{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.9954430379746837,
  "eval_steps": 500,
  "global_step": 1972,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.020253164556962026,
      "grad_norm": 2.8833762486177865,
      "learning_rate": 5e-06,
      "loss": 0.7568,
      "step": 10
    },
    {
      "epoch": 0.04050632911392405,
      "grad_norm": 2.390286912889809,
      "learning_rate": 5e-06,
      "loss": 0.6504,
      "step": 20
    },
    {
      "epoch": 0.060759493670886074,
      "grad_norm": 1.489395380260759,
      "learning_rate": 5e-06,
      "loss": 0.6287,
      "step": 30
    },
    {
      "epoch": 0.0810126582278481,
      "grad_norm": 1.589470284066133,
      "learning_rate": 5e-06,
      "loss": 0.6135,
      "step": 40
    },
    {
      "epoch": 0.10126582278481013,
      "grad_norm": 1.4199327904724377,
      "learning_rate": 5e-06,
      "loss": 0.6037,
      "step": 50
    },
    {
      "epoch": 0.12151898734177215,
      "grad_norm": 1.4578167281681993,
      "learning_rate": 5e-06,
      "loss": 0.5974,
      "step": 60
    },
    {
      "epoch": 0.14177215189873418,
      "grad_norm": 1.3411623258601368,
      "learning_rate": 5e-06,
      "loss": 0.5923,
      "step": 70
    },
    {
      "epoch": 0.1620253164556962,
      "grad_norm": 2.0256881877625204,
      "learning_rate": 5e-06,
      "loss": 0.5879,
      "step": 80
    },
    {
      "epoch": 0.18227848101265823,
      "grad_norm": 1.865143294695778,
      "learning_rate": 5e-06,
      "loss": 0.5869,
      "step": 90
    },
    {
      "epoch": 0.20253164556962025,
      "grad_norm": 2.850869507593689,
      "learning_rate": 5e-06,
      "loss": 0.5894,
      "step": 100
    },
    {
      "epoch": 0.22278481012658227,
      "grad_norm": 2.780764039633903,
      "learning_rate": 5e-06,
      "loss": 0.5825,
      "step": 110
    },
    {
      "epoch": 0.2430379746835443,
      "grad_norm": 2.24595769639212,
      "learning_rate": 5e-06,
      "loss": 0.5792,
      "step": 120
    },
    {
      "epoch": 0.26329113924050634,
      "grad_norm": 1.898945973266495,
      "learning_rate": 5e-06,
      "loss": 0.5765,
      "step": 130
    },
    {
      "epoch": 0.28354430379746837,
      "grad_norm": 2.0985064075463518,
      "learning_rate": 5e-06,
      "loss": 0.5657,
      "step": 140
    },
    {
      "epoch": 0.3037974683544304,
      "grad_norm": 2.1947025380420393,
      "learning_rate": 5e-06,
      "loss": 0.576,
      "step": 150
    },
    {
      "epoch": 0.3240506329113924,
      "grad_norm": 1.9010440206949761,
      "learning_rate": 5e-06,
      "loss": 0.5748,
      "step": 160
    },
    {
      "epoch": 0.34430379746835443,
      "grad_norm": 1.5587857210363367,
      "learning_rate": 5e-06,
      "loss": 0.5762,
      "step": 170
    },
    {
      "epoch": 0.36455696202531646,
      "grad_norm": 1.940350997849539,
      "learning_rate": 5e-06,
      "loss": 0.5726,
      "step": 180
    },
    {
      "epoch": 0.3848101265822785,
      "grad_norm": 1.653915136046625,
      "learning_rate": 5e-06,
      "loss": 0.5724,
      "step": 190
    },
    {
      "epoch": 0.4050632911392405,
      "grad_norm": 2.4614019893025274,
      "learning_rate": 5e-06,
      "loss": 0.567,
      "step": 200
    },
    {
      "epoch": 0.4253164556962025,
      "grad_norm": 1.8586854938543989,
      "learning_rate": 5e-06,
      "loss": 0.5628,
      "step": 210
    },
    {
      "epoch": 0.44556962025316454,
      "grad_norm": 1.4449652115361937,
      "learning_rate": 5e-06,
      "loss": 0.5679,
      "step": 220
    },
    {
      "epoch": 0.46582278481012657,
      "grad_norm": 1.3739469268351123,
      "learning_rate": 5e-06,
      "loss": 0.5676,
      "step": 230
    },
    {
      "epoch": 0.4860759493670886,
      "grad_norm": 1.165737020699501,
      "learning_rate": 5e-06,
      "loss": 0.5644,
      "step": 240
    },
    {
      "epoch": 0.5063291139240507,
      "grad_norm": 1.357956082726849,
      "learning_rate": 5e-06,
      "loss": 0.5686,
      "step": 250
    },
    {
      "epoch": 0.5265822784810127,
      "grad_norm": 1.4295099868510899,
      "learning_rate": 5e-06,
      "loss": 0.5554,
      "step": 260
    },
    {
      "epoch": 0.5468354430379747,
      "grad_norm": 1.4688068967033727,
      "learning_rate": 5e-06,
      "loss": 0.5643,
      "step": 270
    },
    {
      "epoch": 0.5670886075949367,
      "grad_norm": 1.3744420183733652,
      "learning_rate": 5e-06,
      "loss": 0.56,
      "step": 280
    },
    {
      "epoch": 0.5873417721518988,
      "grad_norm": 1.4423763395622504,
      "learning_rate": 5e-06,
      "loss": 0.56,
      "step": 290
    },
    {
      "epoch": 0.6075949367088608,
      "grad_norm": 1.4527708533649162,
      "learning_rate": 5e-06,
      "loss": 0.5596,
      "step": 300
    },
    {
      "epoch": 0.6278481012658228,
      "grad_norm": 1.4417603290241021,
      "learning_rate": 5e-06,
      "loss": 0.5655,
      "step": 310
    },
    {
      "epoch": 0.6481012658227848,
      "grad_norm": 1.6835798959760988,
      "learning_rate": 5e-06,
      "loss": 0.5611,
      "step": 320
    },
    {
      "epoch": 0.6683544303797468,
      "grad_norm": 1.3523279967838302,
      "learning_rate": 5e-06,
      "loss": 0.5607,
      "step": 330
    },
    {
      "epoch": 0.6886075949367089,
      "grad_norm": 1.2500179332984684,
      "learning_rate": 5e-06,
      "loss": 0.5597,
      "step": 340
    },
    {
      "epoch": 0.7088607594936709,
      "grad_norm": 1.2523150009107906,
      "learning_rate": 5e-06,
      "loss": 0.5614,
      "step": 350
    },
    {
      "epoch": 0.7291139240506329,
      "grad_norm": 1.0953008806392797,
      "learning_rate": 5e-06,
      "loss": 0.5638,
      "step": 360
    },
    {
      "epoch": 0.7493670886075949,
      "grad_norm": 1.6446500941969269,
      "learning_rate": 5e-06,
      "loss": 0.5566,
      "step": 370
    },
    {
      "epoch": 0.769620253164557,
      "grad_norm": 1.4079831931594988,
      "learning_rate": 5e-06,
      "loss": 0.5533,
      "step": 380
    },
    {
      "epoch": 0.789873417721519,
      "grad_norm": 1.1110346875099018,
      "learning_rate": 5e-06,
      "loss": 0.5559,
      "step": 390
    },
    {
      "epoch": 0.810126582278481,
      "grad_norm": 1.4268171466763837,
      "learning_rate": 5e-06,
      "loss": 0.5566,
      "step": 400
    },
    {
      "epoch": 0.830379746835443,
      "grad_norm": 1.2447639143712546,
      "learning_rate": 5e-06,
      "loss": 0.5514,
      "step": 410
    },
    {
      "epoch": 0.850632911392405,
      "grad_norm": 1.195155734961536,
      "learning_rate": 5e-06,
      "loss": 0.5587,
      "step": 420
    },
    {
      "epoch": 0.8708860759493671,
      "grad_norm": 1.1003141204515203,
      "learning_rate": 5e-06,
      "loss": 0.5521,
      "step": 430
    },
    {
      "epoch": 0.8911392405063291,
      "grad_norm": 1.3030562652810704,
      "learning_rate": 5e-06,
      "loss": 0.5573,
      "step": 440
    },
    {
      "epoch": 0.9113924050632911,
      "grad_norm": 1.2728739765574453,
      "learning_rate": 5e-06,
      "loss": 0.5488,
      "step": 450
    },
    {
      "epoch": 0.9316455696202531,
      "grad_norm": 1.1393805858707695,
      "learning_rate": 5e-06,
      "loss": 0.5532,
      "step": 460
    },
    {
      "epoch": 0.9518987341772152,
      "grad_norm": 1.252449871115967,
      "learning_rate": 5e-06,
      "loss": 0.5539,
      "step": 470
    },
    {
      "epoch": 0.9721518987341772,
      "grad_norm": 1.3675922433289114,
      "learning_rate": 5e-06,
      "loss": 0.5515,
      "step": 480
    },
    {
      "epoch": 0.9924050632911392,
      "grad_norm": 1.0986012485203254,
      "learning_rate": 5e-06,
      "loss": 0.548,
      "step": 490
    },
    {
      "epoch": 0.9984810126582279,
      "eval_loss": 0.13772521913051605,
      "eval_runtime": 252.9462,
      "eval_samples_per_second": 52.596,
      "eval_steps_per_second": 0.411,
      "step": 493
    },
    {
      "epoch": 1.0131645569620253,
      "grad_norm": 1.8664570600716093,
      "learning_rate": 5e-06,
      "loss": 0.5056,
      "step": 500
    },
    {
      "epoch": 1.0334177215189873,
      "grad_norm": 1.690550013794204,
      "learning_rate": 5e-06,
      "loss": 0.4717,
      "step": 510
    },
    {
      "epoch": 1.0536708860759494,
      "grad_norm": 1.7450606923145526,
      "learning_rate": 5e-06,
      "loss": 0.4683,
      "step": 520
    },
    {
      "epoch": 1.0739240506329113,
      "grad_norm": 1.4739241775856946,
      "learning_rate": 5e-06,
      "loss": 0.4682,
      "step": 530
    },
    {
      "epoch": 1.0941772151898734,
      "grad_norm": 2.196710788601052,
      "learning_rate": 5e-06,
      "loss": 0.467,
      "step": 540
    },
    {
      "epoch": 1.1144303797468353,
      "grad_norm": 1.4622782937118193,
      "learning_rate": 5e-06,
      "loss": 0.4664,
      "step": 550
    },
    {
      "epoch": 1.1346835443037975,
      "grad_norm": 1.204681750576354,
      "learning_rate": 5e-06,
      "loss": 0.4629,
      "step": 560
    },
    {
      "epoch": 1.1549367088607596,
      "grad_norm": 1.2919169624567832,
      "learning_rate": 5e-06,
      "loss": 0.4723,
      "step": 570
    },
    {
      "epoch": 1.1751898734177215,
      "grad_norm": 1.1738791165204896,
      "learning_rate": 5e-06,
      "loss": 0.4696,
      "step": 580
    },
    {
      "epoch": 1.1954430379746834,
      "grad_norm": 1.2749973090696376,
      "learning_rate": 5e-06,
      "loss": 0.4655,
      "step": 590
    },
    {
      "epoch": 1.2156962025316456,
      "grad_norm": 1.3069834745764197,
      "learning_rate": 5e-06,
      "loss": 0.4738,
      "step": 600
    },
    {
      "epoch": 1.2359493670886077,
      "grad_norm": 1.268141928024117,
      "learning_rate": 5e-06,
      "loss": 0.4689,
      "step": 610
    },
    {
      "epoch": 1.2562025316455696,
      "grad_norm": 2.349539426930866,
      "learning_rate": 5e-06,
      "loss": 0.4738,
      "step": 620
    },
    {
      "epoch": 1.2764556962025315,
      "grad_norm": 1.3038280118636631,
      "learning_rate": 5e-06,
      "loss": 0.4724,
      "step": 630
    },
    {
      "epoch": 1.2967088607594937,
      "grad_norm": 1.2561549442694693,
      "learning_rate": 5e-06,
      "loss": 0.4717,
      "step": 640
    },
    {
      "epoch": 1.3169620253164558,
      "grad_norm": 1.2353995568966352,
      "learning_rate": 5e-06,
      "loss": 0.4756,
      "step": 650
    },
    {
      "epoch": 1.3372151898734177,
      "grad_norm": 1.3143696543162657,
      "learning_rate": 5e-06,
      "loss": 0.4653,
      "step": 660
    },
    {
      "epoch": 1.3574683544303796,
      "grad_norm": 1.8332487196614191,
      "learning_rate": 5e-06,
      "loss": 0.4791,
      "step": 670
    },
    {
      "epoch": 1.3777215189873417,
      "grad_norm": 1.5782907788998026,
      "learning_rate": 5e-06,
      "loss": 0.4743,
      "step": 680
    },
    {
      "epoch": 1.3979746835443039,
      "grad_norm": 1.43844179760011,
      "learning_rate": 5e-06,
      "loss": 0.4733,
      "step": 690
    },
    {
      "epoch": 1.4182278481012658,
      "grad_norm": 1.2104409020838625,
      "learning_rate": 5e-06,
      "loss": 0.4695,
      "step": 700
    },
    {
      "epoch": 1.438481012658228,
      "grad_norm": 1.2829692982799845,
      "learning_rate": 5e-06,
      "loss": 0.4756,
      "step": 710
    },
    {
      "epoch": 1.4587341772151898,
      "grad_norm": 1.2115512985925798,
      "learning_rate": 5e-06,
      "loss": 0.4757,
      "step": 720
    },
    {
      "epoch": 1.478987341772152,
      "grad_norm": 1.1708137297250578,
      "learning_rate": 5e-06,
      "loss": 0.479,
      "step": 730
    },
    {
      "epoch": 1.4992405063291139,
      "grad_norm": 1.1860297553473809,
      "learning_rate": 5e-06,
      "loss": 0.4737,
      "step": 740
    },
    {
      "epoch": 1.5194936708860758,
      "grad_norm": 1.159382227654447,
      "learning_rate": 5e-06,
      "loss": 0.4764,
      "step": 750
    },
    {
      "epoch": 1.539746835443038,
      "grad_norm": 1.1694651947442445,
      "learning_rate": 5e-06,
      "loss": 0.4765,
      "step": 760
    },
    {
      "epoch": 1.56,
      "grad_norm": 1.160166128209198,
      "learning_rate": 5e-06,
      "loss": 0.4765,
      "step": 770
    },
    {
      "epoch": 1.5802531645569622,
      "grad_norm": 1.1966330785907486,
      "learning_rate": 5e-06,
      "loss": 0.4762,
      "step": 780
    },
    {
      "epoch": 1.600506329113924,
      "grad_norm": 1.2884100928471158,
      "learning_rate": 5e-06,
      "loss": 0.4797,
      "step": 790
    },
    {
      "epoch": 1.620759493670886,
      "grad_norm": 1.50350568469768,
      "learning_rate": 5e-06,
      "loss": 0.4765,
      "step": 800
    },
    {
      "epoch": 1.6410126582278481,
      "grad_norm": 1.1416454468827366,
      "learning_rate": 5e-06,
      "loss": 0.4685,
      "step": 810
    },
    {
      "epoch": 1.6612658227848103,
      "grad_norm": 1.3289305602168267,
      "learning_rate": 5e-06,
      "loss": 0.4771,
      "step": 820
    },
    {
      "epoch": 1.6815189873417722,
      "grad_norm": 1.242003954761086,
      "learning_rate": 5e-06,
      "loss": 0.4721,
      "step": 830
    },
    {
      "epoch": 1.701772151898734,
      "grad_norm": 1.1084079600907246,
      "learning_rate": 5e-06,
      "loss": 0.4731,
      "step": 840
    },
    {
      "epoch": 1.7220253164556962,
      "grad_norm": 1.268075113702087,
      "learning_rate": 5e-06,
      "loss": 0.4766,
      "step": 850
    },
    {
      "epoch": 1.7422784810126584,
      "grad_norm": 1.152924839399553,
      "learning_rate": 5e-06,
      "loss": 0.4767,
      "step": 860
    },
    {
      "epoch": 1.7625316455696203,
      "grad_norm": 1.0955649434062678,
      "learning_rate": 5e-06,
      "loss": 0.4776,
      "step": 870
    },
    {
      "epoch": 1.7827848101265822,
      "grad_norm": 1.3082664193765503,
      "learning_rate": 5e-06,
      "loss": 0.4815,
      "step": 880
    },
    {
      "epoch": 1.8030379746835443,
      "grad_norm": 1.166931921170078,
      "learning_rate": 5e-06,
      "loss": 0.4788,
      "step": 890
    },
    {
      "epoch": 1.8232911392405065,
      "grad_norm": 1.1423266879559995,
      "learning_rate": 5e-06,
      "loss": 0.477,
      "step": 900
    },
    {
      "epoch": 1.8435443037974684,
      "grad_norm": 1.3005388006776002,
      "learning_rate": 5e-06,
      "loss": 0.4789,
      "step": 910
    },
    {
      "epoch": 1.8637974683544303,
      "grad_norm": 1.5362991154311363,
      "learning_rate": 5e-06,
      "loss": 0.4791,
      "step": 920
    },
    {
      "epoch": 1.8840506329113924,
      "grad_norm": 1.0615549431669202,
      "learning_rate": 5e-06,
      "loss": 0.4746,
      "step": 930
    },
    {
      "epoch": 1.9043037974683545,
      "grad_norm": 1.1359371350640348,
      "learning_rate": 5e-06,
      "loss": 0.4774,
      "step": 940
    },
    {
      "epoch": 1.9245569620253165,
      "grad_norm": 1.338873863277151,
      "learning_rate": 5e-06,
      "loss": 0.4799,
      "step": 950
    },
    {
      "epoch": 1.9448101265822784,
      "grad_norm": 1.0562817698500642,
      "learning_rate": 5e-06,
      "loss": 0.4834,
      "step": 960
    },
    {
      "epoch": 1.9650632911392405,
      "grad_norm": 1.1976389472965596,
      "learning_rate": 5e-06,
      "loss": 0.481,
      "step": 970
    },
    {
      "epoch": 1.9853164556962026,
      "grad_norm": 1.1318384251326352,
      "learning_rate": 5e-06,
      "loss": 0.4823,
      "step": 980
    },
    {
      "epoch": 1.999493670886076,
      "eval_loss": 0.13791824877262115,
      "eval_runtime": 252.4301,
      "eval_samples_per_second": 52.704,
      "eval_steps_per_second": 0.412,
      "step": 987
    },
    {
      "epoch": 2.0060759493670886,
      "grad_norm": 2.24179568741783,
      "learning_rate": 5e-06,
      "loss": 0.4515,
      "step": 990
    },
    {
      "epoch": 2.0263291139240507,
      "grad_norm": 1.6981313244359,
      "learning_rate": 5e-06,
      "loss": 0.3891,
      "step": 1000
    },
    {
      "epoch": 2.046582278481013,
      "grad_norm": 1.5796760743871119,
      "learning_rate": 5e-06,
      "loss": 0.3814,
      "step": 1010
    },
    {
      "epoch": 2.0668354430379745,
      "grad_norm": 1.7079048311976808,
      "learning_rate": 5e-06,
      "loss": 0.3794,
      "step": 1020
    },
    {
      "epoch": 2.0870886075949366,
      "grad_norm": 1.4027876167762106,
      "learning_rate": 5e-06,
      "loss": 0.3793,
      "step": 1030
    },
    {
      "epoch": 2.1073417721518988,
      "grad_norm": 1.2776686544662923,
      "learning_rate": 5e-06,
      "loss": 0.3758,
      "step": 1040
    },
    {
      "epoch": 2.127594936708861,
      "grad_norm": 1.3728804833099486,
      "learning_rate": 5e-06,
      "loss": 0.3868,
      "step": 1050
    },
    {
      "epoch": 2.1478481012658226,
      "grad_norm": 1.4205398673755427,
      "learning_rate": 5e-06,
      "loss": 0.3827,
      "step": 1060
    },
    {
      "epoch": 2.1681012658227847,
      "grad_norm": 1.3832130487234917,
      "learning_rate": 5e-06,
      "loss": 0.3852,
      "step": 1070
    },
    {
      "epoch": 2.188354430379747,
      "grad_norm": 1.5929946445474668,
      "learning_rate": 5e-06,
      "loss": 0.3841,
      "step": 1080
    },
    {
      "epoch": 2.208607594936709,
      "grad_norm": 1.4600989820317136,
      "learning_rate": 5e-06,
      "loss": 0.3818,
      "step": 1090
    },
    {
      "epoch": 2.2288607594936707,
      "grad_norm": 1.4225880515710438,
      "learning_rate": 5e-06,
      "loss": 0.3909,
      "step": 1100
    },
    {
      "epoch": 2.249113924050633,
      "grad_norm": 1.780076806234694,
      "learning_rate": 5e-06,
      "loss": 0.3884,
      "step": 1110
    },
    {
      "epoch": 2.269367088607595,
      "grad_norm": 1.694668518355522,
      "learning_rate": 5e-06,
      "loss": 0.387,
      "step": 1120
    },
    {
      "epoch": 2.289620253164557,
      "grad_norm": 1.7667024915838094,
      "learning_rate": 5e-06,
      "loss": 0.3894,
      "step": 1130
    },
    {
      "epoch": 2.309873417721519,
      "grad_norm": 1.410793594228534,
      "learning_rate": 5e-06,
      "loss": 0.3842,
      "step": 1140
    },
    {
      "epoch": 2.330126582278481,
      "grad_norm": 1.5234909172570381,
      "learning_rate": 5e-06,
      "loss": 0.3908,
      "step": 1150
    },
    {
      "epoch": 2.350379746835443,
      "grad_norm": 1.2213254079078641,
      "learning_rate": 5e-06,
      "loss": 0.3903,
      "step": 1160
    },
    {
      "epoch": 2.370632911392405,
      "grad_norm": 1.4202255106744544,
      "learning_rate": 5e-06,
      "loss": 0.3915,
      "step": 1170
    },
    {
      "epoch": 2.390886075949367,
      "grad_norm": 1.4023194734455904,
      "learning_rate": 5e-06,
      "loss": 0.3924,
      "step": 1180
    },
    {
      "epoch": 2.411139240506329,
      "grad_norm": 1.7343746037355243,
      "learning_rate": 5e-06,
      "loss": 0.3905,
      "step": 1190
    },
    {
      "epoch": 2.431392405063291,
      "grad_norm": 1.4482110997116577,
      "learning_rate": 5e-06,
      "loss": 0.3899,
      "step": 1200
    },
    {
      "epoch": 2.4516455696202533,
      "grad_norm": 1.9131070141039026,
      "learning_rate": 5e-06,
      "loss": 0.3878,
      "step": 1210
    },
    {
      "epoch": 2.4718987341772154,
      "grad_norm": 1.3699773358857317,
      "learning_rate": 5e-06,
      "loss": 0.3907,
      "step": 1220
    },
    {
      "epoch": 2.492151898734177,
      "grad_norm": 1.2435143983285588,
      "learning_rate": 5e-06,
      "loss": 0.3937,
      "step": 1230
    },
    {
      "epoch": 2.512405063291139,
      "grad_norm": 1.271353869459015,
      "learning_rate": 5e-06,
      "loss": 0.393,
      "step": 1240
    },
    {
      "epoch": 2.5326582278481014,
      "grad_norm": 1.9458404824086235,
      "learning_rate": 5e-06,
      "loss": 0.3921,
      "step": 1250
    },
    {
      "epoch": 2.552911392405063,
      "grad_norm": 1.324983619143349,
      "learning_rate": 5e-06,
      "loss": 0.386,
      "step": 1260
    },
    {
      "epoch": 2.573164556962025,
      "grad_norm": 1.5086572692565505,
      "learning_rate": 5e-06,
      "loss": 0.3929,
      "step": 1270
    },
    {
      "epoch": 2.5934177215189873,
      "grad_norm": 1.2387524175778437,
      "learning_rate": 5e-06,
      "loss": 0.3956,
      "step": 1280
    },
    {
      "epoch": 2.6136708860759494,
      "grad_norm": 1.4032957006294775,
      "learning_rate": 5e-06,
      "loss": 0.3985,
      "step": 1290
    },
    {
      "epoch": 2.6339240506329116,
      "grad_norm": 1.4186988248363785,
      "learning_rate": 5e-06,
      "loss": 0.3949,
      "step": 1300
    },
    {
      "epoch": 2.6541772151898733,
      "grad_norm": 1.474152675372263,
      "learning_rate": 5e-06,
      "loss": 0.3949,
      "step": 1310
    },
    {
      "epoch": 2.6744303797468354,
      "grad_norm": 1.388800748370683,
      "learning_rate": 5e-06,
      "loss": 0.3972,
      "step": 1320
    },
    {
      "epoch": 2.6946835443037975,
      "grad_norm": 1.3404535288890715,
      "learning_rate": 5e-06,
      "loss": 0.3975,
      "step": 1330
    },
    {
      "epoch": 2.714936708860759,
      "grad_norm": 1.3485784987514158,
      "learning_rate": 5e-06,
      "loss": 0.3998,
      "step": 1340
    },
    {
      "epoch": 2.7351898734177214,
      "grad_norm": 1.3182287721338872,
      "learning_rate": 5e-06,
      "loss": 0.3972,
      "step": 1350
    },
    {
      "epoch": 2.7554430379746835,
      "grad_norm": 1.2129071324788472,
      "learning_rate": 5e-06,
      "loss": 0.3932,
      "step": 1360
    },
    {
      "epoch": 2.7756962025316456,
      "grad_norm": 1.4082013444619639,
      "learning_rate": 5e-06,
      "loss": 0.3999,
      "step": 1370
    },
    {
      "epoch": 2.7959493670886078,
      "grad_norm": 1.4390382641502573,
      "learning_rate": 5e-06,
      "loss": 0.3974,
      "step": 1380
    },
    {
      "epoch": 2.81620253164557,
      "grad_norm": 1.3463527613931228,
      "learning_rate": 5e-06,
      "loss": 0.4004,
      "step": 1390
    },
    {
      "epoch": 2.8364556962025316,
      "grad_norm": 1.2190952668881454,
      "learning_rate": 5e-06,
      "loss": 0.3945,
      "step": 1400
    },
    {
      "epoch": 2.8567088607594937,
      "grad_norm": 1.2959901372391192,
      "learning_rate": 5e-06,
      "loss": 0.4014,
      "step": 1410
    },
    {
      "epoch": 2.876962025316456,
      "grad_norm": 1.2846058903861945,
      "learning_rate": 5e-06,
      "loss": 0.3987,
      "step": 1420
    },
    {
      "epoch": 2.8972151898734175,
      "grad_norm": 1.340897452737586,
      "learning_rate": 5e-06,
      "loss": 0.3983,
      "step": 1430
    },
    {
      "epoch": 2.9174683544303797,
      "grad_norm": 1.3196158163944824,
      "learning_rate": 5e-06,
      "loss": 0.4016,
      "step": 1440
    },
    {
      "epoch": 2.937721518987342,
      "grad_norm": 1.275687217034204,
      "learning_rate": 5e-06,
      "loss": 0.4105,
      "step": 1450
    },
    {
      "epoch": 2.957974683544304,
      "grad_norm": 1.4052855567194664,
      "learning_rate": 5e-06,
      "loss": 0.3992,
      "step": 1460
    },
    {
      "epoch": 2.978227848101266,
      "grad_norm": 1.3721809126891413,
      "learning_rate": 5e-06,
      "loss": 0.403,
      "step": 1470
    },
    {
      "epoch": 2.9984810126582278,
      "grad_norm": 1.3733986827541713,
      "learning_rate": 5e-06,
      "loss": 0.4008,
      "step": 1480
    },
    {
      "epoch": 2.9984810126582278,
      "eval_loss": 0.1451626569032669,
      "eval_runtime": 252.5403,
      "eval_samples_per_second": 52.681,
      "eval_steps_per_second": 0.412,
      "step": 1480
    },
    {
      "epoch": 3.019240506329114,
      "grad_norm": 2.1233881502453333,
      "learning_rate": 5e-06,
      "loss": 0.3123,
      "step": 1490
    },
    {
      "epoch": 3.039493670886076,
      "grad_norm": 1.733976300717687,
      "learning_rate": 5e-06,
      "loss": 0.2924,
      "step": 1500
    },
    {
      "epoch": 3.059746835443038,
      "grad_norm": 1.7085808896440553,
      "learning_rate": 5e-06,
      "loss": 0.2942,
      "step": 1510
    },
    {
      "epoch": 3.08,
      "grad_norm": 1.4544968881558145,
      "learning_rate": 5e-06,
      "loss": 0.2933,
      "step": 1520
    },
    {
      "epoch": 3.100253164556962,
      "grad_norm": 1.6261331378733803,
      "learning_rate": 5e-06,
      "loss": 0.2944,
      "step": 1530
    },
    {
      "epoch": 3.120506329113924,
      "grad_norm": 1.5609283167478611,
      "learning_rate": 5e-06,
      "loss": 0.292,
      "step": 1540
    },
    {
      "epoch": 3.140759493670886,
      "grad_norm": 1.6902454180217539,
      "learning_rate": 5e-06,
      "loss": 0.29,
      "step": 1550
    },
    {
      "epoch": 3.161012658227848,
      "grad_norm": 1.47961286622397,
      "learning_rate": 5e-06,
      "loss": 0.2964,
      "step": 1560
    },
    {
      "epoch": 3.1812658227848103,
      "grad_norm": 1.6098815338414532,
      "learning_rate": 5e-06,
      "loss": 0.2967,
      "step": 1570
    },
    {
      "epoch": 3.201518987341772,
      "grad_norm": 1.4570975957744257,
      "learning_rate": 5e-06,
      "loss": 0.2999,
      "step": 1580
    },
    {
      "epoch": 3.221772151898734,
      "grad_norm": 1.5616376984698326,
      "learning_rate": 5e-06,
      "loss": 0.3003,
      "step": 1590
    },
    {
      "epoch": 3.2420253164556962,
      "grad_norm": 1.5261875412769847,
      "learning_rate": 5e-06,
      "loss": 0.3007,
      "step": 1600
    },
    {
      "epoch": 3.2622784810126584,
      "grad_norm": 1.5927243321009188,
      "learning_rate": 5e-06,
      "loss": 0.2992,
      "step": 1610
    },
    {
      "epoch": 3.28253164556962,
      "grad_norm": 1.4687003886067878,
      "learning_rate": 5e-06,
      "loss": 0.3016,
      "step": 1620
    },
    {
      "epoch": 3.302784810126582,
      "grad_norm": 1.6212181828314611,
      "learning_rate": 5e-06,
      "loss": 0.3046,
      "step": 1630
    },
    {
      "epoch": 3.3230379746835443,
      "grad_norm": 1.7006560112850782,
      "learning_rate": 5e-06,
      "loss": 0.3014,
      "step": 1640
    },
    {
      "epoch": 3.3432911392405065,
      "grad_norm": 1.6369351197517492,
      "learning_rate": 5e-06,
      "loss": 0.3031,
      "step": 1650
    },
    {
      "epoch": 3.363544303797468,
      "grad_norm": 1.8997824836659962,
      "learning_rate": 5e-06,
      "loss": 0.3052,
      "step": 1660
    },
    {
      "epoch": 3.3837974683544303,
      "grad_norm": 1.7686559384037446,
      "learning_rate": 5e-06,
      "loss": 0.2994,
      "step": 1670
    },
    {
      "epoch": 3.4040506329113924,
      "grad_norm": 1.9852860129783203,
      "learning_rate": 5e-06,
      "loss": 0.2987,
      "step": 1680
    },
    {
      "epoch": 3.4243037974683546,
      "grad_norm": 1.6687727310492642,
      "learning_rate": 5e-06,
      "loss": 0.3028,
      "step": 1690
    },
    {
      "epoch": 3.4445569620253167,
      "grad_norm": 1.555588423959256,
      "learning_rate": 5e-06,
      "loss": 0.3012,
      "step": 1700
    },
    {
      "epoch": 3.4648101265822784,
      "grad_norm": 1.570937882764948,
      "learning_rate": 5e-06,
      "loss": 0.3033,
      "step": 1710
    },
    {
      "epoch": 3.4850632911392405,
      "grad_norm": 1.762794823286088,
      "learning_rate": 5e-06,
      "loss": 0.3078,
      "step": 1720
    },
    {
      "epoch": 3.5053164556962026,
      "grad_norm": 1.5085676767074419,
      "learning_rate": 5e-06,
      "loss": 0.3076,
      "step": 1730
    },
    {
      "epoch": 3.5255696202531643,
      "grad_norm": 1.846690362471807,
      "learning_rate": 5e-06,
      "loss": 0.3058,
      "step": 1740
    },
    {
      "epoch": 3.5458227848101265,
      "grad_norm": 1.888656474961098,
      "learning_rate": 5e-06,
      "loss": 0.3092,
      "step": 1750
    },
    {
      "epoch": 3.5660759493670886,
      "grad_norm": 1.5522432118926228,
      "learning_rate": 5e-06,
      "loss": 0.3031,
      "step": 1760
    },
    {
      "epoch": 3.5863291139240507,
      "grad_norm": 1.7040265273376634,
      "learning_rate": 5e-06,
      "loss": 0.3097,
      "step": 1770
    },
    {
      "epoch": 3.606582278481013,
      "grad_norm": 1.6319175616422348,
      "learning_rate": 5e-06,
      "loss": 0.3076,
      "step": 1780
    },
    {
      "epoch": 3.6268354430379746,
      "grad_norm": 1.6539455217449284,
      "learning_rate": 5e-06,
      "loss": 0.3054,
      "step": 1790
    },
    {
      "epoch": 3.6470886075949367,
      "grad_norm": 1.6323498992182317,
      "learning_rate": 5e-06,
      "loss": 0.3089,
      "step": 1800
    },
    {
      "epoch": 3.667341772151899,
      "grad_norm": 1.9811098470470307,
      "learning_rate": 5e-06,
      "loss": 0.3141,
      "step": 1810
    },
    {
      "epoch": 3.6875949367088605,
      "grad_norm": 1.5750523511747638,
      "learning_rate": 5e-06,
      "loss": 0.3093,
      "step": 1820
    },
    {
      "epoch": 3.7078481012658226,
      "grad_norm": 1.5810037258388918,
      "learning_rate": 5e-06,
      "loss": 0.3105,
      "step": 1830
    },
    {
      "epoch": 3.728101265822785,
      "grad_norm": 1.554399518805066,
      "learning_rate": 5e-06,
      "loss": 0.3124,
      "step": 1840
    },
    {
      "epoch": 3.748354430379747,
      "grad_norm": 1.6069072450441366,
      "learning_rate": 5e-06,
      "loss": 0.3099,
      "step": 1850
    },
    {
      "epoch": 3.768607594936709,
      "grad_norm": 1.6769246041867307,
      "learning_rate": 5e-06,
      "loss": 0.3173,
      "step": 1860
    },
    {
      "epoch": 3.7888607594936707,
      "grad_norm": 1.579060667933051,
      "learning_rate": 5e-06,
      "loss": 0.3145,
      "step": 1870
    },
    {
      "epoch": 3.809113924050633,
      "grad_norm": 2.0501104971409396,
      "learning_rate": 5e-06,
      "loss": 0.3154,
      "step": 1880
    },
    {
      "epoch": 3.829367088607595,
      "grad_norm": 2.2983760386486214,
      "learning_rate": 5e-06,
      "loss": 0.315,
      "step": 1890
    },
    {
      "epoch": 3.8496202531645567,
      "grad_norm": 1.780585915706879,
      "learning_rate": 5e-06,
      "loss": 0.3157,
      "step": 1900
    },
    {
      "epoch": 3.869873417721519,
      "grad_norm": 1.77785313158742,
      "learning_rate": 5e-06,
      "loss": 0.3117,
      "step": 1910
    },
    {
      "epoch": 3.890126582278481,
      "grad_norm": 1.6198590987029773,
      "learning_rate": 5e-06,
      "loss": 0.3172,
      "step": 1920
    },
    {
      "epoch": 3.910379746835443,
      "grad_norm": 1.64334724662568,
      "learning_rate": 5e-06,
      "loss": 0.3147,
      "step": 1930
    },
    {
      "epoch": 3.9306329113924052,
      "grad_norm": 1.5274532742672213,
      "learning_rate": 5e-06,
      "loss": 0.312,
      "step": 1940
    },
    {
      "epoch": 3.9508860759493674,
      "grad_norm": 1.7941457309206295,
      "learning_rate": 5e-06,
      "loss": 0.3164,
      "step": 1950
    },
    {
      "epoch": 3.971139240506329,
      "grad_norm": 1.6138102060492845,
      "learning_rate": 5e-06,
      "loss": 0.3175,
      "step": 1960
    },
    {
      "epoch": 3.991392405063291,
      "grad_norm": 1.7439224514084468,
      "learning_rate": 5e-06,
      "loss": 0.3172,
      "step": 1970
    },
    {
      "epoch": 3.9954430379746837,
      "eval_loss": 0.1617216169834137,
      "eval_runtime": 254.4743,
      "eval_samples_per_second": 52.28,
      "eval_steps_per_second": 0.409,
      "step": 1972
    },
    {
      "epoch": 3.9954430379746837,
      "step": 1972,
      "total_flos": 3302754688696320.0,
      "train_loss": 0.4368948165108176,
      "train_runtime": 56763.579,
      "train_samples_per_second": 17.811,
      "train_steps_per_second": 0.035
    }
  ],
  "logging_steps": 10,
  "max_steps": 1972,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3302754688696320.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}