{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.497545738509594,
  "eval_steps": 70,
  "global_step": 1540,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0178491744756805,
      "grad_norm": 1.8217403888702393,
      "learning_rate": 2.9761904761904763e-06,
      "loss": 2.7425,
      "step": 5
    },
    {
      "epoch": 0.035698348951361,
      "grad_norm": 2.104698419570923,
      "learning_rate": 5.9523809523809525e-06,
      "loss": 2.861,
      "step": 10
    },
    {
      "epoch": 0.0535475234270415,
      "grad_norm": 2.7389333248138428,
      "learning_rate": 8.92857142857143e-06,
      "loss": 2.8281,
      "step": 15
    },
    {
      "epoch": 0.071396697902722,
      "grad_norm": 3.9298207759857178,
      "learning_rate": 1.1904761904761905e-05,
      "loss": 3.1888,
      "step": 20
    },
    {
      "epoch": 0.0892458723784025,
      "grad_norm": 2.648014783859253,
      "learning_rate": 1.4880952380952381e-05,
      "loss": 2.6461,
      "step": 25
    },
    {
      "epoch": 0.107095046854083,
      "grad_norm": 1.587472915649414,
      "learning_rate": 1.785714285714286e-05,
      "loss": 2.3212,
      "step": 30
    },
    {
      "epoch": 0.1249442213297635,
      "grad_norm": 0.8390935063362122,
      "learning_rate": 2.0833333333333336e-05,
      "loss": 1.8036,
      "step": 35
    },
    {
      "epoch": 0.142793395805444,
      "grad_norm": 0.46670979261398315,
      "learning_rate": 2.380952380952381e-05,
      "loss": 1.5552,
      "step": 40
    },
    {
      "epoch": 0.1606425702811245,
      "grad_norm": 0.45171597599983215,
      "learning_rate": 2.6785714285714288e-05,
      "loss": 1.6626,
      "step": 45
    },
    {
      "epoch": 0.178491744756805,
      "grad_norm": 0.5605499744415283,
      "learning_rate": 2.9761904761904762e-05,
      "loss": 1.4897,
      "step": 50
    },
    {
      "epoch": 0.1963409192324855,
      "grad_norm": 0.5553259253501892,
      "learning_rate": 3.273809523809524e-05,
      "loss": 1.5373,
      "step": 55
    },
    {
      "epoch": 0.214190093708166,
      "grad_norm": 0.6260251402854919,
      "learning_rate": 3.571428571428572e-05,
      "loss": 1.4779,
      "step": 60
    },
    {
      "epoch": 0.2320392681838465,
      "grad_norm": 0.6063796877861023,
      "learning_rate": 3.8690476190476195e-05,
      "loss": 1.483,
      "step": 65
    },
    {
      "epoch": 0.249888442659527,
      "grad_norm": 0.5549850463867188,
      "learning_rate": 4.166666666666667e-05,
      "loss": 1.5022,
      "step": 70
    },
    {
      "epoch": 0.249888442659527,
      "eval_loss": 1.451762318611145,
      "eval_runtime": 17.7549,
      "eval_samples_per_second": 2.591,
      "eval_steps_per_second": 2.591,
      "step": 70
    },
    {
      "epoch": 0.2677376171352075,
      "grad_norm": 0.482930988073349,
      "learning_rate": 4.464285714285715e-05,
      "loss": 1.4256,
      "step": 75
    },
    {
      "epoch": 0.285586791610888,
      "grad_norm": 0.4240593910217285,
      "learning_rate": 4.761904761904762e-05,
      "loss": 1.3655,
      "step": 80
    },
    {
      "epoch": 0.3034359660865685,
      "grad_norm": 0.4872314929962158,
      "learning_rate": 5.05952380952381e-05,
      "loss": 1.4478,
      "step": 85
    },
    {
      "epoch": 0.321285140562249,
      "grad_norm": 0.42132768034935,
      "learning_rate": 5.3571428571428575e-05,
      "loss": 1.3305,
      "step": 90
    },
    {
      "epoch": 0.3391343150379295,
      "grad_norm": 0.6932046413421631,
      "learning_rate": 5.6547619047619046e-05,
      "loss": 1.4279,
      "step": 95
    },
    {
      "epoch": 0.35698348951361,
      "grad_norm": 0.6714524626731873,
      "learning_rate": 5.9523809523809524e-05,
      "loss": 1.4967,
      "step": 100
    },
    {
      "epoch": 0.3748326639892905,
      "grad_norm": 0.5682816505432129,
      "learning_rate": 6.25e-05,
      "loss": 1.4739,
      "step": 105
    },
    {
      "epoch": 0.392681838464971,
      "grad_norm": 0.7795937657356262,
      "learning_rate": 6.547619047619048e-05,
      "loss": 1.3751,
      "step": 110
    },
    {
      "epoch": 0.4105310129406515,
      "grad_norm": 0.8056842088699341,
      "learning_rate": 6.845238095238096e-05,
      "loss": 1.3699,
      "step": 115
    },
    {
      "epoch": 0.428380187416332,
      "grad_norm": 0.8373801112174988,
      "learning_rate": 7.142857142857143e-05,
      "loss": 1.4696,
      "step": 120
    },
    {
      "epoch": 0.4462293618920125,
      "grad_norm": 1.0051416158676147,
      "learning_rate": 7.440476190476191e-05,
      "loss": 1.4059,
      "step": 125
    },
    {
      "epoch": 0.464078536367693,
      "grad_norm": 0.5304180383682251,
      "learning_rate": 7.738095238095239e-05,
      "loss": 1.3072,
      "step": 130
    },
    {
      "epoch": 0.4819277108433735,
      "grad_norm": 0.8797634243965149,
      "learning_rate": 8.035714285714287e-05,
      "loss": 1.4132,
      "step": 135
    },
    {
      "epoch": 0.499776885319054,
      "grad_norm": 0.9049625396728516,
      "learning_rate": 8.333333333333334e-05,
      "loss": 1.4121,
      "step": 140
    },
    {
      "epoch": 0.499776885319054,
      "eval_loss": 1.3727394342422485,
      "eval_runtime": 17.745,
      "eval_samples_per_second": 2.592,
      "eval_steps_per_second": 2.592,
      "step": 140
    },
    {
      "epoch": 0.5176260597947345,
      "grad_norm": 0.6793915033340454,
      "learning_rate": 8.630952380952382e-05,
      "loss": 1.3109,
      "step": 145
    },
    {
      "epoch": 0.535475234270415,
      "grad_norm": 0.7171015739440918,
      "learning_rate": 8.92857142857143e-05,
      "loss": 1.3781,
      "step": 150
    },
    {
      "epoch": 0.5533244087460955,
      "grad_norm": 0.6738716959953308,
      "learning_rate": 9.226190476190478e-05,
      "loss": 1.3564,
      "step": 155
    },
    {
      "epoch": 0.571173583221776,
      "grad_norm": 0.699975311756134,
      "learning_rate": 9.523809523809524e-05,
      "loss": 1.2387,
      "step": 160
    },
    {
      "epoch": 0.5890227576974565,
      "grad_norm": 0.7659904956817627,
      "learning_rate": 9.821428571428572e-05,
      "loss": 1.3042,
      "step": 165
    },
    {
      "epoch": 0.606871932173137,
      "grad_norm": 0.9782125353813171,
      "learning_rate": 9.999956828659095e-05,
      "loss": 1.3709,
      "step": 170
    },
    {
      "epoch": 0.6247211066488175,
      "grad_norm": 1.0532957315444946,
      "learning_rate": 9.999471159635539e-05,
      "loss": 1.3844,
      "step": 175
    },
    {
      "epoch": 0.642570281124498,
      "grad_norm": 0.7373877167701721,
      "learning_rate": 9.998445910004082e-05,
      "loss": 1.2852,
      "step": 180
    },
    {
      "epoch": 0.6604194556001785,
      "grad_norm": 1.0207768678665161,
      "learning_rate": 9.996881190417393e-05,
      "loss": 1.4652,
      "step": 185
    },
    {
      "epoch": 0.678268630075859,
      "grad_norm": 0.7943917512893677,
      "learning_rate": 9.994777169751806e-05,
      "loss": 1.3743,
      "step": 190
    },
    {
      "epoch": 0.6961178045515395,
      "grad_norm": 0.7461659908294678,
      "learning_rate": 9.992134075089084e-05,
      "loss": 1.2423,
      "step": 195
    },
    {
      "epoch": 0.71396697902722,
      "grad_norm": 0.9689913988113403,
      "learning_rate": 9.988952191691925e-05,
      "loss": 1.3113,
      "step": 200
    },
    {
      "epoch": 0.7318161535029005,
      "grad_norm": 0.766276478767395,
      "learning_rate": 9.985231862973168e-05,
      "loss": 1.3524,
      "step": 205
    },
    {
      "epoch": 0.749665327978581,
      "grad_norm": 0.6728419661521912,
      "learning_rate": 9.980973490458728e-05,
      "loss": 1.4038,
      "step": 210
    },
    {
      "epoch": 0.749665327978581,
      "eval_loss": 1.3051044940948486,
      "eval_runtime": 17.7559,
      "eval_samples_per_second": 2.591,
      "eval_steps_per_second": 2.591,
      "step": 210
    },
    {
      "epoch": 0.7675145024542614,
      "grad_norm": 1.0456575155258179,
      "learning_rate": 9.976177533744261e-05,
      "loss": 1.3626,
      "step": 215
    },
    {
      "epoch": 0.785363676929942,
      "grad_norm": 0.9017456769943237,
      "learning_rate": 9.97084451044556e-05,
      "loss": 1.3232,
      "step": 220
    },
    {
      "epoch": 0.8032128514056225,
      "grad_norm": 0.9113703966140747,
      "learning_rate": 9.964974996142698e-05,
      "loss": 1.2826,
      "step": 225
    },
    {
      "epoch": 0.821062025881303,
      "grad_norm": 0.7177279591560364,
      "learning_rate": 9.958569624317893e-05,
      "loss": 1.2794,
      "step": 230
    },
    {
      "epoch": 0.8389112003569835,
      "grad_norm": 0.9058728814125061,
      "learning_rate": 9.951629086287151e-05,
      "loss": 1.3853,
      "step": 235
    },
    {
      "epoch": 0.856760374832664,
      "grad_norm": 0.6813459992408752,
      "learning_rate": 9.944154131125642e-05,
      "loss": 1.3533,
      "step": 240
    },
    {
      "epoch": 0.8746095493083444,
      "grad_norm": 0.7113555073738098,
      "learning_rate": 9.936145565586871e-05,
      "loss": 1.3395,
      "step": 245
    },
    {
      "epoch": 0.892458723784025,
      "grad_norm": 1.243597149848938,
      "learning_rate": 9.927604254015585e-05,
      "loss": 1.443,
      "step": 250
    },
    {
      "epoch": 0.9103078982597055,
      "grad_norm": 0.8651953339576721,
      "learning_rate": 9.918531118254507e-05,
      "loss": 1.398,
      "step": 255
    },
    {
      "epoch": 0.928157072735386,
      "grad_norm": 0.8877395987510681,
      "learning_rate": 9.90892713754483e-05,
      "loss": 1.346,
      "step": 260
    },
    {
      "epoch": 0.9460062472110665,
      "grad_norm": 0.8857008814811707,
      "learning_rate": 9.898793348420536e-05,
      "loss": 1.3921,
      "step": 265
    },
    {
      "epoch": 0.963855421686747,
      "grad_norm": 0.8319969177246094,
      "learning_rate": 9.888130844596524e-05,
      "loss": 1.3838,
      "step": 270
    },
    {
      "epoch": 0.9817045961624274,
      "grad_norm": 0.7452044486999512,
      "learning_rate": 9.876940776850569e-05,
      "loss": 1.3529,
      "step": 275
    },
    {
      "epoch": 0.999553770638108,
      "grad_norm": 0.7535015940666199,
      "learning_rate": 9.865224352899119e-05,
      "loss": 1.2739,
      "step": 280
    },
    {
      "epoch": 0.999553770638108,
      "eval_loss": 1.289029836654663,
      "eval_runtime": 17.7491,
      "eval_samples_per_second": 2.592,
      "eval_steps_per_second": 2.592,
      "step": 280
    },
    {
      "epoch": 1.0174029451137885,
      "grad_norm": 0.7779117226600647,
      "learning_rate": 9.852982837266955e-05,
      "loss": 1.2339,
      "step": 285
    },
    {
      "epoch": 1.035252119589469,
      "grad_norm": 0.8113610744476318,
      "learning_rate": 9.840217551150706e-05,
      "loss": 1.0982,
      "step": 290
    },
    {
      "epoch": 1.0531012940651494,
      "grad_norm": 1.004701852798462,
      "learning_rate": 9.826929872276255e-05,
      "loss": 1.2537,
      "step": 295
    },
    {
      "epoch": 1.07095046854083,
      "grad_norm": 1.524734616279602,
      "learning_rate": 9.81312123475006e-05,
      "loss": 1.1664,
      "step": 300
    },
    {
      "epoch": 1.0887996430165106,
      "grad_norm": 1.5680856704711914,
      "learning_rate": 9.798793128904356e-05,
      "loss": 1.08,
      "step": 305
    },
    {
      "epoch": 1.106648817492191,
      "grad_norm": 1.4838035106658936,
      "learning_rate": 9.78394710113631e-05,
      "loss": 1.1029,
      "step": 310
    },
    {
      "epoch": 1.1244979919678715,
      "grad_norm": 1.522316575050354,
      "learning_rate": 9.768584753741134e-05,
      "loss": 1.1524,
      "step": 315
    },
    {
      "epoch": 1.142347166443552,
      "grad_norm": 1.3976528644561768,
      "learning_rate": 9.752707744739145e-05,
      "loss": 1.1328,
      "step": 320
    },
    {
      "epoch": 1.1601963409192324,
      "grad_norm": 1.4764764308929443,
      "learning_rate": 9.736317787696816e-05,
      "loss": 1.1174,
      "step": 325
    },
    {
      "epoch": 1.178045515394913,
      "grad_norm": 1.3623173236846924,
      "learning_rate": 9.719416651541839e-05,
      "loss": 1.0493,
      "step": 330
    },
    {
      "epoch": 1.1958946898705936,
      "grad_norm": 1.3625001907348633,
      "learning_rate": 9.702006160372209e-05,
      "loss": 1.0479,
      "step": 335
    },
    {
      "epoch": 1.213743864346274,
      "grad_norm": 1.7509726285934448,
      "learning_rate": 9.684088193259355e-05,
      "loss": 1.1043,
      "step": 340
    },
    {
      "epoch": 1.2315930388219545,
      "grad_norm": 1.5920188426971436,
      "learning_rate": 9.665664684045333e-05,
      "loss": 1.1096,
      "step": 345
    },
    {
      "epoch": 1.249442213297635,
      "grad_norm": 1.6554943323135376,
      "learning_rate": 9.646737621134112e-05,
      "loss": 1.1436,
      "step": 350
    },
    {
      "epoch": 1.249442213297635,
      "eval_loss": 1.3194608688354492,
      "eval_runtime": 17.7382,
      "eval_samples_per_second": 2.593,
      "eval_steps_per_second": 2.593,
      "step": 350
    },
    {
      "epoch": 1.2672913877733154,
      "grad_norm": 1.881818175315857,
      "learning_rate": 9.627309047276974e-05,
      "loss": 1.0549,
      "step": 355
    },
    {
      "epoch": 1.285140562248996,
      "grad_norm": 1.8770464658737183,
      "learning_rate": 9.607381059352038e-05,
      "loss": 1.1576,
      "step": 360
    },
    {
      "epoch": 1.3029897367246766,
      "grad_norm": 1.6901912689208984,
      "learning_rate": 9.586955808137958e-05,
      "loss": 1.1246,
      "step": 365
    },
    {
      "epoch": 1.320838911200357,
      "grad_norm": 1.7667070627212524,
      "learning_rate": 9.566035498081784e-05,
      "loss": 1.125,
      "step": 370
    },
    {
      "epoch": 1.3386880856760375,
      "grad_norm": 1.6150933504104614,
      "learning_rate": 9.544622387061055e-05,
      "loss": 1.1687,
      "step": 375
    },
    {
      "epoch": 1.356537260151718,
      "grad_norm": 1.5824884176254272,
      "learning_rate": 9.522718786140097e-05,
      "loss": 0.9699,
      "step": 380
    },
    {
      "epoch": 1.3743864346273984,
      "grad_norm": 1.5410280227661133,
      "learning_rate": 9.500327059320606e-05,
      "loss": 1.1379,
      "step": 385
    },
    {
      "epoch": 1.392235609103079,
      "grad_norm": 2.264235496520996,
      "learning_rate": 9.477449623286505e-05,
      "loss": 1.0511,
      "step": 390
    },
    {
      "epoch": 1.4100847835787595,
      "grad_norm": 1.7440612316131592,
      "learning_rate": 9.454088947143116e-05,
      "loss": 1.0003,
      "step": 395
    },
    {
      "epoch": 1.42793395805444,
      "grad_norm": 1.770466923713684,
      "learning_rate": 9.430247552150673e-05,
      "loss": 1.1631,
      "step": 400
    },
    {
      "epoch": 1.4457831325301205,
      "grad_norm": 1.9537169933319092,
      "learning_rate": 9.405928011452211e-05,
      "loss": 1.045,
      "step": 405
    },
    {
      "epoch": 1.463632307005801,
      "grad_norm": 1.452445387840271,
      "learning_rate": 9.381132949795861e-05,
      "loss": 1.0511,
      "step": 410
    },
    {
      "epoch": 1.4814814814814814,
      "grad_norm": 2.176547050476074,
      "learning_rate": 9.35586504325155e-05,
      "loss": 1.1637,
      "step": 415
    },
    {
      "epoch": 1.499330655957162,
      "grad_norm": 2.15567684173584,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.0783,
      "step": 420
    },
    {
      "epoch": 1.499330655957162,
      "eval_loss": 1.3106330633163452,
      "eval_runtime": 17.7447,
      "eval_samples_per_second": 2.592,
      "eval_steps_per_second": 2.592,
      "step": 420
    },
    {
      "epoch": 1.5171798304328425,
      "grad_norm": 1.6800014972686768,
      "learning_rate": 9.303921654649362e-05,
      "loss": 1.0406,
      "step": 425
    },
    {
      "epoch": 1.5350290049085231,
      "grad_norm": 1.926607370376587,
      "learning_rate": 9.277251778713474e-05,
      "loss": 1.1469,
      "step": 430
    },
    {
      "epoch": 1.5528781793842035,
      "grad_norm": 1.7155028581619263,
      "learning_rate": 9.250120269528546e-05,
      "loss": 1.0453,
      "step": 435
    },
    {
      "epoch": 1.5707273538598838,
      "grad_norm": 1.9001247882843018,
      "learning_rate": 9.22253005533154e-05,
      "loss": 1.0611,
      "step": 440
    },
    {
      "epoch": 1.5885765283355644,
      "grad_norm": 2.2804248332977295,
      "learning_rate": 9.194484113866313e-05,
      "loss": 1.082,
      "step": 445
    },
    {
      "epoch": 1.606425702811245,
      "grad_norm": 1.9318439960479736,
      "learning_rate": 9.165985472062246e-05,
      "loss": 1.2404,
      "step": 450
    },
    {
      "epoch": 1.6242748772869255,
      "grad_norm": 1.6018136739730835,
      "learning_rate": 9.137037205707552e-05,
      "loss": 1.0436,
      "step": 455
    },
    {
      "epoch": 1.6421240517626061,
      "grad_norm": 2.1986541748046875,
      "learning_rate": 9.107642439117321e-05,
      "loss": 1.1227,
      "step": 460
    },
    {
      "epoch": 1.6599732262382865,
      "grad_norm": 1.5558295249938965,
      "learning_rate": 9.077804344796302e-05,
      "loss": 1.0858,
      "step": 465
    },
    {
      "epoch": 1.6778224007139668,
      "grad_norm": 1.8423618078231812,
      "learning_rate": 9.04752614309652e-05,
      "loss": 1.0998,
      "step": 470
    },
    {
      "epoch": 1.6956715751896474,
      "grad_norm": 1.9065622091293335,
      "learning_rate": 9.01681110186971e-05,
      "loss": 1.0433,
      "step": 475
    },
    {
      "epoch": 1.713520749665328,
      "grad_norm": 2.0103020668029785,
      "learning_rate": 8.985662536114613e-05,
      "loss": 1.0798,
      "step": 480
    },
    {
      "epoch": 1.7313699241410085,
      "grad_norm": 1.5299313068389893,
      "learning_rate": 8.954083807619208e-05,
      "loss": 1.1012,
      "step": 485
    },
    {
      "epoch": 1.7492190986166891,
      "grad_norm": 1.6331924200057983,
      "learning_rate": 8.922078324597879e-05,
      "loss": 1.1219,
      "step": 490
    },
    {
      "epoch": 1.7492190986166891,
      "eval_loss": 1.3044873476028442,
      "eval_runtime": 17.7401,
      "eval_samples_per_second": 2.593,
      "eval_steps_per_second": 2.593,
      "step": 490
    },
    {
      "epoch": 1.7670682730923695,
      "grad_norm": 1.6050705909729004,
      "learning_rate": 8.889649541323574e-05,
      "loss": 1.16,
      "step": 495
    },
    {
      "epoch": 1.7849174475680498,
      "grad_norm": 1.7604998350143433,
      "learning_rate": 8.856800957755e-05,
      "loss": 1.091,
      "step": 500
    },
    {
      "epoch": 1.8027666220437304,
      "grad_norm": 1.6485258340835571,
      "learning_rate": 8.823536119158864e-05,
      "loss": 1.072,
      "step": 505
    },
    {
      "epoch": 1.820615796519411,
      "grad_norm": 1.8173716068267822,
      "learning_rate": 8.789858615727265e-05,
      "loss": 1.0635,
      "step": 510
    },
    {
      "epoch": 1.8384649709950915,
      "grad_norm": 1.468127965927124,
      "learning_rate": 8.755772082190194e-05,
      "loss": 1.0258,
      "step": 515
    },
    {
      "epoch": 1.8563141454707721,
      "grad_norm": 1.4476536512374878,
      "learning_rate": 8.721280197423258e-05,
      "loss": 1.2011,
      "step": 520
    },
    {
      "epoch": 1.8741633199464525,
      "grad_norm": 2.054915189743042,
      "learning_rate": 8.68638668405062e-05,
      "loss": 1.0539,
      "step": 525
    },
    {
      "epoch": 1.8920124944221328,
      "grad_norm": 1.8471094369888306,
      "learning_rate": 8.651095308043232e-05,
      "loss": 1.0948,
      "step": 530
    },
    {
      "epoch": 1.9098616688978134,
      "grad_norm": 1.7790355682373047,
      "learning_rate": 8.61540987831238e-05,
      "loss": 1.1245,
      "step": 535
    },
    {
      "epoch": 1.927710843373494,
      "grad_norm": 1.6644902229309082,
      "learning_rate": 8.579334246298593e-05,
      "loss": 1.2039,
      "step": 540
    },
    {
      "epoch": 1.9455600178491745,
      "grad_norm": 1.9952303171157837,
      "learning_rate": 8.542872305555978e-05,
      "loss": 1.1077,
      "step": 545
    },
    {
      "epoch": 1.9634091923248551,
      "grad_norm": 2.225977659225464,
      "learning_rate": 8.50602799133199e-05,
      "loss": 1.0603,
      "step": 550
    },
    {
      "epoch": 1.9812583668005355,
      "grad_norm": 1.777342438697815,
      "learning_rate": 8.468805280142709e-05,
      "loss": 1.1376,
      "step": 555
    },
    {
      "epoch": 1.9991075412762158,
      "grad_norm": 2.2195017337799072,
      "learning_rate": 8.43120818934367e-05,
      "loss": 1.0966,
      "step": 560
    },
    {
      "epoch": 1.9991075412762158,
      "eval_loss": 1.3094360828399658,
      "eval_runtime": 17.7539,
      "eval_samples_per_second": 2.591,
      "eval_steps_per_second": 2.591,
      "step": 560
    },
    {
      "epoch": 2.0169567157518964,
      "grad_norm": 2.012312173843384,
      "learning_rate": 8.393240776696274e-05,
      "loss": 0.6867,
      "step": 565
    },
    {
      "epoch": 2.034805890227577,
      "grad_norm": 3.092951774597168,
      "learning_rate": 8.354907139929851e-05,
      "loss": 0.6025,
      "step": 570
    },
    {
      "epoch": 2.0526550647032575,
      "grad_norm": 4.8303399085998535,
      "learning_rate": 8.316211416299397e-05,
      "loss": 0.6497,
      "step": 575
    },
    {
      "epoch": 2.070504239178938,
      "grad_norm": 3.1457698345184326,
      "learning_rate": 8.27715778213905e-05,
      "loss": 0.5803,
      "step": 580
    },
    {
      "epoch": 2.0883534136546187,
      "grad_norm": 2.5240321159362793,
      "learning_rate": 8.237750452411353e-05,
      "loss": 0.494,
      "step": 585
    },
    {
      "epoch": 2.106202588130299,
      "grad_norm": 2.630946636199951,
      "learning_rate": 8.197993680252334e-05,
      "loss": 0.6428,
      "step": 590
    },
    {
      "epoch": 2.1240517626059794,
      "grad_norm": 2.9942588806152344,
      "learning_rate": 8.157891756512488e-05,
      "loss": 0.6612,
      "step": 595
    },
    {
      "epoch": 2.14190093708166,
      "grad_norm": 2.8771650791168213,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.5783,
      "step": 600
    },
    {
      "epoch": 2.1597501115573405,
      "grad_norm": 3.1111013889312744,
      "learning_rate": 8.076669803481965e-05,
      "loss": 0.5799,
      "step": 605
    },
    {
      "epoch": 2.177599286033021,
      "grad_norm": 3.715027093887329,
      "learning_rate": 8.035558540276618e-05,
      "loss": 0.5344,
      "step": 610
    },
    {
      "epoch": 2.1954484605087012,
      "grad_norm": 2.936890125274658,
      "learning_rate": 7.994119656715002e-05,
      "loss": 0.5605,
      "step": 615
    },
    {
      "epoch": 2.213297634984382,
      "grad_norm": 2.79441499710083,
      "learning_rate": 7.952357625193749e-05,
      "loss": 0.5923,
      "step": 620
    },
    {
      "epoch": 2.2311468094600624,
      "grad_norm": 3.444474697113037,
      "learning_rate": 7.91027695298606e-05,
      "loss": 0.6067,
      "step": 625
    },
    {
      "epoch": 2.248995983935743,
      "grad_norm": 3.034071445465088,
      "learning_rate": 7.86788218175523e-05,
      "loss": 0.6134,
      "step": 630
    },
    {
      "epoch": 2.248995983935743,
      "eval_loss": 1.4945974349975586,
      "eval_runtime": 17.7423,
      "eval_samples_per_second": 2.593,
      "eval_steps_per_second": 2.593,
      "step": 630
    },
    {
      "epoch": 2.2668451584114235,
      "grad_norm": 3.0743188858032227,
      "learning_rate": 7.8251778870645e-05,
      "loss": 0.5798,
      "step": 635
    },
    {
      "epoch": 2.284694332887104,
      "grad_norm": 3.250493049621582,
      "learning_rate": 7.782168677883206e-05,
      "loss": 0.5705,
      "step": 640
    },
    {
      "epoch": 2.3025435073627847,
      "grad_norm": 2.4863390922546387,
      "learning_rate": 7.738859196089358e-05,
      "loss": 0.6119,
      "step": 645
    },
    {
      "epoch": 2.320392681838465,
      "grad_norm": 3.1027884483337402,
      "learning_rate": 7.695254115968648e-05,
      "loss": 0.6352,
      "step": 650
    },
    {
      "epoch": 2.3382418563141454,
      "grad_norm": 2.840583562850952,
      "learning_rate": 7.651358143709972e-05,
      "loss": 0.6341,
      "step": 655
    },
    {
      "epoch": 2.356091030789826,
      "grad_norm": 3.057770252227783,
      "learning_rate": 7.60717601689749e-05,
      "loss": 0.6695,
      "step": 660
    },
    {
      "epoch": 2.3739402052655065,
      "grad_norm": 3.563372850418091,
      "learning_rate": 7.562712503999327e-05,
      "loss": 0.5715,
      "step": 665
    },
    {
      "epoch": 2.391789379741187,
      "grad_norm": 3.2286486625671387,
      "learning_rate": 7.517972403852905e-05,
      "loss": 0.7753,
      "step": 670
    },
    {
      "epoch": 2.4096385542168672,
      "grad_norm": 2.9088051319122314,
      "learning_rate": 7.472960545147038e-05,
      "loss": 0.5529,
      "step": 675
    },
    {
      "epoch": 2.427487728692548,
      "grad_norm": 2.9432833194732666,
      "learning_rate": 7.427681785900761e-05,
      "loss": 0.5715,
      "step": 680
    },
    {
      "epoch": 2.4453369031682284,
      "grad_norm": 2.483222723007202,
      "learning_rate": 7.382141012939034e-05,
      "loss": 0.6085,
      "step": 685
    },
    {
      "epoch": 2.463186077643909,
      "grad_norm": 2.9013617038726807,
      "learning_rate": 7.33634314136531e-05,
      "loss": 0.627,
      "step": 690
    },
    {
      "epoch": 2.4810352521195895,
      "grad_norm": 2.746309995651245,
      "learning_rate": 7.290293114031061e-05,
      "loss": 0.6403,
      "step": 695
    },
    {
      "epoch": 2.49888442659527,
      "grad_norm": 2.8350794315338135,
      "learning_rate": 7.243995901002312e-05,
      "loss": 0.6342,
      "step": 700
    },
    {
      "epoch": 2.49888442659527,
      "eval_loss": 1.4858874082565308,
      "eval_runtime": 17.7385,
      "eval_samples_per_second": 2.593,
      "eval_steps_per_second": 2.593,
      "step": 700
    },
    {
      "epoch": 2.5167336010709507,
      "grad_norm": 3.006899833679199,
      "learning_rate": 7.197456499023225e-05,
      "loss": 0.5921,
      "step": 705
    },
    {
      "epoch": 2.534582775546631,
      "grad_norm": 2.9739573001861572,
      "learning_rate": 7.150679930976825e-05,
      "loss": 0.5873,
      "step": 710
    },
    {
      "epoch": 2.5524319500223114,
      "grad_norm": 3.7028846740722656,
      "learning_rate": 7.103671245342887e-05,
      "loss": 0.6661,
      "step": 715
    },
    {
      "epoch": 2.570281124497992,
      "grad_norm": 3.090599775314331,
      "learning_rate": 7.056435515653059e-05,
      "loss": 0.5388,
      "step": 720
    },
    {
      "epoch": 2.5881302989736725,
      "grad_norm": 2.799252986907959,
      "learning_rate": 7.008977839943299e-05,
      "loss": 0.6641,
      "step": 725
    },
    {
      "epoch": 2.605979473449353,
      "grad_norm": 2.8093032836914062,
      "learning_rate": 6.961303340203653e-05,
      "loss": 0.6221,
      "step": 730
    },
    {
      "epoch": 2.6238286479250332,
      "grad_norm": 3.6351985931396484,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.599,
      "step": 735
    },
    {
      "epoch": 2.641677822400714,
      "grad_norm": 2.6190829277038574,
      "learning_rate": 6.86532447304597e-05,
      "loss": 0.6047,
      "step": 740
    },
    {
      "epoch": 2.6595269968763944,
      "grad_norm": 3.227262020111084,
      "learning_rate": 6.817030464390656e-05,
      "loss": 0.614,
      "step": 745
    },
    {
      "epoch": 2.677376171352075,
      "grad_norm": 2.5810439586639404,
      "learning_rate": 6.768540348112907e-05,
      "loss": 0.6367,
      "step": 750
    },
    {
      "epoch": 2.6952253458277555,
      "grad_norm": 3.030888557434082,
      "learning_rate": 6.719859357631535e-05,
      "loss": 0.5681,
      "step": 755
    },
    {
      "epoch": 2.713074520303436,
      "grad_norm": 3.1176657676696777,
      "learning_rate": 6.670992746965938e-05,
      "loss": 0.5723,
      "step": 760
    },
    {
      "epoch": 2.7309236947791167,
      "grad_norm": 3.0151100158691406,
      "learning_rate": 6.621945790169036e-05,
      "loss": 0.6385,
      "step": 765
    },
    {
      "epoch": 2.748772869254797,
      "grad_norm": 3.4799766540527344,
      "learning_rate": 6.572723780758069e-05,
      "loss": 0.6665,
      "step": 770
    },
    {
      "epoch": 2.748772869254797,
      "eval_loss": 1.5236101150512695,
      "eval_runtime": 17.7462,
      "eval_samples_per_second": 2.592,
      "eval_steps_per_second": 2.592,
      "step": 770
    },
    {
      "epoch": 2.7666220437304774,
      "grad_norm": 3.1448163986206055,
      "learning_rate": 6.523332031143272e-05,
      "loss": 0.6083,
      "step": 775
    },
    {
      "epoch": 2.784471218206158,
      "grad_norm": 2.874833106994629,
      "learning_rate": 6.473775872054521e-05,
      "loss": 0.6493,
      "step": 780
    },
    {
      "epoch": 2.8023203926818385,
      "grad_norm": 3.2550127506256104,
      "learning_rate": 6.424060651966007e-05,
      "loss": 0.5722,
      "step": 785
    },
    {
      "epoch": 2.820169567157519,
      "grad_norm": 3.066908121109009,
      "learning_rate": 6.374191736518974e-05,
      "loss": 0.611,
      "step": 790
    },
    {
      "epoch": 2.8380187416331992,
      "grad_norm": 3.05871319770813,
      "learning_rate": 6.324174507942637e-05,
      "loss": 0.6202,
      "step": 795
    },
    {
      "epoch": 2.85586791610888,
      "grad_norm": 3.2599833011627197,
      "learning_rate": 6.274014364473274e-05,
      "loss": 0.5593,
      "step": 800
    },
    {
      "epoch": 2.8737170905845604,
      "grad_norm": 2.897418260574341,
      "learning_rate": 6.22371671977162e-05,
      "loss": 0.7415,
      "step": 805
    },
    {
      "epoch": 2.891566265060241,
      "grad_norm": 3.032317876815796,
      "learning_rate": 6.173287002338577e-05,
      "loss": 0.6544,
      "step": 810
    },
    {
      "epoch": 2.9094154395359215,
      "grad_norm": 2.7111008167266846,
      "learning_rate": 6.122730654929334e-05,
      "loss": 0.6421,
      "step": 815
    },
    {
      "epoch": 2.927264614011602,
      "grad_norm": 2.7735886573791504,
      "learning_rate": 6.072053133965938e-05,
      "loss": 0.6332,
      "step": 820
    },
    {
      "epoch": 2.9451137884872827,
      "grad_norm": 3.4417500495910645,
      "learning_rate": 6.021259908948402e-05,
      "loss": 0.6508,
      "step": 825
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 3.432999849319458,
      "learning_rate": 5.970356461864391e-05,
      "loss": 0.621,
      "step": 830
    },
    {
      "epoch": 2.9808121374386434,
      "grad_norm": 3.470132827758789,
      "learning_rate": 5.919348286597569e-05,
      "loss": 0.6347,
      "step": 835
    },
    {
      "epoch": 2.998661311914324,
      "grad_norm": 3.153116226196289,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.6101,
      "step": 840
    },
    {
      "epoch": 2.998661311914324,
      "eval_loss": 1.5220016241073608,
      "eval_runtime": 17.7399,
      "eval_samples_per_second": 2.593,
      "eval_steps_per_second": 2.593,
      "step": 840
    },
    {
      "epoch": 3.0165104863900045,
      "grad_norm": 2.5395278930664062,
      "learning_rate": 5.8170397829712485e-05,
      "loss": 0.4183,
      "step": 845
    },
    {
      "epoch": 3.034359660865685,
      "grad_norm": 2.833970308303833,
      "learning_rate": 5.765750496516547e-05,
      "loss": 0.1667,
      "step": 850
    },
    {
      "epoch": 3.0522088353413657,
      "grad_norm": 3.447057008743286,
      "learning_rate": 5.714378564496901e-05,
      "loss": 0.255,
      "step": 855
    },
    {
      "epoch": 3.070058009817046,
      "grad_norm": 3.9993224143981934,
      "learning_rate": 5.6629295313583974e-05,
      "loss": 0.2424,
      "step": 860
    },
    {
      "epoch": 3.0879071842927264,
      "grad_norm": 3.626281499862671,
      "learning_rate": 5.611408949868457e-05,
      "loss": 0.2097,
      "step": 865
    },
    {
      "epoch": 3.105756358768407,
      "grad_norm": 2.693284034729004,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.2271,
      "step": 870
    },
    {
      "epoch": 3.1236055332440875,
      "grad_norm": 2.439389705657959,
      "learning_rate": 5.5081753909140096e-05,
      "loss": 0.1982,
      "step": 875
    },
    {
      "epoch": 3.141454707719768,
      "grad_norm": 2.6163575649261475,
      "learning_rate": 5.456473555193242e-05,
      "loss": 0.2192,
      "step": 880
    },
    {
      "epoch": 3.1593038821954487,
      "grad_norm": 2.405829668045044,
      "learning_rate": 5.404722453406017e-05,
      "loss": 0.2097,
      "step": 885
    },
    {
      "epoch": 3.177153056671129,
      "grad_norm": 2.819413423538208,
      "learning_rate": 5.3529276709212816e-05,
      "loss": 0.2213,
      "step": 890
    },
    {
      "epoch": 3.1950022311468094,
      "grad_norm": 3.6370203495025635,
      "learning_rate": 5.30109479782233e-05,
      "loss": 0.2559,
      "step": 895
    },
    {
      "epoch": 3.21285140562249,
      "grad_norm": 3.4090726375579834,
      "learning_rate": 5.249229428303486e-05,
      "loss": 0.1955,
      "step": 900
    },
    {
      "epoch": 3.2307005800981705,
      "grad_norm": 2.8171908855438232,
      "learning_rate": 5.197337160066331e-05,
      "loss": 0.2642,
      "step": 905
    },
    {
      "epoch": 3.248549754573851,
      "grad_norm": 3.926447629928589,
      "learning_rate": 5.145423593715557e-05,
      "loss": 0.2467,
      "step": 910
    },
    {
      "epoch": 3.248549754573851,
      "eval_loss": 1.8390079736709595,
      "eval_runtime": 17.7348,
      "eval_samples_per_second": 2.594,
      "eval_steps_per_second": 2.594,
      "step": 910
    },
    {
      "epoch": 3.266398929049531,
      "grad_norm": 2.7143030166625977,
      "learning_rate": 5.0934943321545115e-05,
      "loss": 0.2239,
      "step": 915
    },
    {
      "epoch": 3.284248103525212,
      "grad_norm": 2.717496871948242,
      "learning_rate": 5.041554979980486e-05,
      "loss": 0.1545,
      "step": 920
    },
    {
      "epoch": 3.3020972780008924,
      "grad_norm": 3.516397714614868,
      "learning_rate": 4.9896111428798254e-05,
      "loss": 0.2819,
      "step": 925
    },
    {
      "epoch": 3.319946452476573,
      "grad_norm": 3.3290677070617676,
      "learning_rate": 4.9376684270229254e-05,
      "loss": 0.3043,
      "step": 930
    },
    {
      "epoch": 3.3377956269522535,
      "grad_norm": 2.914736032485962,
      "learning_rate": 4.8857324384591653e-05,
      "loss": 0.2494,
      "step": 935
    },
    {
      "epoch": 3.355644801427934,
      "grad_norm": 3.37791109085083,
      "learning_rate": 4.8338087825118675e-05,
      "loss": 0.2271,
      "step": 940
    },
    {
      "epoch": 3.3734939759036147,
      "grad_norm": 3.295100688934326,
      "learning_rate": 4.781903063173321e-05,
      "loss": 0.242,
      "step": 945
    },
    {
      "epoch": 3.391343150379295,
      "grad_norm": 2.5792458057403564,
      "learning_rate": 4.730020882499964e-05,
      "loss": 0.2244,
      "step": 950
    },
    {
      "epoch": 3.4091923248549754,
      "grad_norm": 3.0014591217041016,
      "learning_rate": 4.678167840007767e-05,
      "loss": 0.2552,
      "step": 955
    },
    {
      "epoch": 3.427041499330656,
      "grad_norm": 3.207282066345215,
      "learning_rate": 4.626349532067879e-05,
      "loss": 0.2542,
      "step": 960
    },
    {
      "epoch": 3.4448906738063365,
      "grad_norm": 3.85109543800354,
      "learning_rate": 4.574571551302647e-05,
      "loss": 0.3249,
      "step": 965
    },
    {
      "epoch": 3.462739848282017,
      "grad_norm": 3.3335843086242676,
      "learning_rate": 4.522839485981994e-05,
      "loss": 0.2729,
      "step": 970
    },
    {
      "epoch": 3.480589022757697,
      "grad_norm": 2.885708808898926,
      "learning_rate": 4.471158919420312e-05,
      "loss": 0.2595,
      "step": 975
    },
    {
      "epoch": 3.498438197233378,
      "grad_norm": 3.215789556503296,
      "learning_rate": 4.4195354293738484e-05,
      "loss": 0.2284,
      "step": 980
    },
    {
      "epoch": 3.498438197233378,
      "eval_loss": 1.82525634765625,
      "eval_runtime": 17.7537,
      "eval_samples_per_second": 2.591,
      "eval_steps_per_second": 2.591,
      "step": 980
    },
    {
      "epoch": 3.5162873717090584,
      "grad_norm": 3.4772818088531494,
      "learning_rate": 4.367974587438733e-05,
      "loss": 0.1947,
      "step": 985
    },
    {
      "epoch": 3.534136546184739,
      "grad_norm": 2.6401774883270264,
      "learning_rate": 4.316481958449634e-05,
      "loss": 0.2352,
      "step": 990
    },
    {
      "epoch": 3.5519857206604195,
      "grad_norm": 3.997591733932495,
      "learning_rate": 4.2650630998791615e-05,
      "loss": 0.2047,
      "step": 995
    },
    {
      "epoch": 3.5698348951361,
      "grad_norm": 2.5615384578704834,
      "learning_rate": 4.213723561238074e-05,
      "loss": 0.2369,
      "step": 1000
    },
    {
      "epoch": 3.5876840696117807,
      "grad_norm": 2.5114736557006836,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.2416,
      "step": 1005
    },
    {
      "epoch": 3.605533244087461,
      "grad_norm": 4.23993444442749,
      "learning_rate": 4.111304598385018e-05,
      "loss": 0.2353,
      "step": 1010
    },
    {
      "epoch": 3.6233824185631414,
      "grad_norm": 3.239319324493408,
      "learning_rate": 4.060236227999441e-05,
      "loss": 0.2155,
      "step": 1015
    },
    {
      "epoch": 3.641231593038822,
      "grad_norm": 2.030393600463867,
      "learning_rate": 4.0092692840030134e-05,
      "loss": 0.2241,
      "step": 1020
    },
    {
      "epoch": 3.6590807675145025,
      "grad_norm": 3.636963367462158,
      "learning_rate": 3.9584092671324606e-05,
      "loss": 0.2408,
      "step": 1025
    },
    {
      "epoch": 3.676929941990183,
      "grad_norm": 4.295063495635986,
      "learning_rate": 3.907661666584131e-05,
      "loss": 0.2423,
      "step": 1030
    },
    {
      "epoch": 3.694779116465863,
      "grad_norm": 3.268596887588501,
      "learning_rate": 3.857031959421553e-05,
      "loss": 0.2581,
      "step": 1035
    },
    {
      "epoch": 3.7126282909415442,
      "grad_norm": 3.0428457260131836,
      "learning_rate": 3.806525609984312e-05,
      "loss": 0.206,
      "step": 1040
    },
    {
      "epoch": 3.7304774654172244,
      "grad_norm": 3.523777484893799,
      "learning_rate": 3.7561480692983006e-05,
      "loss": 0.1956,
      "step": 1045
    },
    {
      "epoch": 3.748326639892905,
      "grad_norm": 2.972714900970459,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.2839,
      "step": 1050
    },
    {
      "epoch": 3.748326639892905,
      "eval_loss": 1.8687995672225952,
      "eval_runtime": 17.732,
      "eval_samples_per_second": 2.594,
      "eval_steps_per_second": 2.594,
      "step": 1050
    },
    {
      "epoch": 3.7661758143685855,
      "grad_norm": 3.9769251346588135,
      "learning_rate": 3.655801148186655e-05,
      "loss": 0.2433,
      "step": 1055
    },
    {
      "epoch": 3.784024988844266,
      "grad_norm": 3.03606915473938,
      "learning_rate": 3.6058425979570485e-05,
      "loss": 0.2085,
      "step": 1060
    },
    {
      "epoch": 3.8018741633199467,
      "grad_norm": 3.5858893394470215,
      "learning_rate": 3.556034515701852e-05,
      "loss": 0.2277,
      "step": 1065
    },
    {
      "epoch": 3.819723337795627,
      "grad_norm": 2.5949602127075195,
      "learning_rate": 3.506382277084696e-05,
      "loss": 0.2497,
      "step": 1070
    },
    {
      "epoch": 3.8375725122713074,
      "grad_norm": 2.8706088066101074,
      "learning_rate": 3.4568912409493945e-05,
      "loss": 0.2462,
      "step": 1075
    },
    {
      "epoch": 3.855421686746988,
      "grad_norm": 3.238346576690674,
      "learning_rate": 3.4075667487415785e-05,
      "loss": 0.2004,
      "step": 1080
    },
    {
      "epoch": 3.8732708612226685,
      "grad_norm": 3.36478590965271,
      "learning_rate": 3.358414123932195e-05,
      "loss": 0.226,
      "step": 1085
    },
    {
      "epoch": 3.891120035698349,
      "grad_norm": 3.0954155921936035,
      "learning_rate": 3.3094386714429724e-05,
      "loss": 0.2114,
      "step": 1090
    },
    {
      "epoch": 3.908969210174029,
      "grad_norm": 3.016141891479492,
      "learning_rate": 3.2606456770738636e-05,
      "loss": 0.2694,
      "step": 1095
    },
    {
      "epoch": 3.9268183846497102,
      "grad_norm": 2.976658821105957,
      "learning_rate": 3.212040406932569e-05,
      "loss": 0.1828,
      "step": 1100
    },
    {
      "epoch": 3.9446675591253904,
      "grad_norm": 2.8186426162719727,
      "learning_rate": 3.163628106866172e-05,
      "loss": 0.1451,
      "step": 1105
    },
    {
      "epoch": 3.962516733601071,
      "grad_norm": 2.959024429321289,
      "learning_rate": 3.115414001894974e-05,
      "loss": 0.2349,
      "step": 1110
    },
    {
      "epoch": 3.9803659080767515,
      "grad_norm": 2.9852728843688965,
      "learning_rate": 3.067403295648566e-05,
      "loss": 0.2235,
      "step": 1115
    },
    {
      "epoch": 3.998215082552432,
      "grad_norm": 2.79172945022583,
      "learning_rate": 3.019601169804216e-05,
      "loss": 0.2111,
      "step": 1120
    },
    {
      "epoch": 3.998215082552432,
      "eval_loss": 1.891045093536377,
      "eval_runtime": 17.7382,
      "eval_samples_per_second": 2.593,
      "eval_steps_per_second": 2.593,
      "step": 1120
    },
    {
      "epoch": 4.016064257028113,
      "grad_norm": 1.1968103647232056,
      "learning_rate": 2.9720127835276256e-05,
      "loss": 0.1074,
      "step": 1125
    },
    {
      "epoch": 4.033913431503793,
      "grad_norm": 1.4865480661392212,
      "learning_rate": 2.9246432729161055e-05,
      "loss": 0.0628,
      "step": 1130
    },
    {
      "epoch": 4.051762605979474,
      "grad_norm": 2.913541078567505,
      "learning_rate": 2.8774977504442647e-05,
      "loss": 0.0615,
      "step": 1135
    },
    {
      "epoch": 4.069611780455154,
      "grad_norm": 2.1043801307678223,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0658,
      "step": 1140
    },
    {
      "epoch": 4.087460954930834,
      "grad_norm": 1.942076325416565,
      "learning_rate": 2.7838989983964065e-05,
      "loss": 0.0458,
      "step": 1145
    },
    {
      "epoch": 4.105310129406515,
      "grad_norm": 2.3953213691711426,
      "learning_rate": 2.737455870703155e-05,
      "loss": 0.0877,
      "step": 1150
    },
    {
      "epoch": 4.123159303882195,
      "grad_norm": 1.9993913173675537,
      "learning_rate": 2.6912569338248315e-05,
      "loss": 0.0567,
      "step": 1155
    },
    {
      "epoch": 4.141008478357876,
      "grad_norm": 2.4731192588806152,
      "learning_rate": 2.645307173898901e-05,
      "loss": 0.0817,
      "step": 1160
    },
    {
      "epoch": 4.158857652833556,
      "grad_norm": 2.3913474082946777,
      "learning_rate": 2.5996115501697694e-05,
      "loss": 0.0517,
      "step": 1165
    },
    {
      "epoch": 4.176706827309237,
      "grad_norm": 4.154366493225098,
      "learning_rate": 2.5541749944535554e-05,
      "loss": 0.0649,
      "step": 1170
    },
    {
      "epoch": 4.1945560017849175,
      "grad_norm": 1.4376811981201172,
      "learning_rate": 2.5090024106057962e-05,
      "loss": 0.0613,
      "step": 1175
    },
    {
      "epoch": 4.212405176260598,
      "grad_norm": 2.038010835647583,
      "learning_rate": 2.464098673992205e-05,
      "loss": 0.0763,
      "step": 1180
    },
    {
      "epoch": 4.230254350736279,
      "grad_norm": 1.862741470336914,
      "learning_rate": 2.4194686309624663e-05,
      "loss": 0.0733,
      "step": 1185
    },
    {
      "epoch": 4.248103525211959,
      "grad_norm": 2.7354800701141357,
      "learning_rate": 2.3751170983272e-05,
      "loss": 0.0753,
      "step": 1190
    },
    {
      "epoch": 4.248103525211959,
      "eval_loss": 2.2224178314208984,
      "eval_runtime": 17.7489,
      "eval_samples_per_second": 2.592,
      "eval_steps_per_second": 2.592,
      "step": 1190
    },
    {
      "epoch": 4.26595269968764,
      "grad_norm": 1.102008581161499,
      "learning_rate": 2.3310488628380757e-05,
      "loss": 0.0839,
      "step": 1195
    },
    {
      "epoch": 4.28380187416332,
      "grad_norm": 4.02572774887085,
      "learning_rate": 2.2872686806712035e-05,
      "loss": 0.0811,
      "step": 1200
    },
    {
      "epoch": 4.301651048639,
      "grad_norm": 1.9711402654647827,
      "learning_rate": 2.243781276913811e-05,
      "loss": 0.0783,
      "step": 1205
    },
    {
      "epoch": 4.319500223114681,
      "grad_norm": 2.0151891708374023,
      "learning_rate": 2.200591345054267e-05,
      "loss": 0.0488,
      "step": 1210
    },
    {
      "epoch": 4.337349397590361,
      "grad_norm": 4.591026782989502,
      "learning_rate": 2.157703546475539e-05,
      "loss": 0.0704,
      "step": 1215
    },
    {
      "epoch": 4.355198572066042,
      "grad_norm": 1.2874963283538818,
      "learning_rate": 2.115122509952085e-05,
      "loss": 0.0653,
      "step": 1220
    },
    {
      "epoch": 4.373047746541722,
      "grad_norm": 2.7136454582214355,
      "learning_rate": 2.0728528311502976e-05,
      "loss": 0.0471,
      "step": 1225
    },
    {
      "epoch": 4.3908969210174025,
      "grad_norm": 2.6785166263580322,
      "learning_rate": 2.0308990721324927e-05,
      "loss": 0.0757,
      "step": 1230
    },
    {
      "epoch": 4.4087460954930835,
      "grad_norm": 1.6510692834854126,
      "learning_rate": 1.989265760864542e-05,
      "loss": 0.0456,
      "step": 1235
    },
    {
      "epoch": 4.426595269968764,
      "grad_norm": 1.2233620882034302,
      "learning_rate": 1.947957390727185e-05,
      "loss": 0.0555,
      "step": 1240
    },
    {
      "epoch": 4.444444444444445,
      "grad_norm": 2.3564908504486084,
      "learning_rate": 1.906978420031059e-05,
      "loss": 0.0559,
      "step": 1245
    },
    {
      "epoch": 4.462293618920125,
      "grad_norm": 1.9344422817230225,
      "learning_rate": 1.8663332715355396e-05,
      "loss": 0.0395,
      "step": 1250
    },
    {
      "epoch": 4.480142793395806,
      "grad_norm": 1.6214028596878052,
      "learning_rate": 1.8260263319713844e-05,
      "loss": 0.0681,
      "step": 1255
    },
    {
      "epoch": 4.497991967871486,
      "grad_norm": 2.0569422245025635,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.072,
      "step": 1260
    },
    {
      "epoch": 4.497991967871486,
      "eval_loss": 2.309265613555908,
      "eval_runtime": 17.7487,
      "eval_samples_per_second": 2.592,
      "eval_steps_per_second": 2.592,
      "step": 1260
    },
    {
      "epoch": 4.515841142347167,
      "grad_norm": 2.3488802909851074,
      "learning_rate": 1.746444443580433e-05,
      "loss": 0.0614,
      "step": 1265
    },
    {
      "epoch": 4.533690316822847,
      "grad_norm": 2.056544303894043,
      "learning_rate": 1.7071780838308288e-05,
      "loss": 0.0644,
      "step": 1270
    },
    {
      "epoch": 4.551539491298527,
      "grad_norm": 2.576493740081787,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.0678,
      "step": 1275
    },
    {
      "epoch": 4.569388665774208,
      "grad_norm": 1.5977071523666382,
      "learning_rate": 1.629715722373423e-05,
      "loss": 0.0474,
      "step": 1280
    },
    {
      "epoch": 4.587237840249888,
      "grad_norm": 3.0858843326568604,
      "learning_rate": 1.5915280809874932e-05,
      "loss": 0.0813,
      "step": 1285
    },
    {
      "epoch": 4.605087014725569,
      "grad_norm": 2.914644241333008,
      "learning_rate": 1.553708307580265e-05,
      "loss": 0.0483,
      "step": 1290
    },
    {
      "epoch": 4.6229361892012495,
      "grad_norm": 2.8291921615600586,
      "learning_rate": 1.5162604839467265e-05,
      "loss": 0.0644,
      "step": 1295
    },
    {
      "epoch": 4.64078536367693,
      "grad_norm": 2.5296852588653564,
      "learning_rate": 1.4791886517382413e-05,
      "loss": 0.0581,
      "step": 1300
    },
    {
      "epoch": 4.658634538152611,
      "grad_norm": 1.3932641744613647,
      "learning_rate": 1.4424968120263504e-05,
      "loss": 0.0569,
      "step": 1305
    },
    {
      "epoch": 4.676483712628291,
      "grad_norm": 1.6407183408737183,
      "learning_rate": 1.4061889248709343e-05,
      "loss": 0.0645,
      "step": 1310
    },
    {
      "epoch": 4.694332887103972,
      "grad_norm": 2.565559148788452,
      "learning_rate": 1.370268908892825e-05,
      "loss": 0.0588,
      "step": 1315
    },
    {
      "epoch": 4.712182061579652,
      "grad_norm": 2.400225877761841,
      "learning_rate": 1.3347406408508695e-05,
      "loss": 0.078,
      "step": 1320
    },
    {
      "epoch": 4.730031236055332,
      "grad_norm": 3.091597318649292,
      "learning_rate": 1.2996079552235263e-05,
      "loss": 0.0948,
      "step": 1325
    },
    {
      "epoch": 4.747880410531013,
      "grad_norm": 2.0770254135131836,
      "learning_rate": 1.264874643795021e-05,
      "loss": 0.0351,
      "step": 1330
    },
    {
      "epoch": 4.747880410531013,
      "eval_loss": 2.2220773696899414,
      "eval_runtime": 17.7459,
      "eval_samples_per_second": 2.592,
      "eval_steps_per_second": 2.592,
      "step": 1330
    },
    {
      "epoch": 4.765729585006693,
      "grad_norm": 1.403196930885315,
      "learning_rate": 1.230544455246101e-05,
      "loss": 0.031,
      "step": 1335
    },
    {
      "epoch": 4.783578759482374,
      "grad_norm": 2.3339104652404785,
      "learning_rate": 1.1966210947494583e-05,
      "loss": 0.0584,
      "step": 1340
    },
    {
      "epoch": 4.801427933958054,
      "grad_norm": 2.0965840816497803,
      "learning_rate": 1.1631082235698316e-05,
      "loss": 0.0633,
      "step": 1345
    },
    {
      "epoch": 4.8192771084337345,
      "grad_norm": 1.8118559122085571,
      "learning_rate": 1.130009458668863e-05,
      "loss": 0.0485,
      "step": 1350
    },
    {
      "epoch": 4.8371262829094155,
      "grad_norm": 1.4843353033065796,
      "learning_rate": 1.097328372314721e-05,
      "loss": 0.0271,
      "step": 1355
    },
    {
      "epoch": 4.854975457385096,
      "grad_norm": 2.7621233463287354,
      "learning_rate": 1.0650684916965559e-05,
      "loss": 0.0559,
      "step": 1360
    },
    {
      "epoch": 4.872824631860777,
      "grad_norm": 0.8147066831588745,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.0582,
      "step": 1365
    },
    {
      "epoch": 4.890673806336457,
      "grad_norm": 2.686469316482544,
      "learning_rate": 1.0018262287505086e-05,
      "loss": 0.0965,
      "step": 1370
    },
    {
      "epoch": 4.908522980812138,
      "grad_norm": 1.0777071714401245,
      "learning_rate": 9.708506720042932e-06,
      "loss": 0.0565,
      "step": 1375
    },
    {
      "epoch": 4.926372155287818,
      "grad_norm": 3.4182119369506836,
      "learning_rate": 9.403099714207175e-06,
      "loss": 0.0542,
      "step": 1380
    },
    {
      "epoch": 4.944221329763499,
      "grad_norm": 1.8600770235061646,
      "learning_rate": 9.102074231823727e-06,
      "loss": 0.0856,
      "step": 1385
    },
    {
      "epoch": 4.962070504239179,
      "grad_norm": 2.112198829650879,
      "learning_rate": 8.805462761831418e-06,
      "loss": 0.0524,
      "step": 1390
    },
    {
      "epoch": 4.979919678714859,
      "grad_norm": 1.6986050605773926,
      "learning_rate": 8.513297316775625e-06,
      "loss": 0.0641,
      "step": 1395
    },
    {
      "epoch": 4.99776885319054,
      "grad_norm": 1.5771281719207764,
      "learning_rate": 8.225609429353187e-06,
      "loss": 0.0644,
      "step": 1400
    },
    {
      "epoch": 4.99776885319054,
      "eval_loss": 2.2804083824157715,
      "eval_runtime": 17.7438,
      "eval_samples_per_second": 2.592,
      "eval_steps_per_second": 2.592,
      "step": 1400
    },
    {
      "epoch": 5.01561802766622,
      "grad_norm": 0.8998332023620605,
      "learning_rate": 7.942430149009161e-06,
      "loss": 0.0227,
      "step": 1405
    },
    {
      "epoch": 5.033467202141901,
      "grad_norm": 0.6817569136619568,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0175,
      "step": 1410
    },
    {
      "epoch": 5.0513163766175815,
      "grad_norm": 0.35046374797821045,
      "learning_rate": 7.389719171023857e-06,
      "loss": 0.0161,
      "step": 1415
    },
    {
      "epoch": 5.069165551093262,
      "grad_norm": 0.34632906317710876,
      "learning_rate": 7.1202471261170245e-06,
      "loss": 0.0268,
      "step": 1420
    },
    {
      "epoch": 5.087014725568943,
      "grad_norm": 0.5170720219612122,
      "learning_rate": 6.855402987319348e-06,
      "loss": 0.0089,
      "step": 1425
    },
    {
      "epoch": 5.104863900044623,
      "grad_norm": 0.4268277585506439,
      "learning_rate": 6.595215338606397e-06,
      "loss": 0.0178,
      "step": 1430
    },
    {
      "epoch": 5.122713074520304,
      "grad_norm": 0.7124648094177246,
      "learning_rate": 6.339712261390213e-06,
      "loss": 0.0132,
      "step": 1435
    },
    {
      "epoch": 5.140562248995984,
      "grad_norm": 0.5214135050773621,
      "learning_rate": 6.088921331488568e-06,
      "loss": 0.0173,
      "step": 1440
    },
    {
      "epoch": 5.158411423471664,
      "grad_norm": 0.3924752473831177,
      "learning_rate": 5.8428696161488215e-06,
      "loss": 0.0064,
      "step": 1445
    },
    {
      "epoch": 5.176260597947345,
      "grad_norm": 0.33278706669807434,
      "learning_rate": 5.601583671126531e-06,
      "loss": 0.021,
      "step": 1450
    },
    {
      "epoch": 5.194109772423025,
      "grad_norm": 1.2323592901229858,
      "learning_rate": 5.365089537819434e-06,
      "loss": 0.0508,
      "step": 1455
    },
    {
      "epoch": 5.211958946898706,
      "grad_norm": 0.3533659875392914,
      "learning_rate": 5.133412740456806e-06,
      "loss": 0.0196,
      "step": 1460
    },
    {
      "epoch": 5.229808121374386,
      "grad_norm": 0.837640643119812,
      "learning_rate": 4.906578283344759e-06,
      "loss": 0.0109,
      "step": 1465
    },
    {
      "epoch": 5.247657295850067,
      "grad_norm": 0.5542824268341064,
      "learning_rate": 4.684610648167503e-06,
      "loss": 0.0257,
      "step": 1470
    },
    {
      "epoch": 5.247657295850067,
      "eval_loss": 2.559340238571167,
      "eval_runtime": 17.7441,
      "eval_samples_per_second": 2.592,
      "eval_steps_per_second": 2.592,
      "step": 1470
    },
    {
      "epoch": 5.2655064703257475,
      "grad_norm": 1.8598344326019287,
      "learning_rate": 4.467533791345191e-06,
      "loss": 0.0159,
      "step": 1475
    },
    {
      "epoch": 5.283355644801428,
      "grad_norm": 0.721049427986145,
      "learning_rate": 4.255371141448272e-06,
      "loss": 0.0117,
      "step": 1480
    },
    {
      "epoch": 5.301204819277109,
      "grad_norm": 0.5821325778961182,
      "learning_rate": 4.048145596668967e-06,
      "loss": 0.0092,
      "step": 1485
    },
    {
      "epoch": 5.319053993752789,
      "grad_norm": 1.502493977546692,
      "learning_rate": 3.84587952234991e-06,
      "loss": 0.0214,
      "step": 1490
    },
    {
      "epoch": 5.33690316822847,
      "grad_norm": 2.6551506519317627,
      "learning_rate": 3.6485947485702832e-06,
      "loss": 0.0087,
      "step": 1495
    },
    {
      "epoch": 5.35475234270415,
      "grad_norm": 0.7094867825508118,
      "learning_rate": 3.4563125677897932e-06,
      "loss": 0.0193,
      "step": 1500
    },
    {
      "epoch": 5.37260151717983,
      "grad_norm": 0.48095235228538513,
      "learning_rate": 3.269053732550581e-06,
      "loss": 0.0181,
      "step": 1505
    },
    {
      "epoch": 5.390450691655511,
      "grad_norm": 1.0630472898483276,
      "learning_rate": 3.086838453237506e-06,
      "loss": 0.0184,
      "step": 1510
    },
    {
      "epoch": 5.408299866131191,
      "grad_norm": 1.2398452758789062,
      "learning_rate": 2.9096863958968268e-06,
      "loss": 0.0083,
      "step": 1515
    },
    {
      "epoch": 5.426149040606872,
      "grad_norm": 1.2862337827682495,
      "learning_rate": 2.737616680113758e-06,
      "loss": 0.0129,
      "step": 1520
    },
    {
      "epoch": 5.443998215082552,
      "grad_norm": 1.1500790119171143,
      "learning_rate": 2.570647876948895e-06,
      "loss": 0.0176,
      "step": 1525
    },
    {
      "epoch": 5.461847389558233,
      "grad_norm": 1.017544150352478,
      "learning_rate": 2.408798006933882e-06,
      "loss": 0.026,
      "step": 1530
    },
    {
      "epoch": 5.4796965640339135,
      "grad_norm": 0.36417996883392334,
      "learning_rate": 2.252084538126542e-06,
      "loss": 0.0495,
      "step": 1535
    },
    {
      "epoch": 5.497545738509594,
      "grad_norm": 0.6736142039299011,
      "learning_rate": 2.100524384225555e-06,
      "loss": 0.0249,
      "step": 1540
    },
    {
      "epoch": 5.497545738509594,
      "eval_loss": 2.6220109462738037,
      "eval_runtime": 17.7422,
      "eval_samples_per_second": 2.593,
      "eval_steps_per_second": 2.593,
      "step": 1540
    }
  ],
  "logging_steps": 5,
  "max_steps": 1680,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 70,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.6203702398917018e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}