{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.25455440669620877,
  "eval_steps": 500,
  "global_step": 517,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002461841457410143,
      "grad_norm": 4.969754695892334,
      "learning_rate": 4.302e-06,
      "loss": 1.1189,
      "mean_token_accuracy": 0.8113007307052612,
      "num_tokens": 320493.0,
      "step": 5
    },
    {
      "epoch": 0.004923682914820286,
      "grad_norm": 1.6874388456344604,
      "learning_rate": 9.6795e-06,
      "loss": 0.86,
      "mean_token_accuracy": 0.8318304777145386,
      "num_tokens": 641636.0,
      "step": 10
    },
    {
      "epoch": 0.007385524372230428,
      "grad_norm": 1.024154782295227,
      "learning_rate": 1.5056999999999998e-05,
      "loss": 0.5203,
      "mean_token_accuracy": 0.8795766830444336,
      "num_tokens": 964317.0,
      "step": 15
    },
    {
      "epoch": 0.009847365829640572,
      "grad_norm": 0.7188010811805725,
      "learning_rate": 2.04345e-05,
      "loss": 0.2224,
      "mean_token_accuracy": 0.9444798469543457,
      "num_tokens": 1284810.0,
      "step": 20
    },
    {
      "epoch": 0.012309207287050714,
      "grad_norm": 0.44151246547698975,
      "learning_rate": 2.1509842516210667e-05,
      "loss": 0.085,
      "mean_token_accuracy": 0.9784384965896606,
      "num_tokens": 1605399.0,
      "step": 25
    },
    {
      "epoch": 0.014771048744460856,
      "grad_norm": 0.5774744749069214,
      "learning_rate": 2.1509202748855685e-05,
      "loss": 0.0344,
      "mean_token_accuracy": 0.9897613763809204,
      "num_tokens": 1926494.0,
      "step": 30
    },
    {
      "epoch": 0.017232890201871,
      "grad_norm": 0.18032197654247284,
      "learning_rate": 2.1508070894201505e-05,
      "loss": 0.026,
      "mean_token_accuracy": 0.9919694185256958,
      "num_tokens": 2247464.0,
      "step": 35
    },
    {
      "epoch": 0.019694731659281144,
      "grad_norm": 0.13021060824394226,
      "learning_rate": 2.1506447021304556e-05,
      "loss": 0.026,
      "mean_token_accuracy": 0.9920557975769043,
      "num_tokens": 2569609.0,
      "step": 40
    },
    {
      "epoch": 0.022156573116691284,
      "grad_norm": 0.09289778023958206,
      "learning_rate": 2.150433122924014e-05,
      "loss": 0.0284,
      "mean_token_accuracy": 0.9913681268692016,
      "num_tokens": 2890136.0,
      "step": 45
    },
    {
      "epoch": 0.024618414574101428,
      "grad_norm": 0.11910147964954376,
      "learning_rate": 2.1501723647096418e-05,
      "loss": 0.0199,
      "mean_token_accuracy": 0.9929254293441773,
      "num_tokens": 3212967.0,
      "step": 50
    },
    {
      "epoch": 0.02708025603151157,
      "grad_norm": 0.06892787665128708,
      "learning_rate": 2.149862443396651e-05,
      "loss": 0.02,
      "mean_token_accuracy": 0.9933408498764038,
      "num_tokens": 3535443.0,
      "step": 55
    },
    {
      "epoch": 0.029542097488921712,
      "grad_norm": 0.06759732216596603,
      "learning_rate": 2.1495033778938793e-05,
      "loss": 0.0202,
      "mean_token_accuracy": 0.9929208397865296,
      "num_tokens": 3856507.0,
      "step": 60
    },
    {
      "epoch": 0.032003938946331856,
      "grad_norm": 0.07114335149526596,
      "learning_rate": 2.149095190108538e-05,
      "loss": 0.0214,
      "mean_token_accuracy": 0.9924069523811341,
      "num_tokens": 4176799.0,
      "step": 65
    },
    {
      "epoch": 0.034465780403742,
      "grad_norm": 0.06943695992231369,
      "learning_rate": 2.1486379049448737e-05,
      "loss": 0.0169,
      "mean_token_accuracy": 0.993648087978363,
      "num_tokens": 4499735.0,
      "step": 70
    },
    {
      "epoch": 0.03692762186115214,
      "grad_norm": 0.0616086907684803,
      "learning_rate": 2.1481315503026496e-05,
      "loss": 0.0193,
      "mean_token_accuracy": 0.9931790113449097,
      "num_tokens": 4820981.0,
      "step": 75
    },
    {
      "epoch": 0.03938946331856229,
      "grad_norm": 0.0513451024889946,
      "learning_rate": 2.1475761570754427e-05,
      "loss": 0.0207,
      "mean_token_accuracy": 0.9926488041877747,
      "num_tokens": 5141030.0,
      "step": 80
    },
    {
      "epoch": 0.041851304775972424,
      "grad_norm": 0.056912314146757126,
      "learning_rate": 2.1469717591487602e-05,
      "loss": 0.0207,
      "mean_token_accuracy": 0.9930928468704223,
      "num_tokens": 5463284.0,
      "step": 85
    },
    {
      "epoch": 0.04431314623338257,
      "grad_norm": 0.07296790182590485,
      "learning_rate": 2.1463183933979705e-05,
      "loss": 0.015,
      "mean_token_accuracy": 0.9941470623016357,
      "num_tokens": 5785382.0,
      "step": 90
    },
    {
      "epoch": 0.04677498769079271,
      "grad_norm": 0.06787711381912231,
      "learning_rate": 2.1456160996860543e-05,
      "loss": 0.0179,
      "mean_token_accuracy": 0.9935230731964111,
      "num_tokens": 6106054.0,
      "step": 95
    },
    {
      "epoch": 0.049236829148202856,
      "grad_norm": 0.06585029512643814,
      "learning_rate": 2.144864920861172e-05,
      "loss": 0.0186,
      "mean_token_accuracy": 0.9933484435081482,
      "num_tokens": 6428795.0,
      "step": 100
    },
    {
      "epoch": 0.051698670605613,
      "grad_norm": 0.06587713956832886,
      "learning_rate": 2.144064902754051e-05,
      "loss": 0.0185,
      "mean_token_accuracy": 0.9930931210517884,
      "num_tokens": 6750701.0,
      "step": 105
    },
    {
      "epoch": 0.05416051206302314,
      "grad_norm": 0.07679057866334915,
      "learning_rate": 2.1432160941751866e-05,
      "loss": 0.0202,
      "mean_token_accuracy": 0.9929586410522461,
      "num_tokens": 7071691.0,
      "step": 110
    },
    {
      "epoch": 0.05662235352043329,
      "grad_norm": 0.04670145362615585,
      "learning_rate": 2.142318546911867e-05,
      "loss": 0.0189,
      "mean_token_accuracy": 0.9934035181999207,
      "num_tokens": 7393074.0,
      "step": 115
    },
    {
      "epoch": 0.059084194977843424,
      "grad_norm": 0.06476707011461258,
      "learning_rate": 2.1413723157250112e-05,
      "loss": 0.0164,
      "mean_token_accuracy": 0.993677806854248,
      "num_tokens": 7715147.0,
      "step": 120
    },
    {
      "epoch": 0.06154603643525357,
      "grad_norm": 0.051915861666202545,
      "learning_rate": 2.1403774583458295e-05,
      "loss": 0.0157,
      "mean_token_accuracy": 0.9937990188598633,
      "num_tokens": 8036756.0,
      "step": 125
    },
    {
      "epoch": 0.06400787789266371,
      "grad_norm": 0.06622428447008133,
      "learning_rate": 2.1393340354723012e-05,
      "loss": 0.0172,
      "mean_token_accuracy": 0.9937798023223877,
      "num_tokens": 8357904.0,
      "step": 130
    },
    {
      "epoch": 0.06646971935007386,
      "grad_norm": 0.048398587852716446,
      "learning_rate": 2.13824211076547e-05,
      "loss": 0.0169,
      "mean_token_accuracy": 0.9936380386352539,
      "num_tokens": 8679562.0,
      "step": 135
    },
    {
      "epoch": 0.068931560807484,
      "grad_norm": 0.0736224353313446,
      "learning_rate": 2.1371017508455625e-05,
      "loss": 0.0188,
      "mean_token_accuracy": 0.9932926297187805,
      "num_tokens": 9001387.0,
      "step": 140
    },
    {
      "epoch": 0.07139340226489414,
      "grad_norm": 0.047113846987485886,
      "learning_rate": 2.1359130252879188e-05,
      "loss": 0.0157,
      "mean_token_accuracy": 0.9938287138938904,
      "num_tokens": 9323154.0,
      "step": 145
    },
    {
      "epoch": 0.07385524372230429,
      "grad_norm": 0.06331256777048111,
      "learning_rate": 2.1346760066187538e-05,
      "loss": 0.0189,
      "mean_token_accuracy": 0.9930492639541626,
      "num_tokens": 9644568.0,
      "step": 150
    },
    {
      "epoch": 0.07631708517971443,
      "grad_norm": 0.06080303713679314,
      "learning_rate": 2.1333907703107276e-05,
      "loss": 0.0225,
      "mean_token_accuracy": 0.9922333717346191,
      "num_tokens": 9964653.0,
      "step": 155
    },
    {
      "epoch": 0.07877892663712457,
      "grad_norm": 0.07311772555112839,
      "learning_rate": 2.1320573947783423e-05,
      "loss": 0.0184,
      "mean_token_accuracy": 0.9932848572731018,
      "num_tokens": 10285925.0,
      "step": 160
    },
    {
      "epoch": 0.08124076809453472,
      "grad_norm": 0.1281968057155609,
      "learning_rate": 2.1306759613731585e-05,
      "loss": 0.0178,
      "mean_token_accuracy": 0.9935338497161865,
      "num_tokens": 10606433.0,
      "step": 165
    },
    {
      "epoch": 0.08370260955194485,
      "grad_norm": 0.03950123116374016,
      "learning_rate": 2.1292465543788306e-05,
      "loss": 0.0165,
      "mean_token_accuracy": 0.9936023473739624,
      "num_tokens": 10926653.0,
      "step": 170
    },
    {
      "epoch": 0.08616445100935499,
      "grad_norm": 0.074995256960392,
      "learning_rate": 2.127769261005965e-05,
      "loss": 0.0197,
      "mean_token_accuracy": 0.993098521232605,
      "num_tokens": 11247504.0,
      "step": 175
    },
    {
      "epoch": 0.08862629246676514,
      "grad_norm": 0.054995279759168625,
      "learning_rate": 2.1262441713867998e-05,
      "loss": 0.0169,
      "mean_token_accuracy": 0.993760859966278,
      "num_tokens": 11568063.0,
      "step": 180
    },
    {
      "epoch": 0.09108813392417528,
      "grad_norm": 0.053398437798023224,
      "learning_rate": 2.1246713785697052e-05,
      "loss": 0.0169,
      "mean_token_accuracy": 0.9934692978858948,
      "num_tokens": 11888599.0,
      "step": 185
    },
    {
      "epoch": 0.09354997538158542,
      "grad_norm": 0.07271428406238556,
      "learning_rate": 2.1230509785135057e-05,
      "loss": 0.0181,
      "mean_token_accuracy": 0.9933955669403076,
      "num_tokens": 12211086.0,
      "step": 190
    },
    {
      "epoch": 0.09601181683899557,
      "grad_norm": 0.07579043507575989,
      "learning_rate": 2.1213830700816276e-05,
      "loss": 0.0196,
      "mean_token_accuracy": 0.9933238983154297,
      "num_tokens": 12532840.0,
      "step": 195
    },
    {
      "epoch": 0.09847365829640571,
      "grad_norm": 0.05194873362779617,
      "learning_rate": 2.1196677550360644e-05,
      "loss": 0.0172,
      "mean_token_accuracy": 0.993663489818573,
      "num_tokens": 12854971.0,
      "step": 200
    },
    {
      "epoch": 0.10093549975381585,
      "grad_norm": 0.04237228259444237,
      "learning_rate": 2.1179051380311706e-05,
      "loss": 0.0185,
      "mean_token_accuracy": 0.9933023810386657,
      "num_tokens": 13176310.0,
      "step": 205
    },
    {
      "epoch": 0.103397341211226,
      "grad_norm": 0.05479801818728447,
      "learning_rate": 2.116095326607275e-05,
      "loss": 0.019,
      "mean_token_accuracy": 0.9933096051216126,
      "num_tokens": 13497271.0,
      "step": 210
    },
    {
      "epoch": 0.10585918266863614,
      "grad_norm": 0.050505638122558594,
      "learning_rate": 2.11423843118412e-05,
      "loss": 0.0193,
      "mean_token_accuracy": 0.9930040121078492,
      "num_tokens": 13818732.0,
      "step": 215
    },
    {
      "epoch": 0.10832102412604629,
      "grad_norm": 0.04875461012125015,
      "learning_rate": 2.1123345650541254e-05,
      "loss": 0.015,
      "mean_token_accuracy": 0.9943194031715393,
      "num_tokens": 14140155.0,
      "step": 220
    },
    {
      "epoch": 0.11078286558345643,
      "grad_norm": 0.04343048110604286,
      "learning_rate": 2.110383844375474e-05,
      "loss": 0.0173,
      "mean_token_accuracy": 0.9935325264930726,
      "num_tokens": 14461326.0,
      "step": 225
    },
    {
      "epoch": 0.11324470704086657,
      "grad_norm": 0.05743631348013878,
      "learning_rate": 2.1083863881650274e-05,
      "loss": 0.017,
      "mean_token_accuracy": 0.9938044786453247,
      "num_tokens": 14781958.0,
      "step": 230
    },
    {
      "epoch": 0.11570654849827672,
      "grad_norm": 0.06002819910645485,
      "learning_rate": 2.1063423182910628e-05,
      "loss": 0.0179,
      "mean_token_accuracy": 0.9935547947883606,
      "num_tokens": 15103260.0,
      "step": 235
    },
    {
      "epoch": 0.11816838995568685,
      "grad_norm": 0.04813234880566597,
      "learning_rate": 2.1042517594658383e-05,
      "loss": 0.0178,
      "mean_token_accuracy": 0.9934481143951416,
      "num_tokens": 15424845.0,
      "step": 240
    },
    {
      "epoch": 0.12063023141309699,
      "grad_norm": 0.04317139834165573,
      "learning_rate": 2.1021148392379833e-05,
      "loss": 0.0167,
      "mean_token_accuracy": 0.9936479210853577,
      "num_tokens": 15745873.0,
      "step": 245
    },
    {
      "epoch": 0.12309207287050714,
      "grad_norm": 0.04026172310113907,
      "learning_rate": 2.0999316879847178e-05,
      "loss": 0.0144,
      "mean_token_accuracy": 0.9941782236099244,
      "num_tokens": 16068592.0,
      "step": 250
    },
    {
      "epoch": 0.1255539143279173,
      "grad_norm": 0.03913912549614906,
      "learning_rate": 2.097702438903896e-05,
      "loss": 0.0165,
      "mean_token_accuracy": 0.9937353253364563,
      "num_tokens": 16389359.0,
      "step": 255
    },
    {
      "epoch": 0.12801575578532742,
      "grad_norm": 0.04398415982723236,
      "learning_rate": 2.095427228005882e-05,
      "loss": 0.0141,
      "mean_token_accuracy": 0.9943455338478089,
      "num_tokens": 16712502.0,
      "step": 260
    },
    {
      "epoch": 0.13047759724273758,
      "grad_norm": 0.03654300794005394,
      "learning_rate": 2.093106194105249e-05,
      "loss": 0.0155,
      "mean_token_accuracy": 0.9941610932350159,
      "num_tokens": 17032993.0,
      "step": 265
    },
    {
      "epoch": 0.1329394387001477,
      "grad_norm": 0.04314443841576576,
      "learning_rate": 2.090739478812312e-05,
      "loss": 0.0209,
      "mean_token_accuracy": 0.9925150752067566,
      "num_tokens": 17354397.0,
      "step": 270
    },
    {
      "epoch": 0.13540128015755784,
      "grad_norm": 0.039179477840662,
      "learning_rate": 2.0883272265244868e-05,
      "loss": 0.0158,
      "mean_token_accuracy": 0.993960165977478,
      "num_tokens": 17676053.0,
      "step": 275
    },
    {
      "epoch": 0.137863121614968,
      "grad_norm": 0.05969119071960449,
      "learning_rate": 2.0858695844174815e-05,
      "loss": 0.0156,
      "mean_token_accuracy": 0.9940330982208252,
      "num_tokens": 17997892.0,
      "step": 280
    },
    {
      "epoch": 0.14032496307237813,
      "grad_norm": 0.034701548516750336,
      "learning_rate": 2.083366702436315e-05,
      "loss": 0.0162,
      "mean_token_accuracy": 0.99384845495224,
      "num_tokens": 18320416.0,
      "step": 285
    },
    {
      "epoch": 0.14278680452978829,
      "grad_norm": 0.03629715368151665,
      "learning_rate": 2.080818733286169e-05,
      "loss": 0.0136,
      "mean_token_accuracy": 0.9944872379302978,
      "num_tokens": 18641774.0,
      "step": 290
    },
    {
      "epoch": 0.14524864598719842,
      "grad_norm": 0.03510307893157005,
      "learning_rate": 2.078225832423074e-05,
      "loss": 0.0137,
      "mean_token_accuracy": 0.9944174408912658,
      "num_tokens": 18963943.0,
      "step": 295
    },
    {
      "epoch": 0.14771048744460857,
      "grad_norm": 0.05658989027142525,
      "learning_rate": 2.07558815804442e-05,
      "loss": 0.0156,
      "mean_token_accuracy": 0.9939489245414734,
      "num_tokens": 19284670.0,
      "step": 300
    },
    {
      "epoch": 0.1501723289020187,
      "grad_norm": 0.052170414477586746,
      "learning_rate": 2.072905871079309e-05,
      "loss": 0.0146,
      "mean_token_accuracy": 0.9942007660865784,
      "num_tokens": 19605830.0,
      "step": 305
    },
    {
      "epoch": 0.15263417035942886,
      "grad_norm": 0.04669521376490593,
      "learning_rate": 2.0701791351787333e-05,
      "loss": 0.0145,
      "mean_token_accuracy": 0.9942674160003662,
      "num_tokens": 19927683.0,
      "step": 310
    },
    {
      "epoch": 0.155096011816839,
      "grad_norm": 0.045594099909067154,
      "learning_rate": 2.0674081167055918e-05,
      "loss": 0.022,
      "mean_token_accuracy": 0.9924212217330932,
      "num_tokens": 20249155.0,
      "step": 315
    },
    {
      "epoch": 0.15755785327424915,
      "grad_norm": 0.042525216937065125,
      "learning_rate": 2.064592984724541e-05,
      "loss": 0.0141,
      "mean_token_accuracy": 0.9942982792854309,
      "num_tokens": 20570187.0,
      "step": 320
    },
    {
      "epoch": 0.16001969473165928,
      "grad_norm": 0.04177013039588928,
      "learning_rate": 2.0617339109916796e-05,
      "loss": 0.0158,
      "mean_token_accuracy": 0.9939341902732849,
      "num_tokens": 20890900.0,
      "step": 325
    },
    {
      "epoch": 0.16248153618906944,
      "grad_norm": 0.043914180248975754,
      "learning_rate": 2.058831069944068e-05,
      "loss": 0.0159,
      "mean_token_accuracy": 0.994042980670929,
      "num_tokens": 21211005.0,
      "step": 330
    },
    {
      "epoch": 0.16494337764647957,
      "grad_norm": 0.038002047687768936,
      "learning_rate": 2.0558846386890867e-05,
      "loss": 0.0146,
      "mean_token_accuracy": 0.9943417191505433,
      "num_tokens": 21532493.0,
      "step": 335
    },
    {
      "epoch": 0.1674052191038897,
      "grad_norm": 0.03630073741078377,
      "learning_rate": 2.0528947969936308e-05,
      "loss": 0.0141,
      "mean_token_accuracy": 0.9944631576538085,
      "num_tokens": 21854914.0,
      "step": 340
    },
    {
      "epoch": 0.16986706056129985,
      "grad_norm": 0.051170364022254944,
      "learning_rate": 2.0498617272731426e-05,
      "loss": 0.0168,
      "mean_token_accuracy": 0.9939067363739014,
      "num_tokens": 22176913.0,
      "step": 345
    },
    {
      "epoch": 0.17232890201870998,
      "grad_norm": 0.05258825421333313,
      "learning_rate": 2.0467856145804803e-05,
      "loss": 0.0173,
      "mean_token_accuracy": 0.9933236837387085,
      "num_tokens": 22497434.0,
      "step": 350
    },
    {
      "epoch": 0.17479074347612014,
      "grad_norm": 0.06009254977107048,
      "learning_rate": 2.0436666465946293e-05,
      "loss": 0.0159,
      "mean_token_accuracy": 0.9938840627670288,
      "num_tokens": 22817721.0,
      "step": 355
    },
    {
      "epoch": 0.17725258493353027,
      "grad_norm": 0.04241907596588135,
      "learning_rate": 2.0405050136092498e-05,
      "loss": 0.0143,
      "mean_token_accuracy": 0.9944479584693908,
      "num_tokens": 23139931.0,
      "step": 360
    },
    {
      "epoch": 0.17971442639094043,
      "grad_norm": 0.05310116335749626,
      "learning_rate": 2.03730090852107e-05,
      "loss": 0.0165,
      "mean_token_accuracy": 0.9938408613204956,
      "num_tokens": 23462350.0,
      "step": 365
    },
    {
      "epoch": 0.18217626784835056,
      "grad_norm": 0.05389350652694702,
      "learning_rate": 2.034054526818113e-05,
      "loss": 0.0175,
      "mean_token_accuracy": 0.9935489892959595,
      "num_tokens": 23783401.0,
      "step": 370
    },
    {
      "epoch": 0.18463810930576072,
      "grad_norm": 0.054103367030620575,
      "learning_rate": 2.0307660665677727e-05,
      "loss": 0.0158,
      "mean_token_accuracy": 0.9939422011375427,
      "num_tokens": 24104565.0,
      "step": 375
    },
    {
      "epoch": 0.18709995076317085,
      "grad_norm": 0.04009604454040527,
      "learning_rate": 2.027435728404728e-05,
      "loss": 0.0156,
      "mean_token_accuracy": 0.9941097736358643,
      "num_tokens": 24425664.0,
      "step": 380
    },
    {
      "epoch": 0.189561792220581,
      "grad_norm": 0.04380296170711517,
      "learning_rate": 2.0240637155187022e-05,
      "loss": 0.0152,
      "mean_token_accuracy": 0.9941174745559692,
      "num_tokens": 24748557.0,
      "step": 385
    },
    {
      "epoch": 0.19202363367799113,
      "grad_norm": 0.032586026936769485,
      "learning_rate": 2.0206502336420666e-05,
      "loss": 0.0135,
      "mean_token_accuracy": 0.9946724891662597,
      "num_tokens": 25069808.0,
      "step": 390
    },
    {
      "epoch": 0.1944854751354013,
      "grad_norm": 0.06130707263946533,
      "learning_rate": 2.0171954910372855e-05,
      "loss": 0.0197,
      "mean_token_accuracy": 0.9931009531021118,
      "num_tokens": 25390913.0,
      "step": 395
    },
    {
      "epoch": 0.19694731659281142,
      "grad_norm": 0.044839657843112946,
      "learning_rate": 2.0136996984842144e-05,
      "loss": 0.0156,
      "mean_token_accuracy": 0.9942690134048462,
      "num_tokens": 25711590.0,
      "step": 400
    },
    {
      "epoch": 0.19940915805022155,
      "grad_norm": 0.03433138132095337,
      "learning_rate": 2.0101630692672366e-05,
      "loss": 0.0134,
      "mean_token_accuracy": 0.9945015668869018,
      "num_tokens": 26033049.0,
      "step": 405
    },
    {
      "epoch": 0.2018709995076317,
      "grad_norm": 0.06145159527659416,
      "learning_rate": 2.006585819162251e-05,
      "loss": 0.0161,
      "mean_token_accuracy": 0.9938944458961487,
      "num_tokens": 26355422.0,
      "step": 410
    },
    {
      "epoch": 0.20433284096504184,
      "grad_norm": 0.046625472605228424,
      "learning_rate": 2.002968166423509e-05,
      "loss": 0.0145,
      "mean_token_accuracy": 0.9942839503288269,
      "num_tokens": 26676082.0,
      "step": 415
    },
    {
      "epoch": 0.206794682422452,
      "grad_norm": 0.03417025879025459,
      "learning_rate": 1.999310331770294e-05,
      "loss": 0.0138,
      "mean_token_accuracy": 0.9944490194320679,
      "num_tokens": 26997020.0,
      "step": 420
    },
    {
      "epoch": 0.20925652387986213,
      "grad_norm": 0.04904766008257866,
      "learning_rate": 1.9956125383734614e-05,
      "loss": 0.017,
      "mean_token_accuracy": 0.9935599088668823,
      "num_tokens": 27317984.0,
      "step": 425
    },
    {
      "epoch": 0.21171836533727229,
      "grad_norm": 0.03379844129085541,
      "learning_rate": 1.9918750118418164e-05,
      "loss": 0.0149,
      "mean_token_accuracy": 0.9941614151000977,
      "num_tokens": 27638796.0,
      "step": 430
    },
    {
      "epoch": 0.21418020679468242,
      "grad_norm": 0.03055359609425068,
      "learning_rate": 1.988097980208353e-05,
      "loss": 0.0147,
      "mean_token_accuracy": 0.9942783713340759,
      "num_tokens": 27960939.0,
      "step": 435
    },
    {
      "epoch": 0.21664204825209257,
      "grad_norm": 0.03959130495786667,
      "learning_rate": 1.98428167391634e-05,
      "loss": 0.0139,
      "mean_token_accuracy": 0.9945441961288453,
      "num_tokens": 28281371.0,
      "step": 440
    },
    {
      "epoch": 0.2191038897095027,
      "grad_norm": 0.034778300672769547,
      "learning_rate": 1.980426325805261e-05,
      "loss": 0.0173,
      "mean_token_accuracy": 0.9936829090118409,
      "num_tokens": 28602755.0,
      "step": 445
    },
    {
      "epoch": 0.22156573116691286,
      "grad_norm": 0.054818179458379745,
      "learning_rate": 1.97653217109661e-05,
      "loss": 0.0158,
      "mean_token_accuracy": 0.9938953042030334,
      "num_tokens": 28924168.0,
      "step": 450
    },
    {
      "epoch": 0.224027572624323,
      "grad_norm": 0.030057087540626526,
      "learning_rate": 1.9725994473795378e-05,
      "loss": 0.0148,
      "mean_token_accuracy": 0.9941797971725463,
      "num_tokens": 29246171.0,
      "step": 455
    },
    {
      "epoch": 0.22648941408173315,
      "grad_norm": 0.05861424282193184,
      "learning_rate": 1.968628394596358e-05,
      "loss": 0.0144,
      "mean_token_accuracy": 0.9942707657814026,
      "num_tokens": 29569027.0,
      "step": 460
    },
    {
      "epoch": 0.22895125553914328,
      "grad_norm": 0.03463579714298248,
      "learning_rate": 1.9646192550279074e-05,
      "loss": 0.0148,
      "mean_token_accuracy": 0.9943474292755127,
      "num_tokens": 29890638.0,
      "step": 465
    },
    {
      "epoch": 0.23141309699655344,
      "grad_norm": 0.03462537005543709,
      "learning_rate": 1.9605722732787628e-05,
      "loss": 0.014,
      "mean_token_accuracy": 0.9945291399955749,
      "num_tokens": 30212106.0,
      "step": 470
    },
    {
      "epoch": 0.23387493845396357,
      "grad_norm": 0.03469887748360634,
      "learning_rate": 1.9564876962623197e-05,
      "loss": 0.0167,
      "mean_token_accuracy": 0.9939306259155274,
      "num_tokens": 30534173.0,
      "step": 475
    },
    {
      "epoch": 0.2363367799113737,
      "grad_norm": 0.03356148675084114,
      "learning_rate": 1.952365773185726e-05,
      "loss": 0.0179,
      "mean_token_accuracy": 0.9932782292366028,
      "num_tokens": 30855988.0,
      "step": 480
    },
    {
      "epoch": 0.23879862136878385,
      "grad_norm": 0.05688195675611496,
      "learning_rate": 1.9482067555346758e-05,
      "loss": 0.0164,
      "mean_token_accuracy": 0.9938588380813599,
      "num_tokens": 31176045.0,
      "step": 485
    },
    {
      "epoch": 0.24126046282619398,
      "grad_norm": 0.03223969042301178,
      "learning_rate": 1.94401089705807e-05,
      "loss": 0.0172,
      "mean_token_accuracy": 0.9935418725013733,
      "num_tokens": 31497673.0,
      "step": 490
    },
    {
      "epoch": 0.24372230428360414,
      "grad_norm": 0.027766678482294083,
      "learning_rate": 1.9397784537525315e-05,
      "loss": 0.0153,
      "mean_token_accuracy": 0.9940999031066895,
      "num_tokens": 31818418.0,
      "step": 495
    },
    {
      "epoch": 0.24618414574101427,
      "grad_norm": 0.03331609442830086,
      "learning_rate": 1.935509683846787e-05,
      "loss": 0.0143,
      "mean_token_accuracy": 0.9943779587745667,
      "num_tokens": 32140371.0,
      "step": 500
    },
    {
      "epoch": 0.24864598719842443,
      "grad_norm": 0.052040133625268936,
      "learning_rate": 1.9312048477859128e-05,
      "loss": 0.0159,
      "mean_token_accuracy": 0.9938185095787049,
      "num_tokens": 32462318.0,
      "step": 505
    },
    {
      "epoch": 0.2511078286558346,
      "grad_norm": 0.029004910960793495,
      "learning_rate": 1.9268642082154432e-05,
      "loss": 0.0145,
      "mean_token_accuracy": 0.9943286895751953,
      "num_tokens": 32783640.0,
      "step": 510
    },
    {
      "epoch": 0.2535696701132447,
      "grad_norm": 0.03675747662782669,
      "learning_rate": 1.9224880299653475e-05,
      "loss": 0.0161,
      "mean_token_accuracy": 0.9940426826477051,
      "num_tokens": 33104542.0,
      "step": 515
    }
  ],
  "logging_steps": 5,
  "max_steps": 2031,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4742460103760282e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}