{
  "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": 73.5276107788086,
      "learning_rate": 0.0,
      "loss": 3.4696,
      "step": 1
    },
    {
      "epoch": 0.006922810661128418,
      "grad_norm": 30.179004669189453,
      "learning_rate": 5.517241379310345e-06,
      "loss": 3.2174,
      "step": 5
    },
    {
      "epoch": 0.013845621322256836,
      "grad_norm": 18.46404266357422,
      "learning_rate": 1.2413793103448277e-05,
      "loss": 2.7354,
      "step": 10
    },
    {
      "epoch": 0.020768431983385256,
      "grad_norm": 7.723433017730713,
      "learning_rate": 1.9310344827586207e-05,
      "loss": 2.4492,
      "step": 15
    },
    {
      "epoch": 0.027691242644513673,
      "grad_norm": 7.463802337646484,
      "learning_rate": 2.620689655172414e-05,
      "loss": 2.2143,
      "step": 20
    },
    {
      "epoch": 0.034614053305642094,
      "grad_norm": 7.357604503631592,
      "learning_rate": 3.310344827586207e-05,
      "loss": 1.921,
      "step": 25
    },
    {
      "epoch": 0.04153686396677051,
      "grad_norm": 7.084353446960449,
      "learning_rate": 4e-05,
      "loss": 1.5084,
      "step": 30
    },
    {
      "epoch": 0.04845967462789893,
      "grad_norm": 3.4993274211883545,
      "learning_rate": 4.689655172413793e-05,
      "loss": 1.0997,
      "step": 35
    },
    {
      "epoch": 0.055382485289027346,
      "grad_norm": 2.801764965057373,
      "learning_rate": 5.379310344827586e-05,
      "loss": 1.0037,
      "step": 40
    },
    {
      "epoch": 0.06230529595015576,
      "grad_norm": 7.829431533813477,
      "learning_rate": 6.068965517241379e-05,
      "loss": 1.0,
      "step": 45
    },
    {
      "epoch": 0.06922810661128419,
      "grad_norm": 3.6705822944641113,
      "learning_rate": 6.758620689655173e-05,
      "loss": 0.9834,
      "step": 50
    },
    {
      "epoch": 0.0761509172724126,
      "grad_norm": 2.8807718753814697,
      "learning_rate": 7.448275862068966e-05,
      "loss": 0.8439,
      "step": 55
    },
    {
      "epoch": 0.08307372793354102,
      "grad_norm": 2.0084006786346436,
      "learning_rate": 8.137931034482759e-05,
      "loss": 0.754,
      "step": 60
    },
    {
      "epoch": 0.08999653859466944,
      "grad_norm": 9.466357231140137,
      "learning_rate": 8.827586206896552e-05,
      "loss": 0.9603,
      "step": 65
    },
    {
      "epoch": 0.09691934925579786,
      "grad_norm": 2.5492539405822754,
      "learning_rate": 9.517241379310345e-05,
      "loss": 0.8366,
      "step": 70
    },
    {
      "epoch": 0.10384215991692627,
      "grad_norm": 22.056821823120117,
      "learning_rate": 0.0001020689655172414,
      "loss": 0.7592,
      "step": 75
    },
    {
      "epoch": 0.11076497057805469,
      "grad_norm": 29.231815338134766,
      "learning_rate": 0.00010896551724137931,
      "loss": 0.8805,
      "step": 80
    },
    {
      "epoch": 0.11768778123918311,
      "grad_norm": 34.974769592285156,
      "learning_rate": 0.00011586206896551725,
      "loss": 1.0534,
      "step": 85
    },
    {
      "epoch": 0.12461059190031153,
      "grad_norm": 5.458140850067139,
      "learning_rate": 0.00012275862068965518,
      "loss": 1.0965,
      "step": 90
    },
    {
      "epoch": 0.13153340256143994,
      "grad_norm": 4.925862789154053,
      "learning_rate": 0.0001296551724137931,
      "loss": 0.9976,
      "step": 95
    },
    {
      "epoch": 0.13845621322256838,
      "grad_norm": 43.03465270996094,
      "learning_rate": 0.00013655172413793104,
      "loss": 0.821,
      "step": 100
    },
    {
      "epoch": 0.14537902388369678,
      "grad_norm": 17.449140548706055,
      "learning_rate": 0.00014344827586206896,
      "loss": 0.9602,
      "step": 105
    },
    {
      "epoch": 0.1523018345448252,
      "grad_norm": 1.8036819696426392,
      "learning_rate": 0.0001503448275862069,
      "loss": 0.859,
      "step": 110
    },
    {
      "epoch": 0.1592246452059536,
      "grad_norm": 1.6082074642181396,
      "learning_rate": 0.00015724137931034485,
      "loss": 0.7846,
      "step": 115
    },
    {
      "epoch": 0.16614745586708204,
      "grad_norm": 2.0686991214752197,
      "learning_rate": 0.00016413793103448276,
      "loss": 0.8044,
      "step": 120
    },
    {
      "epoch": 0.17307026652821045,
      "grad_norm": 25.762229919433594,
      "learning_rate": 0.0001710344827586207,
      "loss": 0.8199,
      "step": 125
    },
    {
      "epoch": 0.17999307718933888,
      "grad_norm": 3.0691945552825928,
      "learning_rate": 0.00017793103448275862,
      "loss": 0.8383,
      "step": 130
    },
    {
      "epoch": 0.18691588785046728,
      "grad_norm": 1.7510746717453003,
      "learning_rate": 0.00018482758620689654,
      "loss": 0.8982,
      "step": 135
    },
    {
      "epoch": 0.19383869851159571,
      "grad_norm": 1.7901217937469482,
      "learning_rate": 0.0001917241379310345,
      "loss": 0.8741,
      "step": 140
    },
    {
      "epoch": 0.20076150917272412,
      "grad_norm": 2.0487852096557617,
      "learning_rate": 0.00019862068965517243,
      "loss": 0.8404,
      "step": 145
    },
    {
      "epoch": 0.20768431983385255,
      "grad_norm": 1.5697190761566162,
      "learning_rate": 0.0001999953208384105,
      "loss": 0.8212,
      "step": 150
    },
    {
      "epoch": 0.21460713049498095,
      "grad_norm": 11.699938774108887,
      "learning_rate": 0.0001999763124949378,
      "loss": 0.8841,
      "step": 155
    },
    {
      "epoch": 0.22152994115610938,
      "grad_norm": 1.6109673976898193,
      "learning_rate": 0.0001999426852993044,
      "loss": 0.9349,
      "step": 160
    },
    {
      "epoch": 0.2284527518172378,
      "grad_norm": 2.988689661026001,
      "learning_rate": 0.00019989444416858502,
      "loss": 0.9006,
      "step": 165
    },
    {
      "epoch": 0.23537556247836622,
      "grad_norm": 6.933545112609863,
      "learning_rate": 0.0001998315961567502,
      "loss": 1.0421,
      "step": 170
    },
    {
      "epoch": 0.24229837313949462,
      "grad_norm": 5.933894634246826,
      "learning_rate": 0.00019975415045363467,
      "loss": 0.9528,
      "step": 175
    },
    {
      "epoch": 0.24922118380062305,
      "grad_norm": 82.2666244506836,
      "learning_rate": 0.00019966211838359378,
      "loss": 0.947,
      "step": 180
    },
    {
      "epoch": 0.25614399446175146,
      "grad_norm": 2.0857582092285156,
      "learning_rate": 0.00019955551340384743,
      "loss": 0.9174,
      "step": 185
    },
    {
      "epoch": 0.2630668051228799,
      "grad_norm": 4.074726104736328,
      "learning_rate": 0.00019943435110251248,
      "loss": 0.8472,
      "step": 190
    },
    {
      "epoch": 0.2699896157840083,
      "grad_norm": 2.122100591659546,
      "learning_rate": 0.0001992986491963232,
      "loss": 0.8403,
      "step": 195
    },
    {
      "epoch": 0.27691242644513675,
      "grad_norm": 1.1407779455184937,
      "learning_rate": 0.00019914842752804103,
      "loss": 0.8065,
      "step": 200
    },
    {
      "epoch": 0.2838352371062651,
      "grad_norm": 1.0739364624023438,
      "learning_rate": 0.00019898370806355263,
      "loss": 0.7784,
      "step": 205
    },
    {
      "epoch": 0.29075804776739356,
      "grad_norm": 0.9849103093147278,
      "learning_rate": 0.00019880451488865836,
      "loss": 0.8174,
      "step": 210
    },
    {
      "epoch": 0.297680858428522,
      "grad_norm": 0.840072751045227,
      "learning_rate": 0.00019861087420555018,
      "loss": 0.7934,
      "step": 215
    },
    {
      "epoch": 0.3046036690896504,
      "grad_norm": 0.996491551399231,
      "learning_rate": 0.0001984028143289803,
      "loss": 0.7948,
      "step": 220
    },
    {
      "epoch": 0.3115264797507788,
      "grad_norm": 1.0046900510787964,
      "learning_rate": 0.00019818036568212106,
      "loss": 0.7789,
      "step": 225
    },
    {
      "epoch": 0.3184492904119072,
      "grad_norm": 1.3844839334487915,
      "learning_rate": 0.00019794356079211604,
      "loss": 0.8206,
      "step": 230
    },
    {
      "epoch": 0.32537210107303566,
      "grad_norm": 0.9604908227920532,
      "learning_rate": 0.00019769243428532422,
      "loss": 0.7827,
      "step": 235
    },
    {
      "epoch": 0.3322949117341641,
      "grad_norm": 14.684309959411621,
      "learning_rate": 0.00019742702288225652,
      "loss": 0.8219,
      "step": 240
    },
    {
      "epoch": 0.33921772239529246,
      "grad_norm": 1.059198260307312,
      "learning_rate": 0.00019714736539220648,
      "loss": 0.825,
      "step": 245
    },
    {
      "epoch": 0.3461405330564209,
      "grad_norm": 0.8264622688293457,
      "learning_rate": 0.00019685350270757555,
      "loss": 0.7993,
      "step": 250
    },
    {
      "epoch": 0.3530633437175493,
      "grad_norm": 0.8702566623687744,
      "learning_rate": 0.0001965454777978936,
      "loss": 0.8209,
      "step": 255
    },
    {
      "epoch": 0.35998615437867776,
      "grad_norm": 1.260245680809021,
      "learning_rate": 0.00019622333570353567,
      "loss": 0.8117,
      "step": 260
    },
    {
      "epoch": 0.36690896503980613,
      "grad_norm": 0.8236448764801025,
      "learning_rate": 0.00019588712352913625,
      "loss": 0.7933,
      "step": 265
    },
    {
      "epoch": 0.37383177570093457,
      "grad_norm": 0.7921434640884399,
      "learning_rate": 0.00019553689043670127,
      "loss": 0.7715,
      "step": 270
    },
    {
      "epoch": 0.380754586362063,
      "grad_norm": 0.8058004975318909,
      "learning_rate": 0.00019517268763841962,
      "loss": 0.7636,
      "step": 275
    },
    {
      "epoch": 0.38767739702319143,
      "grad_norm": 0.7768955826759338,
      "learning_rate": 0.00019479456838917473,
      "loss": 0.774,
      "step": 280
    },
    {
      "epoch": 0.39460020768431986,
      "grad_norm": 0.7238219380378723,
      "learning_rate": 0.0001944025879787574,
      "loss": 0.7903,
      "step": 285
    },
    {
      "epoch": 0.40152301834544823,
      "grad_norm": 0.9116212725639343,
      "learning_rate": 0.0001939968037237812,
      "loss": 0.7678,
      "step": 290
    },
    {
      "epoch": 0.40844582900657667,
      "grad_norm": 0.9523202180862427,
      "learning_rate": 0.00019357727495930146,
      "loss": 0.7683,
      "step": 295
    },
    {
      "epoch": 0.4153686396677051,
      "grad_norm": 0.902203381061554,
      "learning_rate": 0.00019314406303013904,
      "loss": 0.7641,
      "step": 300
    },
    {
      "epoch": 0.42229145032883353,
      "grad_norm": 0.6467769742012024,
      "learning_rate": 0.00019269723128191048,
      "loss": 0.7636,
      "step": 305
    },
    {
      "epoch": 0.4292142609899619,
      "grad_norm": 0.7330191135406494,
      "learning_rate": 0.00019223684505176517,
      "loss": 0.7551,
      "step": 310
    },
    {
      "epoch": 0.43613707165109034,
      "grad_norm": 0.8263298273086548,
      "learning_rate": 0.00019176297165883165,
      "loss": 0.7655,
      "step": 315
    },
    {
      "epoch": 0.44305988231221877,
      "grad_norm": 0.6522659063339233,
      "learning_rate": 0.00019127568039437406,
      "loss": 0.7607,
      "step": 320
    },
    {
      "epoch": 0.4499826929733472,
      "grad_norm": 0.6384459733963013,
      "learning_rate": 0.00019077504251166006,
      "loss": 0.7559,
      "step": 325
    },
    {
      "epoch": 0.4569055036344756,
      "grad_norm": 0.7025325298309326,
      "learning_rate": 0.00019026113121554204,
      "loss": 0.7348,
      "step": 330
    },
    {
      "epoch": 0.463828314295604,
      "grad_norm": 0.6380446553230286,
      "learning_rate": 0.00018973402165175268,
      "loss": 0.7585,
      "step": 335
    },
    {
      "epoch": 0.47075112495673244,
      "grad_norm": 0.6707427501678467,
      "learning_rate": 0.0001891937908959172,
      "loss": 0.7546,
      "step": 340
    },
    {
      "epoch": 0.47767393561786087,
      "grad_norm": 0.7454755306243896,
      "learning_rate": 0.00018864051794228282,
      "loss": 0.7639,
      "step": 345
    },
    {
      "epoch": 0.48459674627898924,
      "grad_norm": 0.8577032685279846,
      "learning_rate": 0.00018807428369216822,
      "loss": 0.7323,
      "step": 350
    },
    {
      "epoch": 0.4915195569401177,
      "grad_norm": 0.655467689037323,
      "learning_rate": 0.00018749517094213375,
      "loss": 0.7396,
      "step": 355
    },
    {
      "epoch": 0.4984423676012461,
      "grad_norm": 0.6951208114624023,
      "learning_rate": 0.00018690326437187472,
      "loss": 0.7385,
      "step": 360
    },
    {
      "epoch": 0.5053651782623745,
      "grad_norm": 1.1481677293777466,
      "learning_rate": 0.00018629865053183911,
      "loss": 0.7453,
      "step": 365
    },
    {
      "epoch": 0.5122879889235029,
      "grad_norm": 0.7248277068138123,
      "learning_rate": 0.0001856814178305722,
      "loss": 0.7435,
      "step": 370
    },
    {
      "epoch": 0.5192107995846313,
      "grad_norm": 0.787811279296875,
      "learning_rate": 0.00018505165652178893,
      "loss": 0.7515,
      "step": 375
    },
    {
      "epoch": 0.5261336102457598,
      "grad_norm": 0.6863015294075012,
      "learning_rate": 0.00018440945869117675,
      "loss": 0.7192,
      "step": 380
    },
    {
      "epoch": 0.5330564209068882,
      "grad_norm": 0.6457992196083069,
      "learning_rate": 0.00018375491824293067,
      "loss": 0.7192,
      "step": 385
    },
    {
      "epoch": 0.5399792315680166,
      "grad_norm": 0.7503763437271118,
      "learning_rate": 0.00018308813088602227,
      "loss": 0.7396,
      "step": 390
    },
    {
      "epoch": 0.5469020422291451,
      "grad_norm": 0.5836992263793945,
      "learning_rate": 0.00018240919412020466,
      "loss": 0.7118,
      "step": 395
    },
    {
      "epoch": 0.5538248528902735,
      "grad_norm": 5.260194778442383,
      "learning_rate": 0.00018171820722175604,
      "loss": 0.7462,
      "step": 400
    },
    {
      "epoch": 0.5607476635514018,
      "grad_norm": 0.6316019296646118,
      "learning_rate": 0.00018101527122896293,
      "loss": 0.7215,
      "step": 405
    },
    {
      "epoch": 0.5676704742125303,
      "grad_norm": 0.6845203638076782,
      "learning_rate": 0.0001803004889273463,
      "loss": 0.7099,
      "step": 410
    },
    {
      "epoch": 0.5745932848736587,
      "grad_norm": 0.6993951797485352,
      "learning_rate": 0.0001795739648346317,
      "loss": 0.7139,
      "step": 415
    },
    {
      "epoch": 0.5815160955347871,
      "grad_norm": 0.5756929516792297,
      "learning_rate": 0.00017883580518546647,
      "loss": 0.6847,
      "step": 420
    },
    {
      "epoch": 0.5884389061959155,
      "grad_norm": 0.6658014059066772,
      "learning_rate": 0.00017808611791588584,
      "loss": 0.7278,
      "step": 425
    },
    {
      "epoch": 0.595361716857044,
      "grad_norm": 0.6488052010536194,
      "learning_rate": 0.00017732501264752996,
      "loss": 0.7142,
      "step": 430
    },
    {
      "epoch": 0.6022845275181724,
      "grad_norm": 0.5289434790611267,
      "learning_rate": 0.00017655260067161503,
      "loss": 0.7167,
      "step": 435
    },
    {
      "epoch": 0.6092073381793008,
      "grad_norm": 0.6898224949836731,
      "learning_rate": 0.00017576899493265954,
      "loss": 0.7165,
      "step": 440
    },
    {
      "epoch": 0.6161301488404292,
      "grad_norm": 0.6195114850997925,
      "learning_rate": 0.00017497431001196943,
      "loss": 0.699,
      "step": 445
    },
    {
      "epoch": 0.6230529595015576,
      "grad_norm": 0.6543487906455994,
      "learning_rate": 0.00017416866211088366,
      "loss": 0.7115,
      "step": 450
    },
    {
      "epoch": 0.629975770162686,
      "grad_norm": 0.5665395259857178,
      "learning_rate": 0.00017335216903378267,
      "loss": 0.7074,
      "step": 455
    },
    {
      "epoch": 0.6368985808238145,
      "grad_norm": 0.6460801959037781,
      "learning_rate": 0.00017252495017086296,
      "loss": 0.7199,
      "step": 460
    },
    {
      "epoch": 0.6438213914849429,
      "grad_norm": 0.7826030254364014,
      "learning_rate": 0.0001716871264806791,
      "loss": 0.7027,
      "step": 465
    },
    {
      "epoch": 0.6507442021460713,
      "grad_norm": 5.1860504150390625,
      "learning_rate": 0.0001708388204724572,
      "loss": 0.7063,
      "step": 470
    },
    {
      "epoch": 0.6576670128071997,
      "grad_norm": 0.5539765954017639,
      "learning_rate": 0.00016998015618818087,
      "loss": 0.7021,
      "step": 475
    },
    {
      "epoch": 0.6645898234683282,
      "grad_norm": 0.6178136467933655,
      "learning_rate": 0.00016911125918445363,
      "loss": 0.7047,
      "step": 480
    },
    {
      "epoch": 0.6715126341294566,
      "grad_norm": 0.5850706696510315,
      "learning_rate": 0.00016823225651413953,
      "loss": 0.7163,
      "step": 485
    },
    {
      "epoch": 0.6784354447905849,
      "grad_norm": 0.5677686929702759,
      "learning_rate": 0.00016734327670778508,
      "loss": 0.6866,
      "step": 490
    },
    {
      "epoch": 0.6853582554517134,
      "grad_norm": 0.5619258880615234,
      "learning_rate": 0.00016644444975482523,
      "loss": 0.7048,
      "step": 495
    },
    {
      "epoch": 0.6922810661128418,
      "grad_norm": 0.6009318232536316,
      "learning_rate": 0.0001655359070845757,
      "loss": 0.7023,
      "step": 500
    },
    {
      "epoch": 0.6992038767739702,
      "grad_norm": 0.5337724089622498,
      "learning_rate": 0.0001646177815470151,
      "loss": 0.6858,
      "step": 505
    },
    {
      "epoch": 0.7061266874350987,
      "grad_norm": 0.550845205783844,
      "learning_rate": 0.00016369020739335924,
      "loss": 0.6807,
      "step": 510
    },
    {
      "epoch": 0.7130494980962271,
      "grad_norm": 0.5907328724861145,
      "learning_rate": 0.00016275332025643028,
      "loss": 0.7041,
      "step": 515
    },
    {
      "epoch": 0.7199723087573555,
      "grad_norm": 0.5490245223045349,
      "learning_rate": 0.00016180725713082434,
      "loss": 0.6875,
      "step": 520
    },
    {
      "epoch": 0.726895119418484,
      "grad_norm": 0.5875672101974487,
      "learning_rate": 0.0001608521563528795,
      "loss": 0.6942,
      "step": 525
    },
    {
      "epoch": 0.7338179300796123,
      "grad_norm": 0.4903637170791626,
      "learning_rate": 0.00015988815758044792,
      "loss": 0.667,
      "step": 530
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 0.5825007557868958,
      "learning_rate": 0.00015891540177247467,
      "loss": 0.697,
      "step": 535
    },
    {
      "epoch": 0.7476635514018691,
      "grad_norm": 0.6213587522506714,
      "learning_rate": 0.00015793403116838613,
      "loss": 0.6751,
      "step": 540
    },
    {
      "epoch": 0.7545863620629976,
      "grad_norm": 0.6950411796569824,
      "learning_rate": 0.00015694418926729146,
      "loss": 0.6913,
      "step": 545
    },
    {
      "epoch": 0.761509172724126,
      "grad_norm": 0.5191546678543091,
      "learning_rate": 0.00015594602080699956,
      "loss": 0.6758,
      "step": 550
    },
    {
      "epoch": 0.7684319833852544,
      "grad_norm": 0.5811347961425781,
      "learning_rate": 0.00015493967174285512,
      "loss": 0.6892,
      "step": 555
    },
    {
      "epoch": 0.7753547940463829,
      "grad_norm": 0.495950847864151,
      "learning_rate": 0.00015392528922639662,
      "loss": 0.6768,
      "step": 560
    },
    {
      "epoch": 0.7822776047075113,
      "grad_norm": 0.5069176554679871,
      "learning_rate": 0.00015290302158383923,
      "loss": 0.6716,
      "step": 565
    },
    {
      "epoch": 0.7892004153686397,
      "grad_norm": 0.5323678255081177,
      "learning_rate": 0.0001518730182943862,
      "loss": 0.6698,
      "step": 570
    },
    {
      "epoch": 0.796123226029768,
      "grad_norm": 0.7031868100166321,
      "learning_rate": 0.0001508354299683715,
      "loss": 0.6673,
      "step": 575
    },
    {
      "epoch": 0.8030460366908965,
      "grad_norm": 0.55892014503479,
      "learning_rate": 0.0001497904083252371,
      "loss": 0.6675,
      "step": 580
    },
    {
      "epoch": 0.8099688473520249,
      "grad_norm": 0.4777008593082428,
      "learning_rate": 0.00014873810617134806,
      "loss": 0.6807,
      "step": 585
    },
    {
      "epoch": 0.8168916580131533,
      "grad_norm": 0.543347954750061,
      "learning_rate": 0.00014767867737764876,
      "loss": 0.6814,
      "step": 590
    },
    {
      "epoch": 0.8238144686742818,
      "grad_norm": 0.4696509838104248,
      "learning_rate": 0.0001466122768571633,
      "loss": 0.6506,
      "step": 595
    },
    {
      "epoch": 0.8307372793354102,
      "grad_norm": 0.5306531190872192,
      "learning_rate": 0.0001455390605423437,
      "loss": 0.6731,
      "step": 600
    },
    {
      "epoch": 0.8376600899965386,
      "grad_norm": 0.6365358233451843,
      "learning_rate": 0.00014445918536226904,
      "loss": 0.6441,
      "step": 605
    },
    {
      "epoch": 0.8445829006576671,
      "grad_norm": 0.5179509520530701,
      "learning_rate": 0.00014337280921969858,
      "loss": 0.6852,
      "step": 610
    },
    {
      "epoch": 0.8515057113187954,
      "grad_norm": 0.5093657970428467,
      "learning_rate": 0.0001422800909679829,
      "loss": 0.6648,
      "step": 615
    },
    {
      "epoch": 0.8584285219799238,
      "grad_norm": 0.4981916546821594,
      "learning_rate": 0.00014118119038783588,
      "loss": 0.6563,
      "step": 620
    },
    {
      "epoch": 0.8653513326410522,
      "grad_norm": 0.5044928789138794,
      "learning_rate": 0.00014007626816397087,
      "loss": 0.6661,
      "step": 625
    },
    {
      "epoch": 0.8722741433021807,
      "grad_norm": 0.5227713584899902,
      "learning_rate": 0.00013896548586160503,
      "loss": 0.6885,
      "step": 630
    },
    {
      "epoch": 0.8791969539633091,
      "grad_norm": 0.5463073253631592,
      "learning_rate": 0.00013784900590283473,
      "loss": 0.6609,
      "step": 635
    },
    {
      "epoch": 0.8861197646244375,
      "grad_norm": 0.49851828813552856,
      "learning_rate": 0.00013672699154288569,
      "loss": 0.6501,
      "step": 640
    },
    {
      "epoch": 0.893042575285566,
      "grad_norm": 0.5655946731567383,
      "learning_rate": 0.00013559960684624112,
      "loss": 0.6635,
      "step": 645
    },
    {
      "epoch": 0.8999653859466944,
      "grad_norm": 0.5413991808891296,
      "learning_rate": 0.0001344670166626519,
      "loss": 0.6705,
      "step": 650
    },
    {
      "epoch": 0.9068881966078228,
      "grad_norm": 0.5494153499603271,
      "learning_rate": 0.0001333293866030317,
      "loss": 0.6723,
      "step": 655
    },
    {
      "epoch": 0.9138110072689511,
      "grad_norm": 0.5189006328582764,
      "learning_rate": 0.0001321868830152407,
      "loss": 0.6562,
      "step": 660
    },
    {
      "epoch": 0.9207338179300796,
      "grad_norm": 0.5886821746826172,
      "learning_rate": 0.00013103967295976179,
      "loss": 0.6506,
      "step": 665
    },
    {
      "epoch": 0.927656628591208,
      "grad_norm": 0.44091060757637024,
      "learning_rate": 0.0001298879241852724,
      "loss": 0.6543,
      "step": 670
    },
    {
      "epoch": 0.9345794392523364,
      "grad_norm": 0.5451465249061584,
      "learning_rate": 0.0001287318051041159,
      "loss": 0.6436,
      "step": 675
    },
    {
      "epoch": 0.9415022499134649,
      "grad_norm": 0.48705631494522095,
      "learning_rate": 0.00012757148476767553,
      "loss": 0.6486,
      "step": 680
    },
    {
      "epoch": 0.9484250605745933,
      "grad_norm": 0.5340054035186768,
      "learning_rate": 0.0001264071328416555,
      "loss": 0.6415,
      "step": 685
    },
    {
      "epoch": 0.9553478712357217,
      "grad_norm": 0.5495091080665588,
      "learning_rate": 0.00012523891958127168,
      "loss": 0.6737,
      "step": 690
    },
    {
      "epoch": 0.9622706818968502,
      "grad_norm": 0.4970749020576477,
      "learning_rate": 0.0001240670158063565,
      "loss": 0.6546,
      "step": 695
    },
    {
      "epoch": 0.9691934925579785,
      "grad_norm": 0.47575998306274414,
      "learning_rate": 0.00012289159287638105,
      "loss": 0.6449,
      "step": 700
    },
    {
      "epoch": 0.9761163032191069,
      "grad_norm": 0.4925188422203064,
      "learning_rate": 0.00012171282266539845,
      "loss": 0.6609,
      "step": 705
    },
    {
      "epoch": 0.9830391138802353,
      "grad_norm": 0.47044652700424194,
      "learning_rate": 0.00012053087753691172,
      "loss": 0.653,
      "step": 710
    },
    {
      "epoch": 0.9899619245413638,
      "grad_norm": 0.47281110286712646,
      "learning_rate": 0.00011934593031867038,
      "loss": 0.6552,
      "step": 715
    },
    {
      "epoch": 0.9968847352024922,
      "grad_norm": 0.4654919505119324,
      "learning_rate": 0.00011815815427739911,
      "loss": 0.639,
      "step": 720
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.63841313123703,
      "eval_runtime": 75.465,
      "eval_samples_per_second": 27.417,
      "eval_steps_per_second": 1.723,
      "step": 723
    },
    {
      "epoch": 1.0027691242644514,
      "grad_norm": 0.476882666349411,
      "learning_rate": 0.00011696772309346182,
      "loss": 0.591,
      "step": 725
    },
    {
      "epoch": 1.0096919349255797,
      "grad_norm": 0.5042451620101929,
      "learning_rate": 0.0001157748108354659,
      "loss": 0.5285,
      "step": 730
    },
    {
      "epoch": 1.0166147455867083,
      "grad_norm": 0.4443126916885376,
      "learning_rate": 0.00011457959193480925,
      "loss": 0.5251,
      "step": 735
    },
    {
      "epoch": 1.0235375562478366,
      "grad_norm": 0.47023993730545044,
      "learning_rate": 0.00011338224116017423,
      "loss": 0.5307,
      "step": 740
    },
    {
      "epoch": 1.0304603669089651,
      "grad_norm": 0.4469102621078491,
      "learning_rate": 0.00011218293359197267,
      "loss": 0.5406,
      "step": 745
    },
    {
      "epoch": 1.0373831775700935,
      "grad_norm": 0.5018590092658997,
      "learning_rate": 0.00011098184459674484,
      "loss": 0.5217,
      "step": 750
    },
    {
      "epoch": 1.0443059882312218,
      "grad_norm": 0.44223928451538086,
      "learning_rate": 0.00010977914980151691,
      "loss": 0.5215,
      "step": 755
    },
    {
      "epoch": 1.0512287988923503,
      "grad_norm": 0.4535723030567169,
      "learning_rate": 0.00010857502506812029,
      "loss": 0.4987,
      "step": 760
    },
    {
      "epoch": 1.0581516095534786,
      "grad_norm": 0.4797036647796631,
      "learning_rate": 0.00010736964646747629,
      "loss": 0.5018,
      "step": 765
    },
    {
      "epoch": 1.0650744202146072,
      "grad_norm": 0.4599474370479584,
      "learning_rate": 0.00010616319025385089,
      "loss": 0.5222,
      "step": 770
    },
    {
      "epoch": 1.0719972308757355,
      "grad_norm": 0.43609824776649475,
      "learning_rate": 0.00010495583283908177,
      "loss": 0.5227,
      "step": 775
    },
    {
      "epoch": 1.078920041536864,
      "grad_norm": 0.4024893045425415,
      "learning_rate": 0.00010374775076678332,
      "loss": 0.5148,
      "step": 780
    },
    {
      "epoch": 1.0858428521979924,
      "grad_norm": 0.41304945945739746,
      "learning_rate": 0.00010253912068653146,
      "loss": 0.5222,
      "step": 785
    },
    {
      "epoch": 1.092765662859121,
      "grad_norm": 0.4150070250034332,
      "learning_rate": 0.00010133011932803378,
      "loss": 0.5287,
      "step": 790
    },
    {
      "epoch": 1.0996884735202492,
      "grad_norm": 0.4497414827346802,
      "learning_rate": 0.00010012092347528705,
      "loss": 0.5287,
      "step": 795
    },
    {
      "epoch": 1.1066112841813776,
      "grad_norm": 0.4617963433265686,
      "learning_rate": 9.891170994072793e-05,
      "loss": 0.5142,
      "step": 800
    },
    {
      "epoch": 1.113534094842506,
      "grad_norm": 0.4907746911048889,
      "learning_rate": 9.770265553937831e-05,
      "loss": 0.5154,
      "step": 805
    },
    {
      "epoch": 1.1204569055036344,
      "grad_norm": 0.4437863230705261,
      "learning_rate": 9.649393706299127e-05,
      "loss": 0.5114,
      "step": 810
    },
    {
      "epoch": 1.127379716164763,
      "grad_norm": 0.4392574429512024,
      "learning_rate": 9.52857312541998e-05,
      "loss": 0.5054,
      "step": 815
    },
    {
      "epoch": 1.1343025268258913,
      "grad_norm": 0.41205236315727234,
      "learning_rate": 9.407821478067304e-05,
      "loss": 0.5043,
      "step": 820
    },
    {
      "epoch": 1.1412253374870198,
      "grad_norm": 0.4570033848285675,
      "learning_rate": 9.287156420928342e-05,
      "loss": 0.5022,
      "step": 825
    },
    {
      "epoch": 1.1481481481481481,
      "grad_norm": 0.43261808156967163,
      "learning_rate": 9.166595598028832e-05,
      "loss": 0.5218,
      "step": 830
    },
    {
      "epoch": 1.1550709588092767,
      "grad_norm": 0.4350537657737732,
      "learning_rate": 9.046156638153056e-05,
      "loss": 0.5034,
      "step": 835
    },
    {
      "epoch": 1.161993769470405,
      "grad_norm": 0.41802477836608887,
      "learning_rate": 8.925857152266103e-05,
      "loss": 0.4959,
      "step": 840
    },
    {
      "epoch": 1.1689165801315333,
      "grad_norm": 0.4566584527492523,
      "learning_rate": 8.805714730938728e-05,
      "loss": 0.5095,
      "step": 845
    },
    {
      "epoch": 1.1758393907926619,
      "grad_norm": 0.3882467448711395,
      "learning_rate": 8.685746941775219e-05,
      "loss": 0.5031,
      "step": 850
    },
    {
      "epoch": 1.1827622014537902,
      "grad_norm": 0.42582014203071594,
      "learning_rate": 8.565971326844584e-05,
      "loss": 0.5144,
      "step": 855
    },
    {
      "epoch": 1.1896850121149187,
      "grad_norm": 0.4243321418762207,
      "learning_rate": 8.44640540011553e-05,
      "loss": 0.5188,
      "step": 860
    },
    {
      "epoch": 1.196607822776047,
      "grad_norm": 0.4075254797935486,
      "learning_rate": 8.327066644895469e-05,
      "loss": 0.5082,
      "step": 865
    },
    {
      "epoch": 1.2035306334371756,
      "grad_norm": 0.43225353956222534,
      "learning_rate": 8.207972511274095e-05,
      "loss": 0.5182,
      "step": 870
    },
    {
      "epoch": 1.210453444098304,
      "grad_norm": 0.4101962447166443,
      "learning_rate": 8.089140413571747e-05,
      "loss": 0.5116,
      "step": 875
    },
    {
      "epoch": 1.2173762547594325,
      "grad_norm": 0.4450133144855499,
      "learning_rate": 7.970587727793051e-05,
      "loss": 0.4971,
      "step": 880
    },
    {
      "epoch": 1.2242990654205608,
      "grad_norm": 0.43541422486305237,
      "learning_rate": 7.852331789086135e-05,
      "loss": 0.4993,
      "step": 885
    },
    {
      "epoch": 1.231221876081689,
      "grad_norm": 0.39591750502586365,
      "learning_rate": 7.73438988920784e-05,
      "loss": 0.5075,
      "step": 890
    },
    {
      "epoch": 1.2381446867428176,
      "grad_norm": 0.46820273995399475,
      "learning_rate": 7.616779273995252e-05,
      "loss": 0.5218,
      "step": 895
    },
    {
      "epoch": 1.245067497403946,
      "grad_norm": 0.425655722618103,
      "learning_rate": 7.499517140843968e-05,
      "loss": 0.5159,
      "step": 900
    },
    {
      "epoch": 1.2519903080650745,
      "grad_norm": 0.40865471959114075,
      "learning_rate": 7.382620636193438e-05,
      "loss": 0.494,
      "step": 905
    },
    {
      "epoch": 1.2589131187262028,
      "grad_norm": 0.4230162501335144,
      "learning_rate": 7.266106853019759e-05,
      "loss": 0.5007,
      "step": 910
    },
    {
      "epoch": 1.2658359293873311,
      "grad_norm": 0.4216570258140564,
      "learning_rate": 7.149992828336274e-05,
      "loss": 0.5048,
      "step": 915
    },
    {
      "epoch": 1.2727587400484597,
      "grad_norm": 0.41065993905067444,
      "learning_rate": 7.034295540702397e-05,
      "loss": 0.4963,
      "step": 920
    },
    {
      "epoch": 1.2796815507095882,
      "grad_norm": 0.4277260899543762,
      "learning_rate": 6.919031907740922e-05,
      "loss": 0.5049,
      "step": 925
    },
    {
      "epoch": 1.2866043613707165,
      "grad_norm": 0.4380500018596649,
      "learning_rate": 6.804218783664288e-05,
      "loss": 0.5168,
      "step": 930
    },
    {
      "epoch": 1.2935271720318449,
      "grad_norm": 0.40834662318229675,
      "learning_rate": 6.689872956810102e-05,
      "loss": 0.507,
      "step": 935
    },
    {
      "epoch": 1.3004499826929734,
      "grad_norm": 0.39029037952423096,
      "learning_rate": 6.5760111471863e-05,
      "loss": 0.5016,
      "step": 940
    },
    {
      "epoch": 1.3073727933541017,
      "grad_norm": 0.40143686532974243,
      "learning_rate": 6.46265000402628e-05,
      "loss": 0.5116,
      "step": 945
    },
    {
      "epoch": 1.3142956040152303,
      "grad_norm": 0.4155568480491638,
      "learning_rate": 6.349806103354417e-05,
      "loss": 0.499,
      "step": 950
    },
    {
      "epoch": 1.3212184146763586,
      "grad_norm": 0.44305872917175293,
      "learning_rate": 6.23749594556226e-05,
      "loss": 0.4959,
      "step": 955
    },
    {
      "epoch": 1.328141225337487,
      "grad_norm": 0.410986065864563,
      "learning_rate": 6.125735952995775e-05,
      "loss": 0.4927,
      "step": 960
    },
    {
      "epoch": 1.3350640359986155,
      "grad_norm": 0.42151662707328796,
      "learning_rate": 6.0145424675540394e-05,
      "loss": 0.4949,
      "step": 965
    },
    {
      "epoch": 1.341986846659744,
      "grad_norm": 0.3956366181373596,
      "learning_rate": 5.9039317482996735e-05,
      "loss": 0.5057,
      "step": 970
    },
    {
      "epoch": 1.3489096573208723,
      "grad_norm": 0.4053477644920349,
      "learning_rate": 5.793919969081374e-05,
      "loss": 0.4875,
      "step": 975
    },
    {
      "epoch": 1.3558324679820006,
      "grad_norm": 0.3788825273513794,
      "learning_rate": 5.68452321616894e-05,
      "loss": 0.4808,
      "step": 980
    },
    {
      "epoch": 1.3627552786431292,
      "grad_norm": 0.3918589651584625,
      "learning_rate": 5.5757574859010886e-05,
      "loss": 0.4953,
      "step": 985
    },
    {
      "epoch": 1.3696780893042575,
      "grad_norm": 0.39359208941459656,
      "learning_rate": 5.467638682346403e-05,
      "loss": 0.4777,
      "step": 990
    },
    {
      "epoch": 1.376600899965386,
      "grad_norm": 0.3955044448375702,
      "learning_rate": 5.3601826149777966e-05,
      "loss": 0.4992,
      "step": 995
    },
    {
      "epoch": 1.3835237106265144,
      "grad_norm": 0.4178461730480194,
      "learning_rate": 5.25340499636082e-05,
      "loss": 0.485,
      "step": 1000
    },
    {
      "epoch": 1.3904465212876427,
      "grad_norm": 0.40446537733078003,
      "learning_rate": 5.147321439856091e-05,
      "loss": 0.4945,
      "step": 1005
    },
    {
      "epoch": 1.3973693319487712,
      "grad_norm": 0.40754058957099915,
      "learning_rate": 5.041947457336274e-05,
      "loss": 0.5124,
      "step": 1010
    },
    {
      "epoch": 1.4042921426098995,
      "grad_norm": 0.3956260681152344,
      "learning_rate": 4.937298456917889e-05,
      "loss": 0.4949,
      "step": 1015
    },
    {
      "epoch": 1.411214953271028,
      "grad_norm": 0.45337051153182983,
      "learning_rate": 4.8333897407082896e-05,
      "loss": 0.4888,
      "step": 1020
    },
    {
      "epoch": 1.4181377639321564,
      "grad_norm": 0.38214102387428284,
      "learning_rate": 4.7302365025681206e-05,
      "loss": 0.4924,
      "step": 1025
    },
    {
      "epoch": 1.425060574593285,
      "grad_norm": 0.4063718020915985,
      "learning_rate": 4.627853825889642e-05,
      "loss": 0.4932,
      "step": 1030
    },
    {
      "epoch": 1.4319833852544133,
      "grad_norm": 0.42218196392059326,
      "learning_rate": 4.526256681391192e-05,
      "loss": 0.4843,
      "step": 1035
    },
    {
      "epoch": 1.4389061959155418,
      "grad_norm": 0.43437570333480835,
      "learning_rate": 4.4254599249281016e-05,
      "loss": 0.4744,
      "step": 1040
    },
    {
      "epoch": 1.4458290065766701,
      "grad_norm": 0.3987582325935364,
      "learning_rate": 4.3254782953204375e-05,
      "loss": 0.4845,
      "step": 1045
    },
    {
      "epoch": 1.4527518172377984,
      "grad_norm": 0.42256399989128113,
      "learning_rate": 4.2263264121978505e-05,
      "loss": 0.5006,
      "step": 1050
    },
    {
      "epoch": 1.459674627898927,
      "grad_norm": 0.37744051218032837,
      "learning_rate": 4.12801877386183e-05,
      "loss": 0.477,
      "step": 1055
    },
    {
      "epoch": 1.4665974385600553,
      "grad_norm": 0.4157800078392029,
      "learning_rate": 4.030569755165736e-05,
      "loss": 0.4891,
      "step": 1060
    },
    {
      "epoch": 1.4735202492211839,
      "grad_norm": 0.39397871494293213,
      "learning_rate": 3.9339936054128466e-05,
      "loss": 0.4797,
      "step": 1065
    },
    {
      "epoch": 1.4804430598823122,
      "grad_norm": 0.39519259333610535,
      "learning_rate": 3.8383044462727826e-05,
      "loss": 0.4682,
      "step": 1070
    },
    {
      "epoch": 1.4873658705434407,
      "grad_norm": 0.4494350850582123,
      "learning_rate": 3.7435162697166107e-05,
      "loss": 0.4904,
      "step": 1075
    },
    {
      "epoch": 1.494288681204569,
      "grad_norm": 0.3966675400733948,
      "learning_rate": 3.649642935970859e-05,
      "loss": 0.4864,
      "step": 1080
    },
    {
      "epoch": 1.5012114918656976,
      "grad_norm": 0.3766285181045532,
      "learning_rate": 3.556698171490871e-05,
      "loss": 0.478,
      "step": 1085
    },
    {
      "epoch": 1.508134302526826,
      "grad_norm": 0.3993706703186035,
      "learning_rate": 3.464695566953644e-05,
      "loss": 0.4912,
      "step": 1090
    },
    {
      "epoch": 1.5150571131879542,
      "grad_norm": 0.41815367341041565,
      "learning_rate": 3.373648575270576e-05,
      "loss": 0.486,
      "step": 1095
    },
    {
      "epoch": 1.5219799238490828,
      "grad_norm": 0.4036204516887665,
      "learning_rate": 3.283570509620344e-05,
      "loss": 0.4851,
      "step": 1100
    },
    {
      "epoch": 1.5289027345102113,
      "grad_norm": 0.39286836981773376,
      "learning_rate": 3.1944745415021915e-05,
      "loss": 0.4807,
      "step": 1105
    },
    {
      "epoch": 1.5358255451713396,
      "grad_norm": 0.3978467881679535,
      "learning_rate": 3.106373698809958e-05,
      "loss": 0.4763,
      "step": 1110
    },
    {
      "epoch": 1.542748355832468,
      "grad_norm": 0.389644056558609,
      "learning_rate": 3.0192808639271065e-05,
      "loss": 0.4812,
      "step": 1115
    },
    {
      "epoch": 1.5496711664935963,
      "grad_norm": 0.3576400876045227,
      "learning_rate": 2.933208771843018e-05,
      "loss": 0.4883,
      "step": 1120
    },
    {
      "epoch": 1.5565939771547248,
      "grad_norm": 0.3846583068370819,
      "learning_rate": 2.8481700082908268e-05,
      "loss": 0.4731,
      "step": 1125
    },
    {
      "epoch": 1.5635167878158533,
      "grad_norm": 0.3483330309391022,
      "learning_rate": 2.7641770079071127e-05,
      "loss": 0.4695,
      "step": 1130
    },
    {
      "epoch": 1.5704395984769817,
      "grad_norm": 0.3988693654537201,
      "learning_rate": 2.681242052413656e-05,
      "loss": 0.4717,
      "step": 1135
    },
    {
      "epoch": 1.57736240913811,
      "grad_norm": 0.3845638334751129,
      "learning_rate": 2.59937726882158e-05,
      "loss": 0.4769,
      "step": 1140
    },
    {
      "epoch": 1.5842852197992385,
      "grad_norm": 0.39838650822639465,
      "learning_rate": 2.5185946276580918e-05,
      "loss": 0.4745,
      "step": 1145
    },
    {
      "epoch": 1.591208030460367,
      "grad_norm": 0.404542475938797,
      "learning_rate": 2.4389059412161087e-05,
      "loss": 0.4736,
      "step": 1150
    },
    {
      "epoch": 1.5981308411214954,
      "grad_norm": 0.385309100151062,
      "learning_rate": 2.3603228618270356e-05,
      "loss": 0.4769,
      "step": 1155
    },
    {
      "epoch": 1.6050536517826237,
      "grad_norm": 0.4078046679496765,
      "learning_rate": 2.2828568801569283e-05,
      "loss": 0.4577,
      "step": 1160
    },
    {
      "epoch": 1.611976462443752,
      "grad_norm": 0.38839876651763916,
      "learning_rate": 2.2065193235262782e-05,
      "loss": 0.4712,
      "step": 1165
    },
    {
      "epoch": 1.6188992731048806,
      "grad_norm": 0.41136986017227173,
      "learning_rate": 2.1313213542537058e-05,
      "loss": 0.4677,
      "step": 1170
    },
    {
      "epoch": 1.6258220837660091,
      "grad_norm": 0.41455721855163574,
      "learning_rate": 2.0572739680237717e-05,
      "loss": 0.4788,
      "step": 1175
    },
    {
      "epoch": 1.6327448944271374,
      "grad_norm": 0.39108678698539734,
      "learning_rate": 1.984387992279153e-05,
      "loss": 0.4776,
      "step": 1180
    },
    {
      "epoch": 1.6396677050882658,
      "grad_norm": 0.40750446915626526,
      "learning_rate": 1.912674084637409e-05,
      "loss": 0.4618,
      "step": 1185
    },
    {
      "epoch": 1.6465905157493943,
      "grad_norm": 0.389186829328537,
      "learning_rate": 1.8421427313326046e-05,
      "loss": 0.4724,
      "step": 1190
    },
    {
      "epoch": 1.6535133264105226,
      "grad_norm": 0.40712910890579224,
      "learning_rate": 1.7728042456819704e-05,
      "loss": 0.4702,
      "step": 1195
    },
    {
      "epoch": 1.6604361370716512,
      "grad_norm": 0.37883758544921875,
      "learning_rate": 1.7046687665778717e-05,
      "loss": 0.4648,
      "step": 1200
    },
    {
      "epoch": 1.6673589477327795,
      "grad_norm": 0.3762923777103424,
      "learning_rate": 1.6377462570052438e-05,
      "loss": 0.4645,
      "step": 1205
    },
    {
      "epoch": 1.6742817583939078,
      "grad_norm": 0.3841410279273987,
      "learning_rate": 1.5720465025847987e-05,
      "loss": 0.4706,
      "step": 1210
    },
    {
      "epoch": 1.6812045690550363,
      "grad_norm": 0.3858813941478729,
      "learning_rate": 1.5075791101421166e-05,
      "loss": 0.468,
      "step": 1215
    },
    {
      "epoch": 1.6881273797161649,
      "grad_norm": 0.3854951858520508,
      "learning_rate": 1.4443535063029279e-05,
      "loss": 0.4646,
      "step": 1220
    },
    {
      "epoch": 1.6950501903772932,
      "grad_norm": 0.39483922719955444,
      "learning_rate": 1.3823789361147044e-05,
      "loss": 0.4657,
      "step": 1225
    },
    {
      "epoch": 1.7019730010384215,
      "grad_norm": 0.3647611737251282,
      "learning_rate": 1.3216644616948282e-05,
      "loss": 0.4665,
      "step": 1230
    },
    {
      "epoch": 1.70889581169955,
      "grad_norm": 0.3819540739059448,
      "learning_rate": 1.2622189609054979e-05,
      "loss": 0.4631,
      "step": 1235
    },
    {
      "epoch": 1.7158186223606784,
      "grad_norm": 0.394875168800354,
      "learning_rate": 1.2040511260555831e-05,
      "loss": 0.4546,
      "step": 1240
    },
    {
      "epoch": 1.722741433021807,
      "grad_norm": 0.4007471203804016,
      "learning_rate": 1.1471694626296049e-05,
      "loss": 0.4604,
      "step": 1245
    },
    {
      "epoch": 1.7296642436829353,
      "grad_norm": 0.39787620306015015,
      "learning_rate": 1.0915822880440308e-05,
      "loss": 0.4568,
      "step": 1250
    },
    {
      "epoch": 1.7365870543440636,
      "grad_norm": 0.37953585386276245,
      "learning_rate": 1.037297730431085e-05,
      "loss": 0.443,
      "step": 1255
    },
    {
      "epoch": 1.7435098650051921,
      "grad_norm": 0.38411709666252136,
      "learning_rate": 9.843237274502282e-06,
      "loss": 0.4734,
      "step": 1260
    },
    {
      "epoch": 1.7504326756663207,
      "grad_norm": 0.40413138270378113,
      "learning_rate": 9.326680251274777e-06,
      "loss": 0.4563,
      "step": 1265
    },
    {
      "epoch": 1.757355486327449,
      "grad_norm": 0.39860308170318604,
      "learning_rate": 8.823381767227667e-06,
      "loss": 0.4668,
      "step": 1270
    },
    {
      "epoch": 1.7642782969885773,
      "grad_norm": 0.37807101011276245,
      "learning_rate": 8.333415416254831e-06,
      "loss": 0.4599,
      "step": 1275
    },
    {
      "epoch": 1.7712011076497056,
      "grad_norm": 0.3738378882408142,
      "learning_rate": 7.856852842783547e-06,
      "loss": 0.4649,
      "step": 1280
    },
    {
      "epoch": 1.7781239183108342,
      "grad_norm": 0.38058996200561523,
      "learning_rate": 7.393763731298387e-06,
      "loss": 0.4811,
      "step": 1285
    },
    {
      "epoch": 1.7850467289719627,
      "grad_norm": 0.3849298059940338,
      "learning_rate": 6.944215796151765e-06,
      "loss": 0.4643,
      "step": 1290
    },
    {
      "epoch": 1.791969539633091,
      "grad_norm": 0.3965122699737549,
      "learning_rate": 6.5082747716625255e-06,
      "loss": 0.4534,
      "step": 1295
    },
    {
      "epoch": 1.7988923502942193,
      "grad_norm": 0.3806658387184143,
      "learning_rate": 6.086004402504098e-06,
      "loss": 0.4668,
      "step": 1300
    },
    {
      "epoch": 1.8058151609553479,
      "grad_norm": 0.3792901039123535,
      "learning_rate": 5.6774664343834495e-06,
      "loss": 0.4648,
      "step": 1305
    },
    {
      "epoch": 1.8127379716164764,
      "grad_norm": 0.37997448444366455,
      "learning_rate": 5.2827206050125585e-06,
      "loss": 0.4771,
      "step": 1310
    },
    {
      "epoch": 1.8196607822776047,
      "grad_norm": 0.3826618492603302,
      "learning_rate": 4.9018246353732755e-06,
      "loss": 0.475,
      "step": 1315
    },
    {
      "epoch": 1.826583592938733,
      "grad_norm": 0.3670499622821808,
      "learning_rate": 4.534834221277262e-06,
      "loss": 0.4569,
      "step": 1320
    },
    {
      "epoch": 1.8335064035998614,
      "grad_norm": 0.3672844469547272,
      "learning_rate": 4.181803025221898e-06,
      "loss": 0.4691,
      "step": 1325
    },
    {
      "epoch": 1.84042921426099,
      "grad_norm": 0.37513473629951477,
      "learning_rate": 3.842782668543599e-06,
      "loss": 0.4564,
      "step": 1330
    },
    {
      "epoch": 1.8473520249221185,
      "grad_norm": 0.3402206301689148,
      "learning_rate": 3.5178227238696347e-06,
      "loss": 0.4712,
      "step": 1335
    },
    {
      "epoch": 1.8542748355832468,
      "grad_norm": 0.35512781143188477,
      "learning_rate": 3.2069707078694057e-06,
      "loss": 0.4505,
      "step": 1340
    },
    {
      "epoch": 1.8611976462443751,
      "grad_norm": 0.3555276095867157,
      "learning_rate": 2.9102720743064527e-06,
      "loss": 0.4526,
      "step": 1345
    },
    {
      "epoch": 1.8681204569055037,
      "grad_norm": 0.3737949728965759,
      "learning_rate": 2.6277702073919997e-06,
      "loss": 0.456,
      "step": 1350
    },
    {
      "epoch": 1.8750432675666322,
      "grad_norm": 0.3693467378616333,
      "learning_rate": 2.3595064154412374e-06,
      "loss": 0.4629,
      "step": 1355
    },
    {
      "epoch": 1.8819660782277605,
      "grad_norm": 0.3651539385318756,
      "learning_rate": 2.1055199248330546e-06,
      "loss": 0.449,
      "step": 1360
    },
    {
      "epoch": 1.8888888888888888,
      "grad_norm": 0.38853177428245544,
      "learning_rate": 1.8658478742742625e-06,
      "loss": 0.4595,
      "step": 1365
    },
    {
      "epoch": 1.8958116995500172,
      "grad_norm": 0.3724125325679779,
      "learning_rate": 1.6405253093690343e-06,
      "loss": 0.4637,
      "step": 1370
    },
    {
      "epoch": 1.9027345102111457,
      "grad_norm": 0.39097484946250916,
      "learning_rate": 1.429585177494419e-06,
      "loss": 0.46,
      "step": 1375
    },
    {
      "epoch": 1.9096573208722742,
      "grad_norm": 0.40443167090415955,
      "learning_rate": 1.2330583229827053e-06,
      "loss": 0.4738,
      "step": 1380
    },
    {
      "epoch": 1.9165801315334026,
      "grad_norm": 0.37939175963401794,
      "learning_rate": 1.0509734826112394e-06,
      "loss": 0.4544,
      "step": 1385
    },
    {
      "epoch": 1.9235029421945309,
      "grad_norm": 0.39131584763526917,
      "learning_rate": 8.833572814004321e-07,
      "loss": 0.4436,
      "step": 1390
    },
    {
      "epoch": 1.9304257528556594,
      "grad_norm": 0.3646048903465271,
      "learning_rate": 7.302342287205943e-07,
      "loss": 0.4543,
      "step": 1395
    },
    {
      "epoch": 1.937348563516788,
      "grad_norm": 0.36286523938179016,
      "learning_rate": 5.916267147080934e-07,
      "loss": 0.4688,
      "step": 1400
    },
    {
      "epoch": 1.9442713741779163,
      "grad_norm": 0.39855965971946716,
      "learning_rate": 4.6755500699138253e-07,
      "loss": 0.4583,
      "step": 1405
    },
    {
      "epoch": 1.9511941848390446,
      "grad_norm": 0.37583374977111816,
      "learning_rate": 3.5803724772740523e-07,
      "loss": 0.4489,
      "step": 1410
    },
    {
      "epoch": 1.958116995500173,
      "grad_norm": 0.3726235330104828,
      "learning_rate": 2.630894509488058e-07,
      "loss": 0.4689,
      "step": 1415
    },
    {
      "epoch": 1.9650398061613015,
      "grad_norm": 0.3750331997871399,
      "learning_rate": 1.8272550022230272e-07,
      "loss": 0.4647,
      "step": 1420
    },
    {
      "epoch": 1.97196261682243,
      "grad_norm": 0.3834379017353058,
      "learning_rate": 1.1695714661856816e-07,
      "loss": 0.4665,
      "step": 1425
    },
    {
      "epoch": 1.9788854274835583,
      "grad_norm": 0.37510913610458374,
      "learning_rate": 6.579400699397998e-08,
      "loss": 0.459,
      "step": 1430
    },
    {
      "epoch": 1.9858082381446867,
      "grad_norm": 0.36773183941841125,
      "learning_rate": 2.9243562584402305e-08,
      "loss": 0.4565,
      "step": 1435
    },
    {
      "epoch": 1.9927310488058152,
      "grad_norm": 0.3669570982456207,
      "learning_rate": 7.311157911249478e-09,
      "loss": 0.4612,
      "step": 1440
    },
    {
      "epoch": 1.9982692973347178,
      "eval_loss": 0.5933529138565063,
      "eval_runtime": 75.4661,
      "eval_samples_per_second": 27.416,
      "eval_steps_per_second": 1.723,
      "step": 1444
    },
    {
      "epoch": 1.9982692973347178,
      "step": 1444,
      "total_flos": 6.774706456143856e+18,
      "train_loss": 0.6556608070957364,
      "train_runtime": 13724.1641,
      "train_samples_per_second": 6.735,
      "train_steps_per_second": 0.105
    }
  ],
  "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": 6.774706456143856e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}