{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07284240787863483,
  "eval_steps": 75,
  "global_step": 1875,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003884928420193858,
      "grad_norm": 0.49890583753585815,
      "learning_rate": 7.759200756309999e-05,
      "loss": 1.8971,
      "step": 10
    },
    {
      "epoch": 0.0007769856840387716,
      "grad_norm": 1.6535608768463135,
      "learning_rate": 0.0001,
      "loss": 1.6661,
      "step": 20
    },
    {
      "epoch": 0.0011654785260581573,
      "grad_norm": 1.0714327096939087,
      "learning_rate": 0.0001,
      "loss": 1.4684,
      "step": 30
    },
    {
      "epoch": 0.0015539713680775432,
      "grad_norm": 0.6442272067070007,
      "learning_rate": 0.0001,
      "loss": 1.5553,
      "step": 40
    },
    {
      "epoch": 0.0019424642100969289,
      "grad_norm": 0.818639874458313,
      "learning_rate": 0.0001,
      "loss": 1.5007,
      "step": 50
    },
    {
      "epoch": 0.0023309570521163146,
      "grad_norm": 1.3463096618652344,
      "learning_rate": 0.0001,
      "loss": 1.2678,
      "step": 60
    },
    {
      "epoch": 0.0027194498941357005,
      "grad_norm": 0.8409688472747803,
      "learning_rate": 0.0001,
      "loss": 1.4836,
      "step": 70
    },
    {
      "epoch": 0.0029136963151453936,
      "eval_loss": 1.4955415725708008,
      "eval_runtime": 328.1939,
      "eval_samples_per_second": 1.587,
      "eval_steps_per_second": 1.587,
      "step": 75
    },
    {
      "epoch": 0.0031079427361550864,
      "grad_norm": 0.49311453104019165,
      "learning_rate": 0.0001,
      "loss": 1.5626,
      "step": 80
    },
    {
      "epoch": 0.0034964355781744723,
      "grad_norm": 0.5505372881889343,
      "learning_rate": 0.0001,
      "loss": 1.4427,
      "step": 90
    },
    {
      "epoch": 0.0038849284201938577,
      "grad_norm": 1.1296964883804321,
      "learning_rate": 0.0001,
      "loss": 1.4702,
      "step": 100
    },
    {
      "epoch": 0.004273421262213244,
      "grad_norm": 1.38261878490448,
      "learning_rate": 0.0001,
      "loss": 1.5806,
      "step": 110
    },
    {
      "epoch": 0.004661914104232629,
      "grad_norm": 0.5213516354560852,
      "learning_rate": 0.0001,
      "loss": 1.4675,
      "step": 120
    },
    {
      "epoch": 0.0050504069462520155,
      "grad_norm": 2.93784761428833,
      "learning_rate": 0.0001,
      "loss": 1.6413,
      "step": 130
    },
    {
      "epoch": 0.005438899788271401,
      "grad_norm": 0.6772735118865967,
      "learning_rate": 0.0001,
      "loss": 1.2942,
      "step": 140
    },
    {
      "epoch": 0.005827392630290787,
      "grad_norm": 1.1066700220108032,
      "learning_rate": 0.0001,
      "loss": 1.4082,
      "step": 150
    },
    {
      "epoch": 0.005827392630290787,
      "eval_loss": 1.4717903137207031,
      "eval_runtime": 419.3037,
      "eval_samples_per_second": 1.243,
      "eval_steps_per_second": 1.243,
      "step": 150
    },
    {
      "epoch": 0.006215885472310173,
      "grad_norm": 0.5077598690986633,
      "learning_rate": 0.0001,
      "loss": 1.6572,
      "step": 160
    },
    {
      "epoch": 0.006604378314329558,
      "grad_norm": 0.5666481256484985,
      "learning_rate": 0.0001,
      "loss": 1.7344,
      "step": 170
    },
    {
      "epoch": 0.0069928711563489445,
      "grad_norm": 0.7042965888977051,
      "learning_rate": 0.0001,
      "loss": 1.3634,
      "step": 180
    },
    {
      "epoch": 0.00738136399836833,
      "grad_norm": 0.6379776000976562,
      "learning_rate": 0.0001,
      "loss": 1.6191,
      "step": 190
    },
    {
      "epoch": 0.0077698568403877155,
      "grad_norm": 0.7309342622756958,
      "learning_rate": 0.0001,
      "loss": 1.2186,
      "step": 200
    },
    {
      "epoch": 0.008158349682407102,
      "grad_norm": 1.4138643741607666,
      "learning_rate": 0.0001,
      "loss": 1.5201,
      "step": 210
    },
    {
      "epoch": 0.008546842524426487,
      "grad_norm": 1.3856728076934814,
      "learning_rate": 0.0001,
      "loss": 1.4056,
      "step": 220
    },
    {
      "epoch": 0.00874108894543618,
      "eval_loss": 1.473658800125122,
      "eval_runtime": 413.7612,
      "eval_samples_per_second": 1.259,
      "eval_steps_per_second": 1.259,
      "step": 225
    },
    {
      "epoch": 0.008935335366445873,
      "grad_norm": 1.1668083667755127,
      "learning_rate": 0.0001,
      "loss": 1.5261,
      "step": 230
    },
    {
      "epoch": 0.009323828208465258,
      "grad_norm": 0.719367265701294,
      "learning_rate": 0.0001,
      "loss": 1.4151,
      "step": 240
    },
    {
      "epoch": 0.009712321050484645,
      "grad_norm": 0.7443403005599976,
      "learning_rate": 0.0001,
      "loss": 1.3723,
      "step": 250
    },
    {
      "epoch": 0.010100813892504031,
      "grad_norm": 0.8915978670120239,
      "learning_rate": 0.0001,
      "loss": 1.5165,
      "step": 260
    },
    {
      "epoch": 0.010489306734523416,
      "grad_norm": 0.7369945049285889,
      "learning_rate": 0.0001,
      "loss": 1.4225,
      "step": 270
    },
    {
      "epoch": 0.010877799576542802,
      "grad_norm": 1.2632057666778564,
      "learning_rate": 0.0001,
      "loss": 1.3462,
      "step": 280
    },
    {
      "epoch": 0.011266292418562187,
      "grad_norm": 1.6178512573242188,
      "learning_rate": 0.0001,
      "loss": 1.4283,
      "step": 290
    },
    {
      "epoch": 0.011654785260581575,
      "grad_norm": 2.717789649963379,
      "learning_rate": 0.0001,
      "loss": 1.4773,
      "step": 300
    },
    {
      "epoch": 0.011654785260581575,
      "eval_loss": 1.4709599018096924,
      "eval_runtime": 410.5517,
      "eval_samples_per_second": 1.269,
      "eval_steps_per_second": 1.269,
      "step": 300
    },
    {
      "epoch": 0.01204327810260096,
      "grad_norm": 3.8710834980010986,
      "learning_rate": 0.0001,
      "loss": 1.4183,
      "step": 310
    },
    {
      "epoch": 0.012431770944620345,
      "grad_norm": 1.1690031290054321,
      "learning_rate": 0.0001,
      "loss": 1.6159,
      "step": 320
    },
    {
      "epoch": 0.012820263786639731,
      "grad_norm": 1.422135829925537,
      "learning_rate": 0.0001,
      "loss": 1.5327,
      "step": 330
    },
    {
      "epoch": 0.013208756628659116,
      "grad_norm": 1.353925347328186,
      "learning_rate": 0.0001,
      "loss": 1.4782,
      "step": 340
    },
    {
      "epoch": 0.013597249470678504,
      "grad_norm": 0.8083727359771729,
      "learning_rate": 0.0001,
      "loss": 1.3199,
      "step": 350
    },
    {
      "epoch": 0.013985742312697889,
      "grad_norm": 0.6409865021705627,
      "learning_rate": 0.0001,
      "loss": 1.3829,
      "step": 360
    },
    {
      "epoch": 0.014374235154717275,
      "grad_norm": 1.9057331085205078,
      "learning_rate": 0.0001,
      "loss": 1.3386,
      "step": 370
    },
    {
      "epoch": 0.014568481575726967,
      "eval_loss": 1.4621069431304932,
      "eval_runtime": 410.8963,
      "eval_samples_per_second": 1.268,
      "eval_steps_per_second": 1.268,
      "step": 375
    },
    {
      "epoch": 0.01476272799673666,
      "grad_norm": 1.4260625839233398,
      "learning_rate": 0.0001,
      "loss": 1.4447,
      "step": 380
    },
    {
      "epoch": 0.015151220838756045,
      "grad_norm": 2.0252511501312256,
      "learning_rate": 0.0001,
      "loss": 1.4396,
      "step": 390
    },
    {
      "epoch": 0.015539713680775431,
      "grad_norm": 1.5493030548095703,
      "learning_rate": 0.0001,
      "loss": 1.5377,
      "step": 400
    },
    {
      "epoch": 0.015928206522794818,
      "grad_norm": 1.5620871782302856,
      "learning_rate": 0.0001,
      "loss": 1.5368,
      "step": 410
    },
    {
      "epoch": 0.016316699364814204,
      "grad_norm": 1.8342182636260986,
      "learning_rate": 0.0001,
      "loss": 1.4932,
      "step": 420
    },
    {
      "epoch": 0.01670519220683359,
      "grad_norm": 0.8918685913085938,
      "learning_rate": 0.0001,
      "loss": 1.4847,
      "step": 430
    },
    {
      "epoch": 0.017093685048852975,
      "grad_norm": 1.4548940658569336,
      "learning_rate": 0.0001,
      "loss": 1.5184,
      "step": 440
    },
    {
      "epoch": 0.01748217789087236,
      "grad_norm": 1.4839730262756348,
      "learning_rate": 0.0001,
      "loss": 1.4276,
      "step": 450
    },
    {
      "epoch": 0.01748217789087236,
      "eval_loss": 1.4603033065795898,
      "eval_runtime": 408.9003,
      "eval_samples_per_second": 1.274,
      "eval_steps_per_second": 1.274,
      "step": 450
    },
    {
      "epoch": 0.017870670732891746,
      "grad_norm": 0.6719891428947449,
      "learning_rate": 0.0001,
      "loss": 1.3042,
      "step": 460
    },
    {
      "epoch": 0.01825916357491113,
      "grad_norm": 0.8530905246734619,
      "learning_rate": 0.0001,
      "loss": 1.454,
      "step": 470
    },
    {
      "epoch": 0.018647656416930516,
      "grad_norm": 0.8087925910949707,
      "learning_rate": 0.0001,
      "loss": 1.4225,
      "step": 480
    },
    {
      "epoch": 0.019036149258949905,
      "grad_norm": 2.091627359390259,
      "learning_rate": 0.0001,
      "loss": 1.4617,
      "step": 490
    },
    {
      "epoch": 0.01942464210096929,
      "grad_norm": 2.1747212409973145,
      "learning_rate": 0.0001,
      "loss": 1.5124,
      "step": 500
    },
    {
      "epoch": 0.019813134942988676,
      "grad_norm": 1.7147002220153809,
      "learning_rate": 0.0001,
      "loss": 1.4442,
      "step": 510
    },
    {
      "epoch": 0.020201627785008062,
      "grad_norm": 0.7326516509056091,
      "learning_rate": 0.0001,
      "loss": 1.4376,
      "step": 520
    },
    {
      "epoch": 0.020395874206017753,
      "eval_loss": 1.4605984687805176,
      "eval_runtime": 418.9148,
      "eval_samples_per_second": 1.244,
      "eval_steps_per_second": 1.244,
      "step": 525
    },
    {
      "epoch": 0.020590120627027447,
      "grad_norm": 1.7703779935836792,
      "learning_rate": 0.0001,
      "loss": 1.4911,
      "step": 530
    },
    {
      "epoch": 0.020978613469046833,
      "grad_norm": 0.8552814722061157,
      "learning_rate": 0.0001,
      "loss": 1.4079,
      "step": 540
    },
    {
      "epoch": 0.021367106311066218,
      "grad_norm": 1.0003011226654053,
      "learning_rate": 0.0001,
      "loss": 1.5769,
      "step": 550
    },
    {
      "epoch": 0.021755599153085604,
      "grad_norm": 1.0176352262496948,
      "learning_rate": 0.0001,
      "loss": 1.2431,
      "step": 560
    },
    {
      "epoch": 0.02214409199510499,
      "grad_norm": 1.8341186046600342,
      "learning_rate": 0.0001,
      "loss": 1.5053,
      "step": 570
    },
    {
      "epoch": 0.022532584837124375,
      "grad_norm": 0.7317614555358887,
      "learning_rate": 0.0001,
      "loss": 1.5135,
      "step": 580
    },
    {
      "epoch": 0.02292107767914376,
      "grad_norm": 1.3072996139526367,
      "learning_rate": 0.0001,
      "loss": 1.2935,
      "step": 590
    },
    {
      "epoch": 0.02330957052116315,
      "grad_norm": 0.5384438633918762,
      "learning_rate": 0.0001,
      "loss": 1.4028,
      "step": 600
    },
    {
      "epoch": 0.02330957052116315,
      "eval_loss": 1.457323670387268,
      "eval_runtime": 419.1828,
      "eval_samples_per_second": 1.243,
      "eval_steps_per_second": 1.243,
      "step": 600
    },
    {
      "epoch": 0.023698063363182535,
      "grad_norm": 0.6213059425354004,
      "learning_rate": 0.0001,
      "loss": 1.3461,
      "step": 610
    },
    {
      "epoch": 0.02408655620520192,
      "grad_norm": 0.9022939801216125,
      "learning_rate": 0.0001,
      "loss": 1.458,
      "step": 620
    },
    {
      "epoch": 0.024475049047221305,
      "grad_norm": 1.511841893196106,
      "learning_rate": 0.0001,
      "loss": 1.3387,
      "step": 630
    },
    {
      "epoch": 0.02486354188924069,
      "grad_norm": 1.193332552909851,
      "learning_rate": 0.0001,
      "loss": 1.25,
      "step": 640
    },
    {
      "epoch": 0.025252034731260076,
      "grad_norm": 0.664730429649353,
      "learning_rate": 0.0001,
      "loss": 1.4608,
      "step": 650
    },
    {
      "epoch": 0.025640527573279462,
      "grad_norm": 0.9817675352096558,
      "learning_rate": 0.0001,
      "loss": 1.4694,
      "step": 660
    },
    {
      "epoch": 0.026029020415298847,
      "grad_norm": 0.8713122606277466,
      "learning_rate": 0.0001,
      "loss": 1.6154,
      "step": 670
    },
    {
      "epoch": 0.026223266836308542,
      "eval_loss": 1.4552098512649536,
      "eval_runtime": 418.233,
      "eval_samples_per_second": 1.246,
      "eval_steps_per_second": 1.246,
      "step": 675
    },
    {
      "epoch": 0.026417513257318233,
      "grad_norm": 0.8656709790229797,
      "learning_rate": 0.0001,
      "loss": 1.6028,
      "step": 680
    },
    {
      "epoch": 0.02680600609933762,
      "grad_norm": 0.7827064990997314,
      "learning_rate": 0.0001,
      "loss": 1.454,
      "step": 690
    },
    {
      "epoch": 0.027194498941357007,
      "grad_norm": 0.8780921101570129,
      "learning_rate": 0.0001,
      "loss": 1.377,
      "step": 700
    },
    {
      "epoch": 0.027582991783376393,
      "grad_norm": 0.664682149887085,
      "learning_rate": 0.0001,
      "loss": 1.3761,
      "step": 710
    },
    {
      "epoch": 0.027971484625395778,
      "grad_norm": 1.6883013248443604,
      "learning_rate": 0.0001,
      "loss": 1.293,
      "step": 720
    },
    {
      "epoch": 0.028359977467415164,
      "grad_norm": 0.6659910082817078,
      "learning_rate": 0.0001,
      "loss": 1.3595,
      "step": 730
    },
    {
      "epoch": 0.02874847030943455,
      "grad_norm": 1.0495606660842896,
      "learning_rate": 0.0001,
      "loss": 1.3881,
      "step": 740
    },
    {
      "epoch": 0.029136963151453935,
      "grad_norm": 2.0675432682037354,
      "learning_rate": 0.0001,
      "loss": 1.3353,
      "step": 750
    },
    {
      "epoch": 0.029136963151453935,
      "eval_loss": 1.4496526718139648,
      "eval_runtime": 412.105,
      "eval_samples_per_second": 1.264,
      "eval_steps_per_second": 1.264,
      "step": 750
    },
    {
      "epoch": 0.02952545599347332,
      "grad_norm": 2.147975444793701,
      "learning_rate": 0.0001,
      "loss": 1.4715,
      "step": 760
    },
    {
      "epoch": 0.029913948835492706,
      "grad_norm": 1.4400185346603394,
      "learning_rate": 0.0001,
      "loss": 1.704,
      "step": 770
    },
    {
      "epoch": 0.03030244167751209,
      "grad_norm": 0.5840633511543274,
      "learning_rate": 0.0001,
      "loss": 1.2531,
      "step": 780
    },
    {
      "epoch": 0.030690934519531476,
      "grad_norm": 1.9958975315093994,
      "learning_rate": 0.0001,
      "loss": 1.6409,
      "step": 790
    },
    {
      "epoch": 0.031079427361550862,
      "grad_norm": 0.4322706460952759,
      "learning_rate": 0.0001,
      "loss": 1.3866,
      "step": 800
    },
    {
      "epoch": 0.03146792020357025,
      "grad_norm": 0.9608808755874634,
      "learning_rate": 0.0001,
      "loss": 1.2862,
      "step": 810
    },
    {
      "epoch": 0.031856413045589636,
      "grad_norm": 1.0402257442474365,
      "learning_rate": 0.0001,
      "loss": 1.4305,
      "step": 820
    },
    {
      "epoch": 0.03205065946659933,
      "eval_loss": 1.4473251104354858,
      "eval_runtime": 410.7169,
      "eval_samples_per_second": 1.269,
      "eval_steps_per_second": 1.269,
      "step": 825
    },
    {
      "epoch": 0.03224490588760902,
      "grad_norm": 0.6171532273292542,
      "learning_rate": 0.0001,
      "loss": 1.2107,
      "step": 830
    },
    {
      "epoch": 0.03263339872962841,
      "grad_norm": 1.6381995677947998,
      "learning_rate": 0.0001,
      "loss": 1.5369,
      "step": 840
    },
    {
      "epoch": 0.03302189157164779,
      "grad_norm": 0.5398985743522644,
      "learning_rate": 0.0001,
      "loss": 1.4939,
      "step": 850
    },
    {
      "epoch": 0.03341038441366718,
      "grad_norm": 1.1927576065063477,
      "learning_rate": 0.0001,
      "loss": 1.459,
      "step": 860
    },
    {
      "epoch": 0.03379887725568657,
      "grad_norm": 0.5355756878852844,
      "learning_rate": 0.0001,
      "loss": 1.4591,
      "step": 870
    },
    {
      "epoch": 0.03418737009770595,
      "grad_norm": 1.0324468612670898,
      "learning_rate": 0.0001,
      "loss": 1.4079,
      "step": 880
    },
    {
      "epoch": 0.03457586293972534,
      "grad_norm": 0.9082580804824829,
      "learning_rate": 0.0001,
      "loss": 1.4703,
      "step": 890
    },
    {
      "epoch": 0.03496435578174472,
      "grad_norm": 1.0036635398864746,
      "learning_rate": 0.0001,
      "loss": 1.2948,
      "step": 900
    },
    {
      "epoch": 0.03496435578174472,
      "eval_loss": 1.4607137441635132,
      "eval_runtime": 418.5246,
      "eval_samples_per_second": 1.245,
      "eval_steps_per_second": 1.245,
      "step": 900
    },
    {
      "epoch": 0.03535284862376411,
      "grad_norm": 0.7732622027397156,
      "learning_rate": 0.0001,
      "loss": 1.5017,
      "step": 910
    },
    {
      "epoch": 0.03574134146578349,
      "grad_norm": 0.7425190806388855,
      "learning_rate": 0.0001,
      "loss": 1.4275,
      "step": 920
    },
    {
      "epoch": 0.03612983430780288,
      "grad_norm": 0.6782093644142151,
      "learning_rate": 0.0001,
      "loss": 1.4424,
      "step": 930
    },
    {
      "epoch": 0.03651832714982226,
      "grad_norm": 0.6914064288139343,
      "learning_rate": 0.0001,
      "loss": 1.49,
      "step": 940
    },
    {
      "epoch": 0.03690681999184165,
      "grad_norm": 1.2722946405410767,
      "learning_rate": 0.0001,
      "loss": 1.4737,
      "step": 950
    },
    {
      "epoch": 0.03729531283386103,
      "grad_norm": 0.9967614412307739,
      "learning_rate": 0.0001,
      "loss": 1.3731,
      "step": 960
    },
    {
      "epoch": 0.03768380567588042,
      "grad_norm": 0.5614752173423767,
      "learning_rate": 0.0001,
      "loss": 1.3554,
      "step": 970
    },
    {
      "epoch": 0.037878052096890116,
      "eval_loss": 1.4594156742095947,
      "eval_runtime": 414.1638,
      "eval_samples_per_second": 1.258,
      "eval_steps_per_second": 1.258,
      "step": 975
    },
    {
      "epoch": 0.03807229851789981,
      "grad_norm": 1.496825933456421,
      "learning_rate": 0.0001,
      "loss": 1.3043,
      "step": 980
    },
    {
      "epoch": 0.03846079135991919,
      "grad_norm": 0.5324123501777649,
      "learning_rate": 0.0001,
      "loss": 1.5467,
      "step": 990
    },
    {
      "epoch": 0.03884928420193858,
      "grad_norm": 2.828305959701538,
      "learning_rate": 0.0001,
      "loss": 1.4766,
      "step": 1000
    },
    {
      "epoch": 0.039237777043957964,
      "grad_norm": 1.0788389444351196,
      "learning_rate": 0.0001,
      "loss": 1.6391,
      "step": 1010
    },
    {
      "epoch": 0.03962626988597735,
      "grad_norm": 1.3913893699645996,
      "learning_rate": 0.0001,
      "loss": 1.36,
      "step": 1020
    },
    {
      "epoch": 0.040014762727996735,
      "grad_norm": 1.0683279037475586,
      "learning_rate": 0.0001,
      "loss": 1.3993,
      "step": 1030
    },
    {
      "epoch": 0.040403255570016124,
      "grad_norm": 0.14315283298492432,
      "learning_rate": 0.0001,
      "loss": 1.3594,
      "step": 1040
    },
    {
      "epoch": 0.040791748412035506,
      "grad_norm": 1.996098518371582,
      "learning_rate": 0.0001,
      "loss": 1.3501,
      "step": 1050
    },
    {
      "epoch": 0.040791748412035506,
      "eval_loss": 1.4564799070358276,
      "eval_runtime": 407.4512,
      "eval_samples_per_second": 1.279,
      "eval_steps_per_second": 1.279,
      "step": 1050
    },
    {
      "epoch": 0.041180241254054895,
      "grad_norm": 1.9238131046295166,
      "learning_rate": 1e-05,
      "loss": 1.3409,
      "step": 1060
    },
    {
      "epoch": 0.04156873409607428,
      "grad_norm": 0.561337947845459,
      "learning_rate": 1e-05,
      "loss": 1.3931,
      "step": 1070
    },
    {
      "epoch": 0.041957226938093665,
      "grad_norm": 0.6750600934028625,
      "learning_rate": 1e-05,
      "loss": 1.3055,
      "step": 1080
    },
    {
      "epoch": 0.042345719780113054,
      "grad_norm": 1.6704535484313965,
      "learning_rate": 1e-05,
      "loss": 1.4371,
      "step": 1090
    },
    {
      "epoch": 0.042734212622132436,
      "grad_norm": 0.6073994636535645,
      "learning_rate": 1e-05,
      "loss": 1.5461,
      "step": 1100
    },
    {
      "epoch": 0.043122705464151825,
      "grad_norm": 1.1396293640136719,
      "learning_rate": 1e-05,
      "loss": 1.4749,
      "step": 1110
    },
    {
      "epoch": 0.04351119830617121,
      "grad_norm": 0.6748817563056946,
      "learning_rate": 1e-05,
      "loss": 1.4803,
      "step": 1120
    },
    {
      "epoch": 0.0437054447271809,
      "eval_loss": 1.4066863059997559,
      "eval_runtime": 198.1965,
      "eval_samples_per_second": 2.629,
      "eval_steps_per_second": 2.629,
      "step": 1125
    },
    {
      "epoch": 0.043899691148190596,
      "grad_norm": 0.8130941987037659,
      "learning_rate": 1e-05,
      "loss": 1.4579,
      "step": 1130
    },
    {
      "epoch": 0.04428818399020998,
      "grad_norm": 0.5348241329193115,
      "learning_rate": 1e-05,
      "loss": 1.3988,
      "step": 1140
    },
    {
      "epoch": 0.04467667683222937,
      "grad_norm": 0.6961309313774109,
      "learning_rate": 1e-05,
      "loss": 1.4051,
      "step": 1150
    },
    {
      "epoch": 0.04506516967424875,
      "grad_norm": 0.8562794923782349,
      "learning_rate": 1e-05,
      "loss": 1.3631,
      "step": 1160
    },
    {
      "epoch": 0.04545366251626814,
      "grad_norm": 0.6999790668487549,
      "learning_rate": 1e-05,
      "loss": 1.4532,
      "step": 1170
    },
    {
      "epoch": 0.04584215535828752,
      "grad_norm": 0.5127655267715454,
      "learning_rate": 1e-05,
      "loss": 1.4715,
      "step": 1180
    },
    {
      "epoch": 0.04623064820030691,
      "grad_norm": 1.5171382427215576,
      "learning_rate": 1e-05,
      "loss": 1.2901,
      "step": 1190
    },
    {
      "epoch": 0.0466191410423263,
      "grad_norm": 0.7225420475006104,
      "learning_rate": 1e-05,
      "loss": 1.2778,
      "step": 1200
    },
    {
      "epoch": 0.0466191410423263,
      "eval_loss": 1.4001317024230957,
      "eval_runtime": 199.2632,
      "eval_samples_per_second": 2.615,
      "eval_steps_per_second": 2.615,
      "step": 1200
    },
    {
      "epoch": 0.04700763388434568,
      "grad_norm": 1.5108428001403809,
      "learning_rate": 1e-05,
      "loss": 1.6175,
      "step": 1210
    },
    {
      "epoch": 0.04739612672636507,
      "grad_norm": 1.1392805576324463,
      "learning_rate": 1e-05,
      "loss": 1.3466,
      "step": 1220
    },
    {
      "epoch": 0.04778461956838445,
      "grad_norm": 0.94669109582901,
      "learning_rate": 1e-05,
      "loss": 1.3415,
      "step": 1230
    },
    {
      "epoch": 0.04817311241040384,
      "grad_norm": 0.8593105673789978,
      "learning_rate": 1e-05,
      "loss": 1.3334,
      "step": 1240
    },
    {
      "epoch": 0.04856160525242322,
      "grad_norm": 0.8188263773918152,
      "learning_rate": 1e-05,
      "loss": 1.4602,
      "step": 1250
    },
    {
      "epoch": 0.04895009809444261,
      "grad_norm": 0.6875782608985901,
      "learning_rate": 1e-05,
      "loss": 1.3261,
      "step": 1260
    },
    {
      "epoch": 0.04933859093646199,
      "grad_norm": 1.8237006664276123,
      "learning_rate": 1e-05,
      "loss": 1.5862,
      "step": 1270
    },
    {
      "epoch": 0.04953283735747169,
      "eval_loss": 1.3970199823379517,
      "eval_runtime": 205.8088,
      "eval_samples_per_second": 2.531,
      "eval_steps_per_second": 2.531,
      "step": 1275
    },
    {
      "epoch": 0.04972708377848138,
      "grad_norm": 1.319785237312317,
      "learning_rate": 1e-05,
      "loss": 1.3576,
      "step": 1280
    },
    {
      "epoch": 0.050115576620500764,
      "grad_norm": 1.727789282798767,
      "learning_rate": 1e-05,
      "loss": 1.5409,
      "step": 1290
    },
    {
      "epoch": 0.05050406946252015,
      "grad_norm": 0.9914244413375854,
      "learning_rate": 1e-05,
      "loss": 1.3503,
      "step": 1300
    },
    {
      "epoch": 0.05089256230453954,
      "grad_norm": 1.8328955173492432,
      "learning_rate": 1e-05,
      "loss": 1.5384,
      "step": 1310
    },
    {
      "epoch": 0.051281055146558924,
      "grad_norm": 1.7998759746551514,
      "learning_rate": 1e-05,
      "loss": 1.4807,
      "step": 1320
    },
    {
      "epoch": 0.05166954798857831,
      "grad_norm": 1.53579843044281,
      "learning_rate": 1e-05,
      "loss": 1.4255,
      "step": 1330
    },
    {
      "epoch": 0.052058040830597695,
      "grad_norm": 0.9572857022285461,
      "learning_rate": 1e-05,
      "loss": 1.4547,
      "step": 1340
    },
    {
      "epoch": 0.052446533672617084,
      "grad_norm": 0.6299539804458618,
      "learning_rate": 1e-05,
      "loss": 1.2758,
      "step": 1350
    },
    {
      "epoch": 0.052446533672617084,
      "eval_loss": 1.394976258277893,
      "eval_runtime": 206.0718,
      "eval_samples_per_second": 2.528,
      "eval_steps_per_second": 2.528,
      "step": 1350
    },
    {
      "epoch": 0.052835026514636466,
      "grad_norm": 1.1869505643844604,
      "learning_rate": 1e-05,
      "loss": 1.2709,
      "step": 1360
    },
    {
      "epoch": 0.053223519356655855,
      "grad_norm": 0.5684358477592468,
      "learning_rate": 1e-05,
      "loss": 1.3306,
      "step": 1370
    },
    {
      "epoch": 0.05361201219867524,
      "grad_norm": 0.5880847573280334,
      "learning_rate": 1e-05,
      "loss": 1.3093,
      "step": 1380
    },
    {
      "epoch": 0.054000505040694625,
      "grad_norm": 0.6990231275558472,
      "learning_rate": 1e-05,
      "loss": 1.4534,
      "step": 1390
    },
    {
      "epoch": 0.054388997882714014,
      "grad_norm": 1.0700093507766724,
      "learning_rate": 1e-05,
      "loss": 1.3294,
      "step": 1400
    },
    {
      "epoch": 0.054777490724733396,
      "grad_norm": 1.044433832168579,
      "learning_rate": 1e-05,
      "loss": 1.4177,
      "step": 1410
    },
    {
      "epoch": 0.055165983566752785,
      "grad_norm": 2.6891329288482666,
      "learning_rate": 1e-05,
      "loss": 1.4451,
      "step": 1420
    },
    {
      "epoch": 0.05536022998776247,
      "eval_loss": 1.3934379816055298,
      "eval_runtime": 204.0926,
      "eval_samples_per_second": 2.553,
      "eval_steps_per_second": 2.553,
      "step": 1425
    },
    {
      "epoch": 0.05555447640877217,
      "grad_norm": 0.4769861698150635,
      "learning_rate": 1e-05,
      "loss": 1.3179,
      "step": 1430
    },
    {
      "epoch": 0.055942969250791556,
      "grad_norm": 1.0731093883514404,
      "learning_rate": 1e-05,
      "loss": 1.47,
      "step": 1440
    },
    {
      "epoch": 0.05633146209281094,
      "grad_norm": 1.016760230064392,
      "learning_rate": 1e-05,
      "loss": 1.5151,
      "step": 1450
    },
    {
      "epoch": 0.05671995493483033,
      "grad_norm": 1.5259450674057007,
      "learning_rate": 1e-05,
      "loss": 1.4038,
      "step": 1460
    },
    {
      "epoch": 0.05710844777684971,
      "grad_norm": 0.654501736164093,
      "learning_rate": 1e-05,
      "loss": 1.3135,
      "step": 1470
    },
    {
      "epoch": 0.0574969406188691,
      "grad_norm": 0.6827269196510315,
      "learning_rate": 1e-05,
      "loss": 1.2978,
      "step": 1480
    },
    {
      "epoch": 0.05788543346088848,
      "grad_norm": 0.5111151933670044,
      "learning_rate": 1e-05,
      "loss": 1.4352,
      "step": 1490
    },
    {
      "epoch": 0.05827392630290787,
      "grad_norm": 1.9571446180343628,
      "learning_rate": 1e-05,
      "loss": 1.4764,
      "step": 1500
    },
    {
      "epoch": 0.05827392630290787,
      "eval_loss": 1.3912627696990967,
      "eval_runtime": 204.5081,
      "eval_samples_per_second": 2.548,
      "eval_steps_per_second": 2.548,
      "step": 1500
    },
    {
      "epoch": 0.05866241914492726,
      "grad_norm": 0.8712412714958191,
      "learning_rate": 1e-05,
      "loss": 1.3778,
      "step": 1510
    },
    {
      "epoch": 0.05905091198694664,
      "grad_norm": 0.7130087018013,
      "learning_rate": 1e-05,
      "loss": 1.3266,
      "step": 1520
    },
    {
      "epoch": 0.05943940482896603,
      "grad_norm": 1.6288388967514038,
      "learning_rate": 1e-05,
      "loss": 1.4783,
      "step": 1530
    },
    {
      "epoch": 0.05982789767098541,
      "grad_norm": 2.629760503768921,
      "learning_rate": 1e-05,
      "loss": 1.6038,
      "step": 1540
    },
    {
      "epoch": 0.0602163905130048,
      "grad_norm": 1.0394636392593384,
      "learning_rate": 1e-05,
      "loss": 1.4683,
      "step": 1550
    },
    {
      "epoch": 0.06060488335502418,
      "grad_norm": 1.128451943397522,
      "learning_rate": 1e-05,
      "loss": 1.4578,
      "step": 1560
    },
    {
      "epoch": 0.06099337619704357,
      "grad_norm": 2.473900079727173,
      "learning_rate": 1e-05,
      "loss": 1.4326,
      "step": 1570
    },
    {
      "epoch": 0.061187622618053265,
      "eval_loss": 1.3889408111572266,
      "eval_runtime": 205.5592,
      "eval_samples_per_second": 2.535,
      "eval_steps_per_second": 2.535,
      "step": 1575
    },
    {
      "epoch": 0.06138186903906295,
      "grad_norm": 1.940373182296753,
      "learning_rate": 1e-05,
      "loss": 1.5117,
      "step": 1580
    },
    {
      "epoch": 0.06177036188108234,
      "grad_norm": 0.7575955986976624,
      "learning_rate": 1e-05,
      "loss": 1.3894,
      "step": 1590
    },
    {
      "epoch": 0.062158854723101724,
      "grad_norm": 1.4801169633865356,
      "learning_rate": 1e-05,
      "loss": 1.3132,
      "step": 1600
    },
    {
      "epoch": 0.0625473475651211,
      "grad_norm": 1.291632890701294,
      "learning_rate": 1e-05,
      "loss": 1.3286,
      "step": 1610
    },
    {
      "epoch": 0.0629358404071405,
      "grad_norm": 1.9607435464859009,
      "learning_rate": 1e-05,
      "loss": 1.3005,
      "step": 1620
    },
    {
      "epoch": 0.06332433324915988,
      "grad_norm": 0.8362483382225037,
      "learning_rate": 1e-05,
      "loss": 1.4172,
      "step": 1630
    },
    {
      "epoch": 0.06371282609117927,
      "grad_norm": 1.3649120330810547,
      "learning_rate": 1e-05,
      "loss": 1.6757,
      "step": 1640
    },
    {
      "epoch": 0.06410131893319866,
      "grad_norm": 1.0758274793624878,
      "learning_rate": 1e-05,
      "loss": 1.3867,
      "step": 1650
    },
    {
      "epoch": 0.06410131893319866,
      "eval_loss": 1.3888965845108032,
      "eval_runtime": 205.6882,
      "eval_samples_per_second": 2.533,
      "eval_steps_per_second": 2.533,
      "step": 1650
    },
    {
      "epoch": 0.06448981177521804,
      "grad_norm": 0.8754805326461792,
      "learning_rate": 1e-05,
      "loss": 1.3389,
      "step": 1660
    },
    {
      "epoch": 0.06487830461723743,
      "grad_norm": 0.7831467986106873,
      "learning_rate": 1e-05,
      "loss": 1.4257,
      "step": 1670
    },
    {
      "epoch": 0.06526679745925681,
      "grad_norm": 0.4581933915615082,
      "learning_rate": 1e-05,
      "loss": 1.3556,
      "step": 1680
    },
    {
      "epoch": 0.0656552903012762,
      "grad_norm": 0.9837825894355774,
      "learning_rate": 1e-05,
      "loss": 1.3184,
      "step": 1690
    },
    {
      "epoch": 0.06604378314329558,
      "grad_norm": 1.005288004875183,
      "learning_rate": 1e-05,
      "loss": 1.2944,
      "step": 1700
    },
    {
      "epoch": 0.06643227598531497,
      "grad_norm": 0.9397820234298706,
      "learning_rate": 1e-05,
      "loss": 1.4305,
      "step": 1710
    },
    {
      "epoch": 0.06682076882733436,
      "grad_norm": 2.7833900451660156,
      "learning_rate": 1e-05,
      "loss": 1.3273,
      "step": 1720
    },
    {
      "epoch": 0.06701501524834405,
      "eval_loss": 1.3884316682815552,
      "eval_runtime": 206.1573,
      "eval_samples_per_second": 2.527,
      "eval_steps_per_second": 2.527,
      "step": 1725
    },
    {
      "epoch": 0.06720926166935375,
      "grad_norm": 1.1208202838897705,
      "learning_rate": 1e-05,
      "loss": 1.2229,
      "step": 1730
    },
    {
      "epoch": 0.06759775451137313,
      "grad_norm": 0.5742992758750916,
      "learning_rate": 1e-05,
      "loss": 1.3349,
      "step": 1740
    },
    {
      "epoch": 0.06798624735339251,
      "grad_norm": 0.7946904897689819,
      "learning_rate": 1e-05,
      "loss": 1.3682,
      "step": 1750
    },
    {
      "epoch": 0.0683747401954119,
      "grad_norm": 0.7263549566268921,
      "learning_rate": 1e-05,
      "loss": 1.5025,
      "step": 1760
    },
    {
      "epoch": 0.06876323303743129,
      "grad_norm": 0.8954797387123108,
      "learning_rate": 1e-05,
      "loss": 1.4383,
      "step": 1770
    },
    {
      "epoch": 0.06915172587945068,
      "grad_norm": 0.6124446392059326,
      "learning_rate": 1e-05,
      "loss": 1.3322,
      "step": 1780
    },
    {
      "epoch": 0.06954021872147005,
      "grad_norm": 1.140678882598877,
      "learning_rate": 1e-05,
      "loss": 1.5233,
      "step": 1790
    },
    {
      "epoch": 0.06992871156348944,
      "grad_norm": 7.1586689949035645,
      "learning_rate": 1e-05,
      "loss": 1.3691,
      "step": 1800
    },
    {
      "epoch": 0.06992871156348944,
      "eval_loss": 1.387437105178833,
      "eval_runtime": 204.4312,
      "eval_samples_per_second": 2.549,
      "eval_steps_per_second": 2.549,
      "step": 1800
    },
    {
      "epoch": 0.07031720440550883,
      "grad_norm": 0.634140133857727,
      "learning_rate": 1e-05,
      "loss": 1.3735,
      "step": 1810
    },
    {
      "epoch": 0.07070569724752822,
      "grad_norm": 0.7632227540016174,
      "learning_rate": 1e-05,
      "loss": 1.3542,
      "step": 1820
    },
    {
      "epoch": 0.07109419008954761,
      "grad_norm": 0.7211370468139648,
      "learning_rate": 1e-05,
      "loss": 1.2832,
      "step": 1830
    },
    {
      "epoch": 0.07148268293156698,
      "grad_norm": 0.7608075737953186,
      "learning_rate": 1e-05,
      "loss": 1.5292,
      "step": 1840
    },
    {
      "epoch": 0.07187117577358637,
      "grad_norm": 0.8131744265556335,
      "learning_rate": 1e-05,
      "loss": 1.4005,
      "step": 1850
    },
    {
      "epoch": 0.07225966861560576,
      "grad_norm": 0.6415278911590576,
      "learning_rate": 1e-05,
      "loss": 1.4455,
      "step": 1860
    },
    {
      "epoch": 0.07264816145762515,
      "grad_norm": 2.333056688308716,
      "learning_rate": 1e-05,
      "loss": 1.4367,
      "step": 1870
    },
    {
      "epoch": 0.07284240787863483,
      "eval_loss": 1.3867840766906738,
      "eval_runtime": 205.2163,
      "eval_samples_per_second": 2.539,
      "eval_steps_per_second": 2.539,
      "step": 1875
    }
  ],
  "logging_steps": 10,
  "max_steps": 3600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 75,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.331378819072e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}