{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7281237810427773,
  "eval_steps": 100,
  "global_step": 700,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005200884150305552,
      "grad_norm": 4.82585334777832,
      "learning_rate": 5.6140350877192985e-06,
      "loss": 0.7676299571990967,
      "step": 5
    },
    {
      "epoch": 0.010401768300611104,
      "grad_norm": 3.292309522628784,
      "learning_rate": 1.263157894736842e-05,
      "loss": 0.631245470046997,
      "step": 10
    },
    {
      "epoch": 0.015602652450916656,
      "grad_norm": 3.0301995277404785,
      "learning_rate": 1.9649122807017544e-05,
      "loss": 0.6749040126800537,
      "step": 15
    },
    {
      "epoch": 0.02080353660122221,
      "grad_norm": 2.853067398071289,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.7889204978942871,
      "step": 20
    },
    {
      "epoch": 0.02600442075152776,
      "grad_norm": 2.4595491886138916,
      "learning_rate": 3.368421052631579e-05,
      "loss": 0.8261689186096192,
      "step": 25
    },
    {
      "epoch": 0.031205304901833313,
      "grad_norm": 3.285839319229126,
      "learning_rate": 4.070175438596492e-05,
      "loss": 0.8855669021606445,
      "step": 30
    },
    {
      "epoch": 0.03640618905213886,
      "grad_norm": 2.9381635189056396,
      "learning_rate": 4.771929824561404e-05,
      "loss": 0.8640634536743164,
      "step": 35
    },
    {
      "epoch": 0.04160707320244442,
      "grad_norm": 2.142974376678467,
      "learning_rate": 5.4736842105263165e-05,
      "loss": 0.8938538551330566,
      "step": 40
    },
    {
      "epoch": 0.046807957352749965,
      "grad_norm": 3.4374115467071533,
      "learning_rate": 6.175438596491228e-05,
      "loss": 0.9762144088745117,
      "step": 45
    },
    {
      "epoch": 0.05200884150305552,
      "grad_norm": 2.2888057231903076,
      "learning_rate": 6.87719298245614e-05,
      "loss": 1.0100465774536134,
      "step": 50
    },
    {
      "epoch": 0.05720972565336107,
      "grad_norm": 2.101193428039551,
      "learning_rate": 7.578947368421052e-05,
      "loss": 1.0064237594604493,
      "step": 55
    },
    {
      "epoch": 0.062410609803666625,
      "grad_norm": 2.3019754886627197,
      "learning_rate": 7.999977348305978e-05,
      "loss": 1.0382986068725586,
      "step": 60
    },
    {
      "epoch": 0.06761149395397217,
      "grad_norm": 2.0822298526763916,
      "learning_rate": 7.999722519694521e-05,
      "loss": 1.1403823852539063,
      "step": 65
    },
    {
      "epoch": 0.07281237810427772,
      "grad_norm": 2.109672784805298,
      "learning_rate": 7.999184565952555e-05,
      "loss": 1.0954228401184083,
      "step": 70
    },
    {
      "epoch": 0.07801326225458328,
      "grad_norm": 1.9484328031539917,
      "learning_rate": 7.998363525159777e-05,
      "loss": 1.125577735900879,
      "step": 75
    },
    {
      "epoch": 0.08321414640488883,
      "grad_norm": 2.0304486751556396,
      "learning_rate": 7.997259455434539e-05,
      "loss": 1.078431987762451,
      "step": 80
    },
    {
      "epoch": 0.08841503055519438,
      "grad_norm": 1.8764644861221313,
      "learning_rate": 7.995872434929734e-05,
      "loss": 1.0825774192810058,
      "step": 85
    },
    {
      "epoch": 0.09361591470549993,
      "grad_norm": 2.521047353744507,
      "learning_rate": 7.994202561827263e-05,
      "loss": 1.0628202438354493,
      "step": 90
    },
    {
      "epoch": 0.0988167988558055,
      "grad_norm": 1.7737245559692383,
      "learning_rate": 7.992249954331088e-05,
      "loss": 1.0672310829162597,
      "step": 95
    },
    {
      "epoch": 0.10401768300611104,
      "grad_norm": 2.0016262531280518,
      "learning_rate": 7.990014750658856e-05,
      "loss": 1.0844260215759278,
      "step": 100
    },
    {
      "epoch": 0.10401768300611104,
      "eval_loss": 1.090377688407898,
      "eval_runtime": 131.495,
      "eval_samples_per_second": 1.947,
      "eval_steps_per_second": 1.947,
      "step": 100
    },
    {
      "epoch": 0.10921856715641659,
      "grad_norm": 2.2041330337524414,
      "learning_rate": 7.987497109032128e-05,
      "loss": 1.095380973815918,
      "step": 105
    },
    {
      "epoch": 0.11441945130672214,
      "grad_norm": 1.7770912647247314,
      "learning_rate": 7.98469720766517e-05,
      "loss": 1.076313304901123,
      "step": 110
    },
    {
      "epoch": 0.11962033545702769,
      "grad_norm": 2.0055956840515137,
      "learning_rate": 7.98161524475234e-05,
      "loss": 1.069803810119629,
      "step": 115
    },
    {
      "epoch": 0.12482121960733325,
      "grad_norm": 1.9808892011642456,
      "learning_rate": 7.978251438454063e-05,
      "loss": 1.062901496887207,
      "step": 120
    },
    {
      "epoch": 0.13002210375763879,
      "grad_norm": 1.7519869804382324,
      "learning_rate": 7.974606026881378e-05,
      "loss": 1.03425931930542,
      "step": 125
    },
    {
      "epoch": 0.13522298790794435,
      "grad_norm": 1.8879916667938232,
      "learning_rate": 7.970679268079092e-05,
      "loss": 1.085061264038086,
      "step": 130
    },
    {
      "epoch": 0.1404238720582499,
      "grad_norm": 1.855212926864624,
      "learning_rate": 7.966471440007514e-05,
      "loss": 1.0653216361999511,
      "step": 135
    },
    {
      "epoch": 0.14562475620855544,
      "grad_norm": 1.9829131364822388,
      "learning_rate": 7.961982840522773e-05,
      "loss": 1.0679091453552245,
      "step": 140
    },
    {
      "epoch": 0.150825640358861,
      "grad_norm": 1.8631235361099243,
      "learning_rate": 7.957213787355738e-05,
      "loss": 1.0336699485778809,
      "step": 145
    },
    {
      "epoch": 0.15602652450916657,
      "grad_norm": 1.7199710607528687,
      "learning_rate": 7.95216461808953e-05,
      "loss": 1.085853385925293,
      "step": 150
    },
    {
      "epoch": 0.1612274086594721,
      "grad_norm": 1.8429338932037354,
      "learning_rate": 7.946835690135617e-05,
      "loss": 1.039409065246582,
      "step": 155
    },
    {
      "epoch": 0.16642829280977767,
      "grad_norm": 1.9319918155670166,
      "learning_rate": 7.941227380708522e-05,
      "loss": 1.0467087745666503,
      "step": 160
    },
    {
      "epoch": 0.1716291769600832,
      "grad_norm": 2.0441744327545166,
      "learning_rate": 7.93534008679912e-05,
      "loss": 1.0675994873046875,
      "step": 165
    },
    {
      "epoch": 0.17683006111038876,
      "grad_norm": 1.847270131111145,
      "learning_rate": 7.929174225146534e-05,
      "loss": 1.0682602882385255,
      "step": 170
    },
    {
      "epoch": 0.18203094526069433,
      "grad_norm": 1.8770182132720947,
      "learning_rate": 7.922730232208637e-05,
      "loss": 1.0655933380126954,
      "step": 175
    },
    {
      "epoch": 0.18723182941099986,
      "grad_norm": 1.9199661016464233,
      "learning_rate": 7.916008564131158e-05,
      "loss": 1.0514616012573241,
      "step": 180
    },
    {
      "epoch": 0.19243271356130542,
      "grad_norm": 1.7040131092071533,
      "learning_rate": 7.909009696715391e-05,
      "loss": 1.0357669830322265,
      "step": 185
    },
    {
      "epoch": 0.197633597711611,
      "grad_norm": 1.7878484725952148,
      "learning_rate": 7.901734125384515e-05,
      "loss": 1.034726905822754,
      "step": 190
    },
    {
      "epoch": 0.20283448186191652,
      "grad_norm": 1.7647621631622314,
      "learning_rate": 7.89418236514853e-05,
      "loss": 1.0258402824401855,
      "step": 195
    },
    {
      "epoch": 0.20803536601222208,
      "grad_norm": 1.7211089134216309,
      "learning_rate": 7.886354950567789e-05,
      "loss": 1.0237075805664062,
      "step": 200
    },
    {
      "epoch": 0.20803536601222208,
      "eval_loss": 1.0211308002471924,
      "eval_runtime": 130.7508,
      "eval_samples_per_second": 1.958,
      "eval_steps_per_second": 1.958,
      "step": 200
    },
    {
      "epoch": 0.21323625016252762,
      "grad_norm": 1.9167125225067139,
      "learning_rate": 7.878252435715178e-05,
      "loss": 1.0424039840698243,
      "step": 205
    },
    {
      "epoch": 0.21843713431283318,
      "grad_norm": 1.6589795351028442,
      "learning_rate": 7.869875394136873e-05,
      "loss": 0.985629940032959,
      "step": 210
    },
    {
      "epoch": 0.22363801846313874,
      "grad_norm": 1.7960469722747803,
      "learning_rate": 7.861224418811757e-05,
      "loss": 1.0503170013427734,
      "step": 215
    },
    {
      "epoch": 0.22883890261344428,
      "grad_norm": 1.876910924911499,
      "learning_rate": 7.852300122109443e-05,
      "loss": 1.0263469696044922,
      "step": 220
    },
    {
      "epoch": 0.23403978676374984,
      "grad_norm": 1.7034902572631836,
      "learning_rate": 7.843103135746916e-05,
      "loss": 1.0396705627441407,
      "step": 225
    },
    {
      "epoch": 0.23924067091405538,
      "grad_norm": 1.7886664867401123,
      "learning_rate": 7.833634110743832e-05,
      "loss": 1.0125335693359374,
      "step": 230
    },
    {
      "epoch": 0.24444155506436094,
      "grad_norm": 1.7878754138946533,
      "learning_rate": 7.823893717376422e-05,
      "loss": 0.9978487968444825,
      "step": 235
    },
    {
      "epoch": 0.2496424392146665,
      "grad_norm": 1.6163357496261597,
      "learning_rate": 7.813882645130049e-05,
      "loss": 1.0093013763427734,
      "step": 240
    },
    {
      "epoch": 0.25484332336497206,
      "grad_norm": 1.7179474830627441,
      "learning_rate": 7.80360160265041e-05,
      "loss": 0.9946321487426758,
      "step": 245
    },
    {
      "epoch": 0.26004420751527757,
      "grad_norm": 1.828262209892273,
      "learning_rate": 7.793051317693359e-05,
      "loss": 1.0461179733276367,
      "step": 250
    },
    {
      "epoch": 0.26524509166558313,
      "grad_norm": 1.837222933769226,
      "learning_rate": 7.782232537073406e-05,
      "loss": 1.0099411964416505,
      "step": 255
    },
    {
      "epoch": 0.2704459758158887,
      "grad_norm": 1.9459391832351685,
      "learning_rate": 7.771146026610844e-05,
      "loss": 0.9811776161193848,
      "step": 260
    },
    {
      "epoch": 0.27564685996619426,
      "grad_norm": 1.8060634136199951,
      "learning_rate": 7.759792571077545e-05,
      "loss": 0.9858491897583008,
      "step": 265
    },
    {
      "epoch": 0.2808477441164998,
      "grad_norm": 1.8257906436920166,
      "learning_rate": 7.748172974141401e-05,
      "loss": 1.0260663032531738,
      "step": 270
    },
    {
      "epoch": 0.2860486282668054,
      "grad_norm": 1.7271229028701782,
      "learning_rate": 7.736288058309448e-05,
      "loss": 1.0253376007080077,
      "step": 275
    },
    {
      "epoch": 0.2912495124171109,
      "grad_norm": 1.6389424800872803,
      "learning_rate": 7.724138664869628e-05,
      "loss": 0.9872174263000488,
      "step": 280
    },
    {
      "epoch": 0.29645039656741645,
      "grad_norm": 1.7230466604232788,
      "learning_rate": 7.711725653831255e-05,
      "loss": 1.0354929924011231,
      "step": 285
    },
    {
      "epoch": 0.301651280717722,
      "grad_norm": 1.7749247550964355,
      "learning_rate": 7.699049903864125e-05,
      "loss": 0.9916903495788574,
      "step": 290
    },
    {
      "epoch": 0.3068521648680276,
      "grad_norm": 1.7340270280838013,
      "learning_rate": 7.68611231223632e-05,
      "loss": 1.0025782585144043,
      "step": 295
    },
    {
      "epoch": 0.31205304901833314,
      "grad_norm": 1.5753134489059448,
      "learning_rate": 7.672913794750699e-05,
      "loss": 0.9782845497131347,
      "step": 300
    },
    {
      "epoch": 0.31205304901833314,
      "eval_loss": 1.01508629322052,
      "eval_runtime": 130.89,
      "eval_samples_per_second": 1.956,
      "eval_steps_per_second": 1.956,
      "step": 300
    },
    {
      "epoch": 0.31725393316863865,
      "grad_norm": 1.6529031991958618,
      "learning_rate": 7.659455285680071e-05,
      "loss": 0.9918001174926758,
      "step": 305
    },
    {
      "epoch": 0.3224548173189442,
      "grad_norm": 1.6655994653701782,
      "learning_rate": 7.645737737701054e-05,
      "loss": 0.9847027778625488,
      "step": 310
    },
    {
      "epoch": 0.32765570146924977,
      "grad_norm": 1.7864056825637817,
      "learning_rate": 7.631762121826653e-05,
      "loss": 0.9591518402099609,
      "step": 315
    },
    {
      "epoch": 0.33285658561955533,
      "grad_norm": 1.7958587408065796,
      "learning_rate": 7.617529427337507e-05,
      "loss": 0.9712434768676758,
      "step": 320
    },
    {
      "epoch": 0.3380574697698609,
      "grad_norm": 1.7462350130081177,
      "learning_rate": 7.603040661711879e-05,
      "loss": 1.0182976722717285,
      "step": 325
    },
    {
      "epoch": 0.3432583539201664,
      "grad_norm": 1.73703932762146,
      "learning_rate": 7.588296850554326e-05,
      "loss": 0.978699779510498,
      "step": 330
    },
    {
      "epoch": 0.34845923807047197,
      "grad_norm": 1.781213402748108,
      "learning_rate": 7.573299037523115e-05,
      "loss": 1.0263344764709472,
      "step": 335
    },
    {
      "epoch": 0.35366012222077753,
      "grad_norm": 1.7940926551818848,
      "learning_rate": 7.558048284256334e-05,
      "loss": 1.039241409301758,
      "step": 340
    },
    {
      "epoch": 0.3588610063710831,
      "grad_norm": 1.725530982017517,
      "learning_rate": 7.542545670296747e-05,
      "loss": 0.9716745376586914,
      "step": 345
    },
    {
      "epoch": 0.36406189052138865,
      "grad_norm": 1.665209174156189,
      "learning_rate": 7.526792293015382e-05,
      "loss": 0.9396204948425293,
      "step": 350
    },
    {
      "epoch": 0.36926277467169416,
      "grad_norm": 1.8031824827194214,
      "learning_rate": 7.51078926753384e-05,
      "loss": 0.9682992935180664,
      "step": 355
    },
    {
      "epoch": 0.3744636588219997,
      "grad_norm": 1.7742233276367188,
      "learning_rate": 7.494537726645375e-05,
      "loss": 0.9833150863647461,
      "step": 360
    },
    {
      "epoch": 0.3796645429723053,
      "grad_norm": 1.7864766120910645,
      "learning_rate": 7.478038820734698e-05,
      "loss": 0.9690051078796387,
      "step": 365
    },
    {
      "epoch": 0.38486542712261085,
      "grad_norm": 1.7735403776168823,
      "learning_rate": 7.461293717696549e-05,
      "loss": 0.9864785194396972,
      "step": 370
    },
    {
      "epoch": 0.3900663112729164,
      "grad_norm": 1.6049963235855103,
      "learning_rate": 7.444303602853024e-05,
      "loss": 0.9804511070251465,
      "step": 375
    },
    {
      "epoch": 0.395267195423222,
      "grad_norm": 1.6558054685592651,
      "learning_rate": 7.427069678869672e-05,
      "loss": 0.9362913131713867,
      "step": 380
    },
    {
      "epoch": 0.4004680795735275,
      "grad_norm": 1.6555157899856567,
      "learning_rate": 7.409593165670364e-05,
      "loss": 0.948128604888916,
      "step": 385
    },
    {
      "epoch": 0.40566896372383304,
      "grad_norm": 1.812888741493225,
      "learning_rate": 7.391875300350937e-05,
      "loss": 0.9553811073303222,
      "step": 390
    },
    {
      "epoch": 0.4108698478741386,
      "grad_norm": 1.6602718830108643,
      "learning_rate": 7.373917337091626e-05,
      "loss": 0.940127944946289,
      "step": 395
    },
    {
      "epoch": 0.41607073202444417,
      "grad_norm": 1.7474323511123657,
      "learning_rate": 7.355720547068288e-05,
      "loss": 0.9683933258056641,
      "step": 400
    },
    {
      "epoch": 0.41607073202444417,
      "eval_loss": 0.9856516122817993,
      "eval_runtime": 130.2348,
      "eval_samples_per_second": 1.966,
      "eval_steps_per_second": 1.966,
      "step": 400
    },
    {
      "epoch": 0.42127161617474973,
      "grad_norm": 1.7211471796035767,
      "learning_rate": 7.337286218362413e-05,
      "loss": 0.9713785171508789,
      "step": 405
    },
    {
      "epoch": 0.42647250032505524,
      "grad_norm": 1.839705467224121,
      "learning_rate": 7.31861565586995e-05,
      "loss": 0.9828580856323242,
      "step": 410
    },
    {
      "epoch": 0.4316733844753608,
      "grad_norm": 1.6094111204147339,
      "learning_rate": 7.299710181208943e-05,
      "loss": 0.9652169227600098,
      "step": 415
    },
    {
      "epoch": 0.43687426862566636,
      "grad_norm": 1.8238450288772583,
      "learning_rate": 7.280571132625971e-05,
      "loss": 0.9175550460815429,
      "step": 420
    },
    {
      "epoch": 0.4420751527759719,
      "grad_norm": 1.7738935947418213,
      "learning_rate": 7.261199864901423e-05,
      "loss": 0.959293270111084,
      "step": 425
    },
    {
      "epoch": 0.4472760369262775,
      "grad_norm": 1.7823359966278076,
      "learning_rate": 7.241597749253593e-05,
      "loss": 0.9460945129394531,
      "step": 430
    },
    {
      "epoch": 0.452476921076583,
      "grad_norm": 1.852073073387146,
      "learning_rate": 7.221766173241629e-05,
      "loss": 0.9572076797485352,
      "step": 435
    },
    {
      "epoch": 0.45767780522688856,
      "grad_norm": 1.7884498834609985,
      "learning_rate": 7.201706540667293e-05,
      "loss": 0.980253028869629,
      "step": 440
    },
    {
      "epoch": 0.4628786893771941,
      "grad_norm": 1.6045715808868408,
      "learning_rate": 7.181420271475616e-05,
      "loss": 0.9448029518127441,
      "step": 445
    },
    {
      "epoch": 0.4680795735274997,
      "grad_norm": 1.703908920288086,
      "learning_rate": 7.160908801654358e-05,
      "loss": 0.9464167594909668,
      "step": 450
    },
    {
      "epoch": 0.47328045767780524,
      "grad_norm": 1.5748329162597656,
      "learning_rate": 7.14017358313239e-05,
      "loss": 0.9481819152832032,
      "step": 455
    },
    {
      "epoch": 0.47848134182811075,
      "grad_norm": 1.62021803855896,
      "learning_rate": 7.11921608367689e-05,
      "loss": 0.9535123825073242,
      "step": 460
    },
    {
      "epoch": 0.4836822259784163,
      "grad_norm": 1.6786726713180542,
      "learning_rate": 7.09803778678946e-05,
      "loss": 0.9362807273864746,
      "step": 465
    },
    {
      "epoch": 0.4888831101287219,
      "grad_norm": 1.602408528327942,
      "learning_rate": 7.076640191601113e-05,
      "loss": 0.9352068901062012,
      "step": 470
    },
    {
      "epoch": 0.49408399427902744,
      "grad_norm": 1.710305094718933,
      "learning_rate": 7.055024812766153e-05,
      "loss": 0.9479847908020019,
      "step": 475
    },
    {
      "epoch": 0.499284878429333,
      "grad_norm": 1.7393652200698853,
      "learning_rate": 7.03319318035496e-05,
      "loss": 0.9210905075073242,
      "step": 480
    },
    {
      "epoch": 0.5044857625796385,
      "grad_norm": 1.6267069578170776,
      "learning_rate": 7.011146839745681e-05,
      "loss": 0.935267448425293,
      "step": 485
    },
    {
      "epoch": 0.5096866467299441,
      "grad_norm": 1.5649526119232178,
      "learning_rate": 6.98888735151484e-05,
      "loss": 0.950043773651123,
      "step": 490
    },
    {
      "epoch": 0.5148875308802496,
      "grad_norm": 1.7210514545440674,
      "learning_rate": 6.966416291326867e-05,
      "loss": 0.9338683128356934,
      "step": 495
    },
    {
      "epoch": 0.5200884150305551,
      "grad_norm": 1.7836523056030273,
      "learning_rate": 6.943735249822567e-05,
      "loss": 0.9206833839416504,
      "step": 500
    },
    {
      "epoch": 0.5200884150305551,
      "eval_loss": 0.9551063776016235,
      "eval_runtime": 130.2472,
      "eval_samples_per_second": 1.965,
      "eval_steps_per_second": 1.965,
      "step": 500
    },
    {
      "epoch": 0.5252892991808608,
      "grad_norm": 1.6640737056732178,
      "learning_rate": 6.920845832506523e-05,
      "loss": 0.9343124389648437,
      "step": 505
    },
    {
      "epoch": 0.5304901833311663,
      "grad_norm": 1.5780658721923828,
      "learning_rate": 6.897749659633448e-05,
      "loss": 0.9712604522705078,
      "step": 510
    },
    {
      "epoch": 0.5356910674814719,
      "grad_norm": 1.6826986074447632,
      "learning_rate": 6.874448366093497e-05,
      "loss": 0.9570392608642578,
      "step": 515
    },
    {
      "epoch": 0.5408919516317774,
      "grad_norm": 1.6517504453659058,
      "learning_rate": 6.850943601296529e-05,
      "loss": 0.9325905799865722,
      "step": 520
    },
    {
      "epoch": 0.546092835782083,
      "grad_norm": 1.8107248544692993,
      "learning_rate": 6.827237029055364e-05,
      "loss": 0.9377958297729492,
      "step": 525
    },
    {
      "epoch": 0.5512937199323885,
      "grad_norm": 1.6924495697021484,
      "learning_rate": 6.803330327468006e-05,
      "loss": 0.9227448463439941,
      "step": 530
    },
    {
      "epoch": 0.556494604082694,
      "grad_norm": 1.6941320896148682,
      "learning_rate": 6.779225188798846e-05,
      "loss": 0.9221724510192871,
      "step": 535
    },
    {
      "epoch": 0.5616954882329996,
      "grad_norm": 1.605466604232788,
      "learning_rate": 6.754923319358883e-05,
      "loss": 0.9474879264831543,
      "step": 540
    },
    {
      "epoch": 0.5668963723833051,
      "grad_norm": 1.6994117498397827,
      "learning_rate": 6.730426439384939e-05,
      "loss": 0.9544130325317383,
      "step": 545
    },
    {
      "epoch": 0.5720972565336108,
      "grad_norm": 1.6269444227218628,
      "learning_rate": 6.705736282917892e-05,
      "loss": 0.8944686889648438,
      "step": 550
    },
    {
      "epoch": 0.5772981406839163,
      "grad_norm": 1.7221931219100952,
      "learning_rate": 6.680854597679924e-05,
      "loss": 0.9075075149536133,
      "step": 555
    },
    {
      "epoch": 0.5824990248342218,
      "grad_norm": 1.7379156351089478,
      "learning_rate": 6.655783144950809e-05,
      "loss": 0.9554330825805664,
      "step": 560
    },
    {
      "epoch": 0.5876999089845274,
      "grad_norm": 1.7438715696334839,
      "learning_rate": 6.63052369944324e-05,
      "loss": 0.9195778846740723,
      "step": 565
    },
    {
      "epoch": 0.5929007931348329,
      "grad_norm": 1.6393606662750244,
      "learning_rate": 6.605078049177205e-05,
      "loss": 0.915708065032959,
      "step": 570
    },
    {
      "epoch": 0.5981016772851385,
      "grad_norm": 1.7054882049560547,
      "learning_rate": 6.579447995353416e-05,
      "loss": 0.9384199142456054,
      "step": 575
    },
    {
      "epoch": 0.603302561435444,
      "grad_norm": 1.5726091861724854,
      "learning_rate": 6.553635352225812e-05,
      "loss": 0.9182180404663086,
      "step": 580
    },
    {
      "epoch": 0.6085034455857495,
      "grad_norm": 1.827543020248413,
      "learning_rate": 6.52764194697313e-05,
      "loss": 0.9172782897949219,
      "step": 585
    },
    {
      "epoch": 0.6137043297360552,
      "grad_norm": 1.541303038597107,
      "learning_rate": 6.501469619569579e-05,
      "loss": 0.9366864204406739,
      "step": 590
    },
    {
      "epoch": 0.6189052138863607,
      "grad_norm": 1.6896532773971558,
      "learning_rate": 6.475120222654573e-05,
      "loss": 0.91693115234375,
      "step": 595
    },
    {
      "epoch": 0.6241060980366663,
      "grad_norm": 1.8263614177703857,
      "learning_rate": 6.448595621401615e-05,
      "loss": 0.9207332611083985,
      "step": 600
    },
    {
      "epoch": 0.6241060980366663,
      "eval_loss": 0.9301373958587646,
      "eval_runtime": 129.9867,
      "eval_samples_per_second": 1.969,
      "eval_steps_per_second": 1.969,
      "step": 600
    },
    {
      "epoch": 0.6293069821869718,
      "grad_norm": 2.5737788677215576,
      "learning_rate": 6.421897693386245e-05,
      "loss": 1.8008251190185547,
      "step": 605
    },
    {
      "epoch": 0.6345078663372773,
      "grad_norm": 2.3786563873291016,
      "learning_rate": 6.395028328453154e-05,
      "loss": 1.0148398399353027,
      "step": 610
    },
    {
      "epoch": 0.6397087504875829,
      "grad_norm": 2.1619725227355957,
      "learning_rate": 6.367989428582395e-05,
      "loss": 0.9035258293151855,
      "step": 615
    },
    {
      "epoch": 0.6449096346378884,
      "grad_norm": 1.8177882432937622,
      "learning_rate": 6.340782907754754e-05,
      "loss": 0.9431497573852539,
      "step": 620
    },
    {
      "epoch": 0.650110518788194,
      "grad_norm": 2.0389435291290283,
      "learning_rate": 6.313410691816269e-05,
      "loss": 0.9617778778076171,
      "step": 625
    },
    {
      "epoch": 0.6553114029384995,
      "grad_norm": 1.8454713821411133,
      "learning_rate": 6.285874718341898e-05,
      "loss": 0.9618912696838379,
      "step": 630
    },
    {
      "epoch": 0.660512287088805,
      "grad_norm": 1.9317169189453125,
      "learning_rate": 6.25817693649838e-05,
      "loss": 1.020989227294922,
      "step": 635
    },
    {
      "epoch": 0.6657131712391107,
      "grad_norm": 2.249952554702759,
      "learning_rate": 6.230319306906246e-05,
      "loss": 1.0368837356567382,
      "step": 640
    },
    {
      "epoch": 0.6709140553894162,
      "grad_norm": 1.8525416851043701,
      "learning_rate": 6.202303801501045e-05,
      "loss": 0.9958114624023438,
      "step": 645
    },
    {
      "epoch": 0.6761149395397218,
      "grad_norm": 1.99785578250885,
      "learning_rate": 6.174132403393749e-05,
      "loss": 1.0103933334350585,
      "step": 650
    },
    {
      "epoch": 0.6813158236900273,
      "grad_norm": 2.1036858558654785,
      "learning_rate": 6.145807106730384e-05,
      "loss": 1.009110927581787,
      "step": 655
    },
    {
      "epoch": 0.6865167078403328,
      "grad_norm": 1.8276114463806152,
      "learning_rate": 6.11732991655087e-05,
      "loss": 1.0265812873840332,
      "step": 660
    },
    {
      "epoch": 0.6917175919906384,
      "grad_norm": 1.8524454832077026,
      "learning_rate": 6.088702848647087e-05,
      "loss": 1.0076023101806642,
      "step": 665
    },
    {
      "epoch": 0.6969184761409439,
      "grad_norm": 2.044529914855957,
      "learning_rate": 6.059927929420191e-05,
      "loss": 1.0623496055603028,
      "step": 670
    },
    {
      "epoch": 0.7021193602912496,
      "grad_norm": 1.9014661312103271,
      "learning_rate": 6.031007195737173e-05,
      "loss": 1.0505518913269043,
      "step": 675
    },
    {
      "epoch": 0.7073202444415551,
      "grad_norm": 1.7579931020736694,
      "learning_rate": 6.0019426947866685e-05,
      "loss": 1.0260109901428223,
      "step": 680
    },
    {
      "epoch": 0.7125211285918606,
      "grad_norm": 1.9789166450500488,
      "learning_rate": 5.972736483934053e-05,
      "loss": 1.0057721138000488,
      "step": 685
    },
    {
      "epoch": 0.7177220127421662,
      "grad_norm": 1.7603486776351929,
      "learning_rate": 5.943390630575808e-05,
      "loss": 0.9560928344726562,
      "step": 690
    },
    {
      "epoch": 0.7229228968924717,
      "grad_norm": 1.723509669303894,
      "learning_rate": 5.9139072119931735e-05,
      "loss": 1.0287532806396484,
      "step": 695
    },
    {
      "epoch": 0.7281237810427773,
      "grad_norm": 1.880836844444275,
      "learning_rate": 5.884288315205113e-05,
      "loss": 1.0159936904907227,
      "step": 700
    },
    {
      "epoch": 0.7281237810427773,
      "eval_loss": 1.0172600746154785,
      "eval_runtime": 130.5328,
      "eval_samples_per_second": 1.961,
      "eval_steps_per_second": 1.961,
      "step": 700
    }
  ],
  "logging_steps": 5,
  "max_steps": 1924,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.9001517131076895e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}