{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 100.0,
  "eval_steps": 500,
  "global_step": 182300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.27427317608337903,
      "grad_norm": 2.1429903507232666,
      "learning_rate": 4.986286341195831e-05,
      "loss": 7.2532,
      "step": 500
    },
    {
      "epoch": 0.5485463521667581,
      "grad_norm": 2.0887398719787598,
      "learning_rate": 4.972572682391663e-05,
      "loss": 6.4724,
      "step": 1000
    },
    {
      "epoch": 0.8228195282501372,
      "grad_norm": 2.1614580154418945,
      "learning_rate": 4.958859023587493e-05,
      "loss": 6.0973,
      "step": 1500
    },
    {
      "epoch": 1.0970927043335161,
      "grad_norm": 2.202652931213379,
      "learning_rate": 4.9451453647833245e-05,
      "loss": 5.7872,
      "step": 2000
    },
    {
      "epoch": 1.3713658804168953,
      "grad_norm": 2.147414445877075,
      "learning_rate": 4.931431705979155e-05,
      "loss": 5.5399,
      "step": 2500
    },
    {
      "epoch": 1.6456390565002743,
      "grad_norm": 2.1624412536621094,
      "learning_rate": 4.917718047174987e-05,
      "loss": 5.3515,
      "step": 3000
    },
    {
      "epoch": 1.9199122325836533,
      "grad_norm": 2.155363082885742,
      "learning_rate": 4.9040043883708175e-05,
      "loss": 5.1762,
      "step": 3500
    },
    {
      "epoch": 2.1941854086670323,
      "grad_norm": 2.2420756816864014,
      "learning_rate": 4.890290729566648e-05,
      "loss": 5.0364,
      "step": 4000
    },
    {
      "epoch": 2.4684585847504112,
      "grad_norm": 2.4155259132385254,
      "learning_rate": 4.87657707076248e-05,
      "loss": 4.9178,
      "step": 4500
    },
    {
      "epoch": 2.7427317608337907,
      "grad_norm": 2.2149574756622314,
      "learning_rate": 4.8628634119583105e-05,
      "loss": 4.8449,
      "step": 5000
    },
    {
      "epoch": 3.0170049369171696,
      "grad_norm": 2.25925350189209,
      "learning_rate": 4.849149753154142e-05,
      "loss": 4.762,
      "step": 5500
    },
    {
      "epoch": 3.2912781130005486,
      "grad_norm": 2.315990686416626,
      "learning_rate": 4.835436094349973e-05,
      "loss": 4.6713,
      "step": 6000
    },
    {
      "epoch": 3.5655512890839276,
      "grad_norm": 2.425288677215576,
      "learning_rate": 4.821722435545804e-05,
      "loss": 4.6267,
      "step": 6500
    },
    {
      "epoch": 3.8398244651673066,
      "grad_norm": 2.3451356887817383,
      "learning_rate": 4.808008776741635e-05,
      "loss": 4.579,
      "step": 7000
    },
    {
      "epoch": 4.1140976412506856,
      "grad_norm": 2.306058645248413,
      "learning_rate": 4.794295117937466e-05,
      "loss": 4.5148,
      "step": 7500
    },
    {
      "epoch": 4.3883708173340645,
      "grad_norm": 2.3386404514312744,
      "learning_rate": 4.780581459133297e-05,
      "loss": 4.4659,
      "step": 8000
    },
    {
      "epoch": 4.6626439934174435,
      "grad_norm": 2.3117551803588867,
      "learning_rate": 4.766867800329128e-05,
      "loss": 4.4327,
      "step": 8500
    },
    {
      "epoch": 4.9369171695008225,
      "grad_norm": 2.36466908454895,
      "learning_rate": 4.753154141524959e-05,
      "loss": 4.3947,
      "step": 9000
    },
    {
      "epoch": 5.2111903455842015,
      "grad_norm": 2.348733901977539,
      "learning_rate": 4.73944048272079e-05,
      "loss": 4.3441,
      "step": 9500
    },
    {
      "epoch": 5.485463521667581,
      "grad_norm": 2.9133706092834473,
      "learning_rate": 4.7257268239166215e-05,
      "loss": 4.3025,
      "step": 10000
    },
    {
      "epoch": 5.75973669775096,
      "grad_norm": 2.6369545459747314,
      "learning_rate": 4.712013165112452e-05,
      "loss": 4.2785,
      "step": 10500
    },
    {
      "epoch": 6.034009873834339,
      "grad_norm": 2.7040719985961914,
      "learning_rate": 4.698299506308283e-05,
      "loss": 4.2431,
      "step": 11000
    },
    {
      "epoch": 6.308283049917718,
      "grad_norm": 2.7137389183044434,
      "learning_rate": 4.6845858475041146e-05,
      "loss": 4.1796,
      "step": 11500
    },
    {
      "epoch": 6.582556226001097,
      "grad_norm": 2.963534355163574,
      "learning_rate": 4.670872188699945e-05,
      "loss": 4.1432,
      "step": 12000
    },
    {
      "epoch": 6.856829402084476,
      "grad_norm": 2.8243420124053955,
      "learning_rate": 4.6571585298957763e-05,
      "loss": 4.1252,
      "step": 12500
    },
    {
      "epoch": 7.131102578167855,
      "grad_norm": 3.03757905960083,
      "learning_rate": 4.6434448710916076e-05,
      "loss": 4.0713,
      "step": 13000
    },
    {
      "epoch": 7.405375754251234,
      "grad_norm": 3.007908821105957,
      "learning_rate": 4.629731212287439e-05,
      "loss": 4.0248,
      "step": 13500
    },
    {
      "epoch": 7.679648930334613,
      "grad_norm": 2.846788167953491,
      "learning_rate": 4.6160175534832694e-05,
      "loss": 4.0099,
      "step": 14000
    },
    {
      "epoch": 7.953922106417992,
      "grad_norm": 2.961183786392212,
      "learning_rate": 4.6023038946791006e-05,
      "loss": 3.9728,
      "step": 14500
    },
    {
      "epoch": 8.228195282501371,
      "grad_norm": 3.066025733947754,
      "learning_rate": 4.588590235874932e-05,
      "loss": 3.9118,
      "step": 15000
    },
    {
      "epoch": 8.502468458584751,
      "grad_norm": 2.9394822120666504,
      "learning_rate": 4.5748765770707624e-05,
      "loss": 3.8828,
      "step": 15500
    },
    {
      "epoch": 8.776741634668129,
      "grad_norm": 3.012153387069702,
      "learning_rate": 4.5611629182665936e-05,
      "loss": 3.8832,
      "step": 16000
    },
    {
      "epoch": 9.051014810751509,
      "grad_norm": 2.899332046508789,
      "learning_rate": 4.547449259462425e-05,
      "loss": 3.8481,
      "step": 16500
    },
    {
      "epoch": 9.325287986834887,
      "grad_norm": 3.164444923400879,
      "learning_rate": 4.533735600658256e-05,
      "loss": 3.7773,
      "step": 17000
    },
    {
      "epoch": 9.599561162918267,
      "grad_norm": 3.017282009124756,
      "learning_rate": 4.5200219418540867e-05,
      "loss": 3.7689,
      "step": 17500
    },
    {
      "epoch": 9.873834339001645,
      "grad_norm": 3.367647647857666,
      "learning_rate": 4.506308283049918e-05,
      "loss": 3.752,
      "step": 18000
    },
    {
      "epoch": 10.148107515085025,
      "grad_norm": 2.9855947494506836,
      "learning_rate": 4.492594624245749e-05,
      "loss": 3.7182,
      "step": 18500
    },
    {
      "epoch": 10.422380691168403,
      "grad_norm": 3.505870819091797,
      "learning_rate": 4.47888096544158e-05,
      "loss": 3.674,
      "step": 19000
    },
    {
      "epoch": 10.696653867251783,
      "grad_norm": 3.438145160675049,
      "learning_rate": 4.465167306637411e-05,
      "loss": 3.651,
      "step": 19500
    },
    {
      "epoch": 10.970927043335163,
      "grad_norm": 3.0687413215637207,
      "learning_rate": 4.451453647833242e-05,
      "loss": 3.6479,
      "step": 20000
    },
    {
      "epoch": 11.24520021941854,
      "grad_norm": 3.2287588119506836,
      "learning_rate": 4.4377399890290734e-05,
      "loss": 3.5693,
      "step": 20500
    },
    {
      "epoch": 11.51947339550192,
      "grad_norm": 3.3848471641540527,
      "learning_rate": 4.424026330224904e-05,
      "loss": 3.5667,
      "step": 21000
    },
    {
      "epoch": 11.793746571585299,
      "grad_norm": 3.5464422702789307,
      "learning_rate": 4.410312671420735e-05,
      "loss": 3.5589,
      "step": 21500
    },
    {
      "epoch": 12.068019747668679,
      "grad_norm": 3.6160085201263428,
      "learning_rate": 4.3965990126165664e-05,
      "loss": 3.5313,
      "step": 22000
    },
    {
      "epoch": 12.342292923752057,
      "grad_norm": 3.6420817375183105,
      "learning_rate": 4.3828853538123976e-05,
      "loss": 3.4855,
      "step": 22500
    },
    {
      "epoch": 12.616566099835437,
      "grad_norm": 3.583449363708496,
      "learning_rate": 4.369171695008228e-05,
      "loss": 3.4654,
      "step": 23000
    },
    {
      "epoch": 12.890839275918815,
      "grad_norm": 3.5506091117858887,
      "learning_rate": 4.3554580362040594e-05,
      "loss": 3.4512,
      "step": 23500
    },
    {
      "epoch": 13.165112452002194,
      "grad_norm": 4.101990699768066,
      "learning_rate": 4.341744377399891e-05,
      "loss": 3.4055,
      "step": 24000
    },
    {
      "epoch": 13.439385628085573,
      "grad_norm": 4.144250392913818,
      "learning_rate": 4.328030718595721e-05,
      "loss": 3.3755,
      "step": 24500
    },
    {
      "epoch": 13.713658804168952,
      "grad_norm": 3.6288070678710938,
      "learning_rate": 4.3143170597915525e-05,
      "loss": 3.3725,
      "step": 25000
    },
    {
      "epoch": 13.98793198025233,
      "grad_norm": 3.5927882194519043,
      "learning_rate": 4.300603400987384e-05,
      "loss": 3.3693,
      "step": 25500
    },
    {
      "epoch": 14.26220515633571,
      "grad_norm": 3.405404567718506,
      "learning_rate": 4.286889742183215e-05,
      "loss": 3.2955,
      "step": 26000
    },
    {
      "epoch": 14.53647833241909,
      "grad_norm": 4.086198329925537,
      "learning_rate": 4.2731760833790455e-05,
      "loss": 3.3038,
      "step": 26500
    },
    {
      "epoch": 14.810751508502468,
      "grad_norm": 3.3961052894592285,
      "learning_rate": 4.259462424574877e-05,
      "loss": 3.2561,
      "step": 27000
    },
    {
      "epoch": 15.085024684585848,
      "grad_norm": 3.6080105304718018,
      "learning_rate": 4.245748765770708e-05,
      "loss": 3.2539,
      "step": 27500
    },
    {
      "epoch": 15.359297860669226,
      "grad_norm": 3.597956657409668,
      "learning_rate": 4.2320351069665385e-05,
      "loss": 3.2148,
      "step": 28000
    },
    {
      "epoch": 15.633571036752606,
      "grad_norm": 3.466057062149048,
      "learning_rate": 4.21832144816237e-05,
      "loss": 3.2031,
      "step": 28500
    },
    {
      "epoch": 15.907844212835984,
      "grad_norm": 4.239918231964111,
      "learning_rate": 4.204607789358201e-05,
      "loss": 3.1768,
      "step": 29000
    },
    {
      "epoch": 16.182117388919362,
      "grad_norm": 4.533541202545166,
      "learning_rate": 4.190894130554032e-05,
      "loss": 3.1258,
      "step": 29500
    },
    {
      "epoch": 16.456390565002742,
      "grad_norm": 3.8643674850463867,
      "learning_rate": 4.177180471749863e-05,
      "loss": 3.1162,
      "step": 30000
    },
    {
      "epoch": 16.730663741086122,
      "grad_norm": 3.710988998413086,
      "learning_rate": 4.163466812945694e-05,
      "loss": 3.1159,
      "step": 30500
    },
    {
      "epoch": 17.004936917169502,
      "grad_norm": 3.6405742168426514,
      "learning_rate": 4.149753154141525e-05,
      "loss": 3.1137,
      "step": 31000
    },
    {
      "epoch": 17.27921009325288,
      "grad_norm": 4.127532482147217,
      "learning_rate": 4.136039495337356e-05,
      "loss": 3.0327,
      "step": 31500
    },
    {
      "epoch": 17.553483269336258,
      "grad_norm": 3.6551403999328613,
      "learning_rate": 4.122325836533188e-05,
      "loss": 3.0611,
      "step": 32000
    },
    {
      "epoch": 17.827756445419638,
      "grad_norm": 3.6437666416168213,
      "learning_rate": 4.108612177729018e-05,
      "loss": 3.0233,
      "step": 32500
    },
    {
      "epoch": 18.102029621503018,
      "grad_norm": 4.008886814117432,
      "learning_rate": 4.0948985189248495e-05,
      "loss": 3.0099,
      "step": 33000
    },
    {
      "epoch": 18.376302797586398,
      "grad_norm": 3.779545783996582,
      "learning_rate": 4.08118486012068e-05,
      "loss": 2.9663,
      "step": 33500
    },
    {
      "epoch": 18.650575973669774,
      "grad_norm": 3.7845826148986816,
      "learning_rate": 4.067471201316512e-05,
      "loss": 2.9628,
      "step": 34000
    },
    {
      "epoch": 18.924849149753154,
      "grad_norm": 3.866852283477783,
      "learning_rate": 4.0537575425123425e-05,
      "loss": 2.9649,
      "step": 34500
    },
    {
      "epoch": 19.199122325836534,
      "grad_norm": 3.9092442989349365,
      "learning_rate": 4.040043883708173e-05,
      "loss": 2.9199,
      "step": 35000
    },
    {
      "epoch": 19.473395501919914,
      "grad_norm": 4.038732528686523,
      "learning_rate": 4.026330224904005e-05,
      "loss": 2.9078,
      "step": 35500
    },
    {
      "epoch": 19.74766867800329,
      "grad_norm": 3.717470645904541,
      "learning_rate": 4.0126165660998355e-05,
      "loss": 2.8907,
      "step": 36000
    },
    {
      "epoch": 20.02194185408667,
      "grad_norm": 3.9166011810302734,
      "learning_rate": 3.998902907295667e-05,
      "loss": 2.8892,
      "step": 36500
    },
    {
      "epoch": 20.29621503017005,
      "grad_norm": 3.9473681449890137,
      "learning_rate": 3.985189248491497e-05,
      "loss": 2.8274,
      "step": 37000
    },
    {
      "epoch": 20.57048820625343,
      "grad_norm": 4.139565467834473,
      "learning_rate": 3.971475589687329e-05,
      "loss": 2.8371,
      "step": 37500
    },
    {
      "epoch": 20.844761382336806,
      "grad_norm": 3.7124762535095215,
      "learning_rate": 3.95776193088316e-05,
      "loss": 2.8401,
      "step": 38000
    },
    {
      "epoch": 21.119034558420186,
      "grad_norm": 3.772149085998535,
      "learning_rate": 3.9440482720789904e-05,
      "loss": 2.8083,
      "step": 38500
    },
    {
      "epoch": 21.393307734503566,
      "grad_norm": 4.185425758361816,
      "learning_rate": 3.930334613274822e-05,
      "loss": 2.7767,
      "step": 39000
    },
    {
      "epoch": 21.667580910586945,
      "grad_norm": 3.800649881362915,
      "learning_rate": 3.916620954470653e-05,
      "loss": 2.7723,
      "step": 39500
    },
    {
      "epoch": 21.941854086670325,
      "grad_norm": 3.800741195678711,
      "learning_rate": 3.902907295666484e-05,
      "loss": 2.774,
      "step": 40000
    },
    {
      "epoch": 22.2161272627537,
      "grad_norm": 3.7834713459014893,
      "learning_rate": 3.889193636862315e-05,
      "loss": 2.7329,
      "step": 40500
    },
    {
      "epoch": 22.49040043883708,
      "grad_norm": 4.18643045425415,
      "learning_rate": 3.8754799780581465e-05,
      "loss": 2.7181,
      "step": 41000
    },
    {
      "epoch": 22.76467361492046,
      "grad_norm": 3.758415460586548,
      "learning_rate": 3.861766319253977e-05,
      "loss": 2.7148,
      "step": 41500
    },
    {
      "epoch": 23.03894679100384,
      "grad_norm": 4.028139114379883,
      "learning_rate": 3.8480526604498076e-05,
      "loss": 2.7025,
      "step": 42000
    },
    {
      "epoch": 23.313219967087218,
      "grad_norm": 3.779428243637085,
      "learning_rate": 3.8343390016456395e-05,
      "loss": 2.6542,
      "step": 42500
    },
    {
      "epoch": 23.587493143170597,
      "grad_norm": 3.6896047592163086,
      "learning_rate": 3.82062534284147e-05,
      "loss": 2.6662,
      "step": 43000
    },
    {
      "epoch": 23.861766319253977,
      "grad_norm": 3.527114152908325,
      "learning_rate": 3.806911684037301e-05,
      "loss": 2.6697,
      "step": 43500
    },
    {
      "epoch": 24.136039495337357,
      "grad_norm": 3.832408905029297,
      "learning_rate": 3.7931980252331326e-05,
      "loss": 2.6443,
      "step": 44000
    },
    {
      "epoch": 24.410312671420733,
      "grad_norm": 3.912022352218628,
      "learning_rate": 3.779484366428964e-05,
      "loss": 2.6098,
      "step": 44500
    },
    {
      "epoch": 24.684585847504113,
      "grad_norm": 3.832465648651123,
      "learning_rate": 3.7657707076247944e-05,
      "loss": 2.6187,
      "step": 45000
    },
    {
      "epoch": 24.958859023587493,
      "grad_norm": 4.292030334472656,
      "learning_rate": 3.752057048820625e-05,
      "loss": 2.6216,
      "step": 45500
    },
    {
      "epoch": 25.233132199670873,
      "grad_norm": 3.9441139698028564,
      "learning_rate": 3.738343390016457e-05,
      "loss": 2.5674,
      "step": 46000
    },
    {
      "epoch": 25.507405375754253,
      "grad_norm": 3.8073363304138184,
      "learning_rate": 3.7246297312122874e-05,
      "loss": 2.5613,
      "step": 46500
    },
    {
      "epoch": 25.78167855183763,
      "grad_norm": 3.95381498336792,
      "learning_rate": 3.7109160724081186e-05,
      "loss": 2.5744,
      "step": 47000
    },
    {
      "epoch": 26.05595172792101,
      "grad_norm": 4.265843391418457,
      "learning_rate": 3.69720241360395e-05,
      "loss": 2.5581,
      "step": 47500
    },
    {
      "epoch": 26.33022490400439,
      "grad_norm": 3.7907886505126953,
      "learning_rate": 3.683488754799781e-05,
      "loss": 2.5085,
      "step": 48000
    },
    {
      "epoch": 26.60449808008777,
      "grad_norm": 3.9580938816070557,
      "learning_rate": 3.6697750959956116e-05,
      "loss": 2.5244,
      "step": 48500
    },
    {
      "epoch": 26.878771256171145,
      "grad_norm": 3.725271701812744,
      "learning_rate": 3.656061437191443e-05,
      "loss": 2.5283,
      "step": 49000
    },
    {
      "epoch": 27.153044432254525,
      "grad_norm": 4.27789831161499,
      "learning_rate": 3.642347778387274e-05,
      "loss": 2.4978,
      "step": 49500
    },
    {
      "epoch": 27.427317608337905,
      "grad_norm": 4.248454570770264,
      "learning_rate": 3.628634119583105e-05,
      "loss": 2.478,
      "step": 50000
    },
    {
      "epoch": 27.701590784421285,
      "grad_norm": 3.7782256603240967,
      "learning_rate": 3.614920460778936e-05,
      "loss": 2.4797,
      "step": 50500
    },
    {
      "epoch": 27.97586396050466,
      "grad_norm": 3.996277332305908,
      "learning_rate": 3.601206801974767e-05,
      "loss": 2.4872,
      "step": 51000
    },
    {
      "epoch": 28.25013713658804,
      "grad_norm": 4.143040657043457,
      "learning_rate": 3.5874931431705984e-05,
      "loss": 2.4311,
      "step": 51500
    },
    {
      "epoch": 28.52441031267142,
      "grad_norm": 3.6849589347839355,
      "learning_rate": 3.573779484366429e-05,
      "loss": 2.4377,
      "step": 52000
    },
    {
      "epoch": 28.7986834887548,
      "grad_norm": 3.621760606765747,
      "learning_rate": 3.56006582556226e-05,
      "loss": 2.4425,
      "step": 52500
    },
    {
      "epoch": 29.07295666483818,
      "grad_norm": 3.7394306659698486,
      "learning_rate": 3.5463521667580914e-05,
      "loss": 2.4287,
      "step": 53000
    },
    {
      "epoch": 29.347229840921557,
      "grad_norm": 3.782111167907715,
      "learning_rate": 3.532638507953922e-05,
      "loss": 2.3911,
      "step": 53500
    },
    {
      "epoch": 29.621503017004937,
      "grad_norm": 4.35050106048584,
      "learning_rate": 3.518924849149753e-05,
      "loss": 2.4084,
      "step": 54000
    },
    {
      "epoch": 29.895776193088317,
      "grad_norm": 3.8727004528045654,
      "learning_rate": 3.5052111903455844e-05,
      "loss": 2.3928,
      "step": 54500
    },
    {
      "epoch": 30.170049369171696,
      "grad_norm": 3.974501371383667,
      "learning_rate": 3.4914975315414157e-05,
      "loss": 2.3668,
      "step": 55000
    },
    {
      "epoch": 30.444322545255073,
      "grad_norm": 3.7882275581359863,
      "learning_rate": 3.477783872737246e-05,
      "loss": 2.3686,
      "step": 55500
    },
    {
      "epoch": 30.718595721338453,
      "grad_norm": 3.8313581943511963,
      "learning_rate": 3.4640702139330774e-05,
      "loss": 2.3707,
      "step": 56000
    },
    {
      "epoch": 30.992868897421832,
      "grad_norm": 4.046344757080078,
      "learning_rate": 3.450356555128909e-05,
      "loss": 2.3632,
      "step": 56500
    },
    {
      "epoch": 31.267142073505212,
      "grad_norm": 3.7165708541870117,
      "learning_rate": 3.436642896324739e-05,
      "loss": 2.3229,
      "step": 57000
    },
    {
      "epoch": 31.54141524958859,
      "grad_norm": 3.8072948455810547,
      "learning_rate": 3.4229292375205705e-05,
      "loss": 2.3262,
      "step": 57500
    },
    {
      "epoch": 31.81568842567197,
      "grad_norm": 3.8423380851745605,
      "learning_rate": 3.409215578716402e-05,
      "loss": 2.3311,
      "step": 58000
    },
    {
      "epoch": 32.08996160175535,
      "grad_norm": 3.831343650817871,
      "learning_rate": 3.395501919912233e-05,
      "loss": 2.3213,
      "step": 58500
    },
    {
      "epoch": 32.364234777838725,
      "grad_norm": 3.8060476779937744,
      "learning_rate": 3.3817882611080635e-05,
      "loss": 2.2849,
      "step": 59000
    },
    {
      "epoch": 32.63850795392211,
      "grad_norm": 4.033987998962402,
      "learning_rate": 3.368074602303895e-05,
      "loss": 2.2979,
      "step": 59500
    },
    {
      "epoch": 32.912781130005484,
      "grad_norm": 3.870171546936035,
      "learning_rate": 3.354360943499726e-05,
      "loss": 2.2982,
      "step": 60000
    },
    {
      "epoch": 33.18705430608887,
      "grad_norm": 3.848620653152466,
      "learning_rate": 3.340647284695557e-05,
      "loss": 2.264,
      "step": 60500
    },
    {
      "epoch": 33.461327482172244,
      "grad_norm": 4.048386573791504,
      "learning_rate": 3.326933625891388e-05,
      "loss": 2.2568,
      "step": 61000
    },
    {
      "epoch": 33.73560065825562,
      "grad_norm": 4.029069900512695,
      "learning_rate": 3.313219967087219e-05,
      "loss": 2.2602,
      "step": 61500
    },
    {
      "epoch": 34.009873834339004,
      "grad_norm": 3.759799003601074,
      "learning_rate": 3.29950630828305e-05,
      "loss": 2.2763,
      "step": 62000
    },
    {
      "epoch": 34.28414701042238,
      "grad_norm": 4.440002918243408,
      "learning_rate": 3.285792649478881e-05,
      "loss": 2.2137,
      "step": 62500
    },
    {
      "epoch": 34.55842018650576,
      "grad_norm": 3.961390972137451,
      "learning_rate": 3.272078990674713e-05,
      "loss": 2.233,
      "step": 63000
    },
    {
      "epoch": 34.83269336258914,
      "grad_norm": 3.916156768798828,
      "learning_rate": 3.258365331870543e-05,
      "loss": 2.2414,
      "step": 63500
    },
    {
      "epoch": 35.106966538672516,
      "grad_norm": 3.746572732925415,
      "learning_rate": 3.2446516730663745e-05,
      "loss": 2.2137,
      "step": 64000
    },
    {
      "epoch": 35.3812397147559,
      "grad_norm": 3.8424971103668213,
      "learning_rate": 3.230938014262205e-05,
      "loss": 2.1907,
      "step": 64500
    },
    {
      "epoch": 35.655512890839276,
      "grad_norm": 4.250007152557373,
      "learning_rate": 3.217224355458036e-05,
      "loss": 2.2104,
      "step": 65000
    },
    {
      "epoch": 35.92978606692265,
      "grad_norm": 3.760779857635498,
      "learning_rate": 3.2035106966538675e-05,
      "loss": 2.2134,
      "step": 65500
    },
    {
      "epoch": 36.204059243006036,
      "grad_norm": 4.189092636108398,
      "learning_rate": 3.189797037849698e-05,
      "loss": 2.1714,
      "step": 66000
    },
    {
      "epoch": 36.47833241908941,
      "grad_norm": 3.6505000591278076,
      "learning_rate": 3.17608337904553e-05,
      "loss": 2.1635,
      "step": 66500
    },
    {
      "epoch": 36.752605595172795,
      "grad_norm": 3.7696096897125244,
      "learning_rate": 3.1623697202413605e-05,
      "loss": 2.1832,
      "step": 67000
    },
    {
      "epoch": 37.02687877125617,
      "grad_norm": 3.744976282119751,
      "learning_rate": 3.148656061437192e-05,
      "loss": 2.1753,
      "step": 67500
    },
    {
      "epoch": 37.30115194733955,
      "grad_norm": 3.9759116172790527,
      "learning_rate": 3.134942402633022e-05,
      "loss": 2.1326,
      "step": 68000
    },
    {
      "epoch": 37.57542512342293,
      "grad_norm": 3.719237804412842,
      "learning_rate": 3.1212287438288536e-05,
      "loss": 2.1423,
      "step": 68500
    },
    {
      "epoch": 37.84969829950631,
      "grad_norm": 4.290117263793945,
      "learning_rate": 3.107515085024685e-05,
      "loss": 2.1602,
      "step": 69000
    },
    {
      "epoch": 38.123971475589684,
      "grad_norm": 4.060342311859131,
      "learning_rate": 3.0938014262205153e-05,
      "loss": 2.1349,
      "step": 69500
    },
    {
      "epoch": 38.39824465167307,
      "grad_norm": 4.048706531524658,
      "learning_rate": 3.080087767416347e-05,
      "loss": 2.1018,
      "step": 70000
    },
    {
      "epoch": 38.672517827756444,
      "grad_norm": 4.130014896392822,
      "learning_rate": 3.066374108612178e-05,
      "loss": 2.1284,
      "step": 70500
    },
    {
      "epoch": 38.94679100383983,
      "grad_norm": 3.893848419189453,
      "learning_rate": 3.052660449808009e-05,
      "loss": 2.1255,
      "step": 71000
    },
    {
      "epoch": 39.221064179923204,
      "grad_norm": 3.6254563331604004,
      "learning_rate": 3.03894679100384e-05,
      "loss": 2.0848,
      "step": 71500
    },
    {
      "epoch": 39.49533735600658,
      "grad_norm": 4.06374979019165,
      "learning_rate": 3.025233132199671e-05,
      "loss": 2.0933,
      "step": 72000
    },
    {
      "epoch": 39.76961053208996,
      "grad_norm": 3.763274908065796,
      "learning_rate": 3.011519473395502e-05,
      "loss": 2.11,
      "step": 72500
    },
    {
      "epoch": 40.04388370817334,
      "grad_norm": 4.014530181884766,
      "learning_rate": 2.997805814591333e-05,
      "loss": 2.0918,
      "step": 73000
    },
    {
      "epoch": 40.31815688425672,
      "grad_norm": 3.6787962913513184,
      "learning_rate": 2.9840921557871642e-05,
      "loss": 2.0559,
      "step": 73500
    },
    {
      "epoch": 40.5924300603401,
      "grad_norm": 3.752711057662964,
      "learning_rate": 2.970378496982995e-05,
      "loss": 2.067,
      "step": 74000
    },
    {
      "epoch": 40.866703236423476,
      "grad_norm": 3.795217752456665,
      "learning_rate": 2.9566648381788263e-05,
      "loss": 2.0792,
      "step": 74500
    },
    {
      "epoch": 41.14097641250686,
      "grad_norm": 3.7484569549560547,
      "learning_rate": 2.9429511793746572e-05,
      "loss": 2.0608,
      "step": 75000
    },
    {
      "epoch": 41.415249588590235,
      "grad_norm": 3.601229190826416,
      "learning_rate": 2.9292375205704885e-05,
      "loss": 2.0337,
      "step": 75500
    },
    {
      "epoch": 41.68952276467361,
      "grad_norm": 3.9707863330841064,
      "learning_rate": 2.9155238617663194e-05,
      "loss": 2.0426,
      "step": 76000
    },
    {
      "epoch": 41.963795940756995,
      "grad_norm": 3.9523677825927734,
      "learning_rate": 2.9018102029621502e-05,
      "loss": 2.0571,
      "step": 76500
    },
    {
      "epoch": 42.23806911684037,
      "grad_norm": 4.046602725982666,
      "learning_rate": 2.8880965441579815e-05,
      "loss": 2.0225,
      "step": 77000
    },
    {
      "epoch": 42.512342292923755,
      "grad_norm": 4.059443950653076,
      "learning_rate": 2.8743828853538124e-05,
      "loss": 2.0185,
      "step": 77500
    },
    {
      "epoch": 42.78661546900713,
      "grad_norm": 4.066934108734131,
      "learning_rate": 2.8606692265496436e-05,
      "loss": 2.0342,
      "step": 78000
    },
    {
      "epoch": 43.06088864509051,
      "grad_norm": 3.811591386795044,
      "learning_rate": 2.8469555677454745e-05,
      "loss": 2.0216,
      "step": 78500
    },
    {
      "epoch": 43.33516182117389,
      "grad_norm": 3.979374408721924,
      "learning_rate": 2.833241908941306e-05,
      "loss": 1.989,
      "step": 79000
    },
    {
      "epoch": 43.60943499725727,
      "grad_norm": 3.67275333404541,
      "learning_rate": 2.8195282501371366e-05,
      "loss": 1.9958,
      "step": 79500
    },
    {
      "epoch": 43.88370817334065,
      "grad_norm": 3.790217399597168,
      "learning_rate": 2.8058145913329675e-05,
      "loss": 2.0102,
      "step": 80000
    },
    {
      "epoch": 44.15798134942403,
      "grad_norm": 3.9934496879577637,
      "learning_rate": 2.7921009325287988e-05,
      "loss": 1.9847,
      "step": 80500
    },
    {
      "epoch": 44.4322545255074,
      "grad_norm": 4.339521408081055,
      "learning_rate": 2.7783872737246297e-05,
      "loss": 1.9752,
      "step": 81000
    },
    {
      "epoch": 44.70652770159079,
      "grad_norm": 3.5851519107818604,
      "learning_rate": 2.764673614920461e-05,
      "loss": 1.9883,
      "step": 81500
    },
    {
      "epoch": 44.98080087767416,
      "grad_norm": 4.129305362701416,
      "learning_rate": 2.7509599561162918e-05,
      "loss": 1.9896,
      "step": 82000
    },
    {
      "epoch": 45.25507405375754,
      "grad_norm": 3.752852201461792,
      "learning_rate": 2.7372462973121234e-05,
      "loss": 1.9465,
      "step": 82500
    },
    {
      "epoch": 45.52934722984092,
      "grad_norm": 3.923309087753296,
      "learning_rate": 2.723532638507954e-05,
      "loss": 1.9589,
      "step": 83000
    },
    {
      "epoch": 45.8036204059243,
      "grad_norm": 4.141747951507568,
      "learning_rate": 2.7098189797037848e-05,
      "loss": 1.9662,
      "step": 83500
    },
    {
      "epoch": 46.07789358200768,
      "grad_norm": 4.118216514587402,
      "learning_rate": 2.696105320899616e-05,
      "loss": 1.9518,
      "step": 84000
    },
    {
      "epoch": 46.35216675809106,
      "grad_norm": 4.061371326446533,
      "learning_rate": 2.682391662095447e-05,
      "loss": 1.928,
      "step": 84500
    },
    {
      "epoch": 46.626439934174435,
      "grad_norm": 4.138849258422852,
      "learning_rate": 2.6686780032912785e-05,
      "loss": 1.9456,
      "step": 85000
    },
    {
      "epoch": 46.90071311025782,
      "grad_norm": 3.9675650596618652,
      "learning_rate": 2.654964344487109e-05,
      "loss": 1.9465,
      "step": 85500
    },
    {
      "epoch": 47.174986286341195,
      "grad_norm": 3.745779514312744,
      "learning_rate": 2.6412506856829406e-05,
      "loss": 1.9293,
      "step": 86000
    },
    {
      "epoch": 47.44925946242458,
      "grad_norm": 3.6988871097564697,
      "learning_rate": 2.6275370268787712e-05,
      "loss": 1.915,
      "step": 86500
    },
    {
      "epoch": 47.723532638507955,
      "grad_norm": 3.7044730186462402,
      "learning_rate": 2.613823368074602e-05,
      "loss": 1.9199,
      "step": 87000
    },
    {
      "epoch": 47.99780581459133,
      "grad_norm": 3.6700057983398438,
      "learning_rate": 2.6001097092704337e-05,
      "loss": 1.9243,
      "step": 87500
    },
    {
      "epoch": 48.272078990674714,
      "grad_norm": 3.89973521232605,
      "learning_rate": 2.5863960504662642e-05,
      "loss": 1.8846,
      "step": 88000
    },
    {
      "epoch": 48.54635216675809,
      "grad_norm": 4.041015625,
      "learning_rate": 2.5726823916620958e-05,
      "loss": 1.8999,
      "step": 88500
    },
    {
      "epoch": 48.82062534284147,
      "grad_norm": 3.7937917709350586,
      "learning_rate": 2.5589687328579264e-05,
      "loss": 1.9085,
      "step": 89000
    },
    {
      "epoch": 49.09489851892485,
      "grad_norm": 4.050382614135742,
      "learning_rate": 2.545255074053758e-05,
      "loss": 1.8934,
      "step": 89500
    },
    {
      "epoch": 49.36917169500823,
      "grad_norm": 3.809558391571045,
      "learning_rate": 2.5315414152495888e-05,
      "loss": 1.8705,
      "step": 90000
    },
    {
      "epoch": 49.64344487109161,
      "grad_norm": 3.6460201740264893,
      "learning_rate": 2.51782775644542e-05,
      "loss": 1.8904,
      "step": 90500
    },
    {
      "epoch": 49.917718047174986,
      "grad_norm": 3.959718704223633,
      "learning_rate": 2.504114097641251e-05,
      "loss": 1.8936,
      "step": 91000
    },
    {
      "epoch": 50.19199122325836,
      "grad_norm": 3.786888837814331,
      "learning_rate": 2.490400438837082e-05,
      "loss": 1.8683,
      "step": 91500
    },
    {
      "epoch": 50.466264399341746,
      "grad_norm": 3.477952241897583,
      "learning_rate": 2.476686780032913e-05,
      "loss": 1.8634,
      "step": 92000
    },
    {
      "epoch": 50.74053757542512,
      "grad_norm": 3.998764991760254,
      "learning_rate": 2.462973121228744e-05,
      "loss": 1.8637,
      "step": 92500
    },
    {
      "epoch": 51.014810751508506,
      "grad_norm": 4.029101848602295,
      "learning_rate": 2.449259462424575e-05,
      "loss": 1.8749,
      "step": 93000
    },
    {
      "epoch": 51.28908392759188,
      "grad_norm": 3.8711071014404297,
      "learning_rate": 2.435545803620406e-05,
      "loss": 1.8377,
      "step": 93500
    },
    {
      "epoch": 51.56335710367526,
      "grad_norm": 3.922783136367798,
      "learning_rate": 2.421832144816237e-05,
      "loss": 1.8397,
      "step": 94000
    },
    {
      "epoch": 51.83763027975864,
      "grad_norm": 4.025134086608887,
      "learning_rate": 2.4081184860120682e-05,
      "loss": 1.8609,
      "step": 94500
    },
    {
      "epoch": 52.11190345584202,
      "grad_norm": 3.800508975982666,
      "learning_rate": 2.394404827207899e-05,
      "loss": 1.8407,
      "step": 95000
    },
    {
      "epoch": 52.386176631925395,
      "grad_norm": 3.944465160369873,
      "learning_rate": 2.3806911684037304e-05,
      "loss": 1.8263,
      "step": 95500
    },
    {
      "epoch": 52.66044980800878,
      "grad_norm": 4.014648914337158,
      "learning_rate": 2.3669775095995613e-05,
      "loss": 1.8374,
      "step": 96000
    },
    {
      "epoch": 52.934722984092154,
      "grad_norm": 4.08259916305542,
      "learning_rate": 2.353263850795392e-05,
      "loss": 1.8448,
      "step": 96500
    },
    {
      "epoch": 53.20899616017554,
      "grad_norm": 3.941981792449951,
      "learning_rate": 2.3395501919912234e-05,
      "loss": 1.8131,
      "step": 97000
    },
    {
      "epoch": 53.483269336258914,
      "grad_norm": 3.8573715686798096,
      "learning_rate": 2.3258365331870543e-05,
      "loss": 1.8169,
      "step": 97500
    },
    {
      "epoch": 53.75754251234229,
      "grad_norm": 3.987938165664673,
      "learning_rate": 2.3121228743828855e-05,
      "loss": 1.8145,
      "step": 98000
    },
    {
      "epoch": 54.031815688425674,
      "grad_norm": 3.652238607406616,
      "learning_rate": 2.2984092155787164e-05,
      "loss": 1.8213,
      "step": 98500
    },
    {
      "epoch": 54.30608886450905,
      "grad_norm": 3.640587568283081,
      "learning_rate": 2.2846955567745476e-05,
      "loss": 1.7938,
      "step": 99000
    },
    {
      "epoch": 54.58036204059243,
      "grad_norm": 3.884443759918213,
      "learning_rate": 2.2709818979703785e-05,
      "loss": 1.7963,
      "step": 99500
    },
    {
      "epoch": 54.85463521667581,
      "grad_norm": 4.245452880859375,
      "learning_rate": 2.2572682391662098e-05,
      "loss": 1.811,
      "step": 100000
    },
    {
      "epoch": 55.128908392759186,
      "grad_norm": 3.97247576713562,
      "learning_rate": 2.2435545803620407e-05,
      "loss": 1.7964,
      "step": 100500
    },
    {
      "epoch": 55.40318156884257,
      "grad_norm": 3.8827009201049805,
      "learning_rate": 2.2298409215578716e-05,
      "loss": 1.7774,
      "step": 101000
    },
    {
      "epoch": 55.677454744925946,
      "grad_norm": 4.079446792602539,
      "learning_rate": 2.2161272627537028e-05,
      "loss": 1.7884,
      "step": 101500
    },
    {
      "epoch": 55.95172792100932,
      "grad_norm": 4.093244552612305,
      "learning_rate": 2.2024136039495337e-05,
      "loss": 1.7904,
      "step": 102000
    },
    {
      "epoch": 56.226001097092706,
      "grad_norm": 3.674686908721924,
      "learning_rate": 2.188699945145365e-05,
      "loss": 1.7655,
      "step": 102500
    },
    {
      "epoch": 56.50027427317608,
      "grad_norm": 4.042862892150879,
      "learning_rate": 2.174986286341196e-05,
      "loss": 1.7708,
      "step": 103000
    },
    {
      "epoch": 56.774547449259465,
      "grad_norm": 4.069617748260498,
      "learning_rate": 2.161272627537027e-05,
      "loss": 1.777,
      "step": 103500
    },
    {
      "epoch": 57.04882062534284,
      "grad_norm": 3.68752384185791,
      "learning_rate": 2.1475589687328583e-05,
      "loss": 1.7702,
      "step": 104000
    },
    {
      "epoch": 57.32309380142622,
      "grad_norm": 3.998215436935425,
      "learning_rate": 2.133845309928689e-05,
      "loss": 1.7508,
      "step": 104500
    },
    {
      "epoch": 57.5973669775096,
      "grad_norm": 4.300554275512695,
      "learning_rate": 2.12013165112452e-05,
      "loss": 1.7634,
      "step": 105000
    },
    {
      "epoch": 57.87164015359298,
      "grad_norm": 3.649411678314209,
      "learning_rate": 2.106417992320351e-05,
      "loss": 1.7603,
      "step": 105500
    },
    {
      "epoch": 58.14591332967636,
      "grad_norm": 4.17492151260376,
      "learning_rate": 2.0927043335161822e-05,
      "loss": 1.7441,
      "step": 106000
    },
    {
      "epoch": 58.42018650575974,
      "grad_norm": 3.8550057411193848,
      "learning_rate": 2.0789906747120134e-05,
      "loss": 1.7381,
      "step": 106500
    },
    {
      "epoch": 58.694459681843114,
      "grad_norm": 4.004961967468262,
      "learning_rate": 2.0652770159078443e-05,
      "loss": 1.7475,
      "step": 107000
    },
    {
      "epoch": 58.9687328579265,
      "grad_norm": 3.936483144760132,
      "learning_rate": 2.0515633571036756e-05,
      "loss": 1.7532,
      "step": 107500
    },
    {
      "epoch": 59.24300603400987,
      "grad_norm": 3.812488317489624,
      "learning_rate": 2.037849698299506e-05,
      "loss": 1.7232,
      "step": 108000
    },
    {
      "epoch": 59.51727921009325,
      "grad_norm": 4.185512542724609,
      "learning_rate": 2.0241360394953374e-05,
      "loss": 1.7196,
      "step": 108500
    },
    {
      "epoch": 59.79155238617663,
      "grad_norm": 4.278858184814453,
      "learning_rate": 2.0104223806911686e-05,
      "loss": 1.7356,
      "step": 109000
    },
    {
      "epoch": 60.06582556226001,
      "grad_norm": 4.104213714599609,
      "learning_rate": 1.9967087218869995e-05,
      "loss": 1.7328,
      "step": 109500
    },
    {
      "epoch": 60.34009873834339,
      "grad_norm": 4.215428352355957,
      "learning_rate": 1.9829950630828307e-05,
      "loss": 1.7109,
      "step": 110000
    },
    {
      "epoch": 60.61437191442677,
      "grad_norm": 4.020122528076172,
      "learning_rate": 1.9692814042786616e-05,
      "loss": 1.7144,
      "step": 110500
    },
    {
      "epoch": 60.888645090510146,
      "grad_norm": 3.9703729152679443,
      "learning_rate": 1.955567745474493e-05,
      "loss": 1.7335,
      "step": 111000
    },
    {
      "epoch": 61.16291826659353,
      "grad_norm": 3.900017023086548,
      "learning_rate": 1.9418540866703238e-05,
      "loss": 1.7048,
      "step": 111500
    },
    {
      "epoch": 61.437191442676905,
      "grad_norm": 4.7137627601623535,
      "learning_rate": 1.9281404278661547e-05,
      "loss": 1.6902,
      "step": 112000
    },
    {
      "epoch": 61.71146461876029,
      "grad_norm": 4.035908222198486,
      "learning_rate": 1.914426769061986e-05,
      "loss": 1.7104,
      "step": 112500
    },
    {
      "epoch": 61.985737794843665,
      "grad_norm": 4.041805744171143,
      "learning_rate": 1.9007131102578168e-05,
      "loss": 1.7155,
      "step": 113000
    },
    {
      "epoch": 62.26001097092704,
      "grad_norm": 3.817702054977417,
      "learning_rate": 1.886999451453648e-05,
      "loss": 1.6851,
      "step": 113500
    },
    {
      "epoch": 62.534284147010425,
      "grad_norm": 3.8696234226226807,
      "learning_rate": 1.873285792649479e-05,
      "loss": 1.6857,
      "step": 114000
    },
    {
      "epoch": 62.8085573230938,
      "grad_norm": 3.909179925918579,
      "learning_rate": 1.85957213384531e-05,
      "loss": 1.7037,
      "step": 114500
    },
    {
      "epoch": 63.08283049917718,
      "grad_norm": 3.8557326793670654,
      "learning_rate": 1.845858475041141e-05,
      "loss": 1.6936,
      "step": 115000
    },
    {
      "epoch": 63.35710367526056,
      "grad_norm": 4.332828044891357,
      "learning_rate": 1.832144816236972e-05,
      "loss": 1.6786,
      "step": 115500
    },
    {
      "epoch": 63.63137685134394,
      "grad_norm": 4.454130172729492,
      "learning_rate": 1.818431157432803e-05,
      "loss": 1.6768,
      "step": 116000
    },
    {
      "epoch": 63.90565002742732,
      "grad_norm": 3.943071126937866,
      "learning_rate": 1.804717498628634e-05,
      "loss": 1.6905,
      "step": 116500
    },
    {
      "epoch": 64.1799232035107,
      "grad_norm": 4.255739688873291,
      "learning_rate": 1.7910038398244653e-05,
      "loss": 1.663,
      "step": 117000
    },
    {
      "epoch": 64.45419637959408,
      "grad_norm": 4.027384281158447,
      "learning_rate": 1.7772901810202962e-05,
      "loss": 1.6603,
      "step": 117500
    },
    {
      "epoch": 64.72846955567745,
      "grad_norm": 3.8232147693634033,
      "learning_rate": 1.7635765222161274e-05,
      "loss": 1.6701,
      "step": 118000
    },
    {
      "epoch": 65.00274273176083,
      "grad_norm": 3.83734130859375,
      "learning_rate": 1.7498628634119583e-05,
      "loss": 1.6797,
      "step": 118500
    },
    {
      "epoch": 65.27701590784422,
      "grad_norm": 3.9775922298431396,
      "learning_rate": 1.7361492046077896e-05,
      "loss": 1.6441,
      "step": 119000
    },
    {
      "epoch": 65.55128908392759,
      "grad_norm": 3.810086250305176,
      "learning_rate": 1.7224355458036205e-05,
      "loss": 1.6534,
      "step": 119500
    },
    {
      "epoch": 65.82556226001097,
      "grad_norm": 4.3292036056518555,
      "learning_rate": 1.7087218869994513e-05,
      "loss": 1.6651,
      "step": 120000
    },
    {
      "epoch": 66.09983543609435,
      "grad_norm": 4.046462535858154,
      "learning_rate": 1.6950082281952826e-05,
      "loss": 1.654,
      "step": 120500
    },
    {
      "epoch": 66.37410861217774,
      "grad_norm": 4.200257778167725,
      "learning_rate": 1.6812945693911135e-05,
      "loss": 1.6383,
      "step": 121000
    },
    {
      "epoch": 66.6483817882611,
      "grad_norm": 3.98045015335083,
      "learning_rate": 1.6675809105869447e-05,
      "loss": 1.6571,
      "step": 121500
    },
    {
      "epoch": 66.92265496434449,
      "grad_norm": 3.9323537349700928,
      "learning_rate": 1.653867251782776e-05,
      "loss": 1.6486,
      "step": 122000
    },
    {
      "epoch": 67.19692814042787,
      "grad_norm": 3.898150682449341,
      "learning_rate": 1.640153592978607e-05,
      "loss": 1.6288,
      "step": 122500
    },
    {
      "epoch": 67.47120131651124,
      "grad_norm": 3.8490869998931885,
      "learning_rate": 1.6264399341744377e-05,
      "loss": 1.6305,
      "step": 123000
    },
    {
      "epoch": 67.74547449259462,
      "grad_norm": 4.125833034515381,
      "learning_rate": 1.6127262753702686e-05,
      "loss": 1.6393,
      "step": 123500
    },
    {
      "epoch": 68.01974766867801,
      "grad_norm": 4.1837286949157715,
      "learning_rate": 1.5990126165661e-05,
      "loss": 1.6441,
      "step": 124000
    },
    {
      "epoch": 68.29402084476138,
      "grad_norm": 4.150059700012207,
      "learning_rate": 1.585298957761931e-05,
      "loss": 1.6144,
      "step": 124500
    },
    {
      "epoch": 68.56829402084476,
      "grad_norm": 4.325094223022461,
      "learning_rate": 1.571585298957762e-05,
      "loss": 1.6254,
      "step": 125000
    },
    {
      "epoch": 68.84256719692814,
      "grad_norm": 3.9832139015197754,
      "learning_rate": 1.5578716401535932e-05,
      "loss": 1.636,
      "step": 125500
    },
    {
      "epoch": 69.11684037301151,
      "grad_norm": 3.9516079425811768,
      "learning_rate": 1.544157981349424e-05,
      "loss": 1.6183,
      "step": 126000
    },
    {
      "epoch": 69.3911135490949,
      "grad_norm": 3.982802391052246,
      "learning_rate": 1.5304443225452554e-05,
      "loss": 1.6116,
      "step": 126500
    },
    {
      "epoch": 69.66538672517828,
      "grad_norm": 4.178645610809326,
      "learning_rate": 1.516730663741086e-05,
      "loss": 1.6183,
      "step": 127000
    },
    {
      "epoch": 69.93965990126166,
      "grad_norm": 4.045616149902344,
      "learning_rate": 1.5030170049369171e-05,
      "loss": 1.6226,
      "step": 127500
    },
    {
      "epoch": 70.21393307734503,
      "grad_norm": 4.098151206970215,
      "learning_rate": 1.4893033461327482e-05,
      "loss": 1.5999,
      "step": 128000
    },
    {
      "epoch": 70.48820625342842,
      "grad_norm": 4.052021026611328,
      "learning_rate": 1.4755896873285793e-05,
      "loss": 1.5946,
      "step": 128500
    },
    {
      "epoch": 70.7624794295118,
      "grad_norm": 3.7580652236938477,
      "learning_rate": 1.4618760285244103e-05,
      "loss": 1.6172,
      "step": 129000
    },
    {
      "epoch": 71.03675260559517,
      "grad_norm": 4.1435866355896,
      "learning_rate": 1.4481623697202416e-05,
      "loss": 1.6121,
      "step": 129500
    },
    {
      "epoch": 71.31102578167855,
      "grad_norm": 3.739654302597046,
      "learning_rate": 1.4344487109160726e-05,
      "loss": 1.588,
      "step": 130000
    },
    {
      "epoch": 71.58529895776194,
      "grad_norm": 4.380291938781738,
      "learning_rate": 1.4207350521119034e-05,
      "loss": 1.5998,
      "step": 130500
    },
    {
      "epoch": 71.8595721338453,
      "grad_norm": 3.7885782718658447,
      "learning_rate": 1.4070213933077344e-05,
      "loss": 1.5958,
      "step": 131000
    },
    {
      "epoch": 72.13384530992869,
      "grad_norm": 4.236293792724609,
      "learning_rate": 1.3933077345035655e-05,
      "loss": 1.5956,
      "step": 131500
    },
    {
      "epoch": 72.40811848601207,
      "grad_norm": 4.205173015594482,
      "learning_rate": 1.3795940756993966e-05,
      "loss": 1.5766,
      "step": 132000
    },
    {
      "epoch": 72.68239166209544,
      "grad_norm": 4.034268379211426,
      "learning_rate": 1.3658804168952278e-05,
      "loss": 1.5912,
      "step": 132500
    },
    {
      "epoch": 72.95666483817882,
      "grad_norm": 3.9170260429382324,
      "learning_rate": 1.3521667580910589e-05,
      "loss": 1.5897,
      "step": 133000
    },
    {
      "epoch": 73.23093801426221,
      "grad_norm": 3.925799608230591,
      "learning_rate": 1.33845309928689e-05,
      "loss": 1.5765,
      "step": 133500
    },
    {
      "epoch": 73.50521119034559,
      "grad_norm": 4.052227973937988,
      "learning_rate": 1.324739440482721e-05,
      "loss": 1.5775,
      "step": 134000
    },
    {
      "epoch": 73.77948436642896,
      "grad_norm": 4.2378034591674805,
      "learning_rate": 1.3110257816785517e-05,
      "loss": 1.5834,
      "step": 134500
    },
    {
      "epoch": 74.05375754251234,
      "grad_norm": 4.073320388793945,
      "learning_rate": 1.297312122874383e-05,
      "loss": 1.5812,
      "step": 135000
    },
    {
      "epoch": 74.32803071859573,
      "grad_norm": 4.102873802185059,
      "learning_rate": 1.283598464070214e-05,
      "loss": 1.5588,
      "step": 135500
    },
    {
      "epoch": 74.6023038946791,
      "grad_norm": 4.223252773284912,
      "learning_rate": 1.269884805266045e-05,
      "loss": 1.5785,
      "step": 136000
    },
    {
      "epoch": 74.87657707076248,
      "grad_norm": 4.320130825042725,
      "learning_rate": 1.2561711464618761e-05,
      "loss": 1.5686,
      "step": 136500
    },
    {
      "epoch": 75.15085024684586,
      "grad_norm": 4.706448078155518,
      "learning_rate": 1.2424574876577072e-05,
      "loss": 1.5688,
      "step": 137000
    },
    {
      "epoch": 75.42512342292923,
      "grad_norm": 4.024387359619141,
      "learning_rate": 1.2287438288535381e-05,
      "loss": 1.5563,
      "step": 137500
    },
    {
      "epoch": 75.69939659901262,
      "grad_norm": 3.9221880435943604,
      "learning_rate": 1.2150301700493692e-05,
      "loss": 1.5712,
      "step": 138000
    },
    {
      "epoch": 75.973669775096,
      "grad_norm": 4.27291202545166,
      "learning_rate": 1.2013165112452002e-05,
      "loss": 1.5654,
      "step": 138500
    },
    {
      "epoch": 76.24794295117937,
      "grad_norm": 4.373564720153809,
      "learning_rate": 1.1876028524410313e-05,
      "loss": 1.5449,
      "step": 139000
    },
    {
      "epoch": 76.52221612726275,
      "grad_norm": 4.030310153961182,
      "learning_rate": 1.1738891936368624e-05,
      "loss": 1.5571,
      "step": 139500
    },
    {
      "epoch": 76.79648930334614,
      "grad_norm": 4.002580165863037,
      "learning_rate": 1.1601755348326934e-05,
      "loss": 1.5568,
      "step": 140000
    },
    {
      "epoch": 77.07076247942952,
      "grad_norm": 4.0623369216918945,
      "learning_rate": 1.1464618760285245e-05,
      "loss": 1.5545,
      "step": 140500
    },
    {
      "epoch": 77.34503565551289,
      "grad_norm": 4.049304485321045,
      "learning_rate": 1.1327482172243554e-05,
      "loss": 1.5442,
      "step": 141000
    },
    {
      "epoch": 77.61930883159627,
      "grad_norm": 3.891969680786133,
      "learning_rate": 1.1190345584201866e-05,
      "loss": 1.5464,
      "step": 141500
    },
    {
      "epoch": 77.89358200767965,
      "grad_norm": 4.165316104888916,
      "learning_rate": 1.1053208996160177e-05,
      "loss": 1.5509,
      "step": 142000
    },
    {
      "epoch": 78.16785518376302,
      "grad_norm": 4.1472249031066895,
      "learning_rate": 1.0916072408118487e-05,
      "loss": 1.5375,
      "step": 142500
    },
    {
      "epoch": 78.44212835984641,
      "grad_norm": 4.173414707183838,
      "learning_rate": 1.0778935820076796e-05,
      "loss": 1.5345,
      "step": 143000
    },
    {
      "epoch": 78.71640153592979,
      "grad_norm": 3.9279398918151855,
      "learning_rate": 1.0641799232035107e-05,
      "loss": 1.5381,
      "step": 143500
    },
    {
      "epoch": 78.99067471201316,
      "grad_norm": 4.222446441650391,
      "learning_rate": 1.0504662643993418e-05,
      "loss": 1.552,
      "step": 144000
    },
    {
      "epoch": 79.26494788809654,
      "grad_norm": 3.8020248413085938,
      "learning_rate": 1.0367526055951728e-05,
      "loss": 1.5217,
      "step": 144500
    },
    {
      "epoch": 79.53922106417993,
      "grad_norm": 3.8790934085845947,
      "learning_rate": 1.0230389467910039e-05,
      "loss": 1.5346,
      "step": 145000
    },
    {
      "epoch": 79.8134942402633,
      "grad_norm": 4.49297571182251,
      "learning_rate": 1.009325287986835e-05,
      "loss": 1.5354,
      "step": 145500
    },
    {
      "epoch": 80.08776741634668,
      "grad_norm": 4.024161338806152,
      "learning_rate": 9.95611629182666e-06,
      "loss": 1.5326,
      "step": 146000
    },
    {
      "epoch": 80.36204059243006,
      "grad_norm": 3.997326374053955,
      "learning_rate": 9.818979703784971e-06,
      "loss": 1.5133,
      "step": 146500
    },
    {
      "epoch": 80.63631376851345,
      "grad_norm": 4.163906574249268,
      "learning_rate": 9.68184311574328e-06,
      "loss": 1.5252,
      "step": 147000
    },
    {
      "epoch": 80.91058694459682,
      "grad_norm": 4.333358287811279,
      "learning_rate": 9.54470652770159e-06,
      "loss": 1.5356,
      "step": 147500
    },
    {
      "epoch": 81.1848601206802,
      "grad_norm": 4.201995372772217,
      "learning_rate": 9.407569939659903e-06,
      "loss": 1.5191,
      "step": 148000
    },
    {
      "epoch": 81.45913329676358,
      "grad_norm": 3.8196020126342773,
      "learning_rate": 9.270433351618212e-06,
      "loss": 1.5168,
      "step": 148500
    },
    {
      "epoch": 81.73340647284695,
      "grad_norm": 4.32403039932251,
      "learning_rate": 9.133296763576522e-06,
      "loss": 1.5214,
      "step": 149000
    },
    {
      "epoch": 82.00767964893033,
      "grad_norm": 4.165477752685547,
      "learning_rate": 8.996160175534833e-06,
      "loss": 1.5242,
      "step": 149500
    },
    {
      "epoch": 82.28195282501372,
      "grad_norm": 4.155007362365723,
      "learning_rate": 8.859023587493144e-06,
      "loss": 1.5022,
      "step": 150000
    },
    {
      "epoch": 82.55622600109709,
      "grad_norm": 4.049638748168945,
      "learning_rate": 8.721886999451453e-06,
      "loss": 1.5172,
      "step": 150500
    },
    {
      "epoch": 82.83049917718047,
      "grad_norm": 4.376342296600342,
      "learning_rate": 8.584750411409765e-06,
      "loss": 1.5097,
      "step": 151000
    },
    {
      "epoch": 83.10477235326385,
      "grad_norm": 4.413540363311768,
      "learning_rate": 8.447613823368076e-06,
      "loss": 1.5163,
      "step": 151500
    },
    {
      "epoch": 83.37904552934722,
      "grad_norm": 3.754805326461792,
      "learning_rate": 8.310477235326386e-06,
      "loss": 1.5011,
      "step": 152000
    },
    {
      "epoch": 83.6533187054306,
      "grad_norm": 4.167300224304199,
      "learning_rate": 8.173340647284695e-06,
      "loss": 1.5026,
      "step": 152500
    },
    {
      "epoch": 83.92759188151399,
      "grad_norm": 4.1614861488342285,
      "learning_rate": 8.036204059243006e-06,
      "loss": 1.5101,
      "step": 153000
    },
    {
      "epoch": 84.20186505759737,
      "grad_norm": 4.183162212371826,
      "learning_rate": 7.899067471201317e-06,
      "loss": 1.4981,
      "step": 153500
    },
    {
      "epoch": 84.47613823368074,
      "grad_norm": 4.0559539794921875,
      "learning_rate": 7.761930883159627e-06,
      "loss": 1.4965,
      "step": 154000
    },
    {
      "epoch": 84.75041140976413,
      "grad_norm": 4.252512454986572,
      "learning_rate": 7.624794295117937e-06,
      "loss": 1.5019,
      "step": 154500
    },
    {
      "epoch": 85.02468458584751,
      "grad_norm": 3.9115328788757324,
      "learning_rate": 7.4876577070762485e-06,
      "loss": 1.5138,
      "step": 155000
    },
    {
      "epoch": 85.29895776193088,
      "grad_norm": 4.217545032501221,
      "learning_rate": 7.350521119034559e-06,
      "loss": 1.492,
      "step": 155500
    },
    {
      "epoch": 85.57323093801426,
      "grad_norm": 3.974954128265381,
      "learning_rate": 7.21338453099287e-06,
      "loss": 1.4897,
      "step": 156000
    },
    {
      "epoch": 85.84750411409765,
      "grad_norm": 4.266519069671631,
      "learning_rate": 7.07624794295118e-06,
      "loss": 1.4996,
      "step": 156500
    },
    {
      "epoch": 86.12177729018102,
      "grad_norm": 3.8507697582244873,
      "learning_rate": 6.93911135490949e-06,
      "loss": 1.4891,
      "step": 157000
    },
    {
      "epoch": 86.3960504662644,
      "grad_norm": 4.050006866455078,
      "learning_rate": 6.801974766867801e-06,
      "loss": 1.4848,
      "step": 157500
    },
    {
      "epoch": 86.67032364234778,
      "grad_norm": 4.006500720977783,
      "learning_rate": 6.664838178826111e-06,
      "loss": 1.4946,
      "step": 158000
    },
    {
      "epoch": 86.94459681843115,
      "grad_norm": 4.2527289390563965,
      "learning_rate": 6.527701590784421e-06,
      "loss": 1.495,
      "step": 158500
    },
    {
      "epoch": 87.21886999451453,
      "grad_norm": 4.087696552276611,
      "learning_rate": 6.390565002742732e-06,
      "loss": 1.4834,
      "step": 159000
    },
    {
      "epoch": 87.49314317059792,
      "grad_norm": 3.9683475494384766,
      "learning_rate": 6.253428414701043e-06,
      "loss": 1.48,
      "step": 159500
    },
    {
      "epoch": 87.7674163466813,
      "grad_norm": 4.009182453155518,
      "learning_rate": 6.116291826659353e-06,
      "loss": 1.4799,
      "step": 160000
    },
    {
      "epoch": 88.04168952276467,
      "grad_norm": 3.9172310829162598,
      "learning_rate": 5.979155238617663e-06,
      "loss": 1.4827,
      "step": 160500
    },
    {
      "epoch": 88.31596269884805,
      "grad_norm": 3.920940399169922,
      "learning_rate": 5.842018650575974e-06,
      "loss": 1.4772,
      "step": 161000
    },
    {
      "epoch": 88.59023587493144,
      "grad_norm": 4.178516387939453,
      "learning_rate": 5.704882062534284e-06,
      "loss": 1.4831,
      "step": 161500
    },
    {
      "epoch": 88.8645090510148,
      "grad_norm": 4.068806171417236,
      "learning_rate": 5.567745474492595e-06,
      "loss": 1.4796,
      "step": 162000
    },
    {
      "epoch": 89.13878222709819,
      "grad_norm": 3.923023223876953,
      "learning_rate": 5.430608886450905e-06,
      "loss": 1.4734,
      "step": 162500
    },
    {
      "epoch": 89.41305540318157,
      "grad_norm": 4.0538411140441895,
      "learning_rate": 5.293472298409216e-06,
      "loss": 1.4675,
      "step": 163000
    },
    {
      "epoch": 89.68732857926494,
      "grad_norm": 4.289505481719971,
      "learning_rate": 5.156335710367526e-06,
      "loss": 1.4812,
      "step": 163500
    },
    {
      "epoch": 89.96160175534833,
      "grad_norm": 4.2184247970581055,
      "learning_rate": 5.019199122325837e-06,
      "loss": 1.4761,
      "step": 164000
    },
    {
      "epoch": 90.23587493143171,
      "grad_norm": 4.014777183532715,
      "learning_rate": 4.8820625342841474e-06,
      "loss": 1.4659,
      "step": 164500
    },
    {
      "epoch": 90.51014810751508,
      "grad_norm": 4.025433540344238,
      "learning_rate": 4.744925946242457e-06,
      "loss": 1.4701,
      "step": 165000
    },
    {
      "epoch": 90.78442128359846,
      "grad_norm": 4.117000102996826,
      "learning_rate": 4.607789358200768e-06,
      "loss": 1.4745,
      "step": 165500
    },
    {
      "epoch": 91.05869445968185,
      "grad_norm": 4.047626495361328,
      "learning_rate": 4.4706527701590785e-06,
      "loss": 1.4693,
      "step": 166000
    },
    {
      "epoch": 91.33296763576523,
      "grad_norm": 4.17887020111084,
      "learning_rate": 4.333516182117389e-06,
      "loss": 1.4624,
      "step": 166500
    },
    {
      "epoch": 91.6072408118486,
      "grad_norm": 4.2437639236450195,
      "learning_rate": 4.196379594075699e-06,
      "loss": 1.4665,
      "step": 167000
    },
    {
      "epoch": 91.88151398793198,
      "grad_norm": 3.7711315155029297,
      "learning_rate": 4.0592430060340105e-06,
      "loss": 1.4731,
      "step": 167500
    },
    {
      "epoch": 92.15578716401536,
      "grad_norm": 4.002791404724121,
      "learning_rate": 3.92210641799232e-06,
      "loss": 1.4642,
      "step": 168000
    },
    {
      "epoch": 92.43006034009873,
      "grad_norm": 4.0743231773376465,
      "learning_rate": 3.7849698299506313e-06,
      "loss": 1.4584,
      "step": 168500
    },
    {
      "epoch": 92.70433351618212,
      "grad_norm": 4.080685138702393,
      "learning_rate": 3.647833241908941e-06,
      "loss": 1.4623,
      "step": 169000
    },
    {
      "epoch": 92.9786066922655,
      "grad_norm": 4.304593563079834,
      "learning_rate": 3.510696653867252e-06,
      "loss": 1.4682,
      "step": 169500
    },
    {
      "epoch": 93.25287986834887,
      "grad_norm": 4.447428226470947,
      "learning_rate": 3.3735600658255624e-06,
      "loss": 1.4535,
      "step": 170000
    },
    {
      "epoch": 93.52715304443225,
      "grad_norm": 4.22756814956665,
      "learning_rate": 3.236423477783873e-06,
      "loss": 1.4592,
      "step": 170500
    },
    {
      "epoch": 93.80142622051564,
      "grad_norm": 4.293380260467529,
      "learning_rate": 3.0992868897421833e-06,
      "loss": 1.4632,
      "step": 171000
    },
    {
      "epoch": 94.075699396599,
      "grad_norm": 4.07041072845459,
      "learning_rate": 2.962150301700494e-06,
      "loss": 1.4605,
      "step": 171500
    },
    {
      "epoch": 94.34997257268239,
      "grad_norm": 4.039161205291748,
      "learning_rate": 2.825013713658804e-06,
      "loss": 1.4551,
      "step": 172000
    },
    {
      "epoch": 94.62424574876577,
      "grad_norm": 4.1246795654296875,
      "learning_rate": 2.687877125617115e-06,
      "loss": 1.456,
      "step": 172500
    },
    {
      "epoch": 94.89851892484916,
      "grad_norm": 4.026761054992676,
      "learning_rate": 2.550740537575425e-06,
      "loss": 1.4512,
      "step": 173000
    },
    {
      "epoch": 95.17279210093253,
      "grad_norm": 4.5864715576171875,
      "learning_rate": 2.4136039495337357e-06,
      "loss": 1.4575,
      "step": 173500
    },
    {
      "epoch": 95.44706527701591,
      "grad_norm": 4.117992401123047,
      "learning_rate": 2.2764673614920463e-06,
      "loss": 1.4475,
      "step": 174000
    },
    {
      "epoch": 95.72133845309929,
      "grad_norm": 4.155096530914307,
      "learning_rate": 2.1393307734503565e-06,
      "loss": 1.4581,
      "step": 174500
    },
    {
      "epoch": 95.99561162918266,
      "grad_norm": 4.28767204284668,
      "learning_rate": 2.002194185408667e-06,
      "loss": 1.4521,
      "step": 175000
    },
    {
      "epoch": 96.26988480526605,
      "grad_norm": 4.1511077880859375,
      "learning_rate": 1.8650575973669776e-06,
      "loss": 1.4488,
      "step": 175500
    },
    {
      "epoch": 96.54415798134943,
      "grad_norm": 4.336985111236572,
      "learning_rate": 1.727921009325288e-06,
      "loss": 1.4534,
      "step": 176000
    },
    {
      "epoch": 96.8184311574328,
      "grad_norm": 4.181045055389404,
      "learning_rate": 1.5907844212835987e-06,
      "loss": 1.45,
      "step": 176500
    },
    {
      "epoch": 97.09270433351618,
      "grad_norm": 4.217624187469482,
      "learning_rate": 1.453647833241909e-06,
      "loss": 1.4498,
      "step": 177000
    },
    {
      "epoch": 97.36697750959956,
      "grad_norm": 3.8873023986816406,
      "learning_rate": 1.3165112452002194e-06,
      "loss": 1.4507,
      "step": 177500
    },
    {
      "epoch": 97.64125068568293,
      "grad_norm": 4.3951191902160645,
      "learning_rate": 1.17937465715853e-06,
      "loss": 1.451,
      "step": 178000
    },
    {
      "epoch": 97.91552386176632,
      "grad_norm": 4.1204118728637695,
      "learning_rate": 1.0422380691168404e-06,
      "loss": 1.4484,
      "step": 178500
    },
    {
      "epoch": 98.1897970378497,
      "grad_norm": 4.278495788574219,
      "learning_rate": 9.05101481075151e-07,
      "loss": 1.4431,
      "step": 179000
    },
    {
      "epoch": 98.46407021393308,
      "grad_norm": 4.186399459838867,
      "learning_rate": 7.679648930334613e-07,
      "loss": 1.4493,
      "step": 179500
    },
    {
      "epoch": 98.73834339001645,
      "grad_norm": 4.110637187957764,
      "learning_rate": 6.308283049917719e-07,
      "loss": 1.4418,
      "step": 180000
    },
    {
      "epoch": 99.01261656609984,
      "grad_norm": 3.9559993743896484,
      "learning_rate": 4.936917169500823e-07,
      "loss": 1.4407,
      "step": 180500
    },
    {
      "epoch": 99.28688974218322,
      "grad_norm": 4.4722418785095215,
      "learning_rate": 3.565551289083928e-07,
      "loss": 1.4421,
      "step": 181000
    },
    {
      "epoch": 99.56116291826659,
      "grad_norm": 4.151792526245117,
      "learning_rate": 2.1941854086670326e-07,
      "loss": 1.4469,
      "step": 181500
    },
    {
      "epoch": 99.83543609434997,
      "grad_norm": 4.128389835357666,
      "learning_rate": 8.228195282501371e-08,
      "loss": 1.4463,
      "step": 182000
    },
    {
      "epoch": 100.0,
      "step": 182300,
      "total_flos": 3.157662139522744e+17,
      "train_loss": 2.261507166926833,
      "train_runtime": 62730.7046,
      "train_samples_per_second": 185.96,
      "train_steps_per_second": 2.906
    }
  ],
  "logging_steps": 500,
  "max_steps": 182300,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.157662139522744e+17,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}