{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9906542056074765,
  "eval_steps": 100,
  "global_step": 780,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01917086029235562,
      "grad_norm": 10.80891227722168,
      "learning_rate": 1.282051282051282e-05,
      "loss": 2.5867,
      "num_input_tokens_seen": 85900,
      "step": 5
    },
    {
      "epoch": 0.03834172058471124,
      "grad_norm": 5.320851802825928,
      "learning_rate": 2.564102564102564e-05,
      "loss": 1.778,
      "num_input_tokens_seen": 168784,
      "step": 10
    },
    {
      "epoch": 0.05751258087706686,
      "grad_norm": 2.427093982696533,
      "learning_rate": 3.846153846153846e-05,
      "loss": 1.5006,
      "num_input_tokens_seen": 262708,
      "step": 15
    },
    {
      "epoch": 0.07668344116942248,
      "grad_norm": 2.143993854522705,
      "learning_rate": 5.128205128205128e-05,
      "loss": 1.3452,
      "num_input_tokens_seen": 350572,
      "step": 20
    },
    {
      "epoch": 0.09585430146177809,
      "grad_norm": 2.46453595161438,
      "learning_rate": 6.410256410256412e-05,
      "loss": 1.2953,
      "num_input_tokens_seen": 441976,
      "step": 25
    },
    {
      "epoch": 0.11502516175413371,
      "grad_norm": 2.382268190383911,
      "learning_rate": 7.692307692307693e-05,
      "loss": 1.3104,
      "num_input_tokens_seen": 525052,
      "step": 30
    },
    {
      "epoch": 0.13419602204648934,
      "grad_norm": 2.990694761276245,
      "learning_rate": 8.974358974358975e-05,
      "loss": 1.306,
      "num_input_tokens_seen": 626524,
      "step": 35
    },
    {
      "epoch": 0.15336688233884496,
      "grad_norm": 1.8448060750961304,
      "learning_rate": 9.99995506314361e-05,
      "loss": 1.2473,
      "num_input_tokens_seen": 709868,
      "step": 40
    },
    {
      "epoch": 0.17253774263120059,
      "grad_norm": 2.6468124389648438,
      "learning_rate": 9.998382357979809e-05,
      "loss": 1.2091,
      "num_input_tokens_seen": 823312,
      "step": 45
    },
    {
      "epoch": 0.19170860292355618,
      "grad_norm": 1.919690728187561,
      "learning_rate": 9.994563617659665e-05,
      "loss": 1.1985,
      "num_input_tokens_seen": 915100,
      "step": 50
    },
    {
      "epoch": 0.2108794632159118,
      "grad_norm": 2.13997483253479,
      "learning_rate": 9.988500558143337e-05,
      "loss": 1.1922,
      "num_input_tokens_seen": 1014472,
      "step": 55
    },
    {
      "epoch": 0.23005032350826743,
      "grad_norm": 1.7454973459243774,
      "learning_rate": 9.980195903881232e-05,
      "loss": 1.2273,
      "num_input_tokens_seen": 1111288,
      "step": 60
    },
    {
      "epoch": 0.24922118380062305,
      "grad_norm": 2.0489871501922607,
      "learning_rate": 9.969653386589748e-05,
      "loss": 1.1729,
      "num_input_tokens_seen": 1193792,
      "step": 65
    },
    {
      "epoch": 0.2683920440929787,
      "grad_norm": 1.851652979850769,
      "learning_rate": 9.956877743574438e-05,
      "loss": 1.188,
      "num_input_tokens_seen": 1293416,
      "step": 70
    },
    {
      "epoch": 0.2875629043853343,
      "grad_norm": 2.3986475467681885,
      "learning_rate": 9.94187471560127e-05,
      "loss": 1.1459,
      "num_input_tokens_seen": 1383712,
      "step": 75
    },
    {
      "epoch": 0.3067337646776899,
      "grad_norm": 1.6811550855636597,
      "learning_rate": 9.924651044317017e-05,
      "loss": 1.1561,
      "num_input_tokens_seen": 1483596,
      "step": 80
    },
    {
      "epoch": 0.3259046249700455,
      "grad_norm": 2.3249671459198,
      "learning_rate": 9.90521446921987e-05,
      "loss": 1.1224,
      "num_input_tokens_seen": 1561392,
      "step": 85
    },
    {
      "epoch": 0.34507548526240117,
      "grad_norm": 2.17244553565979,
      "learning_rate": 9.883573724181683e-05,
      "loss": 1.1283,
      "num_input_tokens_seen": 1660352,
      "step": 90
    },
    {
      "epoch": 0.36424634555475677,
      "grad_norm": 2.0246732234954834,
      "learning_rate": 9.859738533523383e-05,
      "loss": 1.155,
      "num_input_tokens_seen": 1751904,
      "step": 95
    },
    {
      "epoch": 0.38341720584711236,
      "grad_norm": 1.6448779106140137,
      "learning_rate": 9.833719607645324e-05,
      "loss": 1.0645,
      "num_input_tokens_seen": 1844404,
      "step": 100
    },
    {
      "epoch": 0.38341720584711236,
      "eval_loss": 0.9265391826629639,
      "eval_runtime": 0.8899,
      "eval_samples_per_second": 168.564,
      "eval_steps_per_second": 42.703,
      "num_input_tokens_seen": 1844404,
      "step": 100
    },
    {
      "epoch": 0.402588066139468,
      "grad_norm": 3.241382598876953,
      "learning_rate": 9.805528638214542e-05,
      "loss": 1.1597,
      "num_input_tokens_seen": 1930376,
      "step": 105
    },
    {
      "epoch": 0.4217589264318236,
      "grad_norm": 1.7404630184173584,
      "learning_rate": 9.77517829291108e-05,
      "loss": 1.112,
      "num_input_tokens_seen": 2014196,
      "step": 110
    },
    {
      "epoch": 0.44092978672417926,
      "grad_norm": 2.0619559288024902,
      "learning_rate": 9.742682209735727e-05,
      "loss": 1.1078,
      "num_input_tokens_seen": 2105080,
      "step": 115
    },
    {
      "epoch": 0.46010064701653486,
      "grad_norm": 1.618997573852539,
      "learning_rate": 9.708054990881763e-05,
      "loss": 1.123,
      "num_input_tokens_seen": 2212296,
      "step": 120
    },
    {
      "epoch": 0.4792715073088905,
      "grad_norm": 2.0891501903533936,
      "learning_rate": 9.671312196173412e-05,
      "loss": 1.1139,
      "num_input_tokens_seen": 2297740,
      "step": 125
    },
    {
      "epoch": 0.4984423676012461,
      "grad_norm": 2.8104231357574463,
      "learning_rate": 9.632470336074009e-05,
      "loss": 1.1419,
      "num_input_tokens_seen": 2393552,
      "step": 130
    },
    {
      "epoch": 0.5176132278936018,
      "grad_norm": 2.313002586364746,
      "learning_rate": 9.591546864266983e-05,
      "loss": 1.1122,
      "num_input_tokens_seen": 2485636,
      "step": 135
    },
    {
      "epoch": 0.5367840881859574,
      "grad_norm": 1.6471989154815674,
      "learning_rate": 9.548560169812997e-05,
      "loss": 1.0872,
      "num_input_tokens_seen": 2579380,
      "step": 140
    },
    {
      "epoch": 0.555954948478313,
      "grad_norm": 1.8052936792373657,
      "learning_rate": 9.50352956888678e-05,
      "loss": 1.1084,
      "num_input_tokens_seen": 2660580,
      "step": 145
    },
    {
      "epoch": 0.5751258087706685,
      "grad_norm": 1.9831300973892212,
      "learning_rate": 9.45647529609736e-05,
      "loss": 1.0753,
      "num_input_tokens_seen": 2752664,
      "step": 150
    },
    {
      "epoch": 0.5942966690630243,
      "grad_norm": 1.9232532978057861,
      "learning_rate": 9.4074184953956e-05,
      "loss": 1.0932,
      "num_input_tokens_seen": 2835612,
      "step": 155
    },
    {
      "epoch": 0.6134675293553798,
      "grad_norm": 3.607057571411133,
      "learning_rate": 9.356381210573091e-05,
      "loss": 1.0856,
      "num_input_tokens_seen": 2927884,
      "step": 160
    },
    {
      "epoch": 0.6326383896477354,
      "grad_norm": 1.5196906328201294,
      "learning_rate": 9.303386375356752e-05,
      "loss": 1.0765,
      "num_input_tokens_seen": 3011316,
      "step": 165
    },
    {
      "epoch": 0.651809249940091,
      "grad_norm": 2.0994279384613037,
      "learning_rate": 9.248457803103476e-05,
      "loss": 1.0743,
      "num_input_tokens_seen": 3113324,
      "step": 170
    },
    {
      "epoch": 0.6709801102324466,
      "grad_norm": 2.0873262882232666,
      "learning_rate": 9.191620176099558e-05,
      "loss": 1.0799,
      "num_input_tokens_seen": 3205472,
      "step": 175
    },
    {
      "epoch": 0.6901509705248023,
      "grad_norm": 1.7372593879699707,
      "learning_rate": 9.132899034469647e-05,
      "loss": 1.095,
      "num_input_tokens_seen": 3303772,
      "step": 180
    },
    {
      "epoch": 0.7093218308171579,
      "grad_norm": 1.7090203762054443,
      "learning_rate": 9.072320764700223e-05,
      "loss": 1.0832,
      "num_input_tokens_seen": 3386080,
      "step": 185
    },
    {
      "epoch": 0.7284926911095135,
      "grad_norm": 1.707291603088379,
      "learning_rate": 9.009912587782771e-05,
      "loss": 1.0376,
      "num_input_tokens_seen": 3471524,
      "step": 190
    },
    {
      "epoch": 0.7476635514018691,
      "grad_norm": 1.663960576057434,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.0802,
      "num_input_tokens_seen": 3556336,
      "step": 195
    },
    {
      "epoch": 0.7668344116942247,
      "grad_norm": 1.8464930057525635,
      "learning_rate": 8.879719495234363e-05,
      "loss": 1.0769,
      "num_input_tokens_seen": 3640408,
      "step": 200
    },
    {
      "epoch": 0.7668344116942247,
      "eval_loss": 0.862065851688385,
      "eval_runtime": 0.8351,
      "eval_samples_per_second": 179.628,
      "eval_steps_per_second": 45.506,
      "num_input_tokens_seen": 3640408,
      "step": 200
    },
    {
      "epoch": 0.7860052719865804,
      "grad_norm": 1.7220999002456665,
      "learning_rate": 8.811993082183243e-05,
      "loss": 1.078,
      "num_input_tokens_seen": 3731324,
      "step": 205
    },
    {
      "epoch": 0.805176132278936,
      "grad_norm": 1.7034516334533691,
      "learning_rate": 8.742553740855506e-05,
      "loss": 1.0565,
      "num_input_tokens_seen": 3822944,
      "step": 210
    },
    {
      "epoch": 0.8243469925712916,
      "grad_norm": 2.327296257019043,
      "learning_rate": 8.671432673986494e-05,
      "loss": 1.0721,
      "num_input_tokens_seen": 3922476,
      "step": 215
    },
    {
      "epoch": 0.8435178528636472,
      "grad_norm": 1.6464370489120483,
      "learning_rate": 8.598661839998972e-05,
      "loss": 1.0573,
      "num_input_tokens_seen": 4003388,
      "step": 220
    },
    {
      "epoch": 0.8626887131560029,
      "grad_norm": 2.116698741912842,
      "learning_rate": 8.524273938642538e-05,
      "loss": 1.0459,
      "num_input_tokens_seen": 4084052,
      "step": 225
    },
    {
      "epoch": 0.8818595734483585,
      "grad_norm": 1.5513197183609009,
      "learning_rate": 8.448302396299905e-05,
      "loss": 1.073,
      "num_input_tokens_seen": 4177072,
      "step": 230
    },
    {
      "epoch": 0.9010304337407141,
      "grad_norm": 1.8118634223937988,
      "learning_rate": 8.370781350966683e-05,
      "loss": 1.0786,
      "num_input_tokens_seen": 4272004,
      "step": 235
    },
    {
      "epoch": 0.9202012940330697,
      "grad_norm": 1.542823076248169,
      "learning_rate": 8.291745636911382e-05,
      "loss": 1.0556,
      "num_input_tokens_seen": 4367124,
      "step": 240
    },
    {
      "epoch": 0.9393721543254253,
      "grad_norm": 1.5214637517929077,
      "learning_rate": 8.211230769022551e-05,
      "loss": 1.052,
      "num_input_tokens_seen": 4454860,
      "step": 245
    },
    {
      "epoch": 0.958543014617781,
      "grad_norm": 1.5787030458450317,
      "learning_rate": 8.129272926850079e-05,
      "loss": 1.032,
      "num_input_tokens_seen": 4544744,
      "step": 250
    },
    {
      "epoch": 0.9777138749101366,
      "grad_norm": 1.842089295387268,
      "learning_rate": 8.045908938347828e-05,
      "loss": 1.0585,
      "num_input_tokens_seen": 4627284,
      "step": 255
    },
    {
      "epoch": 0.9968847352024922,
      "grad_norm": 1.8476406335830688,
      "learning_rate": 7.961176263324901e-05,
      "loss": 1.0045,
      "num_input_tokens_seen": 4715336,
      "step": 260
    },
    {
      "epoch": 1.0160555954948478,
      "grad_norm": 1.540380835533142,
      "learning_rate": 7.875112976612984e-05,
      "loss": 0.8789,
      "num_input_tokens_seen": 4811720,
      "step": 265
    },
    {
      "epoch": 1.0352264557872035,
      "grad_norm": 1.593477725982666,
      "learning_rate": 7.787757750957334e-05,
      "loss": 0.8548,
      "num_input_tokens_seen": 4904124,
      "step": 270
    },
    {
      "epoch": 1.054397316079559,
      "grad_norm": 2.4607889652252197,
      "learning_rate": 7.699149839639086e-05,
      "loss": 0.8393,
      "num_input_tokens_seen": 4997508,
      "step": 275
    },
    {
      "epoch": 1.0735681763719147,
      "grad_norm": 2.0560553073883057,
      "learning_rate": 7.609329058836695e-05,
      "loss": 0.8517,
      "num_input_tokens_seen": 5102324,
      "step": 280
    },
    {
      "epoch": 1.0927390366642702,
      "grad_norm": 1.5116240978240967,
      "learning_rate": 7.518335769734439e-05,
      "loss": 0.8498,
      "num_input_tokens_seen": 5203192,
      "step": 285
    },
    {
      "epoch": 1.111909896956626,
      "grad_norm": 1.517767071723938,
      "learning_rate": 7.426210860386031e-05,
      "loss": 0.8269,
      "num_input_tokens_seen": 5300184,
      "step": 290
    },
    {
      "epoch": 1.1310807572489816,
      "grad_norm": 1.6254216432571411,
      "learning_rate": 7.332995727341462e-05,
      "loss": 0.8496,
      "num_input_tokens_seen": 5405724,
      "step": 295
    },
    {
      "epoch": 1.150251617541337,
      "grad_norm": 1.6421043872833252,
      "learning_rate": 7.238732257045372e-05,
      "loss": 0.849,
      "num_input_tokens_seen": 5504644,
      "step": 300
    },
    {
      "epoch": 1.150251617541337,
      "eval_loss": 0.8501759767532349,
      "eval_runtime": 0.8525,
      "eval_samples_per_second": 175.946,
      "eval_steps_per_second": 44.573,
      "num_input_tokens_seen": 5504644,
      "step": 300
    },
    {
      "epoch": 1.1694224778336928,
      "grad_norm": 1.7481452226638794,
      "learning_rate": 7.143462807015271e-05,
      "loss": 0.8823,
      "num_input_tokens_seen": 5597560,
      "step": 305
    },
    {
      "epoch": 1.1885933381260485,
      "grad_norm": 1.725755214691162,
      "learning_rate": 7.047230186808085e-05,
      "loss": 0.8701,
      "num_input_tokens_seen": 5691244,
      "step": 310
    },
    {
      "epoch": 1.207764198418404,
      "grad_norm": 1.4096667766571045,
      "learning_rate": 6.950077638783578e-05,
      "loss": 0.8501,
      "num_input_tokens_seen": 5773336,
      "step": 315
    },
    {
      "epoch": 1.2269350587107597,
      "grad_norm": 1.5906323194503784,
      "learning_rate": 6.8520488186733e-05,
      "loss": 0.8684,
      "num_input_tokens_seen": 5849224,
      "step": 320
    },
    {
      "epoch": 1.2461059190031152,
      "grad_norm": 2.2204673290252686,
      "learning_rate": 6.753187775963773e-05,
      "loss": 0.8688,
      "num_input_tokens_seen": 5943104,
      "step": 325
    },
    {
      "epoch": 1.2652767792954709,
      "grad_norm": 1.40131413936615,
      "learning_rate": 6.653538934102743e-05,
      "loss": 0.8495,
      "num_input_tokens_seen": 6051232,
      "step": 330
    },
    {
      "epoch": 1.2844476395878264,
      "grad_norm": 1.578782558441162,
      "learning_rate": 6.553147070537413e-05,
      "loss": 0.8218,
      "num_input_tokens_seen": 6137520,
      "step": 335
    },
    {
      "epoch": 1.303618499880182,
      "grad_norm": 1.5068399906158447,
      "learning_rate": 6.452057296593568e-05,
      "loss": 0.8964,
      "num_input_tokens_seen": 6237012,
      "step": 340
    },
    {
      "epoch": 1.3227893601725378,
      "grad_norm": 1.6630327701568604,
      "learning_rate": 6.350315037204714e-05,
      "loss": 0.8748,
      "num_input_tokens_seen": 6332764,
      "step": 345
    },
    {
      "epoch": 1.3419602204648933,
      "grad_norm": 1.569263219833374,
      "learning_rate": 6.247966010500258e-05,
      "loss": 0.8478,
      "num_input_tokens_seen": 6416688,
      "step": 350
    },
    {
      "epoch": 1.361131080757249,
      "grad_norm": 1.4157441854476929,
      "learning_rate": 6.145056207261964e-05,
      "loss": 0.8624,
      "num_input_tokens_seen": 6507660,
      "step": 355
    },
    {
      "epoch": 1.3803019410496047,
      "grad_norm": 1.4510629177093506,
      "learning_rate": 6.0416318702578826e-05,
      "loss": 0.851,
      "num_input_tokens_seen": 6608708,
      "step": 360
    },
    {
      "epoch": 1.3994728013419602,
      "grad_norm": 1.660876989364624,
      "learning_rate": 5.9377394734630464e-05,
      "loss": 0.8401,
      "num_input_tokens_seen": 6700852,
      "step": 365
    },
    {
      "epoch": 1.4186436616343159,
      "grad_norm": 1.4707056283950806,
      "learning_rate": 5.833425701176294e-05,
      "loss": 0.8646,
      "num_input_tokens_seen": 6792244,
      "step": 370
    },
    {
      "epoch": 1.4378145219266716,
      "grad_norm": 1.563291311264038,
      "learning_rate": 5.728737427042548e-05,
      "loss": 0.8732,
      "num_input_tokens_seen": 6875536,
      "step": 375
    },
    {
      "epoch": 1.456985382219027,
      "grad_norm": 1.286574125289917,
      "learning_rate": 5.623721692990039e-05,
      "loss": 0.8449,
      "num_input_tokens_seen": 6958384,
      "step": 380
    },
    {
      "epoch": 1.4761562425113828,
      "grad_norm": 1.413732886314392,
      "learning_rate": 5.518425688091906e-05,
      "loss": 0.8459,
      "num_input_tokens_seen": 7040740,
      "step": 385
    },
    {
      "epoch": 1.4953271028037383,
      "grad_norm": 1.3040345907211304,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.8539,
      "num_input_tokens_seen": 7132892,
      "step": 390
    },
    {
      "epoch": 1.514497963096094,
      "grad_norm": 1.4091562032699585,
      "learning_rate": 5.307182230492088e-05,
      "loss": 0.816,
      "num_input_tokens_seen": 7217480,
      "step": 395
    },
    {
      "epoch": 1.5336688233884495,
      "grad_norm": 1.5895339250564575,
      "learning_rate": 5.201329700547076e-05,
      "loss": 0.8612,
      "num_input_tokens_seen": 7316212,
      "step": 400
    },
    {
      "epoch": 1.5336688233884495,
      "eval_loss": 0.8288899064064026,
      "eval_runtime": 0.8525,
      "eval_samples_per_second": 175.948,
      "eval_steps_per_second": 44.574,
      "num_input_tokens_seen": 7316212,
      "step": 400
    },
    {
      "epoch": 1.5528396836808052,
      "grad_norm": 1.523808240890503,
      "learning_rate": 5.095386702616012e-05,
      "loss": 0.8411,
      "num_input_tokens_seen": 7397436,
      "step": 405
    },
    {
      "epoch": 1.5720105439731609,
      "grad_norm": 1.4366319179534912,
      "learning_rate": 4.989400842440289e-05,
      "loss": 0.8179,
      "num_input_tokens_seen": 7489804,
      "step": 410
    },
    {
      "epoch": 1.5911814042655164,
      "grad_norm": 1.335564136505127,
      "learning_rate": 4.883419745021554e-05,
      "loss": 0.8321,
      "num_input_tokens_seen": 7575200,
      "step": 415
    },
    {
      "epoch": 1.610352264557872,
      "grad_norm": 1.5225696563720703,
      "learning_rate": 4.7774910332213e-05,
      "loss": 0.8408,
      "num_input_tokens_seen": 7661620,
      "step": 420
    },
    {
      "epoch": 1.6295231248502278,
      "grad_norm": 1.286909580230713,
      "learning_rate": 4.6716623063614094e-05,
      "loss": 0.8335,
      "num_input_tokens_seen": 7751008,
      "step": 425
    },
    {
      "epoch": 1.6486939851425833,
      "grad_norm": 1.399095058441162,
      "learning_rate": 4.565981118835299e-05,
      "loss": 0.8586,
      "num_input_tokens_seen": 7847504,
      "step": 430
    },
    {
      "epoch": 1.6678648454349387,
      "grad_norm": 1.5877128839492798,
      "learning_rate": 4.4604949587392234e-05,
      "loss": 0.8451,
      "num_input_tokens_seen": 7940004,
      "step": 435
    },
    {
      "epoch": 1.6870357057272947,
      "grad_norm": 1.661634087562561,
      "learning_rate": 4.355251226533396e-05,
      "loss": 0.8517,
      "num_input_tokens_seen": 8037312,
      "step": 440
    },
    {
      "epoch": 1.7062065660196502,
      "grad_norm": 1.2558486461639404,
      "learning_rate": 4.250297213742473e-05,
      "loss": 0.8115,
      "num_input_tokens_seen": 8134436,
      "step": 445
    },
    {
      "epoch": 1.7253774263120056,
      "grad_norm": 1.4006855487823486,
      "learning_rate": 4.145680081704989e-05,
      "loss": 0.8471,
      "num_input_tokens_seen": 8223592,
      "step": 450
    },
    {
      "epoch": 1.7445482866043613,
      "grad_norm": 1.5870461463928223,
      "learning_rate": 4.0414468403813095e-05,
      "loss": 0.8582,
      "num_input_tokens_seen": 8312984,
      "step": 455
    },
    {
      "epoch": 1.763719146896717,
      "grad_norm": 1.4359045028686523,
      "learning_rate": 3.937644327229572e-05,
      "loss": 0.8146,
      "num_input_tokens_seen": 8402888,
      "step": 460
    },
    {
      "epoch": 1.7828900071890725,
      "grad_norm": 1.4591436386108398,
      "learning_rate": 3.8343191861591795e-05,
      "loss": 0.8276,
      "num_input_tokens_seen": 8503552,
      "step": 465
    },
    {
      "epoch": 1.8020608674814282,
      "grad_norm": 1.6432543992996216,
      "learning_rate": 3.7315178465712366e-05,
      "loss": 0.8524,
      "num_input_tokens_seen": 8604500,
      "step": 470
    },
    {
      "epoch": 1.821231727773784,
      "grad_norm": 1.58722984790802,
      "learning_rate": 3.629286502495394e-05,
      "loss": 0.8257,
      "num_input_tokens_seen": 8690612,
      "step": 475
    },
    {
      "epoch": 1.8404025880661394,
      "grad_norm": 1.3321154117584229,
      "learning_rate": 3.52767109183244e-05,
      "loss": 0.8194,
      "num_input_tokens_seen": 8785132,
      "step": 480
    },
    {
      "epoch": 1.8595734483584951,
      "grad_norm": 1.8727712631225586,
      "learning_rate": 3.426717275712e-05,
      "loss": 0.8414,
      "num_input_tokens_seen": 8882700,
      "step": 485
    },
    {
      "epoch": 1.8787443086508508,
      "grad_norm": 1.427962303161621,
      "learning_rate": 3.326470417974604e-05,
      "loss": 0.8275,
      "num_input_tokens_seen": 8982636,
      "step": 490
    },
    {
      "epoch": 1.8979151689432063,
      "grad_norm": 1.391340970993042,
      "learning_rate": 3.226975564787322e-05,
      "loss": 0.8115,
      "num_input_tokens_seen": 9090140,
      "step": 495
    },
    {
      "epoch": 1.9170860292355618,
      "grad_norm": 1.465030312538147,
      "learning_rate": 3.1282774244021715e-05,
      "loss": 0.7934,
      "num_input_tokens_seen": 9167936,
      "step": 500
    },
    {
      "epoch": 1.9170860292355618,
      "eval_loss": 0.8071622252464294,
      "eval_runtime": 0.8763,
      "eval_samples_per_second": 171.177,
      "eval_steps_per_second": 43.365,
      "num_input_tokens_seen": 9167936,
      "step": 500
    },
    {
      "epoch": 1.9362568895279175,
      "grad_norm": 1.6803951263427734,
      "learning_rate": 3.0304203470663505e-05,
      "loss": 0.821,
      "num_input_tokens_seen": 9252204,
      "step": 505
    },
    {
      "epoch": 1.9554277498202732,
      "grad_norm": 1.4982653856277466,
      "learning_rate": 2.9334483050933503e-05,
      "loss": 0.7982,
      "num_input_tokens_seen": 9326444,
      "step": 510
    },
    {
      "epoch": 1.9745986101126287,
      "grad_norm": 1.5553169250488281,
      "learning_rate": 2.8374048731038898e-05,
      "loss": 0.8183,
      "num_input_tokens_seen": 9412396,
      "step": 515
    },
    {
      "epoch": 1.9937694704049844,
      "grad_norm": 1.176651954650879,
      "learning_rate": 2.7423332084455544e-05,
      "loss": 0.7837,
      "num_input_tokens_seen": 9497412,
      "step": 520
    },
    {
      "epoch": 2.01294033069734,
      "grad_norm": 1.2269119024276733,
      "learning_rate": 2.648276031799934e-05,
      "loss": 0.726,
      "num_input_tokens_seen": 9594720,
      "step": 525
    },
    {
      "epoch": 2.0321111909896956,
      "grad_norm": 1.4332973957061768,
      "learning_rate": 2.5552756079859903e-05,
      "loss": 0.6847,
      "num_input_tokens_seen": 9675564,
      "step": 530
    },
    {
      "epoch": 2.051282051282051,
      "grad_norm": 1.3018600940704346,
      "learning_rate": 2.4633737269682543e-05,
      "loss": 0.682,
      "num_input_tokens_seen": 9772140,
      "step": 535
    },
    {
      "epoch": 2.070452911574407,
      "grad_norm": 1.2701021432876587,
      "learning_rate": 2.3726116850783985e-05,
      "loss": 0.6643,
      "num_input_tokens_seen": 9850508,
      "step": 540
    },
    {
      "epoch": 2.0896237718667625,
      "grad_norm": 1.2966877222061157,
      "learning_rate": 2.283030266458644e-05,
      "loss": 0.6868,
      "num_input_tokens_seen": 9949592,
      "step": 545
    },
    {
      "epoch": 2.108794632159118,
      "grad_norm": 1.4499340057373047,
      "learning_rate": 2.194669724735296e-05,
      "loss": 0.6713,
      "num_input_tokens_seen": 10041244,
      "step": 550
    },
    {
      "epoch": 2.127965492451474,
      "grad_norm": 1.791567325592041,
      "learning_rate": 2.1075697649306835e-05,
      "loss": 0.6893,
      "num_input_tokens_seen": 10140004,
      "step": 555
    },
    {
      "epoch": 2.1471363527438294,
      "grad_norm": 1.4607737064361572,
      "learning_rate": 2.0217695256216195e-05,
      "loss": 0.6784,
      "num_input_tokens_seen": 10233820,
      "step": 560
    },
    {
      "epoch": 2.166307213036185,
      "grad_norm": 1.4586418867111206,
      "learning_rate": 1.937307561352373e-05,
      "loss": 0.6829,
      "num_input_tokens_seen": 10324844,
      "step": 565
    },
    {
      "epoch": 2.1854780733285404,
      "grad_norm": 1.4719526767730713,
      "learning_rate": 1.854221825310103e-05,
      "loss": 0.6775,
      "num_input_tokens_seen": 10413592,
      "step": 570
    },
    {
      "epoch": 2.2046489336208963,
      "grad_norm": 1.4231044054031372,
      "learning_rate": 1.7725496522704998e-05,
      "loss": 0.6872,
      "num_input_tokens_seen": 10503432,
      "step": 575
    },
    {
      "epoch": 2.223819793913252,
      "grad_norm": 1.3985334634780884,
      "learning_rate": 1.6923277418213117e-05,
      "loss": 0.65,
      "num_input_tokens_seen": 10600988,
      "step": 580
    },
    {
      "epoch": 2.2429906542056073,
      "grad_norm": 1.3148375749588013,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.6901,
      "num_input_tokens_seen": 10692664,
      "step": 585
    },
    {
      "epoch": 2.262161514497963,
      "grad_norm": 1.3653095960617065,
      "learning_rate": 1.536378232452003e-05,
      "loss": 0.6661,
      "num_input_tokens_seen": 10781516,
      "step": 590
    },
    {
      "epoch": 2.2813323747903187,
      "grad_norm": 1.4331799745559692,
      "learning_rate": 1.4607207098196852e-05,
      "loss": 0.669,
      "num_input_tokens_seen": 10874028,
      "step": 595
    },
    {
      "epoch": 2.300503235082674,
      "grad_norm": 1.3715401887893677,
      "learning_rate": 1.3866535708644334e-05,
      "loss": 0.6701,
      "num_input_tokens_seen": 10969348,
      "step": 600
    },
    {
      "epoch": 2.300503235082674,
      "eval_loss": 0.8050560355186462,
      "eval_runtime": 0.8838,
      "eval_samples_per_second": 169.723,
      "eval_steps_per_second": 42.997,
      "num_input_tokens_seen": 10969348,
      "step": 600
    },
    {
      "epoch": 2.31967409537503,
      "grad_norm": 1.2875298261642456,
      "learning_rate": 1.3142100978336069e-05,
      "loss": 0.6877,
      "num_input_tokens_seen": 11064696,
      "step": 605
    },
    {
      "epoch": 2.3388449556673856,
      "grad_norm": 1.2775810956954956,
      "learning_rate": 1.2434228433763657e-05,
      "loss": 0.6752,
      "num_input_tokens_seen": 11157516,
      "step": 610
    },
    {
      "epoch": 2.358015815959741,
      "grad_norm": 1.3270821571350098,
      "learning_rate": 1.1743236159160653e-05,
      "loss": 0.6915,
      "num_input_tokens_seen": 11236376,
      "step": 615
    },
    {
      "epoch": 2.377186676252097,
      "grad_norm": 1.2592318058013916,
      "learning_rate": 1.1069434653570631e-05,
      "loss": 0.6786,
      "num_input_tokens_seen": 11343512,
      "step": 620
    },
    {
      "epoch": 2.3963575365444525,
      "grad_norm": 1.4185535907745361,
      "learning_rate": 1.0413126691323666e-05,
      "loss": 0.6876,
      "num_input_tokens_seen": 11433156,
      "step": 625
    },
    {
      "epoch": 2.415528396836808,
      "grad_norm": 1.5168098211288452,
      "learning_rate": 9.774607185984002e-06,
      "loss": 0.6911,
      "num_input_tokens_seen": 11517328,
      "step": 630
    },
    {
      "epoch": 2.4346992571291635,
      "grad_norm": 1.2858244180679321,
      "learning_rate": 9.154163057829879e-06,
      "loss": 0.6618,
      "num_input_tokens_seen": 11602144,
      "step": 635
    },
    {
      "epoch": 2.4538701174215194,
      "grad_norm": 1.2297165393829346,
      "learning_rate": 8.552073104925295e-06,
      "loss": 0.6804,
      "num_input_tokens_seen": 11691216,
      "step": 640
    },
    {
      "epoch": 2.473040977713875,
      "grad_norm": 1.2545212507247925,
      "learning_rate": 7.968607877841332e-06,
      "loss": 0.6669,
      "num_input_tokens_seen": 11789340,
      "step": 645
    },
    {
      "epoch": 2.4922118380062304,
      "grad_norm": 1.3260319232940674,
      "learning_rate": 7.404029558083653e-06,
      "loss": 0.6847,
      "num_input_tokens_seen": 11884208,
      "step": 650
    },
    {
      "epoch": 2.5113826982985863,
      "grad_norm": 1.2979117631912231,
      "learning_rate": 6.858591840280626e-06,
      "loss": 0.6592,
      "num_input_tokens_seen": 11972124,
      "step": 655
    },
    {
      "epoch": 2.5305535585909418,
      "grad_norm": 1.2984734773635864,
      "learning_rate": 6.3325398181849845e-06,
      "loss": 0.6579,
      "num_input_tokens_seen": 12057320,
      "step": 660
    },
    {
      "epoch": 2.5497244188832973,
      "grad_norm": 1.2366037368774414,
      "learning_rate": 5.826109874540409e-06,
      "loss": 0.6666,
      "num_input_tokens_seen": 12154952,
      "step": 665
    },
    {
      "epoch": 2.5688952791756527,
      "grad_norm": 1.2756296396255493,
      "learning_rate": 5.33952957486234e-06,
      "loss": 0.6903,
      "num_input_tokens_seen": 12256604,
      "step": 670
    },
    {
      "epoch": 2.5880661394680087,
      "grad_norm": 1.3016470670700073,
      "learning_rate": 4.873017565180871e-06,
      "loss": 0.6654,
      "num_input_tokens_seen": 12341988,
      "step": 675
    },
    {
      "epoch": 2.607236999760364,
      "grad_norm": 1.3244975805282593,
      "learning_rate": 4.4267834737916296e-06,
      "loss": 0.6597,
      "num_input_tokens_seen": 12442644,
      "step": 680
    },
    {
      "epoch": 2.62640786005272,
      "grad_norm": 1.4668656587600708,
      "learning_rate": 4.001027817058789e-06,
      "loss": 0.6709,
      "num_input_tokens_seen": 12538688,
      "step": 685
    },
    {
      "epoch": 2.6455787203450756,
      "grad_norm": 1.4666439294815063,
      "learning_rate": 3.5959419093125946e-06,
      "loss": 0.6793,
      "num_input_tokens_seen": 12621632,
      "step": 690
    },
    {
      "epoch": 2.664749580637431,
      "grad_norm": 1.2680643796920776,
      "learning_rate": 3.211707776881739e-06,
      "loss": 0.6562,
      "num_input_tokens_seen": 12715832,
      "step": 695
    },
    {
      "epoch": 2.6839204409297865,
      "grad_norm": 1.3070735931396484,
      "learning_rate": 2.848498076299483e-06,
      "loss": 0.6579,
      "num_input_tokens_seen": 12814620,
      "step": 700
    },
    {
      "epoch": 2.6839204409297865,
      "eval_loss": 0.7903470396995544,
      "eval_runtime": 0.941,
      "eval_samples_per_second": 159.398,
      "eval_steps_per_second": 40.381,
      "num_input_tokens_seen": 12814620,
      "step": 700
    },
    {
      "epoch": 2.7030913012221425,
      "grad_norm": 1.4454238414764404,
      "learning_rate": 2.506476016719922e-06,
      "loss": 0.6818,
      "num_input_tokens_seen": 12909896,
      "step": 705
    },
    {
      "epoch": 2.722262161514498,
      "grad_norm": 1.249842882156372,
      "learning_rate": 2.1857952865796614e-06,
      "loss": 0.6655,
      "num_input_tokens_seen": 13001288,
      "step": 710
    },
    {
      "epoch": 2.7414330218068534,
      "grad_norm": 1.312296986579895,
      "learning_rate": 1.8865999845374793e-06,
      "loss": 0.656,
      "num_input_tokens_seen": 13094568,
      "step": 715
    },
    {
      "epoch": 2.7606038820992094,
      "grad_norm": 1.1614197492599487,
      "learning_rate": 1.6090245547232707e-06,
      "loss": 0.6664,
      "num_input_tokens_seen": 13181872,
      "step": 720
    },
    {
      "epoch": 2.779774742391565,
      "grad_norm": 1.249230146408081,
      "learning_rate": 1.353193726325247e-06,
      "loss": 0.6643,
      "num_input_tokens_seen": 13276044,
      "step": 725
    },
    {
      "epoch": 2.7989456026839203,
      "grad_norm": 1.3258079290390015,
      "learning_rate": 1.1192224575425848e-06,
      "loss": 0.6352,
      "num_input_tokens_seen": 13361008,
      "step": 730
    },
    {
      "epoch": 2.818116462976276,
      "grad_norm": 1.364700198173523,
      "learning_rate": 9.072158839286748e-07,
      "loss": 0.6686,
      "num_input_tokens_seen": 13458560,
      "step": 735
    },
    {
      "epoch": 2.8372873232686318,
      "grad_norm": 1.3140686750411987,
      "learning_rate": 7.172692711482021e-07,
      "loss": 0.6623,
      "num_input_tokens_seen": 13551928,
      "step": 740
    },
    {
      "epoch": 2.8564581835609872,
      "grad_norm": 1.4460844993591309,
      "learning_rate": 5.494679721693152e-07,
      "loss": 0.6658,
      "num_input_tokens_seen": 13632792,
      "step": 745
    },
    {
      "epoch": 2.875629043853343,
      "grad_norm": 1.2111197710037231,
      "learning_rate": 4.0388738891002366e-07,
      "loss": 0.6239,
      "num_input_tokens_seen": 13723172,
      "step": 750
    },
    {
      "epoch": 2.8947999041456987,
      "grad_norm": 1.2612218856811523,
      "learning_rate": 2.8059293835620003e-07,
      "loss": 0.6682,
      "num_input_tokens_seen": 13820332,
      "step": 755
    },
    {
      "epoch": 2.913970764438054,
      "grad_norm": 1.3601187467575073,
      "learning_rate": 1.7964002316628315e-07,
      "loss": 0.6729,
      "num_input_tokens_seen": 13907996,
      "step": 760
    },
    {
      "epoch": 2.9331416247304096,
      "grad_norm": 1.3947527408599854,
      "learning_rate": 1.0107400677596412e-07,
      "loss": 0.6736,
      "num_input_tokens_seen": 13993196,
      "step": 765
    },
    {
      "epoch": 2.9523124850227656,
      "grad_norm": 1.2355984449386597,
      "learning_rate": 4.493019301401446e-08,
      "loss": 0.6655,
      "num_input_tokens_seen": 14084984,
      "step": 770
    },
    {
      "epoch": 2.971483345315121,
      "grad_norm": 1.2893033027648926,
      "learning_rate": 1.1233810238425735e-08,
      "loss": 0.657,
      "num_input_tokens_seen": 14169848,
      "step": 775
    },
    {
      "epoch": 2.9906542056074765,
      "grad_norm": 1.3213859796524048,
      "learning_rate": 0.0,
      "loss": 0.6589,
      "num_input_tokens_seen": 14258488,
      "step": 780
    },
    {
      "epoch": 2.9906542056074765,
      "num_input_tokens_seen": 14258488,
      "step": 780,
      "total_flos": 3.0175424769490944e+16,
      "train_loss": 0.895275863011678,
      "train_runtime": 860.318,
      "train_samples_per_second": 58.206,
      "train_steps_per_second": 0.907
    }
  ],
  "logging_steps": 5,
  "max_steps": 780,
  "num_input_tokens_seen": 14258488,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.0175424769490944e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}