{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 1890,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010582010582010581,
      "grad_norm": 39.13801574707031,
      "learning_rate": 1.9952380952380953e-05,
      "loss": 5.4194,
      "step": 10
    },
    {
      "epoch": 0.021164021164021163,
      "grad_norm": 24.028564453125,
      "learning_rate": 1.98994708994709e-05,
      "loss": 1.773,
      "step": 20
    },
    {
      "epoch": 0.031746031746031744,
      "grad_norm": 16.863679885864258,
      "learning_rate": 1.9846560846560846e-05,
      "loss": 0.7073,
      "step": 30
    },
    {
      "epoch": 0.042328042328042326,
      "grad_norm": 10.789055824279785,
      "learning_rate": 1.9793650793650796e-05,
      "loss": 0.3436,
      "step": 40
    },
    {
      "epoch": 0.05291005291005291,
      "grad_norm": 8.038490295410156,
      "learning_rate": 1.9740740740740743e-05,
      "loss": 0.2155,
      "step": 50
    },
    {
      "epoch": 0.06349206349206349,
      "grad_norm": 4.677557945251465,
      "learning_rate": 1.968783068783069e-05,
      "loss": 0.1287,
      "step": 60
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 3.4516615867614746,
      "learning_rate": 1.9634920634920636e-05,
      "loss": 0.0824,
      "step": 70
    },
    {
      "epoch": 0.08465608465608465,
      "grad_norm": 1.6580854654312134,
      "learning_rate": 1.9582010582010586e-05,
      "loss": 0.0501,
      "step": 80
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 1.1410599946975708,
      "learning_rate": 1.9529100529100532e-05,
      "loss": 0.0316,
      "step": 90
    },
    {
      "epoch": 0.10582010582010581,
      "grad_norm": 1.6213871240615845,
      "learning_rate": 1.947619047619048e-05,
      "loss": 0.025,
      "step": 100
    },
    {
      "epoch": 0.1164021164021164,
      "grad_norm": 0.5977617502212524,
      "learning_rate": 1.9423280423280425e-05,
      "loss": 0.0153,
      "step": 110
    },
    {
      "epoch": 0.12698412698412698,
      "grad_norm": 2.150684118270874,
      "learning_rate": 1.9370370370370372e-05,
      "loss": 0.0162,
      "step": 120
    },
    {
      "epoch": 0.13756613756613756,
      "grad_norm": 0.3688974678516388,
      "learning_rate": 1.931746031746032e-05,
      "loss": 0.0116,
      "step": 130
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 10.174367904663086,
      "learning_rate": 1.9264550264550265e-05,
      "loss": 0.0149,
      "step": 140
    },
    {
      "epoch": 0.15873015873015872,
      "grad_norm": 0.2287941724061966,
      "learning_rate": 1.921164021164021e-05,
      "loss": 0.0068,
      "step": 150
    },
    {
      "epoch": 0.1693121693121693,
      "grad_norm": 0.7957000136375427,
      "learning_rate": 1.915873015873016e-05,
      "loss": 0.01,
      "step": 160
    },
    {
      "epoch": 0.17989417989417988,
      "grad_norm": 0.24841707944869995,
      "learning_rate": 1.9105820105820108e-05,
      "loss": 0.0161,
      "step": 170
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 1.3141834735870361,
      "learning_rate": 1.9052910052910055e-05,
      "loss": 0.0057,
      "step": 180
    },
    {
      "epoch": 0.20105820105820105,
      "grad_norm": 0.17035521566867828,
      "learning_rate": 1.9e-05,
      "loss": 0.012,
      "step": 190
    },
    {
      "epoch": 0.21164021164021163,
      "grad_norm": 3.853283405303955,
      "learning_rate": 1.894708994708995e-05,
      "loss": 0.0148,
      "step": 200
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.13835227489471436,
      "learning_rate": 1.8894179894179898e-05,
      "loss": 0.0139,
      "step": 210
    },
    {
      "epoch": 0.2328042328042328,
      "grad_norm": 0.3647116422653198,
      "learning_rate": 1.8841269841269844e-05,
      "loss": 0.0117,
      "step": 220
    },
    {
      "epoch": 0.24338624338624337,
      "grad_norm": 4.365599632263184,
      "learning_rate": 1.878835978835979e-05,
      "loss": 0.0102,
      "step": 230
    },
    {
      "epoch": 0.25396825396825395,
      "grad_norm": 0.1187911406159401,
      "learning_rate": 1.8735449735449737e-05,
      "loss": 0.0053,
      "step": 240
    },
    {
      "epoch": 0.26455026455026454,
      "grad_norm": 5.611083507537842,
      "learning_rate": 1.8682539682539684e-05,
      "loss": 0.0052,
      "step": 250
    },
    {
      "epoch": 0.2751322751322751,
      "grad_norm": 1.2097302675247192,
      "learning_rate": 1.862962962962963e-05,
      "loss": 0.0066,
      "step": 260
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.08928469568490982,
      "learning_rate": 1.8576719576719577e-05,
      "loss": 0.0183,
      "step": 270
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 1.7315622568130493,
      "learning_rate": 1.8523809523809527e-05,
      "loss": 0.0049,
      "step": 280
    },
    {
      "epoch": 0.30687830687830686,
      "grad_norm": 0.10508707910776138,
      "learning_rate": 1.8470899470899473e-05,
      "loss": 0.0174,
      "step": 290
    },
    {
      "epoch": 0.31746031746031744,
      "grad_norm": 0.08319881558418274,
      "learning_rate": 1.841798941798942e-05,
      "loss": 0.0068,
      "step": 300
    },
    {
      "epoch": 0.328042328042328,
      "grad_norm": 3.9523701667785645,
      "learning_rate": 1.8365079365079366e-05,
      "loss": 0.0545,
      "step": 310
    },
    {
      "epoch": 0.3386243386243386,
      "grad_norm": 0.11226499825716019,
      "learning_rate": 1.8312169312169313e-05,
      "loss": 0.0066,
      "step": 320
    },
    {
      "epoch": 0.3492063492063492,
      "grad_norm": 1.6739437580108643,
      "learning_rate": 1.825925925925926e-05,
      "loss": 0.0075,
      "step": 330
    },
    {
      "epoch": 0.35978835978835977,
      "grad_norm": 4.503218173980713,
      "learning_rate": 1.8206349206349206e-05,
      "loss": 0.0051,
      "step": 340
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 0.07483673095703125,
      "learning_rate": 1.8153439153439152e-05,
      "loss": 0.0035,
      "step": 350
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 0.06276049464941025,
      "learning_rate": 1.8100529100529102e-05,
      "loss": 0.0368,
      "step": 360
    },
    {
      "epoch": 0.3915343915343915,
      "grad_norm": 3.8753137588500977,
      "learning_rate": 1.804761904761905e-05,
      "loss": 0.0103,
      "step": 370
    },
    {
      "epoch": 0.4021164021164021,
      "grad_norm": 0.8073577880859375,
      "learning_rate": 1.7994708994708995e-05,
      "loss": 0.0112,
      "step": 380
    },
    {
      "epoch": 0.4126984126984127,
      "grad_norm": 5.514145374298096,
      "learning_rate": 1.7941798941798942e-05,
      "loss": 0.0038,
      "step": 390
    },
    {
      "epoch": 0.42328042328042326,
      "grad_norm": 0.3400741517543793,
      "learning_rate": 1.7888888888888892e-05,
      "loss": 0.0027,
      "step": 400
    },
    {
      "epoch": 0.43386243386243384,
      "grad_norm": 6.407121181488037,
      "learning_rate": 1.783597883597884e-05,
      "loss": 0.0061,
      "step": 410
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.0525721050798893,
      "learning_rate": 1.7783068783068785e-05,
      "loss": 0.0031,
      "step": 420
    },
    {
      "epoch": 0.455026455026455,
      "grad_norm": 9.535446166992188,
      "learning_rate": 1.773015873015873e-05,
      "loss": 0.006,
      "step": 430
    },
    {
      "epoch": 0.4656084656084656,
      "grad_norm": 0.08640318363904953,
      "learning_rate": 1.7677248677248678e-05,
      "loss": 0.0062,
      "step": 440
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 0.06083179637789726,
      "learning_rate": 1.7624338624338625e-05,
      "loss": 0.0036,
      "step": 450
    },
    {
      "epoch": 0.48677248677248675,
      "grad_norm": 0.0371096171438694,
      "learning_rate": 1.757142857142857e-05,
      "loss": 0.0009,
      "step": 460
    },
    {
      "epoch": 0.4973544973544973,
      "grad_norm": 0.7781650424003601,
      "learning_rate": 1.7518518518518518e-05,
      "loss": 0.0113,
      "step": 470
    },
    {
      "epoch": 0.5079365079365079,
      "grad_norm": 0.3946099877357483,
      "learning_rate": 1.7465608465608468e-05,
      "loss": 0.004,
      "step": 480
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 0.039193294942379,
      "learning_rate": 1.7412698412698414e-05,
      "loss": 0.0013,
      "step": 490
    },
    {
      "epoch": 0.5291005291005291,
      "grad_norm": 0.037502456456422806,
      "learning_rate": 1.735978835978836e-05,
      "loss": 0.003,
      "step": 500
    },
    {
      "epoch": 0.5396825396825397,
      "grad_norm": 0.03162345662713051,
      "learning_rate": 1.7306878306878307e-05,
      "loss": 0.0011,
      "step": 510
    },
    {
      "epoch": 0.5502645502645502,
      "grad_norm": 0.026782995089888573,
      "learning_rate": 1.7253968253968257e-05,
      "loss": 0.0006,
      "step": 520
    },
    {
      "epoch": 0.5608465608465608,
      "grad_norm": 0.027304725721478462,
      "learning_rate": 1.7201058201058204e-05,
      "loss": 0.0024,
      "step": 530
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.045405562967061996,
      "learning_rate": 1.714814814814815e-05,
      "loss": 0.0079,
      "step": 540
    },
    {
      "epoch": 0.582010582010582,
      "grad_norm": 0.026607122272253036,
      "learning_rate": 1.7095238095238097e-05,
      "loss": 0.0024,
      "step": 550
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.1648360937833786,
      "learning_rate": 1.7042328042328043e-05,
      "loss": 0.0038,
      "step": 560
    },
    {
      "epoch": 0.6031746031746031,
      "grad_norm": 0.2880645990371704,
      "learning_rate": 1.698941798941799e-05,
      "loss": 0.0069,
      "step": 570
    },
    {
      "epoch": 0.6137566137566137,
      "grad_norm": 0.08049669116735458,
      "learning_rate": 1.6936507936507936e-05,
      "loss": 0.0091,
      "step": 580
    },
    {
      "epoch": 0.6243386243386243,
      "grad_norm": 0.16391621530056,
      "learning_rate": 1.6883597883597883e-05,
      "loss": 0.003,
      "step": 590
    },
    {
      "epoch": 0.6349206349206349,
      "grad_norm": 0.31218671798706055,
      "learning_rate": 1.6830687830687833e-05,
      "loss": 0.0009,
      "step": 600
    },
    {
      "epoch": 0.6455026455026455,
      "grad_norm": 0.02184475213289261,
      "learning_rate": 1.677777777777778e-05,
      "loss": 0.0133,
      "step": 610
    },
    {
      "epoch": 0.656084656084656,
      "grad_norm": 0.025240115821361542,
      "learning_rate": 1.6724867724867726e-05,
      "loss": 0.0013,
      "step": 620
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.021431762725114822,
      "learning_rate": 1.6671957671957672e-05,
      "loss": 0.0164,
      "step": 630
    },
    {
      "epoch": 0.6772486772486772,
      "grad_norm": 0.3141108751296997,
      "learning_rate": 1.6619047619047622e-05,
      "loss": 0.0026,
      "step": 640
    },
    {
      "epoch": 0.6878306878306878,
      "grad_norm": 0.021496519446372986,
      "learning_rate": 1.656613756613757e-05,
      "loss": 0.0023,
      "step": 650
    },
    {
      "epoch": 0.6984126984126984,
      "grad_norm": 0.06723565608263016,
      "learning_rate": 1.6513227513227515e-05,
      "loss": 0.0019,
      "step": 660
    },
    {
      "epoch": 0.708994708994709,
      "grad_norm": 0.02188393473625183,
      "learning_rate": 1.6460317460317462e-05,
      "loss": 0.0036,
      "step": 670
    },
    {
      "epoch": 0.7195767195767195,
      "grad_norm": 0.07254693657159805,
      "learning_rate": 1.640740740740741e-05,
      "loss": 0.0061,
      "step": 680
    },
    {
      "epoch": 0.7301587301587301,
      "grad_norm": 3.8045756816864014,
      "learning_rate": 1.6354497354497355e-05,
      "loss": 0.0041,
      "step": 690
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 0.019957900047302246,
      "learning_rate": 1.63015873015873e-05,
      "loss": 0.0005,
      "step": 700
    },
    {
      "epoch": 0.7513227513227513,
      "grad_norm": 0.017905883491039276,
      "learning_rate": 1.6248677248677248e-05,
      "loss": 0.0099,
      "step": 710
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 0.580219030380249,
      "learning_rate": 1.6195767195767198e-05,
      "loss": 0.0033,
      "step": 720
    },
    {
      "epoch": 0.7724867724867724,
      "grad_norm": 0.0343511626124382,
      "learning_rate": 1.6142857142857145e-05,
      "loss": 0.0057,
      "step": 730
    },
    {
      "epoch": 0.783068783068783,
      "grad_norm": 0.6010801196098328,
      "learning_rate": 1.608994708994709e-05,
      "loss": 0.0009,
      "step": 740
    },
    {
      "epoch": 0.7936507936507936,
      "grad_norm": 0.020727235823869705,
      "learning_rate": 1.6037037037037038e-05,
      "loss": 0.0024,
      "step": 750
    },
    {
      "epoch": 0.8042328042328042,
      "grad_norm": 5.676093101501465,
      "learning_rate": 1.5984126984126988e-05,
      "loss": 0.0052,
      "step": 760
    },
    {
      "epoch": 0.8148148148148148,
      "grad_norm": 0.22317780554294586,
      "learning_rate": 1.5931216931216934e-05,
      "loss": 0.0063,
      "step": 770
    },
    {
      "epoch": 0.8253968253968254,
      "grad_norm": 0.983028769493103,
      "learning_rate": 1.587830687830688e-05,
      "loss": 0.0046,
      "step": 780
    },
    {
      "epoch": 0.8359788359788359,
      "grad_norm": 0.018990248441696167,
      "learning_rate": 1.5825396825396827e-05,
      "loss": 0.0044,
      "step": 790
    },
    {
      "epoch": 0.8465608465608465,
      "grad_norm": 6.899256706237793,
      "learning_rate": 1.5772486772486774e-05,
      "loss": 0.004,
      "step": 800
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 4.200356483459473,
      "learning_rate": 1.571957671957672e-05,
      "loss": 0.0046,
      "step": 810
    },
    {
      "epoch": 0.8677248677248677,
      "grad_norm": 2.085758686065674,
      "learning_rate": 1.5666666666666667e-05,
      "loss": 0.0029,
      "step": 820
    },
    {
      "epoch": 0.8783068783068783,
      "grad_norm": 0.07632625102996826,
      "learning_rate": 1.5613756613756613e-05,
      "loss": 0.0054,
      "step": 830
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 5.698914051055908,
      "learning_rate": 1.5560846560846563e-05,
      "loss": 0.0037,
      "step": 840
    },
    {
      "epoch": 0.8994708994708994,
      "grad_norm": 0.16661055386066437,
      "learning_rate": 1.550793650793651e-05,
      "loss": 0.0033,
      "step": 850
    },
    {
      "epoch": 0.91005291005291,
      "grad_norm": 0.061884596943855286,
      "learning_rate": 1.5455026455026456e-05,
      "loss": 0.0021,
      "step": 860
    },
    {
      "epoch": 0.9206349206349206,
      "grad_norm": 1.1297595500946045,
      "learning_rate": 1.5402116402116403e-05,
      "loss": 0.0022,
      "step": 870
    },
    {
      "epoch": 0.9312169312169312,
      "grad_norm": 0.3115411698818207,
      "learning_rate": 1.5349206349206353e-05,
      "loss": 0.0052,
      "step": 880
    },
    {
      "epoch": 0.9417989417989417,
      "grad_norm": 2.6712639331817627,
      "learning_rate": 1.52962962962963e-05,
      "loss": 0.0029,
      "step": 890
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 0.01280083879828453,
      "learning_rate": 1.5243386243386244e-05,
      "loss": 0.0005,
      "step": 900
    },
    {
      "epoch": 0.9629629629629629,
      "grad_norm": 5.4594645500183105,
      "learning_rate": 1.519047619047619e-05,
      "loss": 0.007,
      "step": 910
    },
    {
      "epoch": 0.9735449735449735,
      "grad_norm": 0.01234627328813076,
      "learning_rate": 1.5137566137566139e-05,
      "loss": 0.007,
      "step": 920
    },
    {
      "epoch": 0.9841269841269841,
      "grad_norm": 0.12818680703639984,
      "learning_rate": 1.5084656084656086e-05,
      "loss": 0.0005,
      "step": 930
    },
    {
      "epoch": 0.9947089947089947,
      "grad_norm": 0.010110250674188137,
      "learning_rate": 1.5031746031746032e-05,
      "loss": 0.0011,
      "step": 940
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.03604938089847565,
      "eval_runtime": 462.3812,
      "eval_samples_per_second": 0.227,
      "eval_steps_per_second": 0.115,
      "step": 945
    },
    {
      "epoch": 1.0052910052910053,
      "grad_norm": 0.012420996092259884,
      "learning_rate": 1.4978835978835979e-05,
      "loss": 0.0003,
      "step": 950
    },
    {
      "epoch": 1.0158730158730158,
      "grad_norm": 0.010969682596623898,
      "learning_rate": 1.4925925925925929e-05,
      "loss": 0.0002,
      "step": 960
    },
    {
      "epoch": 1.0264550264550265,
      "grad_norm": 0.009813076816499233,
      "learning_rate": 1.4873015873015875e-05,
      "loss": 0.0064,
      "step": 970
    },
    {
      "epoch": 1.037037037037037,
      "grad_norm": 0.08147811144590378,
      "learning_rate": 1.4820105820105822e-05,
      "loss": 0.0009,
      "step": 980
    },
    {
      "epoch": 1.0476190476190477,
      "grad_norm": 0.010766289196908474,
      "learning_rate": 1.4767195767195768e-05,
      "loss": 0.0025,
      "step": 990
    },
    {
      "epoch": 1.0582010582010581,
      "grad_norm": 0.009957353584468365,
      "learning_rate": 1.4714285714285716e-05,
      "loss": 0.0032,
      "step": 1000
    },
    {
      "epoch": 1.0687830687830688,
      "grad_norm": 7.969147682189941,
      "learning_rate": 1.4661375661375663e-05,
      "loss": 0.0028,
      "step": 1010
    },
    {
      "epoch": 1.0793650793650793,
      "grad_norm": 4.326008319854736,
      "learning_rate": 1.460846560846561e-05,
      "loss": 0.0048,
      "step": 1020
    },
    {
      "epoch": 1.08994708994709,
      "grad_norm": 0.00999133475124836,
      "learning_rate": 1.4555555555555556e-05,
      "loss": 0.0026,
      "step": 1030
    },
    {
      "epoch": 1.1005291005291005,
      "grad_norm": 0.010022982954978943,
      "learning_rate": 1.4502645502645504e-05,
      "loss": 0.0084,
      "step": 1040
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 0.013834713026881218,
      "learning_rate": 1.444973544973545e-05,
      "loss": 0.0043,
      "step": 1050
    },
    {
      "epoch": 1.1216931216931216,
      "grad_norm": 0.011380772106349468,
      "learning_rate": 1.4396825396825397e-05,
      "loss": 0.0352,
      "step": 1060
    },
    {
      "epoch": 1.1322751322751323,
      "grad_norm": 0.07020097970962524,
      "learning_rate": 1.4343915343915344e-05,
      "loss": 0.0018,
      "step": 1070
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.02143331617116928,
      "learning_rate": 1.4291005291005294e-05,
      "loss": 0.0017,
      "step": 1080
    },
    {
      "epoch": 1.1534391534391535,
      "grad_norm": 3.8044309616088867,
      "learning_rate": 1.423809523809524e-05,
      "loss": 0.0009,
      "step": 1090
    },
    {
      "epoch": 1.164021164021164,
      "grad_norm": 0.010620811954140663,
      "learning_rate": 1.4185185185185187e-05,
      "loss": 0.0022,
      "step": 1100
    },
    {
      "epoch": 1.1746031746031746,
      "grad_norm": 0.013597151264548302,
      "learning_rate": 1.4132275132275133e-05,
      "loss": 0.0002,
      "step": 1110
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.009412454441189766,
      "learning_rate": 1.4079365079365082e-05,
      "loss": 0.003,
      "step": 1120
    },
    {
      "epoch": 1.1957671957671958,
      "grad_norm": 9.870640754699707,
      "learning_rate": 1.4026455026455028e-05,
      "loss": 0.0051,
      "step": 1130
    },
    {
      "epoch": 1.2063492063492063,
      "grad_norm": 0.15585137903690338,
      "learning_rate": 1.3973544973544975e-05,
      "loss": 0.0005,
      "step": 1140
    },
    {
      "epoch": 1.216931216931217,
      "grad_norm": 0.011549165472388268,
      "learning_rate": 1.3920634920634921e-05,
      "loss": 0.0017,
      "step": 1150
    },
    {
      "epoch": 1.2275132275132274,
      "grad_norm": 0.022659868001937866,
      "learning_rate": 1.386772486772487e-05,
      "loss": 0.0076,
      "step": 1160
    },
    {
      "epoch": 1.2380952380952381,
      "grad_norm": 1.041445255279541,
      "learning_rate": 1.3814814814814816e-05,
      "loss": 0.0011,
      "step": 1170
    },
    {
      "epoch": 1.2486772486772486,
      "grad_norm": 0.00932463351637125,
      "learning_rate": 1.3761904761904763e-05,
      "loss": 0.0024,
      "step": 1180
    },
    {
      "epoch": 1.2592592592592593,
      "grad_norm": 0.0319746658205986,
      "learning_rate": 1.3708994708994709e-05,
      "loss": 0.0012,
      "step": 1190
    },
    {
      "epoch": 1.2698412698412698,
      "grad_norm": 0.0502803809940815,
      "learning_rate": 1.3656084656084659e-05,
      "loss": 0.0173,
      "step": 1200
    },
    {
      "epoch": 1.2804232804232805,
      "grad_norm": 3.397770881652832,
      "learning_rate": 1.3603174603174606e-05,
      "loss": 0.0135,
      "step": 1210
    },
    {
      "epoch": 1.291005291005291,
      "grad_norm": 0.014460274949669838,
      "learning_rate": 1.3550264550264552e-05,
      "loss": 0.0008,
      "step": 1220
    },
    {
      "epoch": 1.3015873015873016,
      "grad_norm": 0.04834635928273201,
      "learning_rate": 1.3497354497354499e-05,
      "loss": 0.0053,
      "step": 1230
    },
    {
      "epoch": 1.312169312169312,
      "grad_norm": 0.09482118487358093,
      "learning_rate": 1.3444444444444447e-05,
      "loss": 0.0017,
      "step": 1240
    },
    {
      "epoch": 1.3227513227513228,
      "grad_norm": 0.007359776180237532,
      "learning_rate": 1.3391534391534393e-05,
      "loss": 0.0003,
      "step": 1250
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.013864404521882534,
      "learning_rate": 1.333862433862434e-05,
      "loss": 0.0003,
      "step": 1260
    },
    {
      "epoch": 1.343915343915344,
      "grad_norm": 1.8579610586166382,
      "learning_rate": 1.3285714285714287e-05,
      "loss": 0.0014,
      "step": 1270
    },
    {
      "epoch": 1.3544973544973544,
      "grad_norm": 0.007739638909697533,
      "learning_rate": 1.3232804232804235e-05,
      "loss": 0.0005,
      "step": 1280
    },
    {
      "epoch": 1.3650793650793651,
      "grad_norm": 0.010888740420341492,
      "learning_rate": 1.3179894179894181e-05,
      "loss": 0.0003,
      "step": 1290
    },
    {
      "epoch": 1.3756613756613756,
      "grad_norm": 0.007155210245400667,
      "learning_rate": 1.3126984126984128e-05,
      "loss": 0.0093,
      "step": 1300
    },
    {
      "epoch": 1.3862433862433863,
      "grad_norm": 0.014670108444988728,
      "learning_rate": 1.3074074074074074e-05,
      "loss": 0.0056,
      "step": 1310
    },
    {
      "epoch": 1.3968253968253967,
      "grad_norm": 0.007492662873119116,
      "learning_rate": 1.3021164021164023e-05,
      "loss": 0.0031,
      "step": 1320
    },
    {
      "epoch": 1.4074074074074074,
      "grad_norm": 4.942596912384033,
      "learning_rate": 1.296825396825397e-05,
      "loss": 0.0026,
      "step": 1330
    },
    {
      "epoch": 1.417989417989418,
      "grad_norm": 0.007958627305924892,
      "learning_rate": 1.2915343915343916e-05,
      "loss": 0.0089,
      "step": 1340
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 2.9070186614990234,
      "learning_rate": 1.2862433862433862e-05,
      "loss": 0.0021,
      "step": 1350
    },
    {
      "epoch": 1.439153439153439,
      "grad_norm": 0.9513811469078064,
      "learning_rate": 1.2809523809523809e-05,
      "loss": 0.0011,
      "step": 1360
    },
    {
      "epoch": 1.4497354497354498,
      "grad_norm": 0.0836050733923912,
      "learning_rate": 1.2756613756613759e-05,
      "loss": 0.0089,
      "step": 1370
    },
    {
      "epoch": 1.4603174603174602,
      "grad_norm": 0.03550349175930023,
      "learning_rate": 1.2703703703703705e-05,
      "loss": 0.003,
      "step": 1380
    },
    {
      "epoch": 1.470899470899471,
      "grad_norm": 0.8934294581413269,
      "learning_rate": 1.2650793650793652e-05,
      "loss": 0.0032,
      "step": 1390
    },
    {
      "epoch": 1.4814814814814814,
      "grad_norm": 0.006408127024769783,
      "learning_rate": 1.2597883597883598e-05,
      "loss": 0.0088,
      "step": 1400
    },
    {
      "epoch": 1.492063492063492,
      "grad_norm": 0.15951858460903168,
      "learning_rate": 1.2544973544973547e-05,
      "loss": 0.0008,
      "step": 1410
    },
    {
      "epoch": 1.5026455026455028,
      "grad_norm": 0.011819873005151749,
      "learning_rate": 1.2492063492063493e-05,
      "loss": 0.0285,
      "step": 1420
    },
    {
      "epoch": 1.5132275132275133,
      "grad_norm": 0.005755511112511158,
      "learning_rate": 1.243915343915344e-05,
      "loss": 0.0006,
      "step": 1430
    },
    {
      "epoch": 1.5238095238095237,
      "grad_norm": 0.0067981211468577385,
      "learning_rate": 1.2386243386243386e-05,
      "loss": 0.0023,
      "step": 1440
    },
    {
      "epoch": 1.5343915343915344,
      "grad_norm": 0.0054528010077774525,
      "learning_rate": 1.2333333333333334e-05,
      "loss": 0.0002,
      "step": 1450
    },
    {
      "epoch": 1.544973544973545,
      "grad_norm": 0.00653385603800416,
      "learning_rate": 1.2280423280423281e-05,
      "loss": 0.0057,
      "step": 1460
    },
    {
      "epoch": 1.5555555555555556,
      "grad_norm": 0.0077536082826554775,
      "learning_rate": 1.2227513227513227e-05,
      "loss": 0.0002,
      "step": 1470
    },
    {
      "epoch": 1.566137566137566,
      "grad_norm": 0.0057713366113603115,
      "learning_rate": 1.2174603174603174e-05,
      "loss": 0.0004,
      "step": 1480
    },
    {
      "epoch": 1.5767195767195767,
      "grad_norm": 0.019029010087251663,
      "learning_rate": 1.2121693121693124e-05,
      "loss": 0.0053,
      "step": 1490
    },
    {
      "epoch": 1.5873015873015874,
      "grad_norm": 0.783202052116394,
      "learning_rate": 1.206878306878307e-05,
      "loss": 0.0014,
      "step": 1500
    },
    {
      "epoch": 1.597883597883598,
      "grad_norm": 0.18570241332054138,
      "learning_rate": 1.2015873015873017e-05,
      "loss": 0.0019,
      "step": 1510
    },
    {
      "epoch": 1.6084656084656084,
      "grad_norm": 3.245318651199341,
      "learning_rate": 1.1962962962962964e-05,
      "loss": 0.0061,
      "step": 1520
    },
    {
      "epoch": 1.619047619047619,
      "grad_norm": 0.009805947542190552,
      "learning_rate": 1.1910052910052912e-05,
      "loss": 0.0008,
      "step": 1530
    },
    {
      "epoch": 1.6296296296296298,
      "grad_norm": 0.1963416039943695,
      "learning_rate": 1.1857142857142858e-05,
      "loss": 0.0008,
      "step": 1540
    },
    {
      "epoch": 1.6402116402116402,
      "grad_norm": 0.03911126032471657,
      "learning_rate": 1.1804232804232805e-05,
      "loss": 0.0015,
      "step": 1550
    },
    {
      "epoch": 1.6507936507936507,
      "grad_norm": 0.12514500319957733,
      "learning_rate": 1.1751322751322751e-05,
      "loss": 0.0002,
      "step": 1560
    },
    {
      "epoch": 1.6613756613756614,
      "grad_norm": 0.005236633587628603,
      "learning_rate": 1.16984126984127e-05,
      "loss": 0.0037,
      "step": 1570
    },
    {
      "epoch": 1.671957671957672,
      "grad_norm": 0.004985412582755089,
      "learning_rate": 1.1645502645502646e-05,
      "loss": 0.0025,
      "step": 1580
    },
    {
      "epoch": 1.6825396825396826,
      "grad_norm": 0.008958135731518269,
      "learning_rate": 1.1592592592592593e-05,
      "loss": 0.0001,
      "step": 1590
    },
    {
      "epoch": 1.693121693121693,
      "grad_norm": 0.050911322236061096,
      "learning_rate": 1.153968253968254e-05,
      "loss": 0.0018,
      "step": 1600
    },
    {
      "epoch": 1.7037037037037037,
      "grad_norm": 0.8171196579933167,
      "learning_rate": 1.148677248677249e-05,
      "loss": 0.0006,
      "step": 1610
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.00528077082708478,
      "learning_rate": 1.1433862433862436e-05,
      "loss": 0.0001,
      "step": 1620
    },
    {
      "epoch": 1.7248677248677249,
      "grad_norm": 1.8344557285308838,
      "learning_rate": 1.1380952380952382e-05,
      "loss": 0.0012,
      "step": 1630
    },
    {
      "epoch": 1.7354497354497354,
      "grad_norm": 0.1585739254951477,
      "learning_rate": 1.1328042328042327e-05,
      "loss": 0.0002,
      "step": 1640
    },
    {
      "epoch": 1.746031746031746,
      "grad_norm": 12.171996116638184,
      "learning_rate": 1.1275132275132277e-05,
      "loss": 0.0022,
      "step": 1650
    },
    {
      "epoch": 1.7566137566137567,
      "grad_norm": 2.625952959060669,
      "learning_rate": 1.1222222222222224e-05,
      "loss": 0.0063,
      "step": 1660
    },
    {
      "epoch": 1.7671957671957672,
      "grad_norm": 0.4654531180858612,
      "learning_rate": 1.116931216931217e-05,
      "loss": 0.0025,
      "step": 1670
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 3.298426628112793,
      "learning_rate": 1.1116402116402117e-05,
      "loss": 0.0042,
      "step": 1680
    },
    {
      "epoch": 1.7883597883597884,
      "grad_norm": 0.06672941148281097,
      "learning_rate": 1.1063492063492065e-05,
      "loss": 0.0002,
      "step": 1690
    },
    {
      "epoch": 1.798941798941799,
      "grad_norm": 0.9771575927734375,
      "learning_rate": 1.1010582010582011e-05,
      "loss": 0.0019,
      "step": 1700
    },
    {
      "epoch": 1.8095238095238095,
      "grad_norm": 0.1068960428237915,
      "learning_rate": 1.0957671957671958e-05,
      "loss": 0.0039,
      "step": 1710
    },
    {
      "epoch": 1.82010582010582,
      "grad_norm": 0.0055111791007220745,
      "learning_rate": 1.0904761904761905e-05,
      "loss": 0.0014,
      "step": 1720
    },
    {
      "epoch": 1.8306878306878307,
      "grad_norm": 0.34078916907310486,
      "learning_rate": 1.0851851851851853e-05,
      "loss": 0.0007,
      "step": 1730
    },
    {
      "epoch": 1.8412698412698414,
      "grad_norm": 0.02196904458105564,
      "learning_rate": 1.07989417989418e-05,
      "loss": 0.0007,
      "step": 1740
    },
    {
      "epoch": 1.8518518518518519,
      "grad_norm": 0.004520466551184654,
      "learning_rate": 1.0746031746031746e-05,
      "loss": 0.0007,
      "step": 1750
    },
    {
      "epoch": 1.8624338624338623,
      "grad_norm": 0.13541559875011444,
      "learning_rate": 1.0693121693121692e-05,
      "loss": 0.0023,
      "step": 1760
    },
    {
      "epoch": 1.873015873015873,
      "grad_norm": 0.6529462337493896,
      "learning_rate": 1.0640211640211642e-05,
      "loss": 0.0012,
      "step": 1770
    },
    {
      "epoch": 1.8835978835978837,
      "grad_norm": 0.04629633575677872,
      "learning_rate": 1.0587301587301589e-05,
      "loss": 0.0482,
      "step": 1780
    },
    {
      "epoch": 1.8941798941798942,
      "grad_norm": 0.2736707925796509,
      "learning_rate": 1.0534391534391535e-05,
      "loss": 0.0045,
      "step": 1790
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 0.010693887248635292,
      "learning_rate": 1.0481481481481482e-05,
      "loss": 0.0118,
      "step": 1800
    },
    {
      "epoch": 1.9153439153439153,
      "grad_norm": 0.31277382373809814,
      "learning_rate": 1.042857142857143e-05,
      "loss": 0.0004,
      "step": 1810
    },
    {
      "epoch": 1.925925925925926,
      "grad_norm": 0.00564979063346982,
      "learning_rate": 1.0375661375661377e-05,
      "loss": 0.0038,
      "step": 1820
    },
    {
      "epoch": 1.9365079365079365,
      "grad_norm": 0.01478109136223793,
      "learning_rate": 1.0322751322751323e-05,
      "loss": 0.0002,
      "step": 1830
    },
    {
      "epoch": 1.947089947089947,
      "grad_norm": 0.1157880499958992,
      "learning_rate": 1.026984126984127e-05,
      "loss": 0.0007,
      "step": 1840
    },
    {
      "epoch": 1.9576719576719577,
      "grad_norm": 0.011665510945022106,
      "learning_rate": 1.0216931216931218e-05,
      "loss": 0.0003,
      "step": 1850
    },
    {
      "epoch": 1.9682539682539684,
      "grad_norm": 0.005074594635516405,
      "learning_rate": 1.0164021164021165e-05,
      "loss": 0.0002,
      "step": 1860
    },
    {
      "epoch": 1.9788359788359788,
      "grad_norm": 0.004943141248077154,
      "learning_rate": 1.0111111111111111e-05,
      "loss": 0.0003,
      "step": 1870
    },
    {
      "epoch": 1.9894179894179893,
      "grad_norm": 0.004243962932378054,
      "learning_rate": 1.0058201058201058e-05,
      "loss": 0.0027,
      "step": 1880
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.2805013060569763,
      "learning_rate": 1.0005291005291008e-05,
      "loss": 0.0015,
      "step": 1890
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.016391731798648834,
      "eval_runtime": 459.5859,
      "eval_samples_per_second": 0.228,
      "eval_steps_per_second": 0.115,
      "step": 1890
    }
  ],
  "logging_steps": 10,
  "max_steps": 3780,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 1023956924497920.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}