{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9954430379746837,
  "eval_steps": 500,
  "global_step": 1479,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.020253164556962026,
      "grad_norm": 2.8834310159422087,
      "learning_rate": 5e-06,
      "loss": 0.7568,
      "step": 10
    },
    {
      "epoch": 0.04050632911392405,
      "grad_norm": 1.5848810330070573,
      "learning_rate": 5e-06,
      "loss": 0.6502,
      "step": 20
    },
    {
      "epoch": 0.060759493670886074,
      "grad_norm": 2.2536269528481196,
      "learning_rate": 5e-06,
      "loss": 0.6294,
      "step": 30
    },
    {
      "epoch": 0.0810126582278481,
      "grad_norm": 1.4056128500427496,
      "learning_rate": 5e-06,
      "loss": 0.6134,
      "step": 40
    },
    {
      "epoch": 0.10126582278481013,
      "grad_norm": 2.4782034941382483,
      "learning_rate": 5e-06,
      "loss": 0.6031,
      "step": 50
    },
    {
      "epoch": 0.12151898734177215,
      "grad_norm": 1.6622117822947438,
      "learning_rate": 5e-06,
      "loss": 0.5979,
      "step": 60
    },
    {
      "epoch": 0.14177215189873418,
      "grad_norm": 1.4745555891272486,
      "learning_rate": 5e-06,
      "loss": 0.5927,
      "step": 70
    },
    {
      "epoch": 0.1620253164556962,
      "grad_norm": 1.5105255727310936,
      "learning_rate": 5e-06,
      "loss": 0.5878,
      "step": 80
    },
    {
      "epoch": 0.18227848101265823,
      "grad_norm": 1.7030333734245051,
      "learning_rate": 5e-06,
      "loss": 0.5868,
      "step": 90
    },
    {
      "epoch": 0.20253164556962025,
      "grad_norm": 1.7932796543320693,
      "learning_rate": 5e-06,
      "loss": 0.5891,
      "step": 100
    },
    {
      "epoch": 0.22278481012658227,
      "grad_norm": 1.4737708669995326,
      "learning_rate": 5e-06,
      "loss": 0.5812,
      "step": 110
    },
    {
      "epoch": 0.2430379746835443,
      "grad_norm": 1.2394958257711302,
      "learning_rate": 5e-06,
      "loss": 0.5787,
      "step": 120
    },
    {
      "epoch": 0.26329113924050634,
      "grad_norm": 2.0399622743824217,
      "learning_rate": 5e-06,
      "loss": 0.5783,
      "step": 130
    },
    {
      "epoch": 0.28354430379746837,
      "grad_norm": 1.9934667373853558,
      "learning_rate": 5e-06,
      "loss": 0.5684,
      "step": 140
    },
    {
      "epoch": 0.3037974683544304,
      "grad_norm": 2.555380835279648,
      "learning_rate": 5e-06,
      "loss": 0.5777,
      "step": 150
    },
    {
      "epoch": 0.3240506329113924,
      "grad_norm": 2.2286153901450922,
      "learning_rate": 5e-06,
      "loss": 0.5757,
      "step": 160
    },
    {
      "epoch": 0.34430379746835443,
      "grad_norm": 1.6871211334286025,
      "learning_rate": 5e-06,
      "loss": 0.5755,
      "step": 170
    },
    {
      "epoch": 0.36455696202531646,
      "grad_norm": 1.393063112225217,
      "learning_rate": 5e-06,
      "loss": 0.57,
      "step": 180
    },
    {
      "epoch": 0.3848101265822785,
      "grad_norm": 1.7009173550139203,
      "learning_rate": 5e-06,
      "loss": 0.5705,
      "step": 190
    },
    {
      "epoch": 0.4050632911392405,
      "grad_norm": 1.3177862456894094,
      "learning_rate": 5e-06,
      "loss": 0.567,
      "step": 200
    },
    {
      "epoch": 0.4253164556962025,
      "grad_norm": 1.2882352081623971,
      "learning_rate": 5e-06,
      "loss": 0.5638,
      "step": 210
    },
    {
      "epoch": 0.44556962025316454,
      "grad_norm": 1.7286603451574376,
      "learning_rate": 5e-06,
      "loss": 0.5692,
      "step": 220
    },
    {
      "epoch": 0.46582278481012657,
      "grad_norm": 1.5634194623190878,
      "learning_rate": 5e-06,
      "loss": 0.5679,
      "step": 230
    },
    {
      "epoch": 0.4860759493670886,
      "grad_norm": 1.1969445498720603,
      "learning_rate": 5e-06,
      "loss": 0.5636,
      "step": 240
    },
    {
      "epoch": 0.5063291139240507,
      "grad_norm": 1.4145804617947766,
      "learning_rate": 5e-06,
      "loss": 0.5681,
      "step": 250
    },
    {
      "epoch": 0.5265822784810127,
      "grad_norm": 1.385252716815968,
      "learning_rate": 5e-06,
      "loss": 0.5545,
      "step": 260
    },
    {
      "epoch": 0.5468354430379747,
      "grad_norm": 1.3697060387867175,
      "learning_rate": 5e-06,
      "loss": 0.5633,
      "step": 270
    },
    {
      "epoch": 0.5670886075949367,
      "grad_norm": 1.3365887453628227,
      "learning_rate": 5e-06,
      "loss": 0.5584,
      "step": 280
    },
    {
      "epoch": 0.5873417721518988,
      "grad_norm": 1.90214472311916,
      "learning_rate": 5e-06,
      "loss": 0.5588,
      "step": 290
    },
    {
      "epoch": 0.6075949367088608,
      "grad_norm": 1.3111704746964379,
      "learning_rate": 5e-06,
      "loss": 0.5585,
      "step": 300
    },
    {
      "epoch": 0.6278481012658228,
      "grad_norm": 1.3625139681986471,
      "learning_rate": 5e-06,
      "loss": 0.5643,
      "step": 310
    },
    {
      "epoch": 0.6481012658227848,
      "grad_norm": 1.335488340861959,
      "learning_rate": 5e-06,
      "loss": 0.5603,
      "step": 320
    },
    {
      "epoch": 0.6683544303797468,
      "grad_norm": 1.8124728652539073,
      "learning_rate": 5e-06,
      "loss": 0.5607,
      "step": 330
    },
    {
      "epoch": 0.6886075949367089,
      "grad_norm": 1.6695620971649354,
      "learning_rate": 5e-06,
      "loss": 0.5586,
      "step": 340
    },
    {
      "epoch": 0.7088607594936709,
      "grad_norm": 1.9423946772081884,
      "learning_rate": 5e-06,
      "loss": 0.559,
      "step": 350
    },
    {
      "epoch": 0.7291139240506329,
      "grad_norm": 1.5664275604253222,
      "learning_rate": 5e-06,
      "loss": 0.5608,
      "step": 360
    },
    {
      "epoch": 0.7493670886075949,
      "grad_norm": 1.5674509321122239,
      "learning_rate": 5e-06,
      "loss": 0.5532,
      "step": 370
    },
    {
      "epoch": 0.769620253164557,
      "grad_norm": 1.2746845514269205,
      "learning_rate": 5e-06,
      "loss": 0.5497,
      "step": 380
    },
    {
      "epoch": 0.789873417721519,
      "grad_norm": 1.2874073771501444,
      "learning_rate": 5e-06,
      "loss": 0.5531,
      "step": 390
    },
    {
      "epoch": 0.810126582278481,
      "grad_norm": 1.5168793396392315,
      "learning_rate": 5e-06,
      "loss": 0.5539,
      "step": 400
    },
    {
      "epoch": 0.830379746835443,
      "grad_norm": 1.5836724794821497,
      "learning_rate": 5e-06,
      "loss": 0.5487,
      "step": 410
    },
    {
      "epoch": 0.850632911392405,
      "grad_norm": 1.5660472000565586,
      "learning_rate": 5e-06,
      "loss": 0.5564,
      "step": 420
    },
    {
      "epoch": 0.8708860759493671,
      "grad_norm": 1.201864330490989,
      "learning_rate": 5e-06,
      "loss": 0.55,
      "step": 430
    },
    {
      "epoch": 0.8911392405063291,
      "grad_norm": 1.472160215956628,
      "learning_rate": 5e-06,
      "loss": 0.5557,
      "step": 440
    },
    {
      "epoch": 0.9113924050632911,
      "grad_norm": 1.1811056431459517,
      "learning_rate": 5e-06,
      "loss": 0.5469,
      "step": 450
    },
    {
      "epoch": 0.9316455696202531,
      "grad_norm": 1.0752020831340272,
      "learning_rate": 5e-06,
      "loss": 0.5523,
      "step": 460
    },
    {
      "epoch": 0.9518987341772152,
      "grad_norm": 1.2675033847516473,
      "learning_rate": 5e-06,
      "loss": 0.5535,
      "step": 470
    },
    {
      "epoch": 0.9721518987341772,
      "grad_norm": 1.1201617344041725,
      "learning_rate": 5e-06,
      "loss": 0.5513,
      "step": 480
    },
    {
      "epoch": 0.9924050632911392,
      "grad_norm": 1.1390520715284584,
      "learning_rate": 5e-06,
      "loss": 0.5483,
      "step": 490
    },
    {
      "epoch": 0.9984810126582279,
      "eval_loss": 0.06893002241849899,
      "eval_runtime": 505.1746,
      "eval_samples_per_second": 26.335,
      "eval_steps_per_second": 0.412,
      "step": 493
    },
    {
      "epoch": 1.0126582278481013,
      "grad_norm": 1.8605707752609861,
      "learning_rate": 5e-06,
      "loss": 0.509,
      "step": 500
    },
    {
      "epoch": 1.0329113924050632,
      "grad_norm": 1.3998276121696196,
      "learning_rate": 5e-06,
      "loss": 0.4753,
      "step": 510
    },
    {
      "epoch": 1.0531645569620254,
      "grad_norm": 1.3640323649196784,
      "learning_rate": 5e-06,
      "loss": 0.471,
      "step": 520
    },
    {
      "epoch": 1.0734177215189873,
      "grad_norm": 1.6146733727456841,
      "learning_rate": 5e-06,
      "loss": 0.4729,
      "step": 530
    },
    {
      "epoch": 1.0936708860759494,
      "grad_norm": 1.8234575659151315,
      "learning_rate": 5e-06,
      "loss": 0.4701,
      "step": 540
    },
    {
      "epoch": 1.1139240506329113,
      "grad_norm": 1.341604688901184,
      "learning_rate": 5e-06,
      "loss": 0.4708,
      "step": 550
    },
    {
      "epoch": 1.1341772151898735,
      "grad_norm": 1.1511957856667028,
      "learning_rate": 5e-06,
      "loss": 0.4676,
      "step": 560
    },
    {
      "epoch": 1.1544303797468354,
      "grad_norm": 1.340103047525268,
      "learning_rate": 5e-06,
      "loss": 0.4754,
      "step": 570
    },
    {
      "epoch": 1.1746835443037975,
      "grad_norm": 1.1654902808517669,
      "learning_rate": 5e-06,
      "loss": 0.4753,
      "step": 580
    },
    {
      "epoch": 1.1949367088607594,
      "grad_norm": 1.2021528504549726,
      "learning_rate": 5e-06,
      "loss": 0.4698,
      "step": 590
    },
    {
      "epoch": 1.2151898734177216,
      "grad_norm": 1.258045696651176,
      "learning_rate": 5e-06,
      "loss": 0.4768,
      "step": 600
    },
    {
      "epoch": 1.2354430379746835,
      "grad_norm": 1.4640469521027848,
      "learning_rate": 5e-06,
      "loss": 0.4732,
      "step": 610
    },
    {
      "epoch": 1.2556962025316456,
      "grad_norm": 1.3704281822088498,
      "learning_rate": 5e-06,
      "loss": 0.478,
      "step": 620
    },
    {
      "epoch": 1.2759493670886077,
      "grad_norm": 1.3024028438421167,
      "learning_rate": 5e-06,
      "loss": 0.477,
      "step": 630
    },
    {
      "epoch": 1.2962025316455696,
      "grad_norm": 1.5552769715262154,
      "learning_rate": 5e-06,
      "loss": 0.4772,
      "step": 640
    },
    {
      "epoch": 1.3164556962025316,
      "grad_norm": 1.2836640693576777,
      "learning_rate": 5e-06,
      "loss": 0.4802,
      "step": 650
    },
    {
      "epoch": 1.3367088607594937,
      "grad_norm": 1.324140225411003,
      "learning_rate": 5e-06,
      "loss": 0.4695,
      "step": 660
    },
    {
      "epoch": 1.3569620253164558,
      "grad_norm": 1.3034377864365105,
      "learning_rate": 5e-06,
      "loss": 0.4833,
      "step": 670
    },
    {
      "epoch": 1.3772151898734177,
      "grad_norm": 1.288899894609953,
      "learning_rate": 5e-06,
      "loss": 0.4785,
      "step": 680
    },
    {
      "epoch": 1.3974683544303796,
      "grad_norm": 1.1335491566854674,
      "learning_rate": 5e-06,
      "loss": 0.4786,
      "step": 690
    },
    {
      "epoch": 1.4177215189873418,
      "grad_norm": 1.1902525274414393,
      "learning_rate": 5e-06,
      "loss": 0.4759,
      "step": 700
    },
    {
      "epoch": 1.437974683544304,
      "grad_norm": 1.2099886080763382,
      "learning_rate": 5e-06,
      "loss": 0.4818,
      "step": 710
    },
    {
      "epoch": 1.4582278481012658,
      "grad_norm": 1.2206972570765147,
      "learning_rate": 5e-06,
      "loss": 0.4825,
      "step": 720
    },
    {
      "epoch": 1.4784810126582277,
      "grad_norm": 1.1979511635098932,
      "learning_rate": 5e-06,
      "loss": 0.4852,
      "step": 730
    },
    {
      "epoch": 1.4987341772151899,
      "grad_norm": 1.223444548950007,
      "learning_rate": 5e-06,
      "loss": 0.478,
      "step": 740
    },
    {
      "epoch": 1.518987341772152,
      "grad_norm": 1.212271308844042,
      "learning_rate": 5e-06,
      "loss": 0.4808,
      "step": 750
    },
    {
      "epoch": 1.539240506329114,
      "grad_norm": 1.4825031872664458,
      "learning_rate": 5e-06,
      "loss": 0.4816,
      "step": 760
    },
    {
      "epoch": 1.5594936708860758,
      "grad_norm": 1.3782471367887354,
      "learning_rate": 5e-06,
      "loss": 0.4802,
      "step": 770
    },
    {
      "epoch": 1.579746835443038,
      "grad_norm": 1.8051947527343706,
      "learning_rate": 5e-06,
      "loss": 0.4809,
      "step": 780
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.8200634591672311,
      "learning_rate": 5e-06,
      "loss": 0.4837,
      "step": 790
    },
    {
      "epoch": 1.620253164556962,
      "grad_norm": 1.8730022209605697,
      "learning_rate": 5e-06,
      "loss": 0.4778,
      "step": 800
    },
    {
      "epoch": 1.640506329113924,
      "grad_norm": 1.5457078754366798,
      "learning_rate": 5e-06,
      "loss": 0.4699,
      "step": 810
    },
    {
      "epoch": 1.660759493670886,
      "grad_norm": 1.5274155794335695,
      "learning_rate": 5e-06,
      "loss": 0.4787,
      "step": 820
    },
    {
      "epoch": 1.6810126582278482,
      "grad_norm": 1.4806972827307272,
      "learning_rate": 5e-06,
      "loss": 0.4739,
      "step": 830
    },
    {
      "epoch": 1.70126582278481,
      "grad_norm": 1.2055743931937628,
      "learning_rate": 5e-06,
      "loss": 0.4752,
      "step": 840
    },
    {
      "epoch": 1.721518987341772,
      "grad_norm": 1.4159359876598896,
      "learning_rate": 5e-06,
      "loss": 0.4774,
      "step": 850
    },
    {
      "epoch": 1.7417721518987341,
      "grad_norm": 1.254380269789728,
      "learning_rate": 5e-06,
      "loss": 0.4777,
      "step": 860
    },
    {
      "epoch": 1.7620253164556963,
      "grad_norm": 1.462457926071268,
      "learning_rate": 5e-06,
      "loss": 0.4807,
      "step": 870
    },
    {
      "epoch": 1.7822784810126582,
      "grad_norm": 1.1393110128835031,
      "learning_rate": 5e-06,
      "loss": 0.4813,
      "step": 880
    },
    {
      "epoch": 1.80253164556962,
      "grad_norm": 1.2206200693431573,
      "learning_rate": 5e-06,
      "loss": 0.4785,
      "step": 890
    },
    {
      "epoch": 1.8227848101265822,
      "grad_norm": 1.2444564430213727,
      "learning_rate": 5e-06,
      "loss": 0.4787,
      "step": 900
    },
    {
      "epoch": 1.8430379746835444,
      "grad_norm": 1.2631624432182935,
      "learning_rate": 5e-06,
      "loss": 0.4814,
      "step": 910
    },
    {
      "epoch": 1.8632911392405065,
      "grad_norm": 1.2947084245489033,
      "learning_rate": 5e-06,
      "loss": 0.4803,
      "step": 920
    },
    {
      "epoch": 1.8835443037974684,
      "grad_norm": 1.1155641259326083,
      "learning_rate": 5e-06,
      "loss": 0.4769,
      "step": 930
    },
    {
      "epoch": 1.9037974683544303,
      "grad_norm": 1.1602196136988134,
      "learning_rate": 5e-06,
      "loss": 0.4811,
      "step": 940
    },
    {
      "epoch": 1.9240506329113924,
      "grad_norm": 1.2925726150873043,
      "learning_rate": 5e-06,
      "loss": 0.4824,
      "step": 950
    },
    {
      "epoch": 1.9443037974683546,
      "grad_norm": 1.3706494320177713,
      "learning_rate": 5e-06,
      "loss": 0.4867,
      "step": 960
    },
    {
      "epoch": 1.9645569620253165,
      "grad_norm": 1.1789833096040232,
      "learning_rate": 5e-06,
      "loss": 0.4849,
      "step": 970
    },
    {
      "epoch": 1.9848101265822784,
      "grad_norm": 1.2352210077355772,
      "learning_rate": 5e-06,
      "loss": 0.485,
      "step": 980
    },
    {
      "epoch": 1.998987341772152,
      "eval_loss": 0.0688759982585907,
      "eval_runtime": 509.8853,
      "eval_samples_per_second": 26.092,
      "eval_steps_per_second": 0.408,
      "step": 987
    },
    {
      "epoch": 2.0050632911392405,
      "grad_norm": 2.118412822165404,
      "learning_rate": 5e-06,
      "loss": 0.457,
      "step": 990
    },
    {
      "epoch": 2.0253164556962027,
      "grad_norm": 1.8998553054069363,
      "learning_rate": 5e-06,
      "loss": 0.3901,
      "step": 1000
    },
    {
      "epoch": 2.0455696202531644,
      "grad_norm": 1.5192711518295892,
      "learning_rate": 5e-06,
      "loss": 0.386,
      "step": 1010
    },
    {
      "epoch": 2.0658227848101265,
      "grad_norm": 1.422871885983194,
      "learning_rate": 5e-06,
      "loss": 0.3814,
      "step": 1020
    },
    {
      "epoch": 2.0860759493670886,
      "grad_norm": 1.3257151760052064,
      "learning_rate": 5e-06,
      "loss": 0.381,
      "step": 1030
    },
    {
      "epoch": 2.1063291139240508,
      "grad_norm": 1.2869221177843286,
      "learning_rate": 5e-06,
      "loss": 0.379,
      "step": 1040
    },
    {
      "epoch": 2.1265822784810124,
      "grad_norm": 1.59028377943099,
      "learning_rate": 5e-06,
      "loss": 0.389,
      "step": 1050
    },
    {
      "epoch": 2.1468354430379746,
      "grad_norm": 1.471981263128043,
      "learning_rate": 5e-06,
      "loss": 0.3849,
      "step": 1060
    },
    {
      "epoch": 2.1670886075949367,
      "grad_norm": 1.2821578759324024,
      "learning_rate": 5e-06,
      "loss": 0.3886,
      "step": 1070
    },
    {
      "epoch": 2.187341772151899,
      "grad_norm": 1.3746960134484794,
      "learning_rate": 5e-06,
      "loss": 0.3867,
      "step": 1080
    },
    {
      "epoch": 2.207594936708861,
      "grad_norm": 1.339564711838716,
      "learning_rate": 5e-06,
      "loss": 0.3844,
      "step": 1090
    },
    {
      "epoch": 2.2278481012658227,
      "grad_norm": 1.3490512019574192,
      "learning_rate": 5e-06,
      "loss": 0.3934,
      "step": 1100
    },
    {
      "epoch": 2.248101265822785,
      "grad_norm": 1.4690556887985935,
      "learning_rate": 5e-06,
      "loss": 0.3891,
      "step": 1110
    },
    {
      "epoch": 2.268354430379747,
      "grad_norm": 1.327918587634811,
      "learning_rate": 5e-06,
      "loss": 0.3917,
      "step": 1120
    },
    {
      "epoch": 2.2886075949367086,
      "grad_norm": 1.3692936754366893,
      "learning_rate": 5e-06,
      "loss": 0.3926,
      "step": 1130
    },
    {
      "epoch": 2.3088607594936708,
      "grad_norm": 1.3650848753392741,
      "learning_rate": 5e-06,
      "loss": 0.3891,
      "step": 1140
    },
    {
      "epoch": 2.329113924050633,
      "grad_norm": 1.4983756068154461,
      "learning_rate": 5e-06,
      "loss": 0.3956,
      "step": 1150
    },
    {
      "epoch": 2.349367088607595,
      "grad_norm": 1.860929607600757,
      "learning_rate": 5e-06,
      "loss": 0.3962,
      "step": 1160
    },
    {
      "epoch": 2.369620253164557,
      "grad_norm": 1.4311153094207263,
      "learning_rate": 5e-06,
      "loss": 0.3968,
      "step": 1170
    },
    {
      "epoch": 2.389873417721519,
      "grad_norm": 1.2250798797821876,
      "learning_rate": 5e-06,
      "loss": 0.3956,
      "step": 1180
    },
    {
      "epoch": 2.410126582278481,
      "grad_norm": 1.2439883028217633,
      "learning_rate": 5e-06,
      "loss": 0.396,
      "step": 1190
    },
    {
      "epoch": 2.430379746835443,
      "grad_norm": 1.374035038735882,
      "learning_rate": 5e-06,
      "loss": 0.3945,
      "step": 1200
    },
    {
      "epoch": 2.4506329113924052,
      "grad_norm": 1.302797887064942,
      "learning_rate": 5e-06,
      "loss": 0.394,
      "step": 1210
    },
    {
      "epoch": 2.470886075949367,
      "grad_norm": 1.2109892527412365,
      "learning_rate": 5e-06,
      "loss": 0.3978,
      "step": 1220
    },
    {
      "epoch": 2.491139240506329,
      "grad_norm": 1.371554040241299,
      "learning_rate": 5e-06,
      "loss": 0.3975,
      "step": 1230
    },
    {
      "epoch": 2.511392405063291,
      "grad_norm": 1.4659619053054986,
      "learning_rate": 5e-06,
      "loss": 0.4019,
      "step": 1240
    },
    {
      "epoch": 2.5316455696202533,
      "grad_norm": 1.364084604169236,
      "learning_rate": 5e-06,
      "loss": 0.3956,
      "step": 1250
    },
    {
      "epoch": 2.5518987341772155,
      "grad_norm": 1.445809476649577,
      "learning_rate": 5e-06,
      "loss": 0.3915,
      "step": 1260
    },
    {
      "epoch": 2.572151898734177,
      "grad_norm": 1.5466745253205325,
      "learning_rate": 5e-06,
      "loss": 0.3972,
      "step": 1270
    },
    {
      "epoch": 2.5924050632911393,
      "grad_norm": 1.3633619533180656,
      "learning_rate": 5e-06,
      "loss": 0.3989,
      "step": 1280
    },
    {
      "epoch": 2.6126582278481014,
      "grad_norm": 1.281031129480792,
      "learning_rate": 5e-06,
      "loss": 0.4039,
      "step": 1290
    },
    {
      "epoch": 2.632911392405063,
      "grad_norm": 1.3705022467143146,
      "learning_rate": 5e-06,
      "loss": 0.3986,
      "step": 1300
    },
    {
      "epoch": 2.6531645569620252,
      "grad_norm": 1.2316913338581885,
      "learning_rate": 5e-06,
      "loss": 0.3982,
      "step": 1310
    },
    {
      "epoch": 2.6734177215189874,
      "grad_norm": 1.4025614551602366,
      "learning_rate": 5e-06,
      "loss": 0.4008,
      "step": 1320
    },
    {
      "epoch": 2.6936708860759495,
      "grad_norm": 1.3599187544699725,
      "learning_rate": 5e-06,
      "loss": 0.4033,
      "step": 1330
    },
    {
      "epoch": 2.7139240506329116,
      "grad_norm": 1.3641980318640243,
      "learning_rate": 5e-06,
      "loss": 0.4017,
      "step": 1340
    },
    {
      "epoch": 2.7341772151898733,
      "grad_norm": 1.2690981108266888,
      "learning_rate": 5e-06,
      "loss": 0.402,
      "step": 1350
    },
    {
      "epoch": 2.7544303797468355,
      "grad_norm": 1.278277946781532,
      "learning_rate": 5e-06,
      "loss": 0.3975,
      "step": 1360
    },
    {
      "epoch": 2.7746835443037976,
      "grad_norm": 1.4580279665565177,
      "learning_rate": 5e-06,
      "loss": 0.4035,
      "step": 1370
    },
    {
      "epoch": 2.7949367088607593,
      "grad_norm": 1.3593972509885985,
      "learning_rate": 5e-06,
      "loss": 0.4008,
      "step": 1380
    },
    {
      "epoch": 2.8151898734177214,
      "grad_norm": 1.572713763995317,
      "learning_rate": 5e-06,
      "loss": 0.4034,
      "step": 1390
    },
    {
      "epoch": 2.8354430379746836,
      "grad_norm": 1.3603922093484442,
      "learning_rate": 5e-06,
      "loss": 0.3973,
      "step": 1400
    },
    {
      "epoch": 2.8556962025316457,
      "grad_norm": 1.3118672602704928,
      "learning_rate": 5e-06,
      "loss": 0.4057,
      "step": 1410
    },
    {
      "epoch": 2.875949367088608,
      "grad_norm": 1.3052595893359151,
      "learning_rate": 5e-06,
      "loss": 0.4016,
      "step": 1420
    },
    {
      "epoch": 2.8962025316455695,
      "grad_norm": 1.3135936199650753,
      "learning_rate": 5e-06,
      "loss": 0.4028,
      "step": 1430
    },
    {
      "epoch": 2.9164556962025316,
      "grad_norm": 1.3314117087627575,
      "learning_rate": 5e-06,
      "loss": 0.4044,
      "step": 1440
    },
    {
      "epoch": 2.9367088607594938,
      "grad_norm": 1.295792953150207,
      "learning_rate": 5e-06,
      "loss": 0.4133,
      "step": 1450
    },
    {
      "epoch": 2.9569620253164555,
      "grad_norm": 1.3154261450222393,
      "learning_rate": 5e-06,
      "loss": 0.4017,
      "step": 1460
    },
    {
      "epoch": 2.9772151898734176,
      "grad_norm": 1.2836016250191487,
      "learning_rate": 5e-06,
      "loss": 0.4059,
      "step": 1470
    },
    {
      "epoch": 2.9954430379746837,
      "eval_loss": 0.07266594469547272,
      "eval_runtime": 508.6063,
      "eval_samples_per_second": 26.158,
      "eval_steps_per_second": 0.409,
      "step": 1479
    },
    {
      "epoch": 2.9954430379746837,
      "step": 1479,
      "total_flos": 2477170706350080.0,
      "train_loss": 0.48262619037254184,
      "train_runtime": 84591.5062,
      "train_samples_per_second": 8.964,
      "train_steps_per_second": 0.017
    }
  ],
  "logging_steps": 10,
  "max_steps": 1479,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 2477170706350080.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}