{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9982692973347178,
  "eval_steps": 500,
  "global_step": 1444,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013845621322256837,
      "grad_norm": 84.39317321777344,
      "learning_rate": 0.0,
      "loss": 3.6697,
      "step": 1
    },
    {
      "epoch": 0.006922810661128418,
      "grad_norm": 27.68970489501953,
      "learning_rate": 5.517241379310345e-06,
      "loss": 3.4291,
      "step": 5
    },
    {
      "epoch": 0.013845621322256836,
      "grad_norm": 15.845379829406738,
      "learning_rate": 1.2413793103448277e-05,
      "loss": 2.8038,
      "step": 10
    },
    {
      "epoch": 0.020768431983385256,
      "grad_norm": 7.259765148162842,
      "learning_rate": 1.9310344827586207e-05,
      "loss": 2.6016,
      "step": 15
    },
    {
      "epoch": 0.027691242644513673,
      "grad_norm": 6.850363254547119,
      "learning_rate": 2.620689655172414e-05,
      "loss": 2.4071,
      "step": 20
    },
    {
      "epoch": 0.034614053305642094,
      "grad_norm": 6.779935836791992,
      "learning_rate": 3.310344827586207e-05,
      "loss": 2.1635,
      "step": 25
    },
    {
      "epoch": 0.04153686396677051,
      "grad_norm": 6.876138210296631,
      "learning_rate": 4e-05,
      "loss": 1.8278,
      "step": 30
    },
    {
      "epoch": 0.04845967462789893,
      "grad_norm": 4.00146484375,
      "learning_rate": 4.689655172413793e-05,
      "loss": 1.4709,
      "step": 35
    },
    {
      "epoch": 0.055382485289027346,
      "grad_norm": 3.4508628845214844,
      "learning_rate": 5.379310344827586e-05,
      "loss": 1.3059,
      "step": 40
    },
    {
      "epoch": 0.06230529595015576,
      "grad_norm": 3.6667184829711914,
      "learning_rate": 6.068965517241379e-05,
      "loss": 1.2839,
      "step": 45
    },
    {
      "epoch": 0.06922810661128419,
      "grad_norm": 10.48462200164795,
      "learning_rate": 6.758620689655173e-05,
      "loss": 1.5768,
      "step": 50
    },
    {
      "epoch": 0.0761509172724126,
      "grad_norm": 15.30007553100586,
      "learning_rate": 7.448275862068966e-05,
      "loss": 1.7102,
      "step": 55
    },
    {
      "epoch": 0.08307372793354102,
      "grad_norm": 5.958143711090088,
      "learning_rate": 8.137931034482759e-05,
      "loss": 1.3183,
      "step": 60
    },
    {
      "epoch": 0.08999653859466944,
      "grad_norm": 4.754621982574463,
      "learning_rate": 8.827586206896552e-05,
      "loss": 1.1862,
      "step": 65
    },
    {
      "epoch": 0.09691934925579786,
      "grad_norm": 2.633023500442505,
      "learning_rate": 9.517241379310345e-05,
      "loss": 1.1219,
      "step": 70
    },
    {
      "epoch": 0.10384215991692627,
      "grad_norm": 4.135650157928467,
      "learning_rate": 0.0001020689655172414,
      "loss": 1.2148,
      "step": 75
    },
    {
      "epoch": 0.11076497057805469,
      "grad_norm": 10.969470024108887,
      "learning_rate": 0.00010896551724137931,
      "loss": 1.4367,
      "step": 80
    },
    {
      "epoch": 0.11768778123918311,
      "grad_norm": 7.039395332336426,
      "learning_rate": 0.00011586206896551725,
      "loss": 1.2878,
      "step": 85
    },
    {
      "epoch": 0.12461059190031153,
      "grad_norm": 3.5842673778533936,
      "learning_rate": 0.00012275862068965518,
      "loss": 1.1544,
      "step": 90
    },
    {
      "epoch": 0.13153340256143994,
      "grad_norm": 121.72673797607422,
      "learning_rate": 0.0001296551724137931,
      "loss": 1.2037,
      "step": 95
    },
    {
      "epoch": 0.13845621322256838,
      "grad_norm": 4.476109504699707,
      "learning_rate": 0.00013655172413793104,
      "loss": 2.535,
      "step": 100
    },
    {
      "epoch": 0.14537902388369678,
      "grad_norm": 2.3774170875549316,
      "learning_rate": 0.00014344827586206896,
      "loss": 1.1869,
      "step": 105
    },
    {
      "epoch": 0.1523018345448252,
      "grad_norm": 1.9908137321472168,
      "learning_rate": 0.0001503448275862069,
      "loss": 1.1423,
      "step": 110
    },
    {
      "epoch": 0.1592246452059536,
      "grad_norm": 6.313392162322998,
      "learning_rate": 0.00015724137931034485,
      "loss": 1.1662,
      "step": 115
    },
    {
      "epoch": 0.16614745586708204,
      "grad_norm": 10.703524589538574,
      "learning_rate": 0.00016413793103448276,
      "loss": 1.2213,
      "step": 120
    },
    {
      "epoch": 0.17307026652821045,
      "grad_norm": 9.122613906860352,
      "learning_rate": 0.0001710344827586207,
      "loss": 1.4441,
      "step": 125
    },
    {
      "epoch": 0.17999307718933888,
      "grad_norm": 6.565930366516113,
      "learning_rate": 0.00017793103448275862,
      "loss": 1.492,
      "step": 130
    },
    {
      "epoch": 0.18691588785046728,
      "grad_norm": 2.3752644062042236,
      "learning_rate": 0.00018482758620689654,
      "loss": 1.2087,
      "step": 135
    },
    {
      "epoch": 0.19383869851159571,
      "grad_norm": 2.1952130794525146,
      "learning_rate": 0.0001917241379310345,
      "loss": 1.1881,
      "step": 140
    },
    {
      "epoch": 0.20076150917272412,
      "grad_norm": 2.0500988960266113,
      "learning_rate": 0.00019862068965517243,
      "loss": 1.1711,
      "step": 145
    },
    {
      "epoch": 0.20768431983385255,
      "grad_norm": 1.6049162149429321,
      "learning_rate": 0.0001999953208384105,
      "loss": 1.2058,
      "step": 150
    },
    {
      "epoch": 0.21460713049498095,
      "grad_norm": 1.6136459112167358,
      "learning_rate": 0.0001999763124949378,
      "loss": 1.1883,
      "step": 155
    },
    {
      "epoch": 0.22152994115610938,
      "grad_norm": 1.3578557968139648,
      "learning_rate": 0.0001999426852993044,
      "loss": 1.207,
      "step": 160
    },
    {
      "epoch": 0.2284527518172378,
      "grad_norm": 1.4793142080307007,
      "learning_rate": 0.00019989444416858502,
      "loss": 1.1849,
      "step": 165
    },
    {
      "epoch": 0.23537556247836622,
      "grad_norm": 1.4416930675506592,
      "learning_rate": 0.0001998315961567502,
      "loss": 1.2185,
      "step": 170
    },
    {
      "epoch": 0.24229837313949462,
      "grad_norm": 1.5166434049606323,
      "learning_rate": 0.00019975415045363467,
      "loss": 1.2101,
      "step": 175
    },
    {
      "epoch": 0.24922118380062305,
      "grad_norm": 1.503042459487915,
      "learning_rate": 0.00019966211838359378,
      "loss": 1.1991,
      "step": 180
    },
    {
      "epoch": 0.25614399446175146,
      "grad_norm": 1.205989122390747,
      "learning_rate": 0.00019955551340384743,
      "loss": 1.1793,
      "step": 185
    },
    {
      "epoch": 0.2630668051228799,
      "grad_norm": 1.1499744653701782,
      "learning_rate": 0.00019943435110251248,
      "loss": 1.2245,
      "step": 190
    },
    {
      "epoch": 0.2699896157840083,
      "grad_norm": 2.159759044647217,
      "learning_rate": 0.0001992986491963232,
      "loss": 1.191,
      "step": 195
    },
    {
      "epoch": 0.27691242644513675,
      "grad_norm": 1.09286630153656,
      "learning_rate": 0.00019914842752804103,
      "loss": 1.1794,
      "step": 200
    },
    {
      "epoch": 0.2838352371062651,
      "grad_norm": 1.2333486080169678,
      "learning_rate": 0.00019898370806355263,
      "loss": 1.137,
      "step": 205
    },
    {
      "epoch": 0.29075804776739356,
      "grad_norm": 1.0596246719360352,
      "learning_rate": 0.00019880451488865836,
      "loss": 1.1548,
      "step": 210
    },
    {
      "epoch": 0.297680858428522,
      "grad_norm": 1.1800185441970825,
      "learning_rate": 0.00019861087420555018,
      "loss": 1.1696,
      "step": 215
    },
    {
      "epoch": 0.3046036690896504,
      "grad_norm": 1.1409469842910767,
      "learning_rate": 0.0001984028143289803,
      "loss": 1.1503,
      "step": 220
    },
    {
      "epoch": 0.3115264797507788,
      "grad_norm": 1.123025894165039,
      "learning_rate": 0.00019818036568212106,
      "loss": 1.1484,
      "step": 225
    },
    {
      "epoch": 0.3184492904119072,
      "grad_norm": 0.991566002368927,
      "learning_rate": 0.00019794356079211604,
      "loss": 1.1425,
      "step": 230
    },
    {
      "epoch": 0.32537210107303566,
      "grad_norm": 1.1515730619430542,
      "learning_rate": 0.00019769243428532422,
      "loss": 1.173,
      "step": 235
    },
    {
      "epoch": 0.3322949117341641,
      "grad_norm": 1.082554817199707,
      "learning_rate": 0.00019742702288225652,
      "loss": 1.1439,
      "step": 240
    },
    {
      "epoch": 0.33921772239529246,
      "grad_norm": 0.8853589296340942,
      "learning_rate": 0.00019714736539220648,
      "loss": 1.1303,
      "step": 245
    },
    {
      "epoch": 0.3461405330564209,
      "grad_norm": 1.0212119817733765,
      "learning_rate": 0.00019685350270757555,
      "loss": 1.1484,
      "step": 250
    },
    {
      "epoch": 0.3530633437175493,
      "grad_norm": 1.468906044960022,
      "learning_rate": 0.0001965454777978936,
      "loss": 1.1497,
      "step": 255
    },
    {
      "epoch": 0.35998615437867776,
      "grad_norm": 1.0751452445983887,
      "learning_rate": 0.00019622333570353567,
      "loss": 1.1163,
      "step": 260
    },
    {
      "epoch": 0.36690896503980613,
      "grad_norm": 1.0175756216049194,
      "learning_rate": 0.00019588712352913625,
      "loss": 1.0921,
      "step": 265
    },
    {
      "epoch": 0.37383177570093457,
      "grad_norm": 1.0631542205810547,
      "learning_rate": 0.00019553689043670127,
      "loss": 1.1086,
      "step": 270
    },
    {
      "epoch": 0.380754586362063,
      "grad_norm": 0.9073212742805481,
      "learning_rate": 0.00019517268763841962,
      "loss": 1.0797,
      "step": 275
    },
    {
      "epoch": 0.38767739702319143,
      "grad_norm": 0.8963854908943176,
      "learning_rate": 0.00019479456838917473,
      "loss": 1.0805,
      "step": 280
    },
    {
      "epoch": 0.39460020768431986,
      "grad_norm": 0.7784189581871033,
      "learning_rate": 0.0001944025879787574,
      "loss": 1.0716,
      "step": 285
    },
    {
      "epoch": 0.40152301834544823,
      "grad_norm": 0.8633552193641663,
      "learning_rate": 0.0001939968037237812,
      "loss": 1.1037,
      "step": 290
    },
    {
      "epoch": 0.40844582900657667,
      "grad_norm": 0.9031978845596313,
      "learning_rate": 0.00019357727495930146,
      "loss": 1.0748,
      "step": 295
    },
    {
      "epoch": 0.4153686396677051,
      "grad_norm": 0.9887873530387878,
      "learning_rate": 0.00019314406303013904,
      "loss": 1.0752,
      "step": 300
    },
    {
      "epoch": 0.42229145032883353,
      "grad_norm": 0.8844075798988342,
      "learning_rate": 0.00019269723128191048,
      "loss": 1.0604,
      "step": 305
    },
    {
      "epoch": 0.4292142609899619,
      "grad_norm": 0.8241175413131714,
      "learning_rate": 0.00019223684505176517,
      "loss": 1.0675,
      "step": 310
    },
    {
      "epoch": 0.43613707165109034,
      "grad_norm": 0.9136792421340942,
      "learning_rate": 0.00019176297165883165,
      "loss": 1.0792,
      "step": 315
    },
    {
      "epoch": 0.44305988231221877,
      "grad_norm": 0.7512008547782898,
      "learning_rate": 0.00019127568039437406,
      "loss": 1.0509,
      "step": 320
    },
    {
      "epoch": 0.4499826929733472,
      "grad_norm": 0.8454487323760986,
      "learning_rate": 0.00019077504251166006,
      "loss": 1.052,
      "step": 325
    },
    {
      "epoch": 0.4569055036344756,
      "grad_norm": 0.8585478663444519,
      "learning_rate": 0.00019026113121554204,
      "loss": 1.0545,
      "step": 330
    },
    {
      "epoch": 0.463828314295604,
      "grad_norm": 0.7428448796272278,
      "learning_rate": 0.00018973402165175268,
      "loss": 1.0519,
      "step": 335
    },
    {
      "epoch": 0.47075112495673244,
      "grad_norm": 0.7856673002243042,
      "learning_rate": 0.0001891937908959172,
      "loss": 1.0327,
      "step": 340
    },
    {
      "epoch": 0.47767393561786087,
      "grad_norm": 0.7681334614753723,
      "learning_rate": 0.00018864051794228282,
      "loss": 1.0354,
      "step": 345
    },
    {
      "epoch": 0.48459674627898924,
      "grad_norm": 0.7396582961082458,
      "learning_rate": 0.00018807428369216822,
      "loss": 1.0076,
      "step": 350
    },
    {
      "epoch": 0.4915195569401177,
      "grad_norm": 0.712648868560791,
      "learning_rate": 0.00018749517094213375,
      "loss": 1.0033,
      "step": 355
    },
    {
      "epoch": 0.4984423676012461,
      "grad_norm": 0.691340446472168,
      "learning_rate": 0.00018690326437187472,
      "loss": 1.0227,
      "step": 360
    },
    {
      "epoch": 0.5053651782623745,
      "grad_norm": 0.6716147065162659,
      "learning_rate": 0.00018629865053183911,
      "loss": 1.0123,
      "step": 365
    },
    {
      "epoch": 0.5122879889235029,
      "grad_norm": 0.744443953037262,
      "learning_rate": 0.0001856814178305722,
      "loss": 0.9916,
      "step": 370
    },
    {
      "epoch": 0.5192107995846313,
      "grad_norm": 0.8325860500335693,
      "learning_rate": 0.00018505165652178893,
      "loss": 0.9867,
      "step": 375
    },
    {
      "epoch": 0.5261336102457598,
      "grad_norm": 0.7410563230514526,
      "learning_rate": 0.00018440945869117675,
      "loss": 1.0104,
      "step": 380
    },
    {
      "epoch": 0.5330564209068882,
      "grad_norm": 0.8186249136924744,
      "learning_rate": 0.00018375491824293067,
      "loss": 1.0108,
      "step": 385
    },
    {
      "epoch": 0.5399792315680166,
      "grad_norm": 0.8600741624832153,
      "learning_rate": 0.00018308813088602227,
      "loss": 1.0157,
      "step": 390
    },
    {
      "epoch": 0.5469020422291451,
      "grad_norm": 0.755021333694458,
      "learning_rate": 0.00018240919412020466,
      "loss": 0.9888,
      "step": 395
    },
    {
      "epoch": 0.5538248528902735,
      "grad_norm": 0.7720187306404114,
      "learning_rate": 0.00018171820722175604,
      "loss": 1.0113,
      "step": 400
    },
    {
      "epoch": 0.5607476635514018,
      "grad_norm": 0.721126914024353,
      "learning_rate": 0.00018101527122896293,
      "loss": 1.0028,
      "step": 405
    },
    {
      "epoch": 0.5676704742125303,
      "grad_norm": 0.6903390288352966,
      "learning_rate": 0.0001803004889273463,
      "loss": 0.9835,
      "step": 410
    },
    {
      "epoch": 0.5745932848736587,
      "grad_norm": 0.6635528206825256,
      "learning_rate": 0.0001795739648346317,
      "loss": 0.9552,
      "step": 415
    },
    {
      "epoch": 0.5815160955347871,
      "grad_norm": 0.7431291937828064,
      "learning_rate": 0.00017883580518546647,
      "loss": 0.9504,
      "step": 420
    },
    {
      "epoch": 0.5884389061959155,
      "grad_norm": 0.6151255965232849,
      "learning_rate": 0.00017808611791588584,
      "loss": 0.9683,
      "step": 425
    },
    {
      "epoch": 0.595361716857044,
      "grad_norm": 0.7773393988609314,
      "learning_rate": 0.00017732501264752996,
      "loss": 0.9571,
      "step": 430
    },
    {
      "epoch": 0.6022845275181724,
      "grad_norm": 0.6514832377433777,
      "learning_rate": 0.00017655260067161503,
      "loss": 0.9824,
      "step": 435
    },
    {
      "epoch": 0.6092073381793008,
      "grad_norm": 0.6023625731468201,
      "learning_rate": 0.00017576899493265954,
      "loss": 0.9623,
      "step": 440
    },
    {
      "epoch": 0.6161301488404292,
      "grad_norm": 0.7192764282226562,
      "learning_rate": 0.00017497431001196943,
      "loss": 0.9701,
      "step": 445
    },
    {
      "epoch": 0.6230529595015576,
      "grad_norm": 0.7330840229988098,
      "learning_rate": 0.00017416866211088366,
      "loss": 0.9749,
      "step": 450
    },
    {
      "epoch": 0.629975770162686,
      "grad_norm": 0.7194905281066895,
      "learning_rate": 0.00017335216903378267,
      "loss": 0.954,
      "step": 455
    },
    {
      "epoch": 0.6368985808238145,
      "grad_norm": 0.705830991268158,
      "learning_rate": 0.00017252495017086296,
      "loss": 0.945,
      "step": 460
    },
    {
      "epoch": 0.6438213914849429,
      "grad_norm": 0.6004448533058167,
      "learning_rate": 0.0001716871264806791,
      "loss": 0.9585,
      "step": 465
    },
    {
      "epoch": 0.6507442021460713,
      "grad_norm": 0.6676254868507385,
      "learning_rate": 0.0001708388204724572,
      "loss": 0.958,
      "step": 470
    },
    {
      "epoch": 0.6576670128071997,
      "grad_norm": 0.7510408759117126,
      "learning_rate": 0.00016998015618818087,
      "loss": 0.9774,
      "step": 475
    },
    {
      "epoch": 0.6645898234683282,
      "grad_norm": 0.5577638149261475,
      "learning_rate": 0.00016911125918445363,
      "loss": 0.9533,
      "step": 480
    },
    {
      "epoch": 0.6715126341294566,
      "grad_norm": 0.563838541507721,
      "learning_rate": 0.00016823225651413953,
      "loss": 0.9402,
      "step": 485
    },
    {
      "epoch": 0.6784354447905849,
      "grad_norm": 0.6047762036323547,
      "learning_rate": 0.00016734327670778508,
      "loss": 0.9261,
      "step": 490
    },
    {
      "epoch": 0.6853582554517134,
      "grad_norm": 0.668644905090332,
      "learning_rate": 0.00016644444975482523,
      "loss": 0.9215,
      "step": 495
    },
    {
      "epoch": 0.6922810661128418,
      "grad_norm": 0.6146863698959351,
      "learning_rate": 0.0001655359070845757,
      "loss": 0.9303,
      "step": 500
    },
    {
      "epoch": 0.6992038767739702,
      "grad_norm": 0.5876563191413879,
      "learning_rate": 0.0001646177815470151,
      "loss": 0.9332,
      "step": 505
    },
    {
      "epoch": 0.7061266874350987,
      "grad_norm": 0.5674629211425781,
      "learning_rate": 0.00016369020739335924,
      "loss": 0.9115,
      "step": 510
    },
    {
      "epoch": 0.7130494980962271,
      "grad_norm": 0.6317428350448608,
      "learning_rate": 0.00016275332025643028,
      "loss": 0.9282,
      "step": 515
    },
    {
      "epoch": 0.7199723087573555,
      "grad_norm": 0.6540992259979248,
      "learning_rate": 0.00016180725713082434,
      "loss": 0.9356,
      "step": 520
    },
    {
      "epoch": 0.726895119418484,
      "grad_norm": 0.6015810966491699,
      "learning_rate": 0.0001608521563528795,
      "loss": 0.913,
      "step": 525
    },
    {
      "epoch": 0.7338179300796123,
      "grad_norm": 0.6580555438995361,
      "learning_rate": 0.00015988815758044792,
      "loss": 0.9084,
      "step": 530
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 0.7050816416740417,
      "learning_rate": 0.00015891540177247467,
      "loss": 0.9417,
      "step": 535
    },
    {
      "epoch": 0.7476635514018691,
      "grad_norm": 0.6612623333930969,
      "learning_rate": 0.00015793403116838613,
      "loss": 0.9172,
      "step": 540
    },
    {
      "epoch": 0.7545863620629976,
      "grad_norm": 0.6318942308425903,
      "learning_rate": 0.00015694418926729146,
      "loss": 0.9062,
      "step": 545
    },
    {
      "epoch": 0.761509172724126,
      "grad_norm": 0.665798544883728,
      "learning_rate": 0.00015594602080699956,
      "loss": 0.9122,
      "step": 550
    },
    {
      "epoch": 0.7684319833852544,
      "grad_norm": 0.6704463958740234,
      "learning_rate": 0.00015493967174285512,
      "loss": 0.9038,
      "step": 555
    },
    {
      "epoch": 0.7753547940463829,
      "grad_norm": 0.5302876830101013,
      "learning_rate": 0.00015392528922639662,
      "loss": 0.911,
      "step": 560
    },
    {
      "epoch": 0.7822776047075113,
      "grad_norm": 0.560143232345581,
      "learning_rate": 0.00015290302158383923,
      "loss": 0.9049,
      "step": 565
    },
    {
      "epoch": 0.7892004153686397,
      "grad_norm": 0.6260318756103516,
      "learning_rate": 0.0001518730182943862,
      "loss": 0.9006,
      "step": 570
    },
    {
      "epoch": 0.796123226029768,
      "grad_norm": 0.5663220882415771,
      "learning_rate": 0.0001508354299683715,
      "loss": 0.8978,
      "step": 575
    },
    {
      "epoch": 0.8030460366908965,
      "grad_norm": 0.5917235016822815,
      "learning_rate": 0.0001497904083252371,
      "loss": 0.9035,
      "step": 580
    },
    {
      "epoch": 0.8099688473520249,
      "grad_norm": 0.5882086157798767,
      "learning_rate": 0.00014873810617134806,
      "loss": 0.8985,
      "step": 585
    },
    {
      "epoch": 0.8168916580131533,
      "grad_norm": 0.5587283372879028,
      "learning_rate": 0.00014767867737764876,
      "loss": 0.8883,
      "step": 590
    },
    {
      "epoch": 0.8238144686742818,
      "grad_norm": 0.5887295007705688,
      "learning_rate": 0.0001466122768571633,
      "loss": 0.8993,
      "step": 595
    },
    {
      "epoch": 0.8307372793354102,
      "grad_norm": 0.5780234336853027,
      "learning_rate": 0.0001455390605423437,
      "loss": 0.9043,
      "step": 600
    },
    {
      "epoch": 0.8376600899965386,
      "grad_norm": 0.5993393659591675,
      "learning_rate": 0.00014445918536226904,
      "loss": 0.8907,
      "step": 605
    },
    {
      "epoch": 0.8445829006576671,
      "grad_norm": 0.6268749237060547,
      "learning_rate": 0.00014337280921969858,
      "loss": 0.8846,
      "step": 610
    },
    {
      "epoch": 0.8515057113187954,
      "grad_norm": 0.558760404586792,
      "learning_rate": 0.0001422800909679829,
      "loss": 0.8938,
      "step": 615
    },
    {
      "epoch": 0.8584285219799238,
      "grad_norm": 0.581122100353241,
      "learning_rate": 0.00014118119038783588,
      "loss": 0.8895,
      "step": 620
    },
    {
      "epoch": 0.8653513326410522,
      "grad_norm": 0.659567654132843,
      "learning_rate": 0.00014007626816397087,
      "loss": 0.9097,
      "step": 625
    },
    {
      "epoch": 0.8722741433021807,
      "grad_norm": 0.5866315960884094,
      "learning_rate": 0.00013896548586160503,
      "loss": 0.8846,
      "step": 630
    },
    {
      "epoch": 0.8791969539633091,
      "grad_norm": 0.6595350503921509,
      "learning_rate": 0.00013784900590283473,
      "loss": 0.893,
      "step": 635
    },
    {
      "epoch": 0.8861197646244375,
      "grad_norm": 0.6152217984199524,
      "learning_rate": 0.00013672699154288569,
      "loss": 0.8731,
      "step": 640
    },
    {
      "epoch": 0.893042575285566,
      "grad_norm": 0.6661486625671387,
      "learning_rate": 0.00013559960684624112,
      "loss": 0.8985,
      "step": 645
    },
    {
      "epoch": 0.8999653859466944,
      "grad_norm": 0.600180983543396,
      "learning_rate": 0.0001344670166626519,
      "loss": 0.8649,
      "step": 650
    },
    {
      "epoch": 0.9068881966078228,
      "grad_norm": 0.5598291158676147,
      "learning_rate": 0.0001333293866030317,
      "loss": 0.8692,
      "step": 655
    },
    {
      "epoch": 0.9138110072689511,
      "grad_norm": 0.5362780690193176,
      "learning_rate": 0.0001321868830152407,
      "loss": 0.8487,
      "step": 660
    },
    {
      "epoch": 0.9207338179300796,
      "grad_norm": 0.552412211894989,
      "learning_rate": 0.00013103967295976179,
      "loss": 0.8714,
      "step": 665
    },
    {
      "epoch": 0.927656628591208,
      "grad_norm": 0.5372534990310669,
      "learning_rate": 0.0001298879241852724,
      "loss": 0.8671,
      "step": 670
    },
    {
      "epoch": 0.9345794392523364,
      "grad_norm": 0.5404379963874817,
      "learning_rate": 0.0001287318051041159,
      "loss": 0.8745,
      "step": 675
    },
    {
      "epoch": 0.9415022499134649,
      "grad_norm": 0.5374013185501099,
      "learning_rate": 0.00012757148476767553,
      "loss": 0.8613,
      "step": 680
    },
    {
      "epoch": 0.9484250605745933,
      "grad_norm": 0.5705161690711975,
      "learning_rate": 0.0001264071328416555,
      "loss": 0.8632,
      "step": 685
    },
    {
      "epoch": 0.9553478712357217,
      "grad_norm": 0.5051168203353882,
      "learning_rate": 0.00012523891958127168,
      "loss": 0.8672,
      "step": 690
    },
    {
      "epoch": 0.9622706818968502,
      "grad_norm": 0.5407364368438721,
      "learning_rate": 0.0001240670158063565,
      "loss": 0.8514,
      "step": 695
    },
    {
      "epoch": 0.9691934925579785,
      "grad_norm": 0.5593644976615906,
      "learning_rate": 0.00012289159287638105,
      "loss": 0.8637,
      "step": 700
    },
    {
      "epoch": 0.9761163032191069,
      "grad_norm": 0.5774658918380737,
      "learning_rate": 0.00012171282266539845,
      "loss": 0.8623,
      "step": 705
    },
    {
      "epoch": 0.9830391138802353,
      "grad_norm": 0.5526735186576843,
      "learning_rate": 0.00012053087753691172,
      "loss": 0.8443,
      "step": 710
    },
    {
      "epoch": 0.9899619245413638,
      "grad_norm": 0.6029305458068848,
      "learning_rate": 0.00011934593031867038,
      "loss": 0.8601,
      "step": 715
    },
    {
      "epoch": 0.9968847352024922,
      "grad_norm": 0.5075383186340332,
      "learning_rate": 0.00011815815427739911,
      "loss": 0.86,
      "step": 720
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.86182701587677,
      "eval_runtime": 53.9175,
      "eval_samples_per_second": 38.373,
      "eval_steps_per_second": 2.411,
      "step": 723
    },
    {
      "epoch": 1.0027691242644514,
      "grad_norm": 0.5253963470458984,
      "learning_rate": 0.00011696772309346182,
      "loss": 0.7792,
      "step": 725
    },
    {
      "epoch": 1.0096919349255797,
      "grad_norm": 0.574345588684082,
      "learning_rate": 0.0001157748108354659,
      "loss": 0.6699,
      "step": 730
    },
    {
      "epoch": 1.0166147455867083,
      "grad_norm": 0.5087964534759521,
      "learning_rate": 0.00011457959193480925,
      "loss": 0.6738,
      "step": 735
    },
    {
      "epoch": 1.0235375562478366,
      "grad_norm": 0.5173301696777344,
      "learning_rate": 0.00011338224116017423,
      "loss": 0.6741,
      "step": 740
    },
    {
      "epoch": 1.0304603669089651,
      "grad_norm": 0.4978538155555725,
      "learning_rate": 0.00011218293359197267,
      "loss": 0.6769,
      "step": 745
    },
    {
      "epoch": 1.0373831775700935,
      "grad_norm": 0.5095494389533997,
      "learning_rate": 0.00011098184459674484,
      "loss": 0.6408,
      "step": 750
    },
    {
      "epoch": 1.0443059882312218,
      "grad_norm": 0.5378568768501282,
      "learning_rate": 0.00010977914980151691,
      "loss": 0.6788,
      "step": 755
    },
    {
      "epoch": 1.0512287988923503,
      "grad_norm": 0.5674318075180054,
      "learning_rate": 0.00010857502506812029,
      "loss": 0.6513,
      "step": 760
    },
    {
      "epoch": 1.0581516095534786,
      "grad_norm": 0.5232911109924316,
      "learning_rate": 0.00010736964646747629,
      "loss": 0.6596,
      "step": 765
    },
    {
      "epoch": 1.0650744202146072,
      "grad_norm": 0.5317590832710266,
      "learning_rate": 0.00010616319025385089,
      "loss": 0.6743,
      "step": 770
    },
    {
      "epoch": 1.0719972308757355,
      "grad_norm": 0.532939612865448,
      "learning_rate": 0.00010495583283908177,
      "loss": 0.6643,
      "step": 775
    },
    {
      "epoch": 1.078920041536864,
      "grad_norm": 0.49695611000061035,
      "learning_rate": 0.00010374775076678332,
      "loss": 0.641,
      "step": 780
    },
    {
      "epoch": 1.0858428521979924,
      "grad_norm": 0.5251046419143677,
      "learning_rate": 0.00010253912068653146,
      "loss": 0.6666,
      "step": 785
    },
    {
      "epoch": 1.092765662859121,
      "grad_norm": 0.48369261622428894,
      "learning_rate": 0.00010133011932803378,
      "loss": 0.6517,
      "step": 790
    },
    {
      "epoch": 1.0996884735202492,
      "grad_norm": 0.5567379593849182,
      "learning_rate": 0.00010012092347528705,
      "loss": 0.665,
      "step": 795
    },
    {
      "epoch": 1.1066112841813776,
      "grad_norm": 0.5026639699935913,
      "learning_rate": 9.891170994072793e-05,
      "loss": 0.6551,
      "step": 800
    },
    {
      "epoch": 1.113534094842506,
      "grad_norm": 0.5680745840072632,
      "learning_rate": 9.770265553937831e-05,
      "loss": 0.6474,
      "step": 805
    },
    {
      "epoch": 1.1204569055036344,
      "grad_norm": 0.5292742848396301,
      "learning_rate": 9.649393706299127e-05,
      "loss": 0.6361,
      "step": 810
    },
    {
      "epoch": 1.127379716164763,
      "grad_norm": 0.5109537243843079,
      "learning_rate": 9.52857312541998e-05,
      "loss": 0.6513,
      "step": 815
    },
    {
      "epoch": 1.1343025268258913,
      "grad_norm": 0.4781751334667206,
      "learning_rate": 9.407821478067304e-05,
      "loss": 0.6443,
      "step": 820
    },
    {
      "epoch": 1.1412253374870198,
      "grad_norm": 0.5753712058067322,
      "learning_rate": 9.287156420928342e-05,
      "loss": 0.6453,
      "step": 825
    },
    {
      "epoch": 1.1481481481481481,
      "grad_norm": 0.5011494159698486,
      "learning_rate": 9.166595598028832e-05,
      "loss": 0.6607,
      "step": 830
    },
    {
      "epoch": 1.1550709588092767,
      "grad_norm": 0.5434563159942627,
      "learning_rate": 9.046156638153056e-05,
      "loss": 0.6473,
      "step": 835
    },
    {
      "epoch": 1.161993769470405,
      "grad_norm": 0.4749588966369629,
      "learning_rate": 8.925857152266103e-05,
      "loss": 0.6409,
      "step": 840
    },
    {
      "epoch": 1.1689165801315333,
      "grad_norm": 0.5661805868148804,
      "learning_rate": 8.805714730938728e-05,
      "loss": 0.6536,
      "step": 845
    },
    {
      "epoch": 1.1758393907926619,
      "grad_norm": 0.5053838491439819,
      "learning_rate": 8.685746941775219e-05,
      "loss": 0.6448,
      "step": 850
    },
    {
      "epoch": 1.1827622014537902,
      "grad_norm": 0.5024662613868713,
      "learning_rate": 8.565971326844584e-05,
      "loss": 0.6406,
      "step": 855
    },
    {
      "epoch": 1.1896850121149187,
      "grad_norm": 0.5160663723945618,
      "learning_rate": 8.44640540011553e-05,
      "loss": 0.6455,
      "step": 860
    },
    {
      "epoch": 1.196607822776047,
      "grad_norm": 0.47995302081108093,
      "learning_rate": 8.327066644895469e-05,
      "loss": 0.6484,
      "step": 865
    },
    {
      "epoch": 1.2035306334371756,
      "grad_norm": 0.5510280132293701,
      "learning_rate": 8.207972511274095e-05,
      "loss": 0.6368,
      "step": 870
    },
    {
      "epoch": 1.210453444098304,
      "grad_norm": 0.48854583501815796,
      "learning_rate": 8.089140413571747e-05,
      "loss": 0.6386,
      "step": 875
    },
    {
      "epoch": 1.2173762547594325,
      "grad_norm": 0.49065229296684265,
      "learning_rate": 7.970587727793051e-05,
      "loss": 0.632,
      "step": 880
    },
    {
      "epoch": 1.2242990654205608,
      "grad_norm": 0.49308907985687256,
      "learning_rate": 7.852331789086135e-05,
      "loss": 0.6319,
      "step": 885
    },
    {
      "epoch": 1.231221876081689,
      "grad_norm": 0.526637613773346,
      "learning_rate": 7.73438988920784e-05,
      "loss": 0.6423,
      "step": 890
    },
    {
      "epoch": 1.2381446867428176,
      "grad_norm": 0.5177161693572998,
      "learning_rate": 7.616779273995252e-05,
      "loss": 0.6438,
      "step": 895
    },
    {
      "epoch": 1.245067497403946,
      "grad_norm": 0.5067081451416016,
      "learning_rate": 7.499517140843968e-05,
      "loss": 0.6377,
      "step": 900
    },
    {
      "epoch": 1.2519903080650745,
      "grad_norm": 0.49588489532470703,
      "learning_rate": 7.382620636193438e-05,
      "loss": 0.6264,
      "step": 905
    },
    {
      "epoch": 1.2589131187262028,
      "grad_norm": 0.48242148756980896,
      "learning_rate": 7.266106853019759e-05,
      "loss": 0.6324,
      "step": 910
    },
    {
      "epoch": 1.2658359293873311,
      "grad_norm": 0.4694021940231323,
      "learning_rate": 7.149992828336274e-05,
      "loss": 0.639,
      "step": 915
    },
    {
      "epoch": 1.2727587400484597,
      "grad_norm": 0.535815954208374,
      "learning_rate": 7.034295540702397e-05,
      "loss": 0.6293,
      "step": 920
    },
    {
      "epoch": 1.2796815507095882,
      "grad_norm": 0.5116434693336487,
      "learning_rate": 6.919031907740922e-05,
      "loss": 0.6527,
      "step": 925
    },
    {
      "epoch": 1.2866043613707165,
      "grad_norm": 0.5183587670326233,
      "learning_rate": 6.804218783664288e-05,
      "loss": 0.6379,
      "step": 930
    },
    {
      "epoch": 1.2935271720318449,
      "grad_norm": 0.480989009141922,
      "learning_rate": 6.689872956810102e-05,
      "loss": 0.6278,
      "step": 935
    },
    {
      "epoch": 1.3004499826929734,
      "grad_norm": 0.4917803108692169,
      "learning_rate": 6.5760111471863e-05,
      "loss": 0.6229,
      "step": 940
    },
    {
      "epoch": 1.3073727933541017,
      "grad_norm": 0.5207715630531311,
      "learning_rate": 6.46265000402628e-05,
      "loss": 0.6345,
      "step": 945
    },
    {
      "epoch": 1.3142956040152303,
      "grad_norm": 0.49368080496788025,
      "learning_rate": 6.349806103354417e-05,
      "loss": 0.6203,
      "step": 950
    },
    {
      "epoch": 1.3212184146763586,
      "grad_norm": 0.5188437104225159,
      "learning_rate": 6.23749594556226e-05,
      "loss": 0.6218,
      "step": 955
    },
    {
      "epoch": 1.328141225337487,
      "grad_norm": 0.48687297105789185,
      "learning_rate": 6.125735952995775e-05,
      "loss": 0.6255,
      "step": 960
    },
    {
      "epoch": 1.3350640359986155,
      "grad_norm": 0.49582260847091675,
      "learning_rate": 6.0145424675540394e-05,
      "loss": 0.6199,
      "step": 965
    },
    {
      "epoch": 1.341986846659744,
      "grad_norm": 0.46165865659713745,
      "learning_rate": 5.9039317482996735e-05,
      "loss": 0.6348,
      "step": 970
    },
    {
      "epoch": 1.3489096573208723,
      "grad_norm": 0.4516454041004181,
      "learning_rate": 5.793919969081374e-05,
      "loss": 0.6133,
      "step": 975
    },
    {
      "epoch": 1.3558324679820006,
      "grad_norm": 0.500738799571991,
      "learning_rate": 5.68452321616894e-05,
      "loss": 0.6079,
      "step": 980
    },
    {
      "epoch": 1.3627552786431292,
      "grad_norm": 0.49258264899253845,
      "learning_rate": 5.5757574859010886e-05,
      "loss": 0.6334,
      "step": 985
    },
    {
      "epoch": 1.3696780893042575,
      "grad_norm": 0.5447993874549866,
      "learning_rate": 5.467638682346403e-05,
      "loss": 0.6058,
      "step": 990
    },
    {
      "epoch": 1.376600899965386,
      "grad_norm": 0.5091496109962463,
      "learning_rate": 5.3601826149777966e-05,
      "loss": 0.6395,
      "step": 995
    },
    {
      "epoch": 1.3835237106265144,
      "grad_norm": 0.46665337681770325,
      "learning_rate": 5.25340499636082e-05,
      "loss": 0.6213,
      "step": 1000
    },
    {
      "epoch": 1.3904465212876427,
      "grad_norm": 0.5017385482788086,
      "learning_rate": 5.147321439856091e-05,
      "loss": 0.6197,
      "step": 1005
    },
    {
      "epoch": 1.3973693319487712,
      "grad_norm": 0.4815027713775635,
      "learning_rate": 5.041947457336274e-05,
      "loss": 0.6235,
      "step": 1010
    },
    {
      "epoch": 1.4042921426098995,
      "grad_norm": 0.4791295528411865,
      "learning_rate": 4.937298456917889e-05,
      "loss": 0.6044,
      "step": 1015
    },
    {
      "epoch": 1.411214953271028,
      "grad_norm": 0.508419930934906,
      "learning_rate": 4.8333897407082896e-05,
      "loss": 0.6116,
      "step": 1020
    },
    {
      "epoch": 1.4181377639321564,
      "grad_norm": 0.4575812816619873,
      "learning_rate": 4.7302365025681206e-05,
      "loss": 0.6155,
      "step": 1025
    },
    {
      "epoch": 1.425060574593285,
      "grad_norm": 0.4921416640281677,
      "learning_rate": 4.627853825889642e-05,
      "loss": 0.5997,
      "step": 1030
    },
    {
      "epoch": 1.4319833852544133,
      "grad_norm": 0.4817526638507843,
      "learning_rate": 4.526256681391192e-05,
      "loss": 0.6162,
      "step": 1035
    },
    {
      "epoch": 1.4389061959155418,
      "grad_norm": 0.50459885597229,
      "learning_rate": 4.4254599249281016e-05,
      "loss": 0.5963,
      "step": 1040
    },
    {
      "epoch": 1.4458290065766701,
      "grad_norm": 0.48671668767929077,
      "learning_rate": 4.3254782953204375e-05,
      "loss": 0.6025,
      "step": 1045
    },
    {
      "epoch": 1.4527518172377984,
      "grad_norm": 0.4629117250442505,
      "learning_rate": 4.2263264121978505e-05,
      "loss": 0.6075,
      "step": 1050
    },
    {
      "epoch": 1.459674627898927,
      "grad_norm": 0.519282341003418,
      "learning_rate": 4.12801877386183e-05,
      "loss": 0.6009,
      "step": 1055
    },
    {
      "epoch": 1.4665974385600553,
      "grad_norm": 0.46476197242736816,
      "learning_rate": 4.030569755165736e-05,
      "loss": 0.6053,
      "step": 1060
    },
    {
      "epoch": 1.4735202492211839,
      "grad_norm": 0.4634140133857727,
      "learning_rate": 3.9339936054128466e-05,
      "loss": 0.6084,
      "step": 1065
    },
    {
      "epoch": 1.4804430598823122,
      "grad_norm": 0.47767311334609985,
      "learning_rate": 3.8383044462727826e-05,
      "loss": 0.5868,
      "step": 1070
    },
    {
      "epoch": 1.4873658705434407,
      "grad_norm": 0.49947062134742737,
      "learning_rate": 3.7435162697166107e-05,
      "loss": 0.615,
      "step": 1075
    },
    {
      "epoch": 1.494288681204569,
      "grad_norm": 0.4960927367210388,
      "learning_rate": 3.649642935970859e-05,
      "loss": 0.6128,
      "step": 1080
    },
    {
      "epoch": 1.5012114918656976,
      "grad_norm": 0.4698868691921234,
      "learning_rate": 3.556698171490871e-05,
      "loss": 0.5962,
      "step": 1085
    },
    {
      "epoch": 1.508134302526826,
      "grad_norm": 0.4915900230407715,
      "learning_rate": 3.464695566953644e-05,
      "loss": 0.5908,
      "step": 1090
    },
    {
      "epoch": 1.5150571131879542,
      "grad_norm": 0.5037806034088135,
      "learning_rate": 3.373648575270576e-05,
      "loss": 0.5964,
      "step": 1095
    },
    {
      "epoch": 1.5219799238490828,
      "grad_norm": 0.46835029125213623,
      "learning_rate": 3.283570509620344e-05,
      "loss": 0.5972,
      "step": 1100
    },
    {
      "epoch": 1.5289027345102113,
      "grad_norm": 0.4610807001590729,
      "learning_rate": 3.1944745415021915e-05,
      "loss": 0.6001,
      "step": 1105
    },
    {
      "epoch": 1.5358255451713396,
      "grad_norm": 0.4379146695137024,
      "learning_rate": 3.106373698809958e-05,
      "loss": 0.6104,
      "step": 1110
    },
    {
      "epoch": 1.542748355832468,
      "grad_norm": 0.4841795563697815,
      "learning_rate": 3.0192808639271065e-05,
      "loss": 0.6115,
      "step": 1115
    },
    {
      "epoch": 1.5496711664935963,
      "grad_norm": 0.45849722623825073,
      "learning_rate": 2.933208771843018e-05,
      "loss": 0.5972,
      "step": 1120
    },
    {
      "epoch": 1.5565939771547248,
      "grad_norm": 0.4957985579967499,
      "learning_rate": 2.8481700082908268e-05,
      "loss": 0.5939,
      "step": 1125
    },
    {
      "epoch": 1.5635167878158533,
      "grad_norm": 0.4643390476703644,
      "learning_rate": 2.7641770079071127e-05,
      "loss": 0.5982,
      "step": 1130
    },
    {
      "epoch": 1.5704395984769817,
      "grad_norm": 0.4544386565685272,
      "learning_rate": 2.681242052413656e-05,
      "loss": 0.5769,
      "step": 1135
    },
    {
      "epoch": 1.57736240913811,
      "grad_norm": 0.49456363916397095,
      "learning_rate": 2.59937726882158e-05,
      "loss": 0.5777,
      "step": 1140
    },
    {
      "epoch": 1.5842852197992385,
      "grad_norm": 0.5013095140457153,
      "learning_rate": 2.5185946276580918e-05,
      "loss": 0.6156,
      "step": 1145
    },
    {
      "epoch": 1.591208030460367,
      "grad_norm": 0.48197901248931885,
      "learning_rate": 2.4389059412161087e-05,
      "loss": 0.589,
      "step": 1150
    },
    {
      "epoch": 1.5981308411214954,
      "grad_norm": 0.4798251986503601,
      "learning_rate": 2.3603228618270356e-05,
      "loss": 0.5892,
      "step": 1155
    },
    {
      "epoch": 1.6050536517826237,
      "grad_norm": 0.463618665933609,
      "learning_rate": 2.2828568801569283e-05,
      "loss": 0.5678,
      "step": 1160
    },
    {
      "epoch": 1.611976462443752,
      "grad_norm": 0.4392685294151306,
      "learning_rate": 2.2065193235262782e-05,
      "loss": 0.5666,
      "step": 1165
    },
    {
      "epoch": 1.6188992731048806,
      "grad_norm": 0.4790479838848114,
      "learning_rate": 2.1313213542537058e-05,
      "loss": 0.5871,
      "step": 1170
    },
    {
      "epoch": 1.6258220837660091,
      "grad_norm": 0.49823999404907227,
      "learning_rate": 2.0572739680237717e-05,
      "loss": 0.5978,
      "step": 1175
    },
    {
      "epoch": 1.6327448944271374,
      "grad_norm": 0.4643816351890564,
      "learning_rate": 1.984387992279153e-05,
      "loss": 0.6085,
      "step": 1180
    },
    {
      "epoch": 1.6396677050882658,
      "grad_norm": 0.46086233854293823,
      "learning_rate": 1.912674084637409e-05,
      "loss": 0.5975,
      "step": 1185
    },
    {
      "epoch": 1.6465905157493943,
      "grad_norm": 0.463457852602005,
      "learning_rate": 1.8421427313326046e-05,
      "loss": 0.5732,
      "step": 1190
    },
    {
      "epoch": 1.6535133264105226,
      "grad_norm": 0.4712519347667694,
      "learning_rate": 1.7728042456819704e-05,
      "loss": 0.5917,
      "step": 1195
    },
    {
      "epoch": 1.6604361370716512,
      "grad_norm": 0.46482053399086,
      "learning_rate": 1.7046687665778717e-05,
      "loss": 0.5771,
      "step": 1200
    },
    {
      "epoch": 1.6673589477327795,
      "grad_norm": 0.4480438530445099,
      "learning_rate": 1.6377462570052438e-05,
      "loss": 0.5737,
      "step": 1205
    },
    {
      "epoch": 1.6742817583939078,
      "grad_norm": 0.4909604489803314,
      "learning_rate": 1.5720465025847987e-05,
      "loss": 0.5819,
      "step": 1210
    },
    {
      "epoch": 1.6812045690550363,
      "grad_norm": 0.45884647965431213,
      "learning_rate": 1.5075791101421166e-05,
      "loss": 0.5827,
      "step": 1215
    },
    {
      "epoch": 1.6881273797161649,
      "grad_norm": 0.47044360637664795,
      "learning_rate": 1.4443535063029279e-05,
      "loss": 0.5903,
      "step": 1220
    },
    {
      "epoch": 1.6950501903772932,
      "grad_norm": 0.4716072678565979,
      "learning_rate": 1.3823789361147044e-05,
      "loss": 0.5719,
      "step": 1225
    },
    {
      "epoch": 1.7019730010384215,
      "grad_norm": 0.4769097864627838,
      "learning_rate": 1.3216644616948282e-05,
      "loss": 0.5803,
      "step": 1230
    },
    {
      "epoch": 1.70889581169955,
      "grad_norm": 0.46896225214004517,
      "learning_rate": 1.2622189609054979e-05,
      "loss": 0.5683,
      "step": 1235
    },
    {
      "epoch": 1.7158186223606784,
      "grad_norm": 0.5027751326560974,
      "learning_rate": 1.2040511260555831e-05,
      "loss": 0.5774,
      "step": 1240
    },
    {
      "epoch": 1.722741433021807,
      "grad_norm": 0.459954172372818,
      "learning_rate": 1.1471694626296049e-05,
      "loss": 0.578,
      "step": 1245
    },
    {
      "epoch": 1.7296642436829353,
      "grad_norm": 0.4557459354400635,
      "learning_rate": 1.0915822880440308e-05,
      "loss": 0.5741,
      "step": 1250
    },
    {
      "epoch": 1.7365870543440636,
      "grad_norm": 0.4638640582561493,
      "learning_rate": 1.037297730431085e-05,
      "loss": 0.569,
      "step": 1255
    },
    {
      "epoch": 1.7435098650051921,
      "grad_norm": 0.45103228092193604,
      "learning_rate": 9.843237274502282e-06,
      "loss": 0.5806,
      "step": 1260
    },
    {
      "epoch": 1.7504326756663207,
      "grad_norm": 0.4748806357383728,
      "learning_rate": 9.326680251274777e-06,
      "loss": 0.5857,
      "step": 1265
    },
    {
      "epoch": 1.757355486327449,
      "grad_norm": 0.4849424660205841,
      "learning_rate": 8.823381767227667e-06,
      "loss": 0.5869,
      "step": 1270
    },
    {
      "epoch": 1.7642782969885773,
      "grad_norm": 0.4745672941207886,
      "learning_rate": 8.333415416254831e-06,
      "loss": 0.5723,
      "step": 1275
    },
    {
      "epoch": 1.7712011076497056,
      "grad_norm": 0.4644942879676819,
      "learning_rate": 7.856852842783547e-06,
      "loss": 0.5661,
      "step": 1280
    },
    {
      "epoch": 1.7781239183108342,
      "grad_norm": 0.45206427574157715,
      "learning_rate": 7.393763731298387e-06,
      "loss": 0.5659,
      "step": 1285
    },
    {
      "epoch": 1.7850467289719627,
      "grad_norm": 0.4447067081928253,
      "learning_rate": 6.944215796151765e-06,
      "loss": 0.5652,
      "step": 1290
    },
    {
      "epoch": 1.791969539633091,
      "grad_norm": 0.49755769968032837,
      "learning_rate": 6.5082747716625255e-06,
      "loss": 0.5846,
      "step": 1295
    },
    {
      "epoch": 1.7988923502942193,
      "grad_norm": 0.4422699511051178,
      "learning_rate": 6.086004402504098e-06,
      "loss": 0.5579,
      "step": 1300
    },
    {
      "epoch": 1.8058151609553479,
      "grad_norm": 0.4642030596733093,
      "learning_rate": 5.6774664343834495e-06,
      "loss": 0.5886,
      "step": 1305
    },
    {
      "epoch": 1.8127379716164764,
      "grad_norm": 0.468826025724411,
      "learning_rate": 5.2827206050125585e-06,
      "loss": 0.5738,
      "step": 1310
    },
    {
      "epoch": 1.8196607822776047,
      "grad_norm": 0.47206902503967285,
      "learning_rate": 4.9018246353732755e-06,
      "loss": 0.5928,
      "step": 1315
    },
    {
      "epoch": 1.826583592938733,
      "grad_norm": 0.44131016731262207,
      "learning_rate": 4.534834221277262e-06,
      "loss": 0.5642,
      "step": 1320
    },
    {
      "epoch": 1.8335064035998614,
      "grad_norm": 0.46279463171958923,
      "learning_rate": 4.181803025221898e-06,
      "loss": 0.5772,
      "step": 1325
    },
    {
      "epoch": 1.84042921426099,
      "grad_norm": 0.48021042346954346,
      "learning_rate": 3.842782668543599e-06,
      "loss": 0.5777,
      "step": 1330
    },
    {
      "epoch": 1.8473520249221185,
      "grad_norm": 0.4092346131801605,
      "learning_rate": 3.5178227238696347e-06,
      "loss": 0.5577,
      "step": 1335
    },
    {
      "epoch": 1.8542748355832468,
      "grad_norm": 0.48017874360084534,
      "learning_rate": 3.2069707078694057e-06,
      "loss": 0.5532,
      "step": 1340
    },
    {
      "epoch": 1.8611976462443751,
      "grad_norm": 0.45100685954093933,
      "learning_rate": 2.9102720743064527e-06,
      "loss": 0.5823,
      "step": 1345
    },
    {
      "epoch": 1.8681204569055037,
      "grad_norm": 0.4369434714317322,
      "learning_rate": 2.6277702073919997e-06,
      "loss": 0.5561,
      "step": 1350
    },
    {
      "epoch": 1.8750432675666322,
      "grad_norm": 0.44638916850090027,
      "learning_rate": 2.3595064154412374e-06,
      "loss": 0.5625,
      "step": 1355
    },
    {
      "epoch": 1.8819660782277605,
      "grad_norm": 0.4592219889163971,
      "learning_rate": 2.1055199248330546e-06,
      "loss": 0.5696,
      "step": 1360
    },
    {
      "epoch": 1.8888888888888888,
      "grad_norm": 0.48690512776374817,
      "learning_rate": 1.8658478742742625e-06,
      "loss": 0.5638,
      "step": 1365
    },
    {
      "epoch": 1.8958116995500172,
      "grad_norm": 0.4558075964450836,
      "learning_rate": 1.6405253093690343e-06,
      "loss": 0.5636,
      "step": 1370
    },
    {
      "epoch": 1.9027345102111457,
      "grad_norm": 0.45120561122894287,
      "learning_rate": 1.429585177494419e-06,
      "loss": 0.5602,
      "step": 1375
    },
    {
      "epoch": 1.9096573208722742,
      "grad_norm": 0.44356584548950195,
      "learning_rate": 1.2330583229827053e-06,
      "loss": 0.5756,
      "step": 1380
    },
    {
      "epoch": 1.9165801315334026,
      "grad_norm": 0.4665040969848633,
      "learning_rate": 1.0509734826112394e-06,
      "loss": 0.5574,
      "step": 1385
    },
    {
      "epoch": 1.9235029421945309,
      "grad_norm": 0.4631229043006897,
      "learning_rate": 8.833572814004321e-07,
      "loss": 0.5572,
      "step": 1390
    },
    {
      "epoch": 1.9304257528556594,
      "grad_norm": 0.4622645676136017,
      "learning_rate": 7.302342287205943e-07,
      "loss": 0.5696,
      "step": 1395
    },
    {
      "epoch": 1.937348563516788,
      "grad_norm": 0.453389048576355,
      "learning_rate": 5.916267147080934e-07,
      "loss": 0.5672,
      "step": 1400
    },
    {
      "epoch": 1.9442713741779163,
      "grad_norm": 0.4780597686767578,
      "learning_rate": 4.6755500699138253e-07,
      "loss": 0.5585,
      "step": 1405
    },
    {
      "epoch": 1.9511941848390446,
      "grad_norm": 0.4834330081939697,
      "learning_rate": 3.5803724772740523e-07,
      "loss": 0.5582,
      "step": 1410
    },
    {
      "epoch": 1.958116995500173,
      "grad_norm": 0.45172709226608276,
      "learning_rate": 2.630894509488058e-07,
      "loss": 0.5692,
      "step": 1415
    },
    {
      "epoch": 1.9650398061613015,
      "grad_norm": 0.44283580780029297,
      "learning_rate": 1.8272550022230272e-07,
      "loss": 0.5615,
      "step": 1420
    },
    {
      "epoch": 1.97196261682243,
      "grad_norm": 0.4729226231575012,
      "learning_rate": 1.1695714661856816e-07,
      "loss": 0.5507,
      "step": 1425
    },
    {
      "epoch": 1.9788854274835583,
      "grad_norm": 0.45251360535621643,
      "learning_rate": 6.579400699397998e-08,
      "loss": 0.5658,
      "step": 1430
    },
    {
      "epoch": 1.9858082381446867,
      "grad_norm": 0.44953447580337524,
      "learning_rate": 2.9243562584402305e-08,
      "loss": 0.5705,
      "step": 1435
    },
    {
      "epoch": 1.9927310488058152,
      "grad_norm": 0.4522659480571747,
      "learning_rate": 7.311157911249478e-09,
      "loss": 0.5817,
      "step": 1440
    },
    {
      "epoch": 1.9982692973347178,
      "eval_loss": 0.7837347388267517,
      "eval_runtime": 53.9134,
      "eval_samples_per_second": 38.376,
      "eval_steps_per_second": 2.411,
      "step": 1444
    },
    {
      "epoch": 1.9982692973347178,
      "step": 1444,
      "total_flos": 4.672606349949927e+18,
      "train_loss": 0.861372460618904,
      "train_runtime": 10168.9542,
      "train_samples_per_second": 9.09,
      "train_steps_per_second": 0.142
    }
  ],
  "logging_steps": 5,
  "max_steps": 1444,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.672606349949927e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}