{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.23681314029294726,
  "eval_steps": 500,
  "global_step": 2797,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008466683600033867,
      "grad_norm": 2.1896274089813232,
      "learning_rate": 1.1061797752808989e-06,
      "loss": 0.9007,
      "step": 10
    },
    {
      "epoch": 0.0016933367200067733,
      "grad_norm": 1.3733998537063599,
      "learning_rate": 2.2241573033707866e-06,
      "loss": 0.8719,
      "step": 20
    },
    {
      "epoch": 0.00254000508001016,
      "grad_norm": 1.1982183456420898,
      "learning_rate": 3.342134831460675e-06,
      "loss": 0.8299,
      "step": 30
    },
    {
      "epoch": 0.0033866734400135466,
      "grad_norm": 1.1160142421722412,
      "learning_rate": 4.4601123595505624e-06,
      "loss": 0.7803,
      "step": 40
    },
    {
      "epoch": 0.004233341800016934,
      "grad_norm": 0.9138423204421997,
      "learning_rate": 5.5780898876404495e-06,
      "loss": 0.7622,
      "step": 50
    },
    {
      "epoch": 0.00508001016002032,
      "grad_norm": 0.8700115084648132,
      "learning_rate": 6.6960674157303374e-06,
      "loss": 0.7332,
      "step": 60
    },
    {
      "epoch": 0.005926678520023707,
      "grad_norm": 0.8024980425834656,
      "learning_rate": 7.814044943820226e-06,
      "loss": 0.7072,
      "step": 70
    },
    {
      "epoch": 0.006773346880027093,
      "grad_norm": 0.8063226342201233,
      "learning_rate": 8.932022471910112e-06,
      "loss": 0.7082,
      "step": 80
    },
    {
      "epoch": 0.00762001524003048,
      "grad_norm": 0.7324275970458984,
      "learning_rate": 1.005e-05,
      "loss": 0.7095,
      "step": 90
    },
    {
      "epoch": 0.008466683600033867,
      "grad_norm": 0.8663532137870789,
      "learning_rate": 1.1167977528089888e-05,
      "loss": 0.6899,
      "step": 100
    },
    {
      "epoch": 0.009313351960037254,
      "grad_norm": 0.8148631453514099,
      "learning_rate": 1.2285955056179776e-05,
      "loss": 0.6984,
      "step": 110
    },
    {
      "epoch": 0.01016002032004064,
      "grad_norm": 0.7821786403656006,
      "learning_rate": 1.3403932584269664e-05,
      "loss": 0.7066,
      "step": 120
    },
    {
      "epoch": 0.011006688680044027,
      "grad_norm": 0.7769770622253418,
      "learning_rate": 1.4521910112359552e-05,
      "loss": 0.6908,
      "step": 130
    },
    {
      "epoch": 0.011853357040047413,
      "grad_norm": 0.9013803601264954,
      "learning_rate": 1.563988764044944e-05,
      "loss": 0.6885,
      "step": 140
    },
    {
      "epoch": 0.0127000254000508,
      "grad_norm": 0.7101280689239502,
      "learning_rate": 1.6757865168539328e-05,
      "loss": 0.6886,
      "step": 150
    },
    {
      "epoch": 0.013546693760054187,
      "grad_norm": 0.8616020679473877,
      "learning_rate": 1.7875842696629214e-05,
      "loss": 0.6849,
      "step": 160
    },
    {
      "epoch": 0.014393362120057573,
      "grad_norm": 0.8392877578735352,
      "learning_rate": 1.89938202247191e-05,
      "loss": 0.6933,
      "step": 170
    },
    {
      "epoch": 0.01524003048006096,
      "grad_norm": 0.766579806804657,
      "learning_rate": 2e-05,
      "loss": 0.7048,
      "step": 180
    },
    {
      "epoch": 0.016086698840064348,
      "grad_norm": 0.7274855375289917,
      "learning_rate": 2e-05,
      "loss": 0.7039,
      "step": 190
    },
    {
      "epoch": 0.016933367200067734,
      "grad_norm": 0.7656974792480469,
      "learning_rate": 2e-05,
      "loss": 0.6829,
      "step": 200
    },
    {
      "epoch": 0.01778003556007112,
      "grad_norm": 0.7630816102027893,
      "learning_rate": 2e-05,
      "loss": 0.6948,
      "step": 210
    },
    {
      "epoch": 0.018626703920074508,
      "grad_norm": 0.7607164978981018,
      "learning_rate": 2e-05,
      "loss": 0.6976,
      "step": 220
    },
    {
      "epoch": 0.019473372280077894,
      "grad_norm": 0.6640747785568237,
      "learning_rate": 2e-05,
      "loss": 0.6529,
      "step": 230
    },
    {
      "epoch": 0.02032004064008128,
      "grad_norm": 0.648815393447876,
      "learning_rate": 2e-05,
      "loss": 0.687,
      "step": 240
    },
    {
      "epoch": 0.021166709000084667,
      "grad_norm": 0.5993350744247437,
      "learning_rate": 2e-05,
      "loss": 0.693,
      "step": 250
    },
    {
      "epoch": 0.022013377360088054,
      "grad_norm": 0.6671707630157471,
      "learning_rate": 2e-05,
      "loss": 0.7208,
      "step": 260
    },
    {
      "epoch": 0.02286004572009144,
      "grad_norm": 0.5551834106445312,
      "learning_rate": 2e-05,
      "loss": 0.6958,
      "step": 270
    },
    {
      "epoch": 0.023706714080094827,
      "grad_norm": 0.5955666303634644,
      "learning_rate": 2e-05,
      "loss": 0.685,
      "step": 280
    },
    {
      "epoch": 0.024553382440098213,
      "grad_norm": 0.5701448917388916,
      "learning_rate": 2e-05,
      "loss": 0.6796,
      "step": 290
    },
    {
      "epoch": 0.0254000508001016,
      "grad_norm": 0.5824018716812134,
      "learning_rate": 2e-05,
      "loss": 0.6841,
      "step": 300
    },
    {
      "epoch": 0.026246719160104987,
      "grad_norm": 0.576776921749115,
      "learning_rate": 2e-05,
      "loss": 0.6563,
      "step": 310
    },
    {
      "epoch": 0.027093387520108373,
      "grad_norm": 0.5411778688430786,
      "learning_rate": 2e-05,
      "loss": 0.6835,
      "step": 320
    },
    {
      "epoch": 0.02794005588011176,
      "grad_norm": 0.5345405340194702,
      "learning_rate": 2e-05,
      "loss": 0.6657,
      "step": 330
    },
    {
      "epoch": 0.028786724240115146,
      "grad_norm": 0.5346488952636719,
      "learning_rate": 2e-05,
      "loss": 0.6951,
      "step": 340
    },
    {
      "epoch": 0.029633392600118533,
      "grad_norm": 0.49902835488319397,
      "learning_rate": 2e-05,
      "loss": 0.664,
      "step": 350
    },
    {
      "epoch": 0.03048006096012192,
      "grad_norm": 0.6449501514434814,
      "learning_rate": 2e-05,
      "loss": 0.6737,
      "step": 360
    },
    {
      "epoch": 0.031326729320125306,
      "grad_norm": 0.487582802772522,
      "learning_rate": 2e-05,
      "loss": 0.6546,
      "step": 370
    },
    {
      "epoch": 0.032173397680128696,
      "grad_norm": 0.5169985294342041,
      "learning_rate": 2e-05,
      "loss": 0.6731,
      "step": 380
    },
    {
      "epoch": 0.03302006604013208,
      "grad_norm": 0.5427067279815674,
      "learning_rate": 2e-05,
      "loss": 0.6882,
      "step": 390
    },
    {
      "epoch": 0.03386673440013547,
      "grad_norm": 0.5355451107025146,
      "learning_rate": 2e-05,
      "loss": 0.6955,
      "step": 400
    },
    {
      "epoch": 0.03471340276013885,
      "grad_norm": 0.6196058392524719,
      "learning_rate": 2e-05,
      "loss": 0.6807,
      "step": 410
    },
    {
      "epoch": 0.03556007112014224,
      "grad_norm": 0.5216856598854065,
      "learning_rate": 2e-05,
      "loss": 0.6602,
      "step": 420
    },
    {
      "epoch": 0.036406739480145625,
      "grad_norm": 0.5485526323318481,
      "learning_rate": 2e-05,
      "loss": 0.6846,
      "step": 430
    },
    {
      "epoch": 0.037253407840149015,
      "grad_norm": 0.48402827978134155,
      "learning_rate": 2e-05,
      "loss": 0.6669,
      "step": 440
    },
    {
      "epoch": 0.0381000762001524,
      "grad_norm": 0.48090001940727234,
      "learning_rate": 2e-05,
      "loss": 0.6651,
      "step": 450
    },
    {
      "epoch": 0.03894674456015579,
      "grad_norm": 1.9493638277053833,
      "learning_rate": 2e-05,
      "loss": 0.6813,
      "step": 460
    },
    {
      "epoch": 0.03979341292015917,
      "grad_norm": 0.5349039435386658,
      "learning_rate": 2e-05,
      "loss": 0.6901,
      "step": 470
    },
    {
      "epoch": 0.04064008128016256,
      "grad_norm": 0.4926290214061737,
      "learning_rate": 2e-05,
      "loss": 0.6514,
      "step": 480
    },
    {
      "epoch": 0.041486749640165944,
      "grad_norm": 0.6464523077011108,
      "learning_rate": 2e-05,
      "loss": 0.6758,
      "step": 490
    },
    {
      "epoch": 0.042333418000169334,
      "grad_norm": 0.5073714256286621,
      "learning_rate": 2e-05,
      "loss": 0.6941,
      "step": 500
    },
    {
      "epoch": 0.04318008636017272,
      "grad_norm": 0.5042576193809509,
      "learning_rate": 2e-05,
      "loss": 0.6788,
      "step": 510
    },
    {
      "epoch": 0.04402675472017611,
      "grad_norm": 0.4722915589809418,
      "learning_rate": 2e-05,
      "loss": 0.6555,
      "step": 520
    },
    {
      "epoch": 0.04487342308017949,
      "grad_norm": 0.5186958312988281,
      "learning_rate": 2e-05,
      "loss": 0.657,
      "step": 530
    },
    {
      "epoch": 0.04572009144018288,
      "grad_norm": 0.47601163387298584,
      "learning_rate": 2e-05,
      "loss": 0.6734,
      "step": 540
    },
    {
      "epoch": 0.046566759800186264,
      "grad_norm": 0.4465620517730713,
      "learning_rate": 2e-05,
      "loss": 0.6834,
      "step": 550
    },
    {
      "epoch": 0.047413428160189654,
      "grad_norm": 0.4941118359565735,
      "learning_rate": 2e-05,
      "loss": 0.6476,
      "step": 560
    },
    {
      "epoch": 0.048260096520193044,
      "grad_norm": 0.479648232460022,
      "learning_rate": 2e-05,
      "loss": 0.6544,
      "step": 570
    },
    {
      "epoch": 0.04910676488019643,
      "grad_norm": 0.5040650963783264,
      "learning_rate": 2e-05,
      "loss": 0.6754,
      "step": 580
    },
    {
      "epoch": 0.04995343324019982,
      "grad_norm": 0.4866141378879547,
      "learning_rate": 2e-05,
      "loss": 0.6917,
      "step": 590
    },
    {
      "epoch": 0.0508001016002032,
      "grad_norm": 0.46658095717430115,
      "learning_rate": 2e-05,
      "loss": 0.6811,
      "step": 600
    },
    {
      "epoch": 0.05164676996020659,
      "grad_norm": 0.6377661228179932,
      "learning_rate": 2e-05,
      "loss": 0.6355,
      "step": 610
    },
    {
      "epoch": 0.05249343832020997,
      "grad_norm": 0.4834534823894501,
      "learning_rate": 2e-05,
      "loss": 0.6957,
      "step": 620
    },
    {
      "epoch": 0.05334010668021336,
      "grad_norm": 0.44412001967430115,
      "learning_rate": 2e-05,
      "loss": 0.6678,
      "step": 630
    },
    {
      "epoch": 0.054186775040216746,
      "grad_norm": 0.5037946701049805,
      "learning_rate": 2e-05,
      "loss": 0.6785,
      "step": 640
    },
    {
      "epoch": 0.055033443400220136,
      "grad_norm": 0.45366835594177246,
      "learning_rate": 2e-05,
      "loss": 0.676,
      "step": 650
    },
    {
      "epoch": 0.05588011176022352,
      "grad_norm": 0.4277074337005615,
      "learning_rate": 2e-05,
      "loss": 0.6591,
      "step": 660
    },
    {
      "epoch": 0.05672678012022691,
      "grad_norm": 0.4375869035720825,
      "learning_rate": 2e-05,
      "loss": 0.6616,
      "step": 670
    },
    {
      "epoch": 0.05757344848023029,
      "grad_norm": 0.46945950388908386,
      "learning_rate": 2e-05,
      "loss": 0.6838,
      "step": 680
    },
    {
      "epoch": 0.05842011684023368,
      "grad_norm": 0.4755280315876007,
      "learning_rate": 2e-05,
      "loss": 0.661,
      "step": 690
    },
    {
      "epoch": 0.059266785200237065,
      "grad_norm": 0.4614129960536957,
      "learning_rate": 2e-05,
      "loss": 0.6465,
      "step": 700
    },
    {
      "epoch": 0.060113453560240455,
      "grad_norm": 0.4619314968585968,
      "learning_rate": 2e-05,
      "loss": 0.6829,
      "step": 710
    },
    {
      "epoch": 0.06096012192024384,
      "grad_norm": 0.4906548261642456,
      "learning_rate": 2e-05,
      "loss": 0.6863,
      "step": 720
    },
    {
      "epoch": 0.06180679028024723,
      "grad_norm": 0.5654237866401672,
      "learning_rate": 2e-05,
      "loss": 0.6994,
      "step": 730
    },
    {
      "epoch": 0.06265345864025061,
      "grad_norm": 0.4611152112483978,
      "learning_rate": 2e-05,
      "loss": 0.6601,
      "step": 740
    },
    {
      "epoch": 0.063500127000254,
      "grad_norm": 0.4759562015533447,
      "learning_rate": 2e-05,
      "loss": 0.6537,
      "step": 750
    },
    {
      "epoch": 0.06434679536025739,
      "grad_norm": 0.45463666319847107,
      "learning_rate": 2e-05,
      "loss": 0.6623,
      "step": 760
    },
    {
      "epoch": 0.06519346372026077,
      "grad_norm": 0.45970118045806885,
      "learning_rate": 2e-05,
      "loss": 0.6557,
      "step": 770
    },
    {
      "epoch": 0.06604013208026416,
      "grad_norm": 0.45690014958381653,
      "learning_rate": 2e-05,
      "loss": 0.6478,
      "step": 780
    },
    {
      "epoch": 0.06688680044026754,
      "grad_norm": 0.45209041237831116,
      "learning_rate": 2e-05,
      "loss": 0.651,
      "step": 790
    },
    {
      "epoch": 0.06773346880027094,
      "grad_norm": 0.5716219544410706,
      "learning_rate": 2e-05,
      "loss": 0.6647,
      "step": 800
    },
    {
      "epoch": 0.06858013716027432,
      "grad_norm": 0.43732336163520813,
      "learning_rate": 2e-05,
      "loss": 0.6604,
      "step": 810
    },
    {
      "epoch": 0.0694268055202777,
      "grad_norm": 0.4478982388973236,
      "learning_rate": 2e-05,
      "loss": 0.6509,
      "step": 820
    },
    {
      "epoch": 0.07027347388028109,
      "grad_norm": 0.44605377316474915,
      "learning_rate": 2e-05,
      "loss": 0.6619,
      "step": 830
    },
    {
      "epoch": 0.07112014224028448,
      "grad_norm": 0.4520704746246338,
      "learning_rate": 2e-05,
      "loss": 0.6541,
      "step": 840
    },
    {
      "epoch": 0.07196681060028787,
      "grad_norm": 0.45137783885002136,
      "learning_rate": 2e-05,
      "loss": 0.6632,
      "step": 850
    },
    {
      "epoch": 0.07281347896029125,
      "grad_norm": 0.4655689299106598,
      "learning_rate": 2e-05,
      "loss": 0.6519,
      "step": 860
    },
    {
      "epoch": 0.07366014732029465,
      "grad_norm": 0.43631526827812195,
      "learning_rate": 2e-05,
      "loss": 0.6597,
      "step": 870
    },
    {
      "epoch": 0.07450681568029803,
      "grad_norm": 0.42785879969596863,
      "learning_rate": 2e-05,
      "loss": 0.6464,
      "step": 880
    },
    {
      "epoch": 0.07535348404030141,
      "grad_norm": 0.43011021614074707,
      "learning_rate": 2e-05,
      "loss": 0.6528,
      "step": 890
    },
    {
      "epoch": 0.0762001524003048,
      "grad_norm": 0.46899306774139404,
      "learning_rate": 2e-05,
      "loss": 0.6666,
      "step": 900
    },
    {
      "epoch": 0.0770468207603082,
      "grad_norm": 0.46042707562446594,
      "learning_rate": 2e-05,
      "loss": 0.645,
      "step": 910
    },
    {
      "epoch": 0.07789348912031158,
      "grad_norm": 0.4511071741580963,
      "learning_rate": 2e-05,
      "loss": 0.6436,
      "step": 920
    },
    {
      "epoch": 0.07874015748031496,
      "grad_norm": 0.4230646789073944,
      "learning_rate": 2e-05,
      "loss": 0.6743,
      "step": 930
    },
    {
      "epoch": 0.07958682584031834,
      "grad_norm": 0.43698370456695557,
      "learning_rate": 2e-05,
      "loss": 0.6481,
      "step": 940
    },
    {
      "epoch": 0.08043349420032174,
      "grad_norm": 0.4549170732498169,
      "learning_rate": 2e-05,
      "loss": 0.6514,
      "step": 950
    },
    {
      "epoch": 0.08128016256032512,
      "grad_norm": 0.45507657527923584,
      "learning_rate": 2e-05,
      "loss": 0.6554,
      "step": 960
    },
    {
      "epoch": 0.0821268309203285,
      "grad_norm": 0.42522671818733215,
      "learning_rate": 2e-05,
      "loss": 0.656,
      "step": 970
    },
    {
      "epoch": 0.08297349928033189,
      "grad_norm": 0.43912380933761597,
      "learning_rate": 2e-05,
      "loss": 0.6608,
      "step": 980
    },
    {
      "epoch": 0.08382016764033529,
      "grad_norm": 0.4183550179004669,
      "learning_rate": 2e-05,
      "loss": 0.6492,
      "step": 990
    },
    {
      "epoch": 0.08466683600033867,
      "grad_norm": 0.44775786995887756,
      "learning_rate": 2e-05,
      "loss": 0.6292,
      "step": 1000
    },
    {
      "epoch": 0.08551350436034205,
      "grad_norm": 0.44851788878440857,
      "learning_rate": 2e-05,
      "loss": 0.6579,
      "step": 1010
    },
    {
      "epoch": 0.08636017272034544,
      "grad_norm": 0.45955589413642883,
      "learning_rate": 2e-05,
      "loss": 0.6468,
      "step": 1020
    },
    {
      "epoch": 0.08720684108034883,
      "grad_norm": 0.4205484688282013,
      "learning_rate": 2e-05,
      "loss": 0.651,
      "step": 1030
    },
    {
      "epoch": 0.08805350944035222,
      "grad_norm": 0.42118069529533386,
      "learning_rate": 2e-05,
      "loss": 0.648,
      "step": 1040
    },
    {
      "epoch": 0.0889001778003556,
      "grad_norm": 0.45766347646713257,
      "learning_rate": 2e-05,
      "loss": 0.6386,
      "step": 1050
    },
    {
      "epoch": 0.08974684616035898,
      "grad_norm": 0.4297139346599579,
      "learning_rate": 2e-05,
      "loss": 0.6334,
      "step": 1060
    },
    {
      "epoch": 0.09059351452036238,
      "grad_norm": 0.4587555229663849,
      "learning_rate": 2e-05,
      "loss": 0.6688,
      "step": 1070
    },
    {
      "epoch": 0.09144018288036576,
      "grad_norm": 0.4319729506969452,
      "learning_rate": 2e-05,
      "loss": 0.6453,
      "step": 1080
    },
    {
      "epoch": 0.09228685124036914,
      "grad_norm": 0.4240010976791382,
      "learning_rate": 2e-05,
      "loss": 0.6387,
      "step": 1090
    },
    {
      "epoch": 0.09313351960037253,
      "grad_norm": 0.41819435358047485,
      "learning_rate": 2e-05,
      "loss": 0.636,
      "step": 1100
    },
    {
      "epoch": 0.09398018796037592,
      "grad_norm": 0.4749411344528198,
      "learning_rate": 2e-05,
      "loss": 0.6502,
      "step": 1110
    },
    {
      "epoch": 0.09482685632037931,
      "grad_norm": 0.4842819571495056,
      "learning_rate": 2e-05,
      "loss": 0.6601,
      "step": 1120
    },
    {
      "epoch": 0.09567352468038269,
      "grad_norm": 0.39176562428474426,
      "learning_rate": 2e-05,
      "loss": 0.6316,
      "step": 1130
    },
    {
      "epoch": 0.09652019304038609,
      "grad_norm": 0.46135643124580383,
      "learning_rate": 2e-05,
      "loss": 0.6763,
      "step": 1140
    },
    {
      "epoch": 0.09736686140038947,
      "grad_norm": 0.4732727110385895,
      "learning_rate": 2e-05,
      "loss": 0.6577,
      "step": 1150
    },
    {
      "epoch": 0.09821352976039285,
      "grad_norm": 0.4651736319065094,
      "learning_rate": 2e-05,
      "loss": 0.6385,
      "step": 1160
    },
    {
      "epoch": 0.09906019812039624,
      "grad_norm": 0.44102978706359863,
      "learning_rate": 2e-05,
      "loss": 0.644,
      "step": 1170
    },
    {
      "epoch": 0.09990686648039963,
      "grad_norm": 0.399547815322876,
      "learning_rate": 2e-05,
      "loss": 0.6441,
      "step": 1180
    },
    {
      "epoch": 0.10075353484040302,
      "grad_norm": 0.5150323510169983,
      "learning_rate": 2e-05,
      "loss": 0.6812,
      "step": 1190
    },
    {
      "epoch": 0.1016002032004064,
      "grad_norm": 0.43167948722839355,
      "learning_rate": 2e-05,
      "loss": 0.6416,
      "step": 1200
    },
    {
      "epoch": 0.10244687156040978,
      "grad_norm": 0.4367421567440033,
      "learning_rate": 2e-05,
      "loss": 0.6689,
      "step": 1210
    },
    {
      "epoch": 0.10329353992041318,
      "grad_norm": 0.4407538175582886,
      "learning_rate": 2e-05,
      "loss": 0.6628,
      "step": 1220
    },
    {
      "epoch": 0.10414020828041656,
      "grad_norm": 0.4248872995376587,
      "learning_rate": 2e-05,
      "loss": 0.6584,
      "step": 1230
    },
    {
      "epoch": 0.10498687664041995,
      "grad_norm": 0.42799079418182373,
      "learning_rate": 2e-05,
      "loss": 0.6496,
      "step": 1240
    },
    {
      "epoch": 0.10583354500042333,
      "grad_norm": 0.4394405484199524,
      "learning_rate": 2e-05,
      "loss": 0.6398,
      "step": 1250
    },
    {
      "epoch": 0.10668021336042673,
      "grad_norm": 0.43604040145874023,
      "learning_rate": 2e-05,
      "loss": 0.6502,
      "step": 1260
    },
    {
      "epoch": 0.10752688172043011,
      "grad_norm": 0.43875670433044434,
      "learning_rate": 2e-05,
      "loss": 0.6564,
      "step": 1270
    },
    {
      "epoch": 0.10837355008043349,
      "grad_norm": 0.4250807762145996,
      "learning_rate": 2e-05,
      "loss": 0.6389,
      "step": 1280
    },
    {
      "epoch": 0.10922021844043688,
      "grad_norm": 0.48220178484916687,
      "learning_rate": 2e-05,
      "loss": 0.6617,
      "step": 1290
    },
    {
      "epoch": 0.11006688680044027,
      "grad_norm": 0.41790634393692017,
      "learning_rate": 2e-05,
      "loss": 0.636,
      "step": 1300
    },
    {
      "epoch": 0.11091355516044366,
      "grad_norm": 0.5080624222755432,
      "learning_rate": 2e-05,
      "loss": 0.6733,
      "step": 1310
    },
    {
      "epoch": 0.11176022352044704,
      "grad_norm": 0.4096316695213318,
      "learning_rate": 2e-05,
      "loss": 0.6447,
      "step": 1320
    },
    {
      "epoch": 0.11260689188045042,
      "grad_norm": 0.4489736557006836,
      "learning_rate": 2e-05,
      "loss": 0.6723,
      "step": 1330
    },
    {
      "epoch": 0.11345356024045382,
      "grad_norm": 0.4486621022224426,
      "learning_rate": 2e-05,
      "loss": 0.6536,
      "step": 1340
    },
    {
      "epoch": 0.1143002286004572,
      "grad_norm": 0.7986853122711182,
      "learning_rate": 2e-05,
      "loss": 0.67,
      "step": 1350
    },
    {
      "epoch": 0.11514689696046058,
      "grad_norm": 0.4286498427391052,
      "learning_rate": 2e-05,
      "loss": 0.6441,
      "step": 1360
    },
    {
      "epoch": 0.11599356532046397,
      "grad_norm": 0.4120442271232605,
      "learning_rate": 2e-05,
      "loss": 0.6506,
      "step": 1370
    },
    {
      "epoch": 0.11684023368046736,
      "grad_norm": 0.43085169792175293,
      "learning_rate": 2e-05,
      "loss": 0.6505,
      "step": 1380
    },
    {
      "epoch": 0.11768690204047075,
      "grad_norm": 0.4295996129512787,
      "learning_rate": 2e-05,
      "loss": 0.6562,
      "step": 1390
    },
    {
      "epoch": 0.11853357040047413,
      "grad_norm": 0.43393197655677795,
      "learning_rate": 2e-05,
      "loss": 0.6433,
      "step": 1400
    },
    {
      "epoch": 0.11938023876047753,
      "grad_norm": 0.41177472472190857,
      "learning_rate": 2e-05,
      "loss": 0.6619,
      "step": 1410
    },
    {
      "epoch": 0.12022690712048091,
      "grad_norm": 0.4898812174797058,
      "learning_rate": 2e-05,
      "loss": 0.6394,
      "step": 1420
    },
    {
      "epoch": 0.1210735754804843,
      "grad_norm": 0.4619840085506439,
      "learning_rate": 2e-05,
      "loss": 0.6438,
      "step": 1430
    },
    {
      "epoch": 0.12192024384048768,
      "grad_norm": 0.5120882987976074,
      "learning_rate": 2e-05,
      "loss": 0.6645,
      "step": 1440
    },
    {
      "epoch": 0.12276691220049107,
      "grad_norm": 0.4201647937297821,
      "learning_rate": 2e-05,
      "loss": 0.6625,
      "step": 1450
    },
    {
      "epoch": 0.12361358056049446,
      "grad_norm": 0.4196993112564087,
      "learning_rate": 2e-05,
      "loss": 0.6477,
      "step": 1460
    },
    {
      "epoch": 0.12446024892049784,
      "grad_norm": 0.4666191637516022,
      "learning_rate": 2e-05,
      "loss": 0.6605,
      "step": 1470
    },
    {
      "epoch": 0.12530691728050122,
      "grad_norm": 0.42628341913223267,
      "learning_rate": 2e-05,
      "loss": 0.6635,
      "step": 1480
    },
    {
      "epoch": 0.1261535856405046,
      "grad_norm": 0.46635255217552185,
      "learning_rate": 2e-05,
      "loss": 0.6519,
      "step": 1490
    },
    {
      "epoch": 0.127000254000508,
      "grad_norm": 0.39531210064888,
      "learning_rate": 2e-05,
      "loss": 0.6597,
      "step": 1500
    },
    {
      "epoch": 0.1278469223605114,
      "grad_norm": 0.416293740272522,
      "learning_rate": 2e-05,
      "loss": 0.6476,
      "step": 1510
    },
    {
      "epoch": 0.12869359072051478,
      "grad_norm": 0.4376610815525055,
      "learning_rate": 2e-05,
      "loss": 0.6471,
      "step": 1520
    },
    {
      "epoch": 0.12954025908051817,
      "grad_norm": 0.9239709377288818,
      "learning_rate": 2e-05,
      "loss": 0.6483,
      "step": 1530
    },
    {
      "epoch": 0.13038692744052155,
      "grad_norm": 0.44836151599884033,
      "learning_rate": 2e-05,
      "loss": 0.6476,
      "step": 1540
    },
    {
      "epoch": 0.13123359580052493,
      "grad_norm": 0.40565115213394165,
      "learning_rate": 2e-05,
      "loss": 0.6477,
      "step": 1550
    },
    {
      "epoch": 0.13208026416052832,
      "grad_norm": 0.4043814241886139,
      "learning_rate": 2e-05,
      "loss": 0.6422,
      "step": 1560
    },
    {
      "epoch": 0.1329269325205317,
      "grad_norm": 0.48815831542015076,
      "learning_rate": 2e-05,
      "loss": 0.667,
      "step": 1570
    },
    {
      "epoch": 0.13377360088053508,
      "grad_norm": 0.4149971902370453,
      "learning_rate": 2e-05,
      "loss": 0.6428,
      "step": 1580
    },
    {
      "epoch": 0.1346202692405385,
      "grad_norm": 0.43481072783470154,
      "learning_rate": 2e-05,
      "loss": 0.6297,
      "step": 1590
    },
    {
      "epoch": 0.13546693760054188,
      "grad_norm": 0.5290552377700806,
      "learning_rate": 2e-05,
      "loss": 0.6571,
      "step": 1600
    },
    {
      "epoch": 0.13631360596054526,
      "grad_norm": 0.48005440831184387,
      "learning_rate": 2e-05,
      "loss": 0.6375,
      "step": 1610
    },
    {
      "epoch": 0.13716027432054864,
      "grad_norm": 0.41244378685951233,
      "learning_rate": 2e-05,
      "loss": 0.6465,
      "step": 1620
    },
    {
      "epoch": 0.13800694268055202,
      "grad_norm": 0.4275606572628021,
      "learning_rate": 2e-05,
      "loss": 0.6496,
      "step": 1630
    },
    {
      "epoch": 0.1388536110405554,
      "grad_norm": 0.40932148694992065,
      "learning_rate": 2e-05,
      "loss": 0.6617,
      "step": 1640
    },
    {
      "epoch": 0.1397002794005588,
      "grad_norm": 0.46909376978874207,
      "learning_rate": 2e-05,
      "loss": 0.654,
      "step": 1650
    },
    {
      "epoch": 0.14054694776056217,
      "grad_norm": 0.40658414363861084,
      "learning_rate": 2e-05,
      "loss": 0.6148,
      "step": 1660
    },
    {
      "epoch": 0.14139361612056559,
      "grad_norm": 0.45841172337532043,
      "learning_rate": 2e-05,
      "loss": 0.6511,
      "step": 1670
    },
    {
      "epoch": 0.14224028448056897,
      "grad_norm": 0.4471743702888489,
      "learning_rate": 2e-05,
      "loss": 0.6448,
      "step": 1680
    },
    {
      "epoch": 0.14308695284057235,
      "grad_norm": 0.43427541851997375,
      "learning_rate": 2e-05,
      "loss": 0.6435,
      "step": 1690
    },
    {
      "epoch": 0.14393362120057573,
      "grad_norm": 0.4472843408584595,
      "learning_rate": 2e-05,
      "loss": 0.6357,
      "step": 1700
    },
    {
      "epoch": 0.14478028956057912,
      "grad_norm": 0.42029255628585815,
      "learning_rate": 2e-05,
      "loss": 0.6575,
      "step": 1710
    },
    {
      "epoch": 0.1456269579205825,
      "grad_norm": 0.4621073603630066,
      "learning_rate": 2e-05,
      "loss": 0.6361,
      "step": 1720
    },
    {
      "epoch": 0.14647362628058588,
      "grad_norm": 0.4484656751155853,
      "learning_rate": 2e-05,
      "loss": 0.6355,
      "step": 1730
    },
    {
      "epoch": 0.1473202946405893,
      "grad_norm": 0.4217395782470703,
      "learning_rate": 2e-05,
      "loss": 0.6682,
      "step": 1740
    },
    {
      "epoch": 0.14816696300059268,
      "grad_norm": 0.42961055040359497,
      "learning_rate": 2e-05,
      "loss": 0.645,
      "step": 1750
    },
    {
      "epoch": 0.14901363136059606,
      "grad_norm": 0.46678170561790466,
      "learning_rate": 2e-05,
      "loss": 0.6401,
      "step": 1760
    },
    {
      "epoch": 0.14986029972059944,
      "grad_norm": 0.5399910807609558,
      "learning_rate": 2e-05,
      "loss": 0.6507,
      "step": 1770
    },
    {
      "epoch": 0.15070696808060283,
      "grad_norm": 0.47768858075141907,
      "learning_rate": 2e-05,
      "loss": 0.6342,
      "step": 1780
    },
    {
      "epoch": 0.1515536364406062,
      "grad_norm": 0.44225838780403137,
      "learning_rate": 2e-05,
      "loss": 0.6567,
      "step": 1790
    },
    {
      "epoch": 0.1524003048006096,
      "grad_norm": 0.4229118227958679,
      "learning_rate": 2e-05,
      "loss": 0.6597,
      "step": 1800
    },
    {
      "epoch": 0.15324697316061298,
      "grad_norm": 1.9519200325012207,
      "learning_rate": 2e-05,
      "loss": 0.6483,
      "step": 1810
    },
    {
      "epoch": 0.1540936415206164,
      "grad_norm": 0.5570772290229797,
      "learning_rate": 2e-05,
      "loss": 0.646,
      "step": 1820
    },
    {
      "epoch": 0.15494030988061977,
      "grad_norm": 0.42859718203544617,
      "learning_rate": 2e-05,
      "loss": 0.6163,
      "step": 1830
    },
    {
      "epoch": 0.15578697824062315,
      "grad_norm": 0.4103221297264099,
      "learning_rate": 2e-05,
      "loss": 0.6527,
      "step": 1840
    },
    {
      "epoch": 0.15663364660062654,
      "grad_norm": 0.4725561738014221,
      "learning_rate": 2e-05,
      "loss": 0.6624,
      "step": 1850
    },
    {
      "epoch": 0.15748031496062992,
      "grad_norm": 0.43084171414375305,
      "learning_rate": 2e-05,
      "loss": 0.6424,
      "step": 1860
    },
    {
      "epoch": 0.1583269833206333,
      "grad_norm": 0.4549056887626648,
      "learning_rate": 2e-05,
      "loss": 0.6319,
      "step": 1870
    },
    {
      "epoch": 0.15917365168063669,
      "grad_norm": 0.43331679701805115,
      "learning_rate": 2e-05,
      "loss": 0.6443,
      "step": 1880
    },
    {
      "epoch": 0.16002032004064007,
      "grad_norm": 0.4841455817222595,
      "learning_rate": 2e-05,
      "loss": 0.6349,
      "step": 1890
    },
    {
      "epoch": 0.16086698840064348,
      "grad_norm": 0.4443437159061432,
      "learning_rate": 2e-05,
      "loss": 0.6631,
      "step": 1900
    },
    {
      "epoch": 0.16171365676064686,
      "grad_norm": 0.44019854068756104,
      "learning_rate": 2e-05,
      "loss": 0.6318,
      "step": 1910
    },
    {
      "epoch": 0.16256032512065025,
      "grad_norm": 0.45389479398727417,
      "learning_rate": 2e-05,
      "loss": 0.6717,
      "step": 1920
    },
    {
      "epoch": 0.16340699348065363,
      "grad_norm": 0.4448392689228058,
      "learning_rate": 2e-05,
      "loss": 0.6636,
      "step": 1930
    },
    {
      "epoch": 0.164253661840657,
      "grad_norm": 0.48700398206710815,
      "learning_rate": 2e-05,
      "loss": 0.6337,
      "step": 1940
    },
    {
      "epoch": 0.1651003302006604,
      "grad_norm": 0.42143478989601135,
      "learning_rate": 2e-05,
      "loss": 0.6544,
      "step": 1950
    },
    {
      "epoch": 0.16594699856066378,
      "grad_norm": 0.4352879524230957,
      "learning_rate": 2e-05,
      "loss": 0.6514,
      "step": 1960
    },
    {
      "epoch": 0.1667936669206672,
      "grad_norm": 0.414305716753006,
      "learning_rate": 2e-05,
      "loss": 0.6481,
      "step": 1970
    },
    {
      "epoch": 0.16764033528067057,
      "grad_norm": 0.39161503314971924,
      "learning_rate": 2e-05,
      "loss": 0.6566,
      "step": 1980
    },
    {
      "epoch": 0.16848700364067395,
      "grad_norm": 0.421457976102829,
      "learning_rate": 2e-05,
      "loss": 0.6449,
      "step": 1990
    },
    {
      "epoch": 0.16933367200067734,
      "grad_norm": 0.448140949010849,
      "learning_rate": 2e-05,
      "loss": 0.6477,
      "step": 2000
    },
    {
      "epoch": 0.17018034036068072,
      "grad_norm": 0.4220173954963684,
      "learning_rate": 2e-05,
      "loss": 0.6366,
      "step": 2010
    },
    {
      "epoch": 0.1710270087206841,
      "grad_norm": 0.3872855603694916,
      "learning_rate": 2e-05,
      "loss": 0.6646,
      "step": 2020
    },
    {
      "epoch": 0.1718736770806875,
      "grad_norm": 0.5094623565673828,
      "learning_rate": 2e-05,
      "loss": 0.6433,
      "step": 2030
    },
    {
      "epoch": 0.17272034544069087,
      "grad_norm": 0.43138524889945984,
      "learning_rate": 2e-05,
      "loss": 0.6399,
      "step": 2040
    },
    {
      "epoch": 0.17356701380069428,
      "grad_norm": 0.4579676687717438,
      "learning_rate": 2e-05,
      "loss": 0.643,
      "step": 2050
    },
    {
      "epoch": 0.17441368216069766,
      "grad_norm": 1.0642181634902954,
      "learning_rate": 2e-05,
      "loss": 0.6466,
      "step": 2060
    },
    {
      "epoch": 0.17526035052070105,
      "grad_norm": 0.4300776422023773,
      "learning_rate": 2e-05,
      "loss": 0.6264,
      "step": 2070
    },
    {
      "epoch": 0.17610701888070443,
      "grad_norm": 0.43561115860939026,
      "learning_rate": 2e-05,
      "loss": 0.6274,
      "step": 2080
    },
    {
      "epoch": 0.1769536872407078,
      "grad_norm": 0.4419814348220825,
      "learning_rate": 2e-05,
      "loss": 0.6189,
      "step": 2090
    },
    {
      "epoch": 0.1778003556007112,
      "grad_norm": 0.40943095088005066,
      "learning_rate": 2e-05,
      "loss": 0.6575,
      "step": 2100
    },
    {
      "epoch": 0.17864702396071458,
      "grad_norm": 0.4220316708087921,
      "learning_rate": 2e-05,
      "loss": 0.6321,
      "step": 2110
    },
    {
      "epoch": 0.17949369232071796,
      "grad_norm": 0.4069748818874359,
      "learning_rate": 2e-05,
      "loss": 0.6249,
      "step": 2120
    },
    {
      "epoch": 0.18034036068072137,
      "grad_norm": 0.4093238115310669,
      "learning_rate": 2e-05,
      "loss": 0.6367,
      "step": 2130
    },
    {
      "epoch": 0.18118702904072476,
      "grad_norm": 0.42871996760368347,
      "learning_rate": 2e-05,
      "loss": 0.6319,
      "step": 2140
    },
    {
      "epoch": 0.18203369740072814,
      "grad_norm": 0.4586758613586426,
      "learning_rate": 2e-05,
      "loss": 0.6043,
      "step": 2150
    },
    {
      "epoch": 0.18288036576073152,
      "grad_norm": 0.43323299288749695,
      "learning_rate": 2e-05,
      "loss": 0.6518,
      "step": 2160
    },
    {
      "epoch": 0.1837270341207349,
      "grad_norm": 0.4545518159866333,
      "learning_rate": 2e-05,
      "loss": 0.6365,
      "step": 2170
    },
    {
      "epoch": 0.1845737024807383,
      "grad_norm": 0.4953419268131256,
      "learning_rate": 2e-05,
      "loss": 0.6426,
      "step": 2180
    },
    {
      "epoch": 0.18542037084074167,
      "grad_norm": 0.4099434018135071,
      "learning_rate": 2e-05,
      "loss": 0.6429,
      "step": 2190
    },
    {
      "epoch": 0.18626703920074505,
      "grad_norm": 0.4271218180656433,
      "learning_rate": 2e-05,
      "loss": 0.6341,
      "step": 2200
    },
    {
      "epoch": 0.18711370756074847,
      "grad_norm": 0.44617754220962524,
      "learning_rate": 2e-05,
      "loss": 0.6261,
      "step": 2210
    },
    {
      "epoch": 0.18796037592075185,
      "grad_norm": 0.4889068901538849,
      "learning_rate": 2e-05,
      "loss": 0.6611,
      "step": 2220
    },
    {
      "epoch": 0.18880704428075523,
      "grad_norm": 0.41321495175361633,
      "learning_rate": 2e-05,
      "loss": 0.645,
      "step": 2230
    },
    {
      "epoch": 0.18965371264075861,
      "grad_norm": 0.3996637463569641,
      "learning_rate": 2e-05,
      "loss": 0.6471,
      "step": 2240
    },
    {
      "epoch": 0.190500381000762,
      "grad_norm": 0.43380239605903625,
      "learning_rate": 2e-05,
      "loss": 0.6328,
      "step": 2250
    },
    {
      "epoch": 0.19134704936076538,
      "grad_norm": 0.43314844369888306,
      "learning_rate": 2e-05,
      "loss": 0.6528,
      "step": 2260
    },
    {
      "epoch": 0.19219371772076876,
      "grad_norm": 0.396233469247818,
      "learning_rate": 2e-05,
      "loss": 0.6331,
      "step": 2270
    },
    {
      "epoch": 0.19304038608077217,
      "grad_norm": 0.42943382263183594,
      "learning_rate": 2e-05,
      "loss": 0.6604,
      "step": 2280
    },
    {
      "epoch": 0.19388705444077556,
      "grad_norm": 0.5218196511268616,
      "learning_rate": 2e-05,
      "loss": 0.6573,
      "step": 2290
    },
    {
      "epoch": 0.19473372280077894,
      "grad_norm": 0.4184105396270752,
      "learning_rate": 2e-05,
      "loss": 0.6361,
      "step": 2300
    },
    {
      "epoch": 0.19558039116078232,
      "grad_norm": 0.5651347041130066,
      "learning_rate": 2e-05,
      "loss": 0.636,
      "step": 2310
    },
    {
      "epoch": 0.1964270595207857,
      "grad_norm": 0.42529258131980896,
      "learning_rate": 2e-05,
      "loss": 0.6444,
      "step": 2320
    },
    {
      "epoch": 0.1972737278807891,
      "grad_norm": 0.44605952501296997,
      "learning_rate": 2e-05,
      "loss": 0.6382,
      "step": 2330
    },
    {
      "epoch": 0.19812039624079247,
      "grad_norm": 0.4468037188053131,
      "learning_rate": 2e-05,
      "loss": 0.6302,
      "step": 2340
    },
    {
      "epoch": 0.19896706460079586,
      "grad_norm": 0.3863542973995209,
      "learning_rate": 2e-05,
      "loss": 0.6215,
      "step": 2350
    },
    {
      "epoch": 0.19981373296079927,
      "grad_norm": 0.4320015013217926,
      "learning_rate": 2e-05,
      "loss": 0.6421,
      "step": 2360
    },
    {
      "epoch": 0.20066040132080265,
      "grad_norm": 0.43013012409210205,
      "learning_rate": 2e-05,
      "loss": 0.6474,
      "step": 2370
    },
    {
      "epoch": 0.20150706968080603,
      "grad_norm": 0.3912484049797058,
      "learning_rate": 2e-05,
      "loss": 0.6179,
      "step": 2380
    },
    {
      "epoch": 0.20235373804080942,
      "grad_norm": 0.39495962858200073,
      "learning_rate": 2e-05,
      "loss": 0.6356,
      "step": 2390
    },
    {
      "epoch": 0.2032004064008128,
      "grad_norm": 0.384694367647171,
      "learning_rate": 2e-05,
      "loss": 0.6634,
      "step": 2400
    },
    {
      "epoch": 0.20404707476081618,
      "grad_norm": 0.6632846593856812,
      "learning_rate": 2e-05,
      "loss": 0.6283,
      "step": 2410
    },
    {
      "epoch": 0.20489374312081957,
      "grad_norm": 0.4242749512195587,
      "learning_rate": 2e-05,
      "loss": 0.6316,
      "step": 2420
    },
    {
      "epoch": 0.20574041148082295,
      "grad_norm": 0.41551467776298523,
      "learning_rate": 2e-05,
      "loss": 0.6519,
      "step": 2430
    },
    {
      "epoch": 0.20658707984082636,
      "grad_norm": 0.3853192925453186,
      "learning_rate": 2e-05,
      "loss": 0.6487,
      "step": 2440
    },
    {
      "epoch": 0.20743374820082974,
      "grad_norm": 0.4175145626068115,
      "learning_rate": 2e-05,
      "loss": 0.6397,
      "step": 2450
    },
    {
      "epoch": 0.20828041656083313,
      "grad_norm": 0.41761279106140137,
      "learning_rate": 2e-05,
      "loss": 0.656,
      "step": 2460
    },
    {
      "epoch": 0.2091270849208365,
      "grad_norm": 0.39868006110191345,
      "learning_rate": 2e-05,
      "loss": 0.6412,
      "step": 2470
    },
    {
      "epoch": 0.2099737532808399,
      "grad_norm": 0.3972877264022827,
      "learning_rate": 2e-05,
      "loss": 0.6403,
      "step": 2480
    },
    {
      "epoch": 0.21082042164084328,
      "grad_norm": 0.3830007314682007,
      "learning_rate": 2e-05,
      "loss": 0.6371,
      "step": 2490
    },
    {
      "epoch": 0.21166709000084666,
      "grad_norm": 0.4232046604156494,
      "learning_rate": 2e-05,
      "loss": 0.6531,
      "step": 2500
    },
    {
      "epoch": 0.21251375836085004,
      "grad_norm": 0.3900882303714752,
      "learning_rate": 2e-05,
      "loss": 0.6222,
      "step": 2510
    },
    {
      "epoch": 0.21336042672085345,
      "grad_norm": 0.39245057106018066,
      "learning_rate": 2e-05,
      "loss": 0.6153,
      "step": 2520
    },
    {
      "epoch": 0.21420709508085684,
      "grad_norm": 0.43386736512184143,
      "learning_rate": 2e-05,
      "loss": 0.6382,
      "step": 2530
    },
    {
      "epoch": 0.21505376344086022,
      "grad_norm": 0.3844192326068878,
      "learning_rate": 2e-05,
      "loss": 0.6534,
      "step": 2540
    },
    {
      "epoch": 0.2159004318008636,
      "grad_norm": 0.4117423892021179,
      "learning_rate": 1.997261400182901e-05,
      "loss": 0.6465,
      "step": 2550
    },
    {
      "epoch": 0.21674710016086698,
      "grad_norm": 0.44179949164390564,
      "learning_rate": 1.9805800746810423e-05,
      "loss": 0.6386,
      "step": 2560
    },
    {
      "epoch": 0.21759376852087037,
      "grad_norm": 0.41474664211273193,
      "learning_rate": 1.9489934220110274e-05,
      "loss": 0.6555,
      "step": 2570
    },
    {
      "epoch": 0.21844043688087375,
      "grad_norm": 0.3735704720020294,
      "learning_rate": 1.9029840364820392e-05,
      "loss": 0.6356,
      "step": 2580
    },
    {
      "epoch": 0.21928710524087716,
      "grad_norm": 0.421866774559021,
      "learning_rate": 1.8432548690479908e-05,
      "loss": 0.6545,
      "step": 2590
    },
    {
      "epoch": 0.22013377360088054,
      "grad_norm": 0.40879929065704346,
      "learning_rate": 1.7707184873239772e-05,
      "loss": 0.6547,
      "step": 2600
    },
    {
      "epoch": 0.22098044196088393,
      "grad_norm": 0.376902312040329,
      "learning_rate": 1.6864831329902565e-05,
      "loss": 0.6576,
      "step": 2610
    },
    {
      "epoch": 0.2218271103208873,
      "grad_norm": 0.39529693126678467,
      "learning_rate": 1.591835789604667e-05,
      "loss": 0.617,
      "step": 2620
    },
    {
      "epoch": 0.2226737786808907,
      "grad_norm": 1.598371148109436,
      "learning_rate": 1.4882225195206459e-05,
      "loss": 0.6398,
      "step": 2630
    },
    {
      "epoch": 0.22352044704089408,
      "grad_norm": 0.4078064262866974,
      "learning_rate": 1.3772263703317695e-05,
      "loss": 0.6267,
      "step": 2640
    },
    {
      "epoch": 0.22436711540089746,
      "grad_norm": 0.4152591824531555,
      "learning_rate": 1.2605431883975547e-05,
      "loss": 0.6346,
      "step": 2650
    },
    {
      "epoch": 0.22521378376090084,
      "grad_norm": 0.40525496006011963,
      "learning_rate": 1.1399557089817574e-05,
      "loss": 0.6317,
      "step": 2660
    },
    {
      "epoch": 0.22606045212090425,
      "grad_norm": 0.40020552277565,
      "learning_rate": 1.0173063188650463e-05,
      "loss": 0.6524,
      "step": 2670
    },
    {
      "epoch": 0.22690712048090764,
      "grad_norm": 0.4070807099342346,
      "learning_rate": 8.944689075764396e-06,
      "loss": 0.646,
      "step": 2680
    },
    {
      "epoch": 0.22775378884091102,
      "grad_norm": 0.41979649662971497,
      "learning_rate": 7.73320237312362e-06,
      "loss": 0.6344,
      "step": 2690
    },
    {
      "epoch": 0.2286004572009144,
      "grad_norm": 0.41402050852775574,
      "learning_rate": 6.557112689658629e-06,
      "loss": 0.6281,
      "step": 2700
    },
    {
      "epoch": 0.2294471255609178,
      "grad_norm": 0.40832775831222534,
      "learning_rate": 5.434388823591213e-06,
      "loss": 0.6166,
      "step": 2710
    },
    {
      "epoch": 0.23029379392092117,
      "grad_norm": 0.38844034075737,
      "learning_rate": 4.382184227495424e-06,
      "loss": 0.6368,
      "step": 2720
    },
    {
      "epoch": 0.23114046228092455,
      "grad_norm": 0.43598899245262146,
      "learning_rate": 3.4165749305560203e-06,
      "loss": 0.6601,
      "step": 2730
    },
    {
      "epoch": 0.23198713064092794,
      "grad_norm": 0.41606220602989197,
      "learning_rate": 2.5523139221595556e-06,
      "loss": 0.6397,
      "step": 2740
    },
    {
      "epoch": 0.23283379900093135,
      "grad_norm": 0.3936404287815094,
      "learning_rate": 1.8026057494499821e-06,
      "loss": 0.6307,
      "step": 2750
    },
    {
      "epoch": 0.23368046736093473,
      "grad_norm": 0.37929078936576843,
      "learning_rate": 1.178904772643223e-06,
      "loss": 0.6326,
      "step": 2760
    },
    {
      "epoch": 0.2345271357209381,
      "grad_norm": 0.37881144881248474,
      "learning_rate": 6.90740160441754e-07,
      "loss": 0.6307,
      "step": 2770
    },
    {
      "epoch": 0.2353738040809415,
      "grad_norm": 0.5167031288146973,
      "learning_rate": 3.45570299343632e-07,
      "loss": 0.6378,
      "step": 2780
    },
    {
      "epoch": 0.23622047244094488,
      "grad_norm": 0.38428762555122375,
      "learning_rate": 1.486688412425152e-07,
      "loss": 0.6091,
      "step": 2790
    },
    {
      "epoch": 0.23681314029294726,
      "step": 2797,
      "total_flos": 1.2485883762455871e+19,
      "train_loss": 0.05799589150285227,
      "train_runtime": 2855.8168,
      "train_samples_per_second": 11.753,
      "train_steps_per_second": 0.979
    }
  ],
  "logging_steps": 10,
  "max_steps": 2797,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2543,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2485883762455871e+19,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}