79746835443038,
      "grad_norm": 0.4720567464828491,
      "learning_rate": 8.681433667619065e-06,
      "loss": 0.5635,
      "step": 2085
    },
    {
      "epoch": 8.818565400843882,
      "grad_norm": 0.45980048179626465,
      "learning_rate": 8.383786794224569e-06,
      "loss": 0.5715,
      "step": 2090
    },
    {
      "epoch": 8.839662447257384,
      "grad_norm": 0.4796925187110901,
      "learning_rate": 8.09110845656187e-06,
      "loss": 0.5785,
      "step": 2095
    },
    {
      "epoch": 8.860759493670885,
      "grad_norm": 0.4801785349845886,
      "learning_rate": 7.803414527179343e-06,
      "loss": 0.5772,
      "step": 2100
    },
    {
      "epoch": 8.881856540084389,
      "grad_norm": 0.4780319631099701,
      "learning_rate": 7.520720608310683e-06,
      "loss": 0.5726,
      "step": 2105
    },
    {
      "epoch": 8.90295358649789,
      "grad_norm": 0.4621387720108032,
      "learning_rate": 7.243042031028713e-06,
      "loss": 0.5752,
      "step": 2110
    },
    {
      "epoch": 8.924050632911392,
      "grad_norm": 0.4708462059497833,
      "learning_rate": 6.9703938544139706e-06,
      "loss": 0.5716,
      "step": 2115
    },
    {
      "epoch": 8.945147679324894,
      "grad_norm": 0.4696125090122223,
      "learning_rate": 6.702790864738018e-06,
      "loss": 0.5666,
      "step": 2120
    },
    {
      "epoch": 8.966244725738397,
      "grad_norm": 0.47694242000579834,
      "learning_rate": 6.440247574661573e-06,
      "loss": 0.568,
      "step": 2125
    },
    {
      "epoch": 8.987341772151899,
      "grad_norm": 0.4875074326992035,
      "learning_rate": 6.182778222447383e-06,
      "loss": 0.5677,
      "step": 2130
    },
    {
      "epoch": 9.0,
      "eval_loss": 1.984204888343811,
      "eval_runtime": 0.5545,
      "eval_samples_per_second": 3.607,
      "eval_steps_per_second": 1.804,
      "step": 2133
    },
    {
      "epoch": 9.0084388185654,
      "grad_norm": 0.4417002499103546,
      "learning_rate": 5.930396771188129e-06,
      "loss": 0.566,
      "step": 2135
    },
    {
      "epoch": 9.029535864978904,
      "grad_norm": 0.4602307677268982,
      "learning_rate": 5.683116908049168e-06,
      "loss": 0.5625,
      "step": 2140
    },
    {
      "epoch": 9.050632911392405,
      "grad_norm": 0.4665865898132324,
      "learning_rate": 5.440952043526215e-06,
      "loss": 0.5584,
      "step": 2145
    },
    {
      "epoch": 9.071729957805907,
      "grad_norm": 0.47397249937057495,
      "learning_rate": 5.203915310718099e-06,
      "loss": 0.558,
      "step": 2150
    },
    {
      "epoch": 9.092827004219409,
      "grad_norm": 0.47351840138435364,
      "learning_rate": 4.972019564614539e-06,
      "loss": 0.5516,
      "step": 2155
    },
    {
      "epoch": 9.113924050632912,
      "grad_norm": 0.4746864438056946,
      "learning_rate": 4.745277381398938e-06,
      "loss": 0.5536,
      "step": 2160
    },
    {
      "epoch": 9.135021097046414,
      "grad_norm": 0.4737743139266968,
      "learning_rate": 4.523701057766361e-06,
      "loss": 0.5577,
      "step": 2165
    },
    {
      "epoch": 9.156118143459915,
      "grad_norm": 0.4778996706008911,
      "learning_rate": 4.307302610256736e-06,
      "loss": 0.5541,
      "step": 2170
    },
    {
      "epoch": 9.177215189873417,
      "grad_norm": 0.4771966338157654,
      "learning_rate": 4.0960937746030605e-06,
      "loss": 0.552,
      "step": 2175
    },
    {
      "epoch": 9.19831223628692,
      "grad_norm": 0.4708782732486725,
      "learning_rate": 3.890086005095051e-06,
      "loss": 0.5515,
      "step": 2180
    },
    {
      "epoch": 9.219409282700422,
      "grad_norm": 0.49065274000167847,
      "learning_rate": 3.6892904739578736e-06,
      "loss": 0.5593,
      "step": 2185
    },
    {
      "epoch": 9.240506329113924,
      "grad_norm": 0.47753557562828064,
      "learning_rate": 3.493718070746299e-06,
      "loss": 0.5558,
      "step": 2190
    },
    {
      "epoch": 9.261603375527427,
      "grad_norm": 0.4750811755657196,
      "learning_rate": 3.3033794017541254e-06,
      "loss": 0.5588,
      "step": 2195
    },
    {
      "epoch": 9.282700421940929,
      "grad_norm": 0.46534910798072815,
      "learning_rate": 3.1182847894389634e-06,
      "loss": 0.5567,
      "step": 2200
    },
    {
      "epoch": 9.30379746835443,
      "grad_norm": 0.46732398867607117,
      "learning_rate": 2.9384442718624395e-06,
      "loss": 0.5712,
      "step": 2205
    },
    {
      "epoch": 9.324894514767932,
      "grad_norm": 0.4703245759010315,
      "learning_rate": 2.763867602145842e-06,
      "loss": 0.5566,
      "step": 2210
    },
    {
      "epoch": 9.345991561181435,
      "grad_norm": 0.4757389426231384,
      "learning_rate": 2.5945642479411448e-06,
      "loss": 0.5669,
      "step": 2215
    },
    {
      "epoch": 9.367088607594937,
      "grad_norm": 0.49615395069122314,
      "learning_rate": 2.430543390917539e-06,
      "loss": 0.5771,
      "step": 2220
    },
    {
      "epoch": 9.388185654008439,
      "grad_norm": 0.4786005914211273,
      "learning_rate": 2.2718139262635775e-06,
      "loss": 0.5581,
      "step": 2225
    },
    {
      "epoch": 9.40928270042194,
      "grad_norm": 0.4749692380428314,
      "learning_rate": 2.1183844622047034e-06,
      "loss": 0.5566,
      "step": 2230
    },
    {
      "epoch": 9.430379746835444,
      "grad_norm": 0.4892341196537018,
      "learning_rate": 1.9702633195363917e-06,
      "loss": 0.5577,
      "step": 2235
    },
    {
      "epoch": 9.451476793248945,
      "grad_norm": 0.485775351524353,
      "learning_rate": 1.8274585311729653e-06,
      "loss": 0.5724,
      "step": 2240
    },
    {
      "epoch": 9.472573839662447,
      "grad_norm": 0.47523242235183716,
      "learning_rate": 1.6899778417118983e-06,
      "loss": 0.5472,
      "step": 2245
    },
    {
      "epoch": 9.49367088607595,
      "grad_norm": 0.45913201570510864,
      "learning_rate": 1.557828707013831e-06,
      "loss": 0.5576,
      "step": 2250
    },
    {
      "epoch": 9.514767932489452,
      "grad_norm": 0.4752641022205353,
      "learning_rate": 1.4310182937982141e-06,
      "loss": 0.5605,
      "step": 2255
    },
    {
      "epoch": 9.535864978902953,
      "grad_norm": 0.47292277216911316,
      "learning_rate": 1.309553479254666e-06,
      "loss": 0.5653,
      "step": 2260
    },
    {
      "epoch": 9.556962025316455,
      "grad_norm": 0.4652714133262634,
      "learning_rate": 1.1934408506699802e-06,
      "loss": 0.5571,
      "step": 2265
    },
    {
      "epoch": 9.578059071729959,
      "grad_norm": 0.4648183584213257,
      "learning_rate": 1.0826867050708678e-06,
      "loss": 0.5603,
      "step": 2270
    },
    {
      "epoch": 9.59915611814346,
      "grad_norm": 0.4922165274620056,
      "learning_rate": 9.772970488825417e-07,
      "loss": 0.5627,
      "step": 2275
    },
    {
      "epoch": 9.620253164556962,
      "grad_norm": 0.4720841348171234,
      "learning_rate": 8.772775976028546e-07,
      "loss": 0.5517,
      "step": 2280
    },
    {
      "epoch": 9.641350210970463,
      "grad_norm": 0.510443389415741,
      "learning_rate": 7.826337754924473e-07,
      "loss": 0.5641,
      "step": 2285
    },
    {
      "epoch": 9.662447257383967,
      "grad_norm": 0.46088987588882446,
      "learning_rate": 6.933707152805058e-07,
      "loss": 0.5595,
      "step": 2290
    },
    {
      "epoch": 9.683544303797468,
      "grad_norm": 0.48828017711639404,
      "learning_rate": 6.094932578864287e-07,
      "loss": 0.565,
      "step": 2295
    },
    {
      "epoch": 9.70464135021097,
      "grad_norm": 0.4722835421562195,
      "learning_rate": 5.31005952157304e-07,
      "loss": 0.5611,
      "step": 2300
    },
    {
      "epoch": 9.725738396624472,
      "grad_norm": 0.4879083037376404,
      "learning_rate": 4.5791305462120625e-07,
      "loss": 0.5746,
      "step": 2305
    },
    {
      "epoch": 9.746835443037975,
      "grad_norm": 0.4783223271369934,
      "learning_rate": 3.902185292563365e-07,
      "loss": 0.569,
      "step": 2310
    },
    {
      "epoch": 9.767932489451477,
      "grad_norm": 0.4648023247718811,
      "learning_rate": 3.2792604727608367e-07,
      "loss": 0.5503,
      "step": 2315
    },
    {
      "epoch": 9.789029535864978,
      "grad_norm": 0.47712016105651855,
      "learning_rate": 2.710389869298946e-07,
      "loss": 0.5522,
      "step": 2320
    },
    {
      "epoch": 9.810126582278482,
      "grad_norm": 0.4652068614959717,
      "learning_rate": 2.1956043332010955e-07,
      "loss": 0.556,
      "step": 2325
    },
    {
      "epoch": 9.831223628691983,
      "grad_norm": 0.48310577869415283,
      "learning_rate": 1.7349317823459609e-07,
      "loss": 0.5637,
      "step": 2330
    },
    {
      "epoch": 9.852320675105485,
      "grad_norm": 0.5295414924621582,
      "learning_rate": 1.3283971999537015e-07,
      "loss": 0.5559,
      "step": 2335
    },
    {
      "epoch": 9.873417721518987,
      "grad_norm": 0.4798893928527832,
      "learning_rate": 9.76022633231155e-08,
      "loss": 0.5543,
      "step": 2340
    },
    {
      "epoch": 9.89451476793249,
      "grad_norm": 0.48038187623023987,
      "learning_rate": 6.778271921760171e-08,
      "loss": 0.5626,
      "step": 2345
    },
    {
      "epoch": 9.915611814345992,
      "grad_norm": 0.47445496916770935,
      "learning_rate": 4.338270485405582e-08,
      "loss": 0.5545,
      "step": 2350
    },
    {
      "epoch": 9.936708860759493,
      "grad_norm": 0.47432997822761536,
      "learning_rate": 2.4403543495454818e-08,
      "loss": 0.5651,
      "step": 2355
    },
    {
      "epoch": 9.957805907172995,
      "grad_norm": 0.4740554094314575,
      "learning_rate": 1.0846264420771857e-08,
      "loss": 0.5637,
      "step": 2360
    },
    {
      "epoch": 9.978902953586498,
      "grad_norm": 0.4762984812259674,
      "learning_rate": 2.7116028691431817e-09,
      "loss": 0.5611,
      "step": 2365
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.4564709961414337,
      "learning_rate": 0.0,
      "loss": 0.5648,
      "step": 2370
    },
    {
      "epoch": 10.0,
      "eval_loss": 2.0032131671905518,
      "eval_runtime": 0.5807,
      "eval_samples_per_second": 3.444,
      "eval_steps_per_second": 1.722,
      "step": 2370
    },
    {
      "epoch": 10.0,
      "step": 2370,
      "total_flos": 3.5097090775444357e+18,
      "train_loss": 0.7390849222110797,
      "train_runtime": 8188.9555,
      "train_samples_per_second": 9.243,
      "train_steps_per_second": 0.289
    }
  ],
  "logging_steps": 5,
  "max_steps": 2370,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 3.5097090775444357e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}