{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 19.688,
  "eval_steps": 500,
  "global_step": 1240,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16,
      "grad_norm": 16.156723022460938,
      "learning_rate": 8.064516129032258e-07,
      "loss": 1.7136,
      "step": 10
    },
    {
      "epoch": 0.32,
      "grad_norm": 8.073517799377441,
      "learning_rate": 2.4193548387096776e-06,
      "loss": 1.2809,
      "step": 20
    },
    {
      "epoch": 0.48,
      "grad_norm": 2.825227737426758,
      "learning_rate": 4.032258064516129e-06,
      "loss": 0.8516,
      "step": 30
    },
    {
      "epoch": 0.64,
      "grad_norm": 1.599808692932129,
      "learning_rate": 5.645161290322582e-06,
      "loss": 0.8144,
      "step": 40
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.7444440126419067,
      "learning_rate": 7.258064516129033e-06,
      "loss": 0.6716,
      "step": 50
    },
    {
      "epoch": 0.96,
      "grad_norm": 1.365881323814392,
      "learning_rate": 8.870967741935484e-06,
      "loss": 0.6604,
      "step": 60
    },
    {
      "epoch": 1.112,
      "grad_norm": 1.2223279476165771,
      "learning_rate": 1.0483870967741936e-05,
      "loss": 0.5284,
      "step": 70
    },
    {
      "epoch": 1.272,
      "grad_norm": 1.4933074712753296,
      "learning_rate": 1.1935483870967743e-05,
      "loss": 0.5844,
      "step": 80
    },
    {
      "epoch": 1.432,
      "grad_norm": 1.5303218364715576,
      "learning_rate": 1.3548387096774194e-05,
      "loss": 0.604,
      "step": 90
    },
    {
      "epoch": 1.592,
      "grad_norm": 1.146931529045105,
      "learning_rate": 1.5161290322580646e-05,
      "loss": 0.6135,
      "step": 100
    },
    {
      "epoch": 1.752,
      "grad_norm": 1.2514358758926392,
      "learning_rate": 1.6774193548387098e-05,
      "loss": 0.5823,
      "step": 110
    },
    {
      "epoch": 1.912,
      "grad_norm": 1.1219581365585327,
      "learning_rate": 1.838709677419355e-05,
      "loss": 0.5869,
      "step": 120
    },
    {
      "epoch": 2.064,
      "grad_norm": 1.2538785934448242,
      "learning_rate": 2e-05,
      "loss": 0.529,
      "step": 130
    },
    {
      "epoch": 2.224,
      "grad_norm": 1.4412481784820557,
      "learning_rate": 1.9996038016334953e-05,
      "loss": 0.4977,
      "step": 140
    },
    {
      "epoch": 2.384,
      "grad_norm": 1.280132532119751,
      "learning_rate": 1.9984155204802715e-05,
      "loss": 0.5153,
      "step": 150
    },
    {
      "epoch": 2.544,
      "grad_norm": 1.388814091682434,
      "learning_rate": 1.996436098130433e-05,
      "loss": 0.5185,
      "step": 160
    },
    {
      "epoch": 2.7039999999999997,
      "grad_norm": 1.2465498447418213,
      "learning_rate": 1.9936671030717832e-05,
      "loss": 0.5093,
      "step": 170
    },
    {
      "epoch": 2.864,
      "grad_norm": 6.404733657836914,
      "learning_rate": 1.9901107294469595e-05,
      "loss": 0.5256,
      "step": 180
    },
    {
      "epoch": 3.016,
      "grad_norm": 2.126950263977051,
      "learning_rate": 1.985769795314804e-05,
      "loss": 0.4664,
      "step": 190
    },
    {
      "epoch": 3.176,
      "grad_norm": 1.7593132257461548,
      "learning_rate": 1.9806477404173414e-05,
      "loss": 0.4251,
      "step": 200
    },
    {
      "epoch": 3.336,
      "grad_norm": 1.0036180019378662,
      "learning_rate": 1.9747486234541382e-05,
      "loss": 0.4481,
      "step": 210
    },
    {
      "epoch": 3.496,
      "grad_norm": 1.5059189796447754,
      "learning_rate": 1.9680771188662044e-05,
      "loss": 0.4185,
      "step": 220
    },
    {
      "epoch": 3.656,
      "grad_norm": 2.5380663871765137,
      "learning_rate": 1.9606385131319795e-05,
      "loss": 0.4336,
      "step": 230
    },
    {
      "epoch": 3.816,
      "grad_norm": 1.0066611766815186,
      "learning_rate": 1.9524387005783453e-05,
      "loss": 0.4488,
      "step": 240
    },
    {
      "epoch": 3.976,
      "grad_norm": 2.824939489364624,
      "learning_rate": 1.9434841787099804e-05,
      "loss": 0.4068,
      "step": 250
    },
    {
      "epoch": 4.128,
      "grad_norm": 1.2720246315002441,
      "learning_rate": 1.9337820430607594e-05,
      "loss": 0.3575,
      "step": 260
    },
    {
      "epoch": 4.288,
      "grad_norm": 3.2268316745758057,
      "learning_rate": 1.9233399815712737e-05,
      "loss": 0.3638,
      "step": 270
    },
    {
      "epoch": 4.448,
      "grad_norm": 1.3898473978042603,
      "learning_rate": 1.9121662684969337e-05,
      "loss": 0.3891,
      "step": 280
    },
    {
      "epoch": 4.608,
      "grad_norm": 2.0828278064727783,
      "learning_rate": 1.9002697578514747e-05,
      "loss": 0.3652,
      "step": 290
    },
    {
      "epoch": 4.768,
      "grad_norm": 1.149625539779663,
      "learning_rate": 1.8876598763910666e-05,
      "loss": 0.4091,
      "step": 300
    },
    {
      "epoch": 4.928,
      "grad_norm": 1.3654099702835083,
      "learning_rate": 1.8743466161445823e-05,
      "loss": 0.3508,
      "step": 310
    },
    {
      "epoch": 5.08,
      "grad_norm": 1.3550388813018799,
      "learning_rate": 1.8603405264959467e-05,
      "loss": 0.3232,
      "step": 320
    },
    {
      "epoch": 5.24,
      "grad_norm": 1.4081593751907349,
      "learning_rate": 1.8456527058248398e-05,
      "loss": 0.2735,
      "step": 330
    },
    {
      "epoch": 5.4,
      "grad_norm": 2.1102137565612793,
      "learning_rate": 1.8302947927123767e-05,
      "loss": 0.3039,
      "step": 340
    },
    {
      "epoch": 5.5600000000000005,
      "grad_norm": 2.0371267795562744,
      "learning_rate": 1.8142789567187327e-05,
      "loss": 0.3298,
      "step": 350
    },
    {
      "epoch": 5.72,
      "grad_norm": 1.2168771028518677,
      "learning_rate": 1.7976178887400263e-05,
      "loss": 0.3153,
      "step": 360
    },
    {
      "epoch": 5.88,
      "grad_norm": 1.5159831047058105,
      "learning_rate": 1.780324790952092e-05,
      "loss": 0.3051,
      "step": 370
    },
    {
      "epoch": 6.032,
      "grad_norm": 1.4497977495193481,
      "learning_rate": 1.7624133663491204e-05,
      "loss": 0.2808,
      "step": 380
    },
    {
      "epoch": 6.192,
      "grad_norm": 1.5660399198532104,
      "learning_rate": 1.7438978078854512e-05,
      "loss": 0.2225,
      "step": 390
    },
    {
      "epoch": 6.352,
      "grad_norm": 2.0142195224761963,
      "learning_rate": 1.72479278722912e-05,
      "loss": 0.2526,
      "step": 400
    },
    {
      "epoch": 6.5120000000000005,
      "grad_norm": 1.3689491748809814,
      "learning_rate": 1.7051134431360795e-05,
      "loss": 0.2372,
      "step": 410
    },
    {
      "epoch": 6.672,
      "grad_norm": 2.383648633956909,
      "learning_rate": 1.6848753694542966e-05,
      "loss": 0.2611,
      "step": 420
    },
    {
      "epoch": 6.832,
      "grad_norm": 2.9119460582733154,
      "learning_rate": 1.6640946027672395e-05,
      "loss": 0.2292,
      "step": 430
    },
    {
      "epoch": 6.992,
      "grad_norm": 1.594862461090088,
      "learning_rate": 1.6427876096865394e-05,
      "loss": 0.2484,
      "step": 440
    },
    {
      "epoch": 7.144,
      "grad_norm": 2.313305616378784,
      "learning_rate": 1.620971273803905e-05,
      "loss": 0.1605,
      "step": 450
    },
    {
      "epoch": 7.304,
      "grad_norm": 1.8747406005859375,
      "learning_rate": 1.598662882312615e-05,
      "loss": 0.1881,
      "step": 460
    },
    {
      "epoch": 7.464,
      "grad_norm": 2.306143045425415,
      "learning_rate": 1.5758801123092066e-05,
      "loss": 0.1805,
      "step": 470
    },
    {
      "epoch": 7.624,
      "grad_norm": 2.0819358825683594,
      "learning_rate": 1.552641016786199e-05,
      "loss": 0.1365,
      "step": 480
    },
    {
      "epoch": 7.784,
      "grad_norm": 1.9174208641052246,
      "learning_rate": 1.5289640103269626e-05,
      "loss": 0.1521,
      "step": 490
    },
    {
      "epoch": 7.944,
      "grad_norm": 1.3912276029586792,
      "learning_rate": 1.5048678545140634e-05,
      "loss": 0.1691,
      "step": 500
    },
    {
      "epoch": 8.096,
      "grad_norm": 1.8673287630081177,
      "learning_rate": 1.4803716430626455e-05,
      "loss": 0.1194,
      "step": 510
    },
    {
      "epoch": 8.256,
      "grad_norm": 4.073314189910889,
      "learning_rate": 1.455494786690634e-05,
      "loss": 0.1136,
      "step": 520
    },
    {
      "epoch": 8.416,
      "grad_norm": 1.3980969190597534,
      "learning_rate": 1.4302569977377462e-05,
      "loss": 0.0987,
      "step": 530
    },
    {
      "epoch": 8.576,
      "grad_norm": 1.0765067338943481,
      "learning_rate": 1.404678274545496e-05,
      "loss": 0.125,
      "step": 540
    },
    {
      "epoch": 8.736,
      "grad_norm": 1.532691240310669,
      "learning_rate": 1.3787788856105762e-05,
      "loss": 0.0986,
      "step": 550
    },
    {
      "epoch": 8.896,
      "grad_norm": 1.394974708557129,
      "learning_rate": 1.3525793535241654e-05,
      "loss": 0.1131,
      "step": 560
    },
    {
      "epoch": 9.048,
      "grad_norm": 1.7207937240600586,
      "learning_rate": 1.3261004387098951e-05,
      "loss": 0.0854,
      "step": 570
    },
    {
      "epoch": 9.208,
      "grad_norm": 1.8617466688156128,
      "learning_rate": 1.2993631229733584e-05,
      "loss": 0.0808,
      "step": 580
    },
    {
      "epoch": 9.368,
      "grad_norm": 1.5372612476348877,
      "learning_rate": 1.2723885928761934e-05,
      "loss": 0.0694,
      "step": 590
    },
    {
      "epoch": 9.528,
      "grad_norm": 0.963295042514801,
      "learning_rate": 1.2451982229479245e-05,
      "loss": 0.0792,
      "step": 600
    },
    {
      "epoch": 9.688,
      "grad_norm": 1.102954387664795,
      "learning_rate": 1.2178135587488515e-05,
      "loss": 0.0704,
      "step": 610
    },
    {
      "epoch": 9.848,
      "grad_norm": 0.988452672958374,
      "learning_rate": 1.1902562997974211e-05,
      "loss": 0.0904,
      "step": 620
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.3999573886394501,
      "learning_rate": 1.1625482823755965e-05,
      "loss": 0.0537,
      "step": 630
    },
    {
      "epoch": 10.16,
      "grad_norm": 1.1528918743133545,
      "learning_rate": 1.1347114622258613e-05,
      "loss": 0.0433,
      "step": 640
    },
    {
      "epoch": 10.32,
      "grad_norm": 0.7834718823432922,
      "learning_rate": 1.106767897153559e-05,
      "loss": 0.0415,
      "step": 650
    },
    {
      "epoch": 10.48,
      "grad_norm": 1.2862722873687744,
      "learning_rate": 1.078739729548362e-05,
      "loss": 0.0537,
      "step": 660
    },
    {
      "epoch": 10.64,
      "grad_norm": 1.1977423429489136,
      "learning_rate": 1.0506491688387128e-05,
      "loss": 0.0561,
      "step": 670
    },
    {
      "epoch": 10.8,
      "grad_norm": 2.4095022678375244,
      "learning_rate": 1.0225184738931461e-05,
      "loss": 0.0434,
      "step": 680
    },
    {
      "epoch": 10.96,
      "grad_norm": 0.9543105959892273,
      "learning_rate": 9.943699353824344e-06,
      "loss": 0.0554,
      "step": 690
    },
    {
      "epoch": 11.112,
      "grad_norm": 0.7812919616699219,
      "learning_rate": 9.66225858116532e-06,
      "loss": 0.0356,
      "step": 700
    },
    {
      "epoch": 11.272,
      "grad_norm": 0.16588281095027924,
      "learning_rate": 9.381085433703183e-06,
      "loss": 0.0304,
      "step": 710
    },
    {
      "epoch": 11.432,
      "grad_norm": 0.9616058468818665,
      "learning_rate": 9.10040271212139e-06,
      "loss": 0.0326,
      "step": 720
    },
    {
      "epoch": 11.592,
      "grad_norm": 0.7438204288482666,
      "learning_rate": 8.820432828491542e-06,
      "loss": 0.0387,
      "step": 730
    },
    {
      "epoch": 11.752,
      "grad_norm": 0.6004329919815063,
      "learning_rate": 8.541397630034757e-06,
      "loss": 0.0344,
      "step": 740
    },
    {
      "epoch": 11.912,
      "grad_norm": 2.2135913372039795,
      "learning_rate": 8.263518223330698e-06,
      "loss": 0.0192,
      "step": 750
    },
    {
      "epoch": 12.064,
      "grad_norm": 0.8558197021484375,
      "learning_rate": 7.987014799113398e-06,
      "loss": 0.0203,
      "step": 760
    },
    {
      "epoch": 12.224,
      "grad_norm": 2.0103511810302734,
      "learning_rate": 7.712106457792883e-06,
      "loss": 0.0152,
      "step": 770
    },
    {
      "epoch": 12.384,
      "grad_norm": 1.6075392961502075,
      "learning_rate": 7.439011035840684e-06,
      "loss": 0.0168,
      "step": 780
    },
    {
      "epoch": 12.544,
      "grad_norm": 2.277149200439453,
      "learning_rate": 7.16794493317696e-06,
      "loss": 0.0174,
      "step": 790
    },
    {
      "epoch": 12.704,
      "grad_norm": 0.9537448287010193,
      "learning_rate": 6.899122941695894e-06,
      "loss": 0.0146,
      "step": 800
    },
    {
      "epoch": 12.864,
      "grad_norm": 0.9526250958442688,
      "learning_rate": 6.632758075065288e-06,
      "loss": 0.0262,
      "step": 810
    },
    {
      "epoch": 13.016,
      "grad_norm": 0.5227965712547302,
      "learning_rate": 6.369061399935255e-06,
      "loss": 0.0205,
      "step": 820
    },
    {
      "epoch": 13.176,
      "grad_norm": 0.3879546821117401,
      "learning_rate": 6.108241868689675e-06,
      "loss": 0.0075,
      "step": 830
    },
    {
      "epoch": 13.336,
      "grad_norm": 0.11712963879108429,
      "learning_rate": 5.8505061538730105e-06,
      "loss": 0.0089,
      "step": 840
    },
    {
      "epoch": 13.496,
      "grad_norm": 0.2489776313304901,
      "learning_rate": 5.5960584844236565e-06,
      "loss": 0.0093,
      "step": 850
    },
    {
      "epoch": 13.656,
      "grad_norm": 0.24504923820495605,
      "learning_rate": 5.345100483843617e-06,
      "loss": 0.0086,
      "step": 860
    },
    {
      "epoch": 13.816,
      "grad_norm": 0.9373164176940918,
      "learning_rate": 5.097831010432666e-06,
      "loss": 0.0056,
      "step": 870
    },
    {
      "epoch": 13.975999999999999,
      "grad_norm": 0.16996854543685913,
      "learning_rate": 4.854445999713715e-06,
      "loss": 0.0044,
      "step": 880
    },
    {
      "epoch": 14.128,
      "grad_norm": 0.40567436814308167,
      "learning_rate": 4.615138309174112e-06,
      "loss": 0.003,
      "step": 890
    },
    {
      "epoch": 14.288,
      "grad_norm": 0.05296005308628082,
      "learning_rate": 4.38009756544603e-06,
      "loss": 0.002,
      "step": 900
    },
    {
      "epoch": 14.448,
      "grad_norm": 0.034155845642089844,
      "learning_rate": 4.149510014046922e-06,
      "loss": 0.0051,
      "step": 910
    },
    {
      "epoch": 14.608,
      "grad_norm": 0.5557677149772644,
      "learning_rate": 3.923558371799194e-06,
      "loss": 0.0035,
      "step": 920
    },
    {
      "epoch": 14.768,
      "grad_norm": 0.2064237892627716,
      "learning_rate": 3.7024216820459757e-06,
      "loss": 0.0016,
      "step": 930
    },
    {
      "epoch": 14.928,
      "grad_norm": 0.2826680541038513,
      "learning_rate": 3.48627517277778e-06,
      "loss": 0.0014,
      "step": 940
    },
    {
      "epoch": 15.08,
      "grad_norm": 0.06162280961871147,
      "learning_rate": 3.275290117782397e-06,
      "loss": 0.0017,
      "step": 950
    },
    {
      "epoch": 15.24,
      "grad_norm": 0.08669278025627136,
      "learning_rate": 3.0696337009281263e-06,
      "loss": 0.0009,
      "step": 960
    },
    {
      "epoch": 15.4,
      "grad_norm": 0.04744670167565346,
      "learning_rate": 2.869468883687798e-06,
      "loss": 0.0017,
      "step": 970
    },
    {
      "epoch": 15.56,
      "grad_norm": 0.04455321654677391,
      "learning_rate": 2.6749542760086613e-06,
      "loss": 0.0012,
      "step": 980
    },
    {
      "epoch": 15.72,
      "grad_norm": 0.03492380306124687,
      "learning_rate": 2.4862440106303664e-06,
      "loss": 0.0009,
      "step": 990
    },
    {
      "epoch": 15.88,
      "grad_norm": 0.04152894765138626,
      "learning_rate": 2.303487620950677e-06,
      "loss": 0.0015,
      "step": 1000
    },
    {
      "epoch": 16.032,
      "grad_norm": 0.058656930923461914,
      "learning_rate": 2.126829922535718e-06,
      "loss": 0.0011,
      "step": 1010
    },
    {
      "epoch": 16.192,
      "grad_norm": 0.023427117615938187,
      "learning_rate": 1.9564108983685758e-06,
      "loss": 0.0008,
      "step": 1020
    },
    {
      "epoch": 16.352,
      "grad_norm": 0.02621988020837307,
      "learning_rate": 1.7923655879272395e-06,
      "loss": 0.0011,
      "step": 1030
    },
    {
      "epoch": 16.512,
      "grad_norm": 0.02891433797776699,
      "learning_rate": 1.634823980179766e-06,
      "loss": 0.001,
      "step": 1040
    },
    {
      "epoch": 16.672,
      "grad_norm": 0.044328656047582626,
      "learning_rate": 1.483910910581452e-06,
      "loss": 0.0012,
      "step": 1050
    },
    {
      "epoch": 16.832,
      "grad_norm": 0.05566035583615303,
      "learning_rate": 1.339745962155613e-06,
      "loss": 0.0008,
      "step": 1060
    },
    {
      "epoch": 16.992,
      "grad_norm": 0.030019577592611313,
      "learning_rate": 1.2024433707364002e-06,
      "loss": 0.0013,
      "step": 1070
    },
    {
      "epoch": 17.144,
      "grad_norm": 0.07299891859292984,
      "learning_rate": 1.0721119344486841e-06,
      "loss": 0.0013,
      "step": 1080
    },
    {
      "epoch": 17.304,
      "grad_norm": 0.0282142274081707,
      "learning_rate": 9.488549274967873e-07,
      "loss": 0.0008,
      "step": 1090
    },
    {
      "epoch": 17.464,
      "grad_norm": 0.028321148827672005,
      "learning_rate": 8.327700183303433e-07,
      "loss": 0.0009,
      "step": 1100
    },
    {
      "epoch": 17.624,
      "grad_norm": 0.03647984564304352,
      "learning_rate": 7.239491922521247e-07,
      "loss": 0.0011,
      "step": 1110
    },
    {
      "epoch": 17.784,
      "grad_norm": 0.029092855751514435,
      "learning_rate": 6.22478678529197e-07,
      "loss": 0.0008,
      "step": 1120
    },
    {
      "epoch": 17.944,
      "grad_norm": 0.028766291216015816,
      "learning_rate": 5.284388820651331e-07,
      "loss": 0.001,
      "step": 1130
    },
    {
      "epoch": 18.096,
      "grad_norm": 0.03702507168054581,
      "learning_rate": 4.41904319687424e-07,
      "loss": 0.0011,
      "step": 1140
    },
    {
      "epoch": 18.256,
      "grad_norm": 0.025985565036535263,
      "learning_rate": 3.629435611005916e-07,
      "loss": 0.0008,
      "step": 1150
    },
    {
      "epoch": 18.416,
      "grad_norm": 0.0245125163346529,
      "learning_rate": 2.916191745517749e-07,
      "loss": 0.001,
      "step": 1160
    },
    {
      "epoch": 18.576,
      "grad_norm": 0.01987411454319954,
      "learning_rate": 2.2798767725185856e-07,
      "loss": 0.0007,
      "step": 1170
    },
    {
      "epoch": 18.736,
      "grad_norm": 0.06840561330318451,
      "learning_rate": 1.7209949059142084e-07,
      "loss": 0.001,
      "step": 1180
    },
    {
      "epoch": 18.896,
      "grad_norm": 0.018267642706632614,
      "learning_rate": 1.2399890018698345e-07,
      "loss": 0.001,
      "step": 1190
    },
    {
      "epoch": 19.048,
      "grad_norm": 0.02801842987537384,
      "learning_rate": 8.372402078924092e-08,
      "loss": 0.0008,
      "step": 1200
    },
    {
      "epoch": 19.208,
      "grad_norm": 0.030942991375923157,
      "learning_rate": 5.1306766081048456e-08,
      "loss": 0.0008,
      "step": 1210
    },
    {
      "epoch": 19.368,
      "grad_norm": 0.030538473278284073,
      "learning_rate": 2.6772823389131787e-08,
      "loss": 0.0009,
      "step": 1220
    },
    {
      "epoch": 19.528,
      "grad_norm": 0.0364975668489933,
      "learning_rate": 1.0141633329525669e-08,
      "loss": 0.0012,
      "step": 1230
    },
    {
      "epoch": 19.688,
      "grad_norm": 0.029744159430265427,
      "learning_rate": 1.4263744029019422e-09,
      "loss": 0.0008,
      "step": 1240
    }
  ],
  "logging_steps": 10,
  "max_steps": 1240,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 10000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.817147240873984e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}