{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 23.272232304900182,
  "eval_steps": 100,
  "global_step": 1600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.14519056261343014,
      "grad_norm": 20.98495864868164,
      "learning_rate": 5.882352941176471e-07,
      "loss": 9.4496,
      "step": 10
    },
    {
      "epoch": 0.29038112522686027,
      "grad_norm": 16.1613712310791,
      "learning_rate": 1.1764705882352942e-06,
      "loss": 8.8125,
      "step": 20
    },
    {
      "epoch": 0.4355716878402904,
      "grad_norm": 6.7023138999938965,
      "learning_rate": 1.7647058823529414e-06,
      "loss": 7.7501,
      "step": 30
    },
    {
      "epoch": 0.5807622504537205,
      "grad_norm": 4.253345489501953,
      "learning_rate": 2.3529411764705885e-06,
      "loss": 7.0378,
      "step": 40
    },
    {
      "epoch": 0.7259528130671506,
      "grad_norm": 2.4256012439727783,
      "learning_rate": 2.9411764705882355e-06,
      "loss": 6.6558,
      "step": 50
    },
    {
      "epoch": 0.8711433756805808,
      "grad_norm": 1.664031982421875,
      "learning_rate": 3.529411764705883e-06,
      "loss": 6.3545,
      "step": 60
    },
    {
      "epoch": 1.0181488203266789,
      "grad_norm": 1.206116795539856,
      "learning_rate": 4.11764705882353e-06,
      "loss": 6.2306,
      "step": 70
    },
    {
      "epoch": 1.1633393829401089,
      "grad_norm": 1.1027638912200928,
      "learning_rate": 4.705882352941177e-06,
      "loss": 5.8555,
      "step": 80
    },
    {
      "epoch": 1.308529945553539,
      "grad_norm": 1.2014143466949463,
      "learning_rate": 5.294117647058824e-06,
      "loss": 5.6277,
      "step": 90
    },
    {
      "epoch": 1.453720508166969,
      "grad_norm": 1.3407199382781982,
      "learning_rate": 5.882352941176471e-06,
      "loss": 5.4611,
      "step": 100
    },
    {
      "epoch": 1.453720508166969,
      "eval_loss": 5.380606174468994,
      "eval_runtime": 14.5497,
      "eval_samples_per_second": 195.88,
      "eval_steps_per_second": 6.186,
      "step": 100
    },
    {
      "epoch": 1.5989110707803993,
      "grad_norm": 1.6456304788589478,
      "learning_rate": 6.470588235294119e-06,
      "loss": 5.3117,
      "step": 110
    },
    {
      "epoch": 1.7441016333938295,
      "grad_norm": 2.4888839721679688,
      "learning_rate": 7.058823529411766e-06,
      "loss": 5.1868,
      "step": 120
    },
    {
      "epoch": 1.8892921960072595,
      "grad_norm": 2.137110471725464,
      "learning_rate": 7.647058823529411e-06,
      "loss": 5.0505,
      "step": 130
    },
    {
      "epoch": 2.0362976406533577,
      "grad_norm": 2.2031850814819336,
      "learning_rate": 8.23529411764706e-06,
      "loss": 5.0571,
      "step": 140
    },
    {
      "epoch": 2.1814882032667877,
      "grad_norm": 2.2017667293548584,
      "learning_rate": 8.823529411764707e-06,
      "loss": 4.8034,
      "step": 150
    },
    {
      "epoch": 2.3266787658802177,
      "grad_norm": 2.2998626232147217,
      "learning_rate": 9.411764705882354e-06,
      "loss": 4.6938,
      "step": 160
    },
    {
      "epoch": 2.471869328493648,
      "grad_norm": 2.088256359100342,
      "learning_rate": 1e-05,
      "loss": 4.5817,
      "step": 170
    },
    {
      "epoch": 2.617059891107078,
      "grad_norm": 2.1210474967956543,
      "learning_rate": 1.0588235294117648e-05,
      "loss": 4.4561,
      "step": 180
    },
    {
      "epoch": 2.762250453720508,
      "grad_norm": 2.330993175506592,
      "learning_rate": 1.1176470588235295e-05,
      "loss": 4.368,
      "step": 190
    },
    {
      "epoch": 2.907441016333938,
      "grad_norm": 2.2989509105682373,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 4.268,
      "step": 200
    },
    {
      "epoch": 2.907441016333938,
      "eval_loss": 4.2127814292907715,
      "eval_runtime": 14.464,
      "eval_samples_per_second": 197.041,
      "eval_steps_per_second": 6.222,
      "step": 200
    },
    {
      "epoch": 3.0544464609800364,
      "grad_norm": 1.6547863483428955,
      "learning_rate": 1.235294117647059e-05,
      "loss": 4.2584,
      "step": 210
    },
    {
      "epoch": 3.1996370235934664,
      "grad_norm": 2.2462234497070312,
      "learning_rate": 1.2941176470588238e-05,
      "loss": 4.0844,
      "step": 220
    },
    {
      "epoch": 3.344827586206897,
      "grad_norm": 2.176753044128418,
      "learning_rate": 1.3529411764705885e-05,
      "loss": 3.9943,
      "step": 230
    },
    {
      "epoch": 3.490018148820327,
      "grad_norm": 2.2812905311584473,
      "learning_rate": 1.4117647058823532e-05,
      "loss": 3.9237,
      "step": 240
    },
    {
      "epoch": 3.635208711433757,
      "grad_norm": 2.2799627780914307,
      "learning_rate": 1.4705882352941179e-05,
      "loss": 3.849,
      "step": 250
    },
    {
      "epoch": 3.780399274047187,
      "grad_norm": 2.3910913467407227,
      "learning_rate": 1.5294117647058822e-05,
      "loss": 3.7829,
      "step": 260
    },
    {
      "epoch": 3.925589836660617,
      "grad_norm": 2.793339490890503,
      "learning_rate": 1.5882352941176473e-05,
      "loss": 3.7159,
      "step": 270
    },
    {
      "epoch": 4.072595281306715,
      "grad_norm": 4.1607465744018555,
      "learning_rate": 1.647058823529412e-05,
      "loss": 3.7605,
      "step": 280
    },
    {
      "epoch": 4.217785843920145,
      "grad_norm": 2.6675713062286377,
      "learning_rate": 1.7058823529411767e-05,
      "loss": 3.6045,
      "step": 290
    },
    {
      "epoch": 4.362976406533575,
      "grad_norm": 3.1864140033721924,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 3.5499,
      "step": 300
    },
    {
      "epoch": 4.362976406533575,
      "eval_loss": 3.5333378314971924,
      "eval_runtime": 14.5283,
      "eval_samples_per_second": 196.168,
      "eval_steps_per_second": 6.195,
      "step": 300
    },
    {
      "epoch": 4.508166969147005,
      "grad_norm": 3.361107110977173,
      "learning_rate": 1.823529411764706e-05,
      "loss": 3.4898,
      "step": 310
    },
    {
      "epoch": 4.653357531760435,
      "grad_norm": 3.826258897781372,
      "learning_rate": 1.8823529411764708e-05,
      "loss": 3.4595,
      "step": 320
    },
    {
      "epoch": 4.798548094373865,
      "grad_norm": 3.7704880237579346,
      "learning_rate": 1.9411764705882355e-05,
      "loss": 3.4113,
      "step": 330
    },
    {
      "epoch": 4.943738656987296,
      "grad_norm": 3.5223851203918457,
      "learning_rate": 2e-05,
      "loss": 3.3734,
      "step": 340
    },
    {
      "epoch": 5.090744101633394,
      "grad_norm": 3.332577705383301,
      "learning_rate": 1.9999472984871734e-05,
      "loss": 3.4133,
      "step": 350
    },
    {
      "epoch": 5.235934664246824,
      "grad_norm": 4.306556701660156,
      "learning_rate": 1.9997891995035914e-05,
      "loss": 3.2955,
      "step": 360
    },
    {
      "epoch": 5.381125226860254,
      "grad_norm": 4.148169040679932,
      "learning_rate": 1.999525719713366e-05,
      "loss": 3.2456,
      "step": 370
    },
    {
      "epoch": 5.526315789473684,
      "grad_norm": 4.137167930603027,
      "learning_rate": 1.999156886888064e-05,
      "loss": 3.2064,
      "step": 380
    },
    {
      "epoch": 5.671506352087114,
      "grad_norm": 3.123608350753784,
      "learning_rate": 1.998682739903781e-05,
      "loss": 3.1841,
      "step": 390
    },
    {
      "epoch": 5.816696914700545,
      "grad_norm": 4.209367752075195,
      "learning_rate": 1.9981033287370443e-05,
      "loss": 3.1453,
      "step": 400
    },
    {
      "epoch": 5.816696914700545,
      "eval_loss": 3.1412713527679443,
      "eval_runtime": 14.4671,
      "eval_samples_per_second": 196.998,
      "eval_steps_per_second": 6.221,
      "step": 400
    },
    {
      "epoch": 5.961887477313975,
      "grad_norm": 3.708157539367676,
      "learning_rate": 1.9974187144595433e-05,
      "loss": 3.1183,
      "step": 410
    },
    {
      "epoch": 6.108892921960073,
      "grad_norm": 6.567568778991699,
      "learning_rate": 1.9966289692316944e-05,
      "loss": 3.166,
      "step": 420
    },
    {
      "epoch": 6.254083484573503,
      "grad_norm": 4.073953151702881,
      "learning_rate": 1.9957341762950346e-05,
      "loss": 3.0523,
      "step": 430
    },
    {
      "epoch": 6.399274047186933,
      "grad_norm": 4.078774452209473,
      "learning_rate": 1.9947344299634464e-05,
      "loss": 3.018,
      "step": 440
    },
    {
      "epoch": 6.544464609800363,
      "grad_norm": 2.7505741119384766,
      "learning_rate": 1.993629835613218e-05,
      "loss": 2.9874,
      "step": 450
    },
    {
      "epoch": 6.689655172413794,
      "grad_norm": 4.441661834716797,
      "learning_rate": 1.992420509671936e-05,
      "loss": 2.9679,
      "step": 460
    },
    {
      "epoch": 6.834845735027224,
      "grad_norm": 3.656827211380005,
      "learning_rate": 1.9911065796062137e-05,
      "loss": 2.9333,
      "step": 470
    },
    {
      "epoch": 6.980036297640654,
      "grad_norm": 3.519759178161621,
      "learning_rate": 1.9896881839082554e-05,
      "loss": 2.9003,
      "step": 480
    },
    {
      "epoch": 7.127041742286751,
      "grad_norm": 2.58138108253479,
      "learning_rate": 1.9881654720812594e-05,
      "loss": 2.9466,
      "step": 490
    },
    {
      "epoch": 7.272232304900181,
      "grad_norm": 3.1261541843414307,
      "learning_rate": 1.9865386046236597e-05,
      "loss": 2.865,
      "step": 500
    },
    {
      "epoch": 7.272232304900181,
      "eval_loss": 2.8578507900238037,
      "eval_runtime": 14.4738,
      "eval_samples_per_second": 196.908,
      "eval_steps_per_second": 6.218,
      "step": 500
    },
    {
      "epoch": 7.417422867513611,
      "grad_norm": 4.163350582122803,
      "learning_rate": 1.9848077530122083e-05,
      "loss": 2.8359,
      "step": 510
    },
    {
      "epoch": 7.562613430127042,
      "grad_norm": 2.9917635917663574,
      "learning_rate": 1.982973099683902e-05,
      "loss": 2.7953,
      "step": 520
    },
    {
      "epoch": 7.707803992740472,
      "grad_norm": 3.293595790863037,
      "learning_rate": 1.9810348380167527e-05,
      "loss": 2.7838,
      "step": 530
    },
    {
      "epoch": 7.852994555353902,
      "grad_norm": 3.7709453105926514,
      "learning_rate": 1.9789931723094046e-05,
      "loss": 2.7497,
      "step": 540
    },
    {
      "epoch": 7.998185117967332,
      "grad_norm": 3.3971333503723145,
      "learning_rate": 1.9768483177596008e-05,
      "loss": 2.8238,
      "step": 550
    },
    {
      "epoch": 8.14519056261343,
      "grad_norm": 4.206657886505127,
      "learning_rate": 1.9746005004415004e-05,
      "loss": 2.7141,
      "step": 560
    },
    {
      "epoch": 8.29038112522686,
      "grad_norm": 3.42154598236084,
      "learning_rate": 1.9722499572818496e-05,
      "loss": 2.7061,
      "step": 570
    },
    {
      "epoch": 8.43557168784029,
      "grad_norm": 2.6466500759124756,
      "learning_rate": 1.9697969360350098e-05,
      "loss": 2.6849,
      "step": 580
    },
    {
      "epoch": 8.58076225045372,
      "grad_norm": 3.4602091312408447,
      "learning_rate": 1.9672416952568416e-05,
      "loss": 2.6546,
      "step": 590
    },
    {
      "epoch": 8.72595281306715,
      "grad_norm": 2.882288694381714,
      "learning_rate": 1.9645845042774555e-05,
      "loss": 2.6592,
      "step": 600
    },
    {
      "epoch": 8.72595281306715,
      "eval_loss": 2.655930280685425,
      "eval_runtime": 14.4429,
      "eval_samples_per_second": 197.329,
      "eval_steps_per_second": 6.231,
      "step": 600
    },
    {
      "epoch": 8.87114337568058,
      "grad_norm": 2.86531662940979,
      "learning_rate": 1.961825643172819e-05,
      "loss": 2.6246,
      "step": 610
    },
    {
      "epoch": 9.01814882032668,
      "grad_norm": 2.0800743103027344,
      "learning_rate": 1.9589654027352412e-05,
      "loss": 2.6887,
      "step": 620
    },
    {
      "epoch": 9.163339382940109,
      "grad_norm": 2.1428987979888916,
      "learning_rate": 1.956004084442718e-05,
      "loss": 2.6034,
      "step": 630
    },
    {
      "epoch": 9.30852994555354,
      "grad_norm": 2.0337836742401123,
      "learning_rate": 1.9529420004271568e-05,
      "loss": 2.6018,
      "step": 640
    },
    {
      "epoch": 9.453720508166969,
      "grad_norm": 2.25555419921875,
      "learning_rate": 1.9497794734414782e-05,
      "loss": 2.5723,
      "step": 650
    },
    {
      "epoch": 9.5989110707804,
      "grad_norm": 2.281365156173706,
      "learning_rate": 1.9465168368255946e-05,
      "loss": 2.5639,
      "step": 660
    },
    {
      "epoch": 9.744101633393829,
      "grad_norm": 1.9673478603363037,
      "learning_rate": 1.9431544344712776e-05,
      "loss": 2.5486,
      "step": 670
    },
    {
      "epoch": 9.88929219600726,
      "grad_norm": 2.3862695693969727,
      "learning_rate": 1.9396926207859085e-05,
      "loss": 2.5319,
      "step": 680
    },
    {
      "epoch": 10.036297640653357,
      "grad_norm": 2.3560924530029297,
      "learning_rate": 1.936131760655124e-05,
      "loss": 2.5827,
      "step": 690
    },
    {
      "epoch": 10.181488203266788,
      "grad_norm": 3.1034605503082275,
      "learning_rate": 1.932472229404356e-05,
      "loss": 2.514,
      "step": 700
    },
    {
      "epoch": 10.181488203266788,
      "eval_loss": 2.5237531661987305,
      "eval_runtime": 14.6638,
      "eval_samples_per_second": 194.356,
      "eval_steps_per_second": 6.138,
      "step": 700
    },
    {
      "epoch": 10.326678765880217,
      "grad_norm": 2.507720470428467,
      "learning_rate": 1.9287144127592704e-05,
      "loss": 2.5069,
      "step": 710
    },
    {
      "epoch": 10.471869328493648,
      "grad_norm": 2.375530481338501,
      "learning_rate": 1.924858706805112e-05,
      "loss": 2.4914,
      "step": 720
    },
    {
      "epoch": 10.617059891107077,
      "grad_norm": 2.781869649887085,
      "learning_rate": 1.920905517944954e-05,
      "loss": 2.4731,
      "step": 730
    },
    {
      "epoch": 10.762250453720508,
      "grad_norm": 2.3014352321624756,
      "learning_rate": 1.9168552628568632e-05,
      "loss": 2.4679,
      "step": 740
    },
    {
      "epoch": 10.907441016333939,
      "grad_norm": 2.277211904525757,
      "learning_rate": 1.9127083684499805e-05,
      "loss": 2.4708,
      "step": 750
    },
    {
      "epoch": 11.054446460980037,
      "grad_norm": 2.731947660446167,
      "learning_rate": 1.9084652718195237e-05,
      "loss": 2.5219,
      "step": 760
    },
    {
      "epoch": 11.199637023593466,
      "grad_norm": 2.070516347885132,
      "learning_rate": 1.9041264202007158e-05,
      "loss": 2.4407,
      "step": 770
    },
    {
      "epoch": 11.344827586206897,
      "grad_norm": 2.526477098464966,
      "learning_rate": 1.8996922709216456e-05,
      "loss": 2.4408,
      "step": 780
    },
    {
      "epoch": 11.490018148820326,
      "grad_norm": 2.280230760574341,
      "learning_rate": 1.8951632913550625e-05,
      "loss": 2.4217,
      "step": 790
    },
    {
      "epoch": 11.635208711433757,
      "grad_norm": 2.5102462768554688,
      "learning_rate": 1.8905399588691165e-05,
      "loss": 2.4129,
      "step": 800
    },
    {
      "epoch": 11.635208711433757,
      "eval_loss": 2.4271934032440186,
      "eval_runtime": 14.4721,
      "eval_samples_per_second": 196.93,
      "eval_steps_per_second": 6.219,
      "step": 800
    },
    {
      "epoch": 11.780399274047188,
      "grad_norm": 2.3329319953918457,
      "learning_rate": 1.8858227607770398e-05,
      "loss": 2.4068,
      "step": 810
    },
    {
      "epoch": 11.925589836660617,
      "grad_norm": 2.9200258255004883,
      "learning_rate": 1.8810121942857848e-05,
      "loss": 2.393,
      "step": 820
    },
    {
      "epoch": 12.072595281306715,
      "grad_norm": 2.835029363632202,
      "learning_rate": 1.8761087664436137e-05,
      "loss": 2.4508,
      "step": 830
    },
    {
      "epoch": 12.217785843920145,
      "grad_norm": 2.7595760822296143,
      "learning_rate": 1.8711129940866577e-05,
      "loss": 2.3873,
      "step": 840
    },
    {
      "epoch": 12.362976406533575,
      "grad_norm": 2.940290689468384,
      "learning_rate": 1.866025403784439e-05,
      "loss": 2.3817,
      "step": 850
    },
    {
      "epoch": 12.508166969147005,
      "grad_norm": 2.936760902404785,
      "learning_rate": 1.860846531784368e-05,
      "loss": 2.3642,
      "step": 860
    },
    {
      "epoch": 12.653357531760436,
      "grad_norm": 3.160423994064331,
      "learning_rate": 1.8555769239552232e-05,
      "loss": 2.3586,
      "step": 870
    },
    {
      "epoch": 12.798548094373865,
      "grad_norm": 2.8737099170684814,
      "learning_rate": 1.8502171357296144e-05,
      "loss": 2.3481,
      "step": 880
    },
    {
      "epoch": 12.943738656987296,
      "grad_norm": 2.706122398376465,
      "learning_rate": 1.8447677320454367e-05,
      "loss": 2.3496,
      "step": 890
    },
    {
      "epoch": 13.090744101633394,
      "grad_norm": 2.1658377647399902,
      "learning_rate": 1.839229287286327e-05,
      "loss": 2.3982,
      "step": 900
    },
    {
      "epoch": 13.090744101633394,
      "eval_loss": 2.3612313270568848,
      "eval_runtime": 14.4663,
      "eval_samples_per_second": 197.009,
      "eval_steps_per_second": 6.221,
      "step": 900
    },
    {
      "epoch": 13.235934664246823,
      "grad_norm": 2.8399763107299805,
      "learning_rate": 1.8336023852211197e-05,
      "loss": 2.3385,
      "step": 910
    },
    {
      "epoch": 13.381125226860254,
      "grad_norm": 2.8449740409851074,
      "learning_rate": 1.827887618942318e-05,
      "loss": 2.329,
      "step": 920
    },
    {
      "epoch": 13.526315789473685,
      "grad_norm": 3.4475836753845215,
      "learning_rate": 1.8220855908035783e-05,
      "loss": 2.3102,
      "step": 930
    },
    {
      "epoch": 13.671506352087114,
      "grad_norm": 2.820624589920044,
      "learning_rate": 1.816196912356222e-05,
      "loss": 2.3118,
      "step": 940
    },
    {
      "epoch": 13.816696914700545,
      "grad_norm": 2.9867615699768066,
      "learning_rate": 1.8102222042847735e-05,
      "loss": 2.3077,
      "step": 950
    },
    {
      "epoch": 13.961887477313974,
      "grad_norm": 4.323665142059326,
      "learning_rate": 1.8041620963415418e-05,
      "loss": 2.3013,
      "step": 960
    },
    {
      "epoch": 14.108892921960072,
      "grad_norm": 4.4349236488342285,
      "learning_rate": 1.7980172272802398e-05,
      "loss": 2.3514,
      "step": 970
    },
    {
      "epoch": 14.254083484573503,
      "grad_norm": 4.404689311981201,
      "learning_rate": 1.7917882447886585e-05,
      "loss": 2.2881,
      "step": 980
    },
    {
      "epoch": 14.399274047186934,
      "grad_norm": 4.489727020263672,
      "learning_rate": 1.785475805420399e-05,
      "loss": 2.2839,
      "step": 990
    },
    {
      "epoch": 14.544464609800363,
      "grad_norm": 3.8734374046325684,
      "learning_rate": 1.7790805745256703e-05,
      "loss": 2.2785,
      "step": 1000
    },
    {
      "epoch": 14.544464609800363,
      "eval_loss": 2.2907564640045166,
      "eval_runtime": 14.4981,
      "eval_samples_per_second": 196.577,
      "eval_steps_per_second": 6.208,
      "step": 1000
    },
    {
      "epoch": 14.689655172413794,
      "grad_norm": 4.450066089630127,
      "learning_rate": 1.772603226181159e-05,
      "loss": 2.2566,
      "step": 1010
    },
    {
      "epoch": 14.834845735027223,
      "grad_norm": 4.106595993041992,
      "learning_rate": 1.766044443118978e-05,
      "loss": 2.261,
      "step": 1020
    },
    {
      "epoch": 14.980036297640654,
      "grad_norm": 3.8136234283447266,
      "learning_rate": 1.7594049166547073e-05,
      "loss": 2.2535,
      "step": 1030
    },
    {
      "epoch": 15.127041742286751,
      "grad_norm": 5.098197937011719,
      "learning_rate": 1.7526853466145248e-05,
      "loss": 2.3093,
      "step": 1040
    },
    {
      "epoch": 15.272232304900182,
      "grad_norm": 3.752929210662842,
      "learning_rate": 1.7458864412614436e-05,
      "loss": 2.2377,
      "step": 1050
    },
    {
      "epoch": 15.417422867513611,
      "grad_norm": 3.992673397064209,
      "learning_rate": 1.7390089172206594e-05,
      "loss": 2.2416,
      "step": 1060
    },
    {
      "epoch": 15.562613430127042,
      "grad_norm": 3.857272148132324,
      "learning_rate": 1.7320534994040148e-05,
      "loss": 2.2251,
      "step": 1070
    },
    {
      "epoch": 15.707803992740471,
      "grad_norm": 4.833571434020996,
      "learning_rate": 1.725020920933593e-05,
      "loss": 2.2262,
      "step": 1080
    },
    {
      "epoch": 15.852994555353902,
      "grad_norm": 2.919546127319336,
      "learning_rate": 1.717911923064442e-05,
      "loss": 2.2204,
      "step": 1090
    },
    {
      "epoch": 15.998185117967331,
      "grad_norm": 4.030925273895264,
      "learning_rate": 1.710727255106447e-05,
      "loss": 2.274,
      "step": 1100
    },
    {
      "epoch": 15.998185117967331,
      "eval_loss": 2.2391433715820312,
      "eval_runtime": 14.4613,
      "eval_samples_per_second": 197.077,
      "eval_steps_per_second": 6.223,
      "step": 1100
    },
    {
      "epoch": 16.14519056261343,
      "grad_norm": 3.9502663612365723,
      "learning_rate": 1.70346767434535e-05,
      "loss": 2.2167,
      "step": 1110
    },
    {
      "epoch": 16.29038112522686,
      "grad_norm": 3.8203535079956055,
      "learning_rate": 1.696133945962927e-05,
      "loss": 2.2083,
      "step": 1120
    },
    {
      "epoch": 16.43557168784029,
      "grad_norm": 4.025405406951904,
      "learning_rate": 1.6887268429563387e-05,
      "loss": 2.1931,
      "step": 1130
    },
    {
      "epoch": 16.58076225045372,
      "grad_norm": 3.5635058879852295,
      "learning_rate": 1.681247146056654e-05,
      "loss": 2.1873,
      "step": 1140
    },
    {
      "epoch": 16.72595281306715,
      "grad_norm": 3.3059027194976807,
      "learning_rate": 1.6736956436465573e-05,
      "loss": 2.1844,
      "step": 1150
    },
    {
      "epoch": 16.87114337568058,
      "grad_norm": 4.572406768798828,
      "learning_rate": 1.6660731316772503e-05,
      "loss": 2.1869,
      "step": 1160
    },
    {
      "epoch": 17.01814882032668,
      "grad_norm": 4.2072858810424805,
      "learning_rate": 1.6583804135845582e-05,
      "loss": 2.2311,
      "step": 1170
    },
    {
      "epoch": 17.16333938294011,
      "grad_norm": 3.021080732345581,
      "learning_rate": 1.650618300204242e-05,
      "loss": 2.1811,
      "step": 1180
    },
    {
      "epoch": 17.308529945553538,
      "grad_norm": 3.794221878051758,
      "learning_rate": 1.6427876096865394e-05,
      "loss": 2.173,
      "step": 1190
    },
    {
      "epoch": 17.45372050816697,
      "grad_norm": 2.7157645225524902,
      "learning_rate": 1.634889167409923e-05,
      "loss": 2.1565,
      "step": 1200
    },
    {
      "epoch": 17.45372050816697,
      "eval_loss": 2.190614938735962,
      "eval_runtime": 14.4975,
      "eval_samples_per_second": 196.585,
      "eval_steps_per_second": 6.208,
      "step": 1200
    },
    {
      "epoch": 17.5989110707804,
      "grad_norm": 2.9268596172332764,
      "learning_rate": 1.626923805894107e-05,
      "loss": 2.1555,
      "step": 1210
    },
    {
      "epoch": 17.74410163339383,
      "grad_norm": 3.686579942703247,
      "learning_rate": 1.6188923647122946e-05,
      "loss": 2.1556,
      "step": 1220
    },
    {
      "epoch": 17.88929219600726,
      "grad_norm": 4.035010814666748,
      "learning_rate": 1.610795690402688e-05,
      "loss": 2.1488,
      "step": 1230
    },
    {
      "epoch": 18.03629764065336,
      "grad_norm": 3.6302409172058105,
      "learning_rate": 1.6026346363792565e-05,
      "loss": 2.187,
      "step": 1240
    },
    {
      "epoch": 18.181488203266788,
      "grad_norm": 4.382446765899658,
      "learning_rate": 1.594410062841787e-05,
      "loss": 2.1317,
      "step": 1250
    },
    {
      "epoch": 18.326678765880217,
      "grad_norm": 3.663515567779541,
      "learning_rate": 1.5861228366852148e-05,
      "loss": 2.1395,
      "step": 1260
    },
    {
      "epoch": 18.471869328493646,
      "grad_norm": 4.221041679382324,
      "learning_rate": 1.5777738314082514e-05,
      "loss": 2.1335,
      "step": 1270
    },
    {
      "epoch": 18.61705989110708,
      "grad_norm": 2.963515043258667,
      "learning_rate": 1.5693639270213138e-05,
      "loss": 2.1366,
      "step": 1280
    },
    {
      "epoch": 18.762250453720508,
      "grad_norm": 3.6942713260650635,
      "learning_rate": 1.56089400995377e-05,
      "loss": 2.1127,
      "step": 1290
    },
    {
      "epoch": 18.907441016333937,
      "grad_norm": 3.9856643676757812,
      "learning_rate": 1.552364972960506e-05,
      "loss": 2.1151,
      "step": 1300
    },
    {
      "epoch": 18.907441016333937,
      "eval_loss": 2.1343271732330322,
      "eval_runtime": 14.4663,
      "eval_samples_per_second": 197.009,
      "eval_steps_per_second": 6.221,
      "step": 1300
    },
    {
      "epoch": 19.054446460980035,
      "grad_norm": 3.4405646324157715,
      "learning_rate": 1.5437777150278268e-05,
      "loss": 2.1568,
      "step": 1310
    },
    {
      "epoch": 19.199637023593468,
      "grad_norm": 3.63427472114563,
      "learning_rate": 1.5351331412787004e-05,
      "loss": 2.0952,
      "step": 1320
    },
    {
      "epoch": 19.344827586206897,
      "grad_norm": 3.7811665534973145,
      "learning_rate": 1.526432162877356e-05,
      "loss": 2.1059,
      "step": 1330
    },
    {
      "epoch": 19.490018148820326,
      "grad_norm": 4.82371187210083,
      "learning_rate": 1.5176756969332428e-05,
      "loss": 2.1137,
      "step": 1340
    },
    {
      "epoch": 19.635208711433755,
      "grad_norm": 2.7587039470672607,
      "learning_rate": 1.5088646664043652e-05,
      "loss": 2.0951,
      "step": 1350
    },
    {
      "epoch": 19.780399274047188,
      "grad_norm": 3.3458638191223145,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 2.0987,
      "step": 1360
    },
    {
      "epoch": 19.925589836660617,
      "grad_norm": 3.0390782356262207,
      "learning_rate": 1.4910826320828085e-05,
      "loss": 2.0854,
      "step": 1370
    },
    {
      "epoch": 20.072595281306715,
      "grad_norm": 4.020959854125977,
      "learning_rate": 1.4821135025703491e-05,
      "loss": 2.1504,
      "step": 1380
    },
    {
      "epoch": 20.217785843920144,
      "grad_norm": 3.3670413494110107,
      "learning_rate": 1.4730935568360103e-05,
      "loss": 2.0924,
      "step": 1390
    },
    {
      "epoch": 20.362976406533576,
      "grad_norm": 3.5803141593933105,
      "learning_rate": 1.4640237456093636e-05,
      "loss": 2.0649,
      "step": 1400
    },
    {
      "epoch": 20.362976406533576,
      "eval_loss": 2.100735902786255,
      "eval_runtime": 14.4583,
      "eval_samples_per_second": 197.118,
      "eval_steps_per_second": 6.225,
      "step": 1400
    },
    {
      "epoch": 20.508166969147005,
      "grad_norm": 3.7825708389282227,
      "learning_rate": 1.4549050248759546e-05,
      "loss": 2.0681,
      "step": 1410
    },
    {
      "epoch": 20.653357531760435,
      "grad_norm": 2.811061382293701,
      "learning_rate": 1.4457383557765385e-05,
      "loss": 2.0663,
      "step": 1420
    },
    {
      "epoch": 20.798548094373867,
      "grad_norm": 2.962312698364258,
      "learning_rate": 1.4365247045057732e-05,
      "loss": 2.0614,
      "step": 1430
    },
    {
      "epoch": 20.943738656987296,
      "grad_norm": 2.2117114067077637,
      "learning_rate": 1.427265042210381e-05,
      "loss": 2.0595,
      "step": 1440
    },
    {
      "epoch": 21.090744101633394,
      "grad_norm": 4.001194953918457,
      "learning_rate": 1.4179603448867836e-05,
      "loss": 2.121,
      "step": 1450
    },
    {
      "epoch": 21.235934664246823,
      "grad_norm": 3.026092767715454,
      "learning_rate": 1.4086115932782316e-05,
      "loss": 2.0485,
      "step": 1460
    },
    {
      "epoch": 21.381125226860256,
      "grad_norm": 3.9385151863098145,
      "learning_rate": 1.399219772771431e-05,
      "loss": 2.0477,
      "step": 1470
    },
    {
      "epoch": 21.526315789473685,
      "grad_norm": 3.3123228549957275,
      "learning_rate": 1.3897858732926794e-05,
      "loss": 2.0427,
      "step": 1480
    },
    {
      "epoch": 21.671506352087114,
      "grad_norm": 3.20367169380188,
      "learning_rate": 1.3803108892035259e-05,
      "loss": 2.0504,
      "step": 1490
    },
    {
      "epoch": 21.816696914700543,
      "grad_norm": 3.5425407886505127,
      "learning_rate": 1.3707958191959609e-05,
      "loss": 2.0474,
      "step": 1500
    },
    {
      "epoch": 21.816696914700543,
      "eval_loss": 2.065798044204712,
      "eval_runtime": 14.4887,
      "eval_samples_per_second": 196.705,
      "eval_steps_per_second": 6.212,
      "step": 1500
    },
    {
      "epoch": 21.961887477313976,
      "grad_norm": 3.0119071006774902,
      "learning_rate": 1.3612416661871532e-05,
      "loss": 2.0418,
      "step": 1510
    },
    {
      "epoch": 22.108892921960074,
      "grad_norm": 3.1108176708221436,
      "learning_rate": 1.3516494372137368e-05,
      "loss": 2.0866,
      "step": 1520
    },
    {
      "epoch": 22.254083484573503,
      "grad_norm": 3.3773062229156494,
      "learning_rate": 1.342020143325669e-05,
      "loss": 2.0343,
      "step": 1530
    },
    {
      "epoch": 22.399274047186932,
      "grad_norm": 3.3889658451080322,
      "learning_rate": 1.3323547994796597e-05,
      "loss": 2.0236,
      "step": 1540
    },
    {
      "epoch": 22.544464609800364,
      "grad_norm": 2.263582229614258,
      "learning_rate": 1.322654424432195e-05,
      "loss": 2.0312,
      "step": 1550
    },
    {
      "epoch": 22.689655172413794,
      "grad_norm": 2.6817829608917236,
      "learning_rate": 1.3129200406321545e-05,
      "loss": 2.0299,
      "step": 1560
    },
    {
      "epoch": 22.834845735027223,
      "grad_norm": 3.2429702281951904,
      "learning_rate": 1.3031526741130435e-05,
      "loss": 2.0159,
      "step": 1570
    },
    {
      "epoch": 22.980036297640652,
      "grad_norm": 2.677948236465454,
      "learning_rate": 1.2933533543848462e-05,
      "loss": 2.0198,
      "step": 1580
    },
    {
      "epoch": 23.12704174228675,
      "grad_norm": 2.9102084636688232,
      "learning_rate": 1.283523114325511e-05,
      "loss": 2.0692,
      "step": 1590
    },
    {
      "epoch": 23.272232304900182,
      "grad_norm": 3.3689348697662354,
      "learning_rate": 1.2736629900720832e-05,
      "loss": 2.0121,
      "step": 1600
    },
    {
      "epoch": 23.272232304900182,
      "eval_loss": 2.03466534614563,
      "eval_runtime": 14.4631,
      "eval_samples_per_second": 197.053,
      "eval_steps_per_second": 6.223,
      "step": 1600
    }
  ],
  "logging_steps": 10,
  "max_steps": 3400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.967214202780385e+19,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}