{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 117,
  "global_step": 585,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00857449088960343,
      "grad_norm": 3.7779083251953125,
      "learning_rate": 0.0,
      "loss": 2.021087646484375,
      "step": 1
    },
    {
      "epoch": 0.01714898177920686,
      "grad_norm": 3.676138162612915,
      "learning_rate": 9.999999999999999e-06,
      "loss": 2.1905517578125,
      "step": 2
    },
    {
      "epoch": 0.02572347266881029,
      "grad_norm": 2.95475697517395,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 1.93475341796875,
      "step": 3
    },
    {
      "epoch": 0.03429796355841372,
      "grad_norm": 1.789101243019104,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 1.593719482421875,
      "step": 4
    },
    {
      "epoch": 0.04287245444801715,
      "grad_norm": 0.5764492154121399,
      "learning_rate": 3.9999999999999996e-05,
      "loss": 1.57080078125,
      "step": 5
    },
    {
      "epoch": 0.05144694533762058,
      "grad_norm": 0.38636514544487,
      "learning_rate": 4.9999999999999996e-05,
      "loss": 1.3313140869140625,
      "step": 6
    },
    {
      "epoch": 0.06002143622722401,
      "grad_norm": 0.3458130657672882,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 1.4019775390625,
      "step": 7
    },
    {
      "epoch": 0.06859592711682744,
      "grad_norm": 0.2730095386505127,
      "learning_rate": 7e-05,
      "loss": 1.405029296875,
      "step": 8
    },
    {
      "epoch": 0.07717041800643087,
      "grad_norm": 0.31020307540893555,
      "learning_rate": 7.999999999999999e-05,
      "loss": 1.302490234375,
      "step": 9
    },
    {
      "epoch": 0.0857449088960343,
      "grad_norm": 0.3809811770915985,
      "learning_rate": 8.999999999999999e-05,
      "loss": 1.25286865234375,
      "step": 10
    },
    {
      "epoch": 0.09431939978563773,
      "grad_norm": 0.3229080140590668,
      "learning_rate": 9.999999999999999e-05,
      "loss": 1.28662109375,
      "step": 11
    },
    {
      "epoch": 0.10289389067524116,
      "grad_norm": 0.30960822105407715,
      "learning_rate": 0.00010999999999999998,
      "loss": 1.35015869140625,
      "step": 12
    },
    {
      "epoch": 0.11146838156484459,
      "grad_norm": 0.2183811515569687,
      "learning_rate": 0.00011999999999999999,
      "loss": 1.3233642578125,
      "step": 13
    },
    {
      "epoch": 0.12004287245444802,
      "grad_norm": 0.17086774110794067,
      "learning_rate": 0.00013,
      "loss": 1.07220458984375,
      "step": 14
    },
    {
      "epoch": 0.12861736334405144,
      "grad_norm": 0.1786772459745407,
      "learning_rate": 0.00014,
      "loss": 1.272705078125,
      "step": 15
    },
    {
      "epoch": 0.13719185423365488,
      "grad_norm": 0.12576226890087128,
      "learning_rate": 0.00015,
      "loss": 1.0848388671875,
      "step": 16
    },
    {
      "epoch": 0.1457663451232583,
      "grad_norm": 0.14402814209461212,
      "learning_rate": 0.00015999999999999999,
      "loss": 1.17193603515625,
      "step": 17
    },
    {
      "epoch": 0.15434083601286175,
      "grad_norm": 0.11978624016046524,
      "learning_rate": 0.00016999999999999999,
      "loss": 1.1719970703125,
      "step": 18
    },
    {
      "epoch": 0.16291532690246516,
      "grad_norm": 0.12938663363456726,
      "learning_rate": 0.00017999999999999998,
      "loss": 1.2777099609375,
      "step": 19
    },
    {
      "epoch": 0.1714898177920686,
      "grad_norm": 0.0901847705245018,
      "learning_rate": 0.00018999999999999998,
      "loss": 1.208251953125,
      "step": 20
    },
    {
      "epoch": 0.18006430868167203,
      "grad_norm": 0.10554253309965134,
      "learning_rate": 0.00019999999999999998,
      "loss": 1.03802490234375,
      "step": 21
    },
    {
      "epoch": 0.18863879957127547,
      "grad_norm": 0.12466742098331451,
      "learning_rate": 0.00020999999999999998,
      "loss": 1.07562255859375,
      "step": 22
    },
    {
      "epoch": 0.19721329046087888,
      "grad_norm": 0.09356667846441269,
      "learning_rate": 0.00021999999999999995,
      "loss": 1.07720947265625,
      "step": 23
    },
    {
      "epoch": 0.2057877813504823,
      "grad_norm": 0.06951848417520523,
      "learning_rate": 0.00023,
      "loss": 1.08258056640625,
      "step": 24
    },
    {
      "epoch": 0.21436227224008575,
      "grad_norm": 0.0911501869559288,
      "learning_rate": 0.00023999999999999998,
      "loss": 1.090087890625,
      "step": 25
    },
    {
      "epoch": 0.22293676312968919,
      "grad_norm": 0.0814780592918396,
      "learning_rate": 0.00025,
      "loss": 1.0770263671875,
      "step": 26
    },
    {
      "epoch": 0.2315112540192926,
      "grad_norm": 0.06549561023712158,
      "learning_rate": 0.00026,
      "loss": 0.981964111328125,
      "step": 27
    },
    {
      "epoch": 0.24008574490889603,
      "grad_norm": 0.07616422325372696,
      "learning_rate": 0.00027,
      "loss": 1.09735107421875,
      "step": 28
    },
    {
      "epoch": 0.24866023579849947,
      "grad_norm": 0.073006272315979,
      "learning_rate": 0.00028,
      "loss": 1.06982421875,
      "step": 29
    },
    {
      "epoch": 0.2572347266881029,
      "grad_norm": 0.06448492407798767,
      "learning_rate": 0.00029,
      "loss": 1.0225830078125,
      "step": 30
    },
    {
      "epoch": 0.2658092175777063,
      "grad_norm": 0.07610519230365753,
      "learning_rate": 0.0003,
      "loss": 1.03765869140625,
      "step": 31
    },
    {
      "epoch": 0.27438370846730975,
      "grad_norm": 0.06598562747240067,
      "learning_rate": 0.0002999980775109719,
      "loss": 0.96734619140625,
      "step": 32
    },
    {
      "epoch": 0.2829581993569132,
      "grad_norm": 0.059809714555740356,
      "learning_rate": 0.00029999231010548704,
      "loss": 0.9747314453125,
      "step": 33
    },
    {
      "epoch": 0.2915326902465166,
      "grad_norm": 0.0725642517209053,
      "learning_rate": 0.00029998269796834156,
      "loss": 1.03759765625,
      "step": 34
    },
    {
      "epoch": 0.30010718113612006,
      "grad_norm": 0.05093242600560188,
      "learning_rate": 0.0002999692414075227,
      "loss": 0.88287353515625,
      "step": 35
    },
    {
      "epoch": 0.3086816720257235,
      "grad_norm": 0.06363542377948761,
      "learning_rate": 0.0002999519408541986,
      "loss": 0.929473876953125,
      "step": 36
    },
    {
      "epoch": 0.3172561629153269,
      "grad_norm": 0.05722099915146828,
      "learning_rate": 0.00029993079686270463,
      "loss": 0.98468017578125,
      "step": 37
    },
    {
      "epoch": 0.3258306538049303,
      "grad_norm": 0.05595114827156067,
      "learning_rate": 0.0002999058101105257,
      "loss": 1.0023193359375,
      "step": 38
    },
    {
      "epoch": 0.33440514469453375,
      "grad_norm": 0.050741806626319885,
      "learning_rate": 0.00029987698139827436,
      "loss": 1.0379638671875,
      "step": 39
    },
    {
      "epoch": 0.3429796355841372,
      "grad_norm": 0.06433671712875366,
      "learning_rate": 0.00029984431164966534,
      "loss": 0.97332763671875,
      "step": 40
    },
    {
      "epoch": 0.3515541264737406,
      "grad_norm": 0.05012759566307068,
      "learning_rate": 0.00029980780191148597,
      "loss": 0.9510498046875,
      "step": 41
    },
    {
      "epoch": 0.36012861736334406,
      "grad_norm": 0.05333322286605835,
      "learning_rate": 0.00029976745335356226,
      "loss": 0.96490478515625,
      "step": 42
    },
    {
      "epoch": 0.3687031082529475,
      "grad_norm": 0.056672509759664536,
      "learning_rate": 0.000299723267268722,
      "loss": 0.94415283203125,
      "step": 43
    },
    {
      "epoch": 0.37727759914255093,
      "grad_norm": 0.058475445955991745,
      "learning_rate": 0.00029967524507275295,
      "loss": 0.91949462890625,
      "step": 44
    },
    {
      "epoch": 0.3858520900321543,
      "grad_norm": 0.04630405083298683,
      "learning_rate": 0.00029962338830435736,
      "loss": 0.95892333984375,
      "step": 45
    },
    {
      "epoch": 0.39442658092175775,
      "grad_norm": 0.05727069824934006,
      "learning_rate": 0.0002995676986251032,
      "loss": 0.990234375,
      "step": 46
    },
    {
      "epoch": 0.4030010718113612,
      "grad_norm": 0.04908052459359169,
      "learning_rate": 0.0002995081778193703,
      "loss": 1.011474609375,
      "step": 47
    },
    {
      "epoch": 0.4115755627009646,
      "grad_norm": 0.05973237380385399,
      "learning_rate": 0.0002994448277942936,
      "loss": 0.94342041015625,
      "step": 48
    },
    {
      "epoch": 0.42015005359056806,
      "grad_norm": 0.051539432257413864,
      "learning_rate": 0.000299377650579702,
      "loss": 0.93463134765625,
      "step": 49
    },
    {
      "epoch": 0.4287245444801715,
      "grad_norm": 0.04831636697053909,
      "learning_rate": 0.0002993066483280531,
      "loss": 0.9033203125,
      "step": 50
    },
    {
      "epoch": 0.43729903536977494,
      "grad_norm": 0.05341218784451485,
      "learning_rate": 0.00029923182331436434,
      "loss": 0.890838623046875,
      "step": 51
    },
    {
      "epoch": 0.44587352625937837,
      "grad_norm": 0.0462009459733963,
      "learning_rate": 0.00029915317793614024,
      "loss": 0.86248779296875,
      "step": 52
    },
    {
      "epoch": 0.45444801714898175,
      "grad_norm": 0.05351356416940689,
      "learning_rate": 0.00029907071471329535,
      "loss": 0.8692626953125,
      "step": 53
    },
    {
      "epoch": 0.4630225080385852,
      "grad_norm": 0.057779181748628616,
      "learning_rate": 0.0002989844362880738,
      "loss": 0.853668212890625,
      "step": 54
    },
    {
      "epoch": 0.4715969989281886,
      "grad_norm": 0.06440568715333939,
      "learning_rate": 0.0002988943454249642,
      "loss": 0.851409912109375,
      "step": 55
    },
    {
      "epoch": 0.48017148981779206,
      "grad_norm": 0.056649211794137955,
      "learning_rate": 0.0002988004450106116,
      "loss": 0.952392578125,
      "step": 56
    },
    {
      "epoch": 0.4887459807073955,
      "grad_norm": 0.05292658880352974,
      "learning_rate": 0.0002987027380537246,
      "loss": 0.7855987548828125,
      "step": 57
    },
    {
      "epoch": 0.49732047159699894,
      "grad_norm": 0.06440464407205582,
      "learning_rate": 0.00029860122768497906,
      "loss": 0.86767578125,
      "step": 58
    },
    {
      "epoch": 0.5058949624866024,
      "grad_norm": 0.07794512063264847,
      "learning_rate": 0.00029849591715691776,
      "loss": 0.870697021484375,
      "step": 59
    },
    {
      "epoch": 0.5144694533762058,
      "grad_norm": 0.06821154057979584,
      "learning_rate": 0.0002983868098438464,
      "loss": 0.8333740234375,
      "step": 60
    },
    {
      "epoch": 0.5230439442658092,
      "grad_norm": 0.06468360871076584,
      "learning_rate": 0.00029827390924172504,
      "loss": 0.883697509765625,
      "step": 61
    },
    {
      "epoch": 0.5316184351554126,
      "grad_norm": 0.07485311478376389,
      "learning_rate": 0.00029815721896805654,
      "loss": 0.8365478515625,
      "step": 62
    },
    {
      "epoch": 0.5401929260450161,
      "grad_norm": 0.05626165494322777,
      "learning_rate": 0.00029803674276177044,
      "loss": 0.88043212890625,
      "step": 63
    },
    {
      "epoch": 0.5487674169346195,
      "grad_norm": 0.05174149572849274,
      "learning_rate": 0.00029791248448310316,
      "loss": 0.993377685546875,
      "step": 64
    },
    {
      "epoch": 0.5573419078242229,
      "grad_norm": 0.06781824678182602,
      "learning_rate": 0.0002977844481134744,
      "loss": 0.78167724609375,
      "step": 65
    },
    {
      "epoch": 0.5659163987138264,
      "grad_norm": 0.0659022107720375,
      "learning_rate": 0.0002976526377553592,
      "loss": 0.8673095703125,
      "step": 66
    },
    {
      "epoch": 0.5744908896034298,
      "grad_norm": 0.06762973219156265,
      "learning_rate": 0.0002975170576321572,
      "loss": 0.79547119140625,
      "step": 67
    },
    {
      "epoch": 0.5830653804930332,
      "grad_norm": 0.05919407680630684,
      "learning_rate": 0.0002973777120880567,
      "loss": 0.773040771484375,
      "step": 68
    },
    {
      "epoch": 0.5916398713826366,
      "grad_norm": 0.05946492403745651,
      "learning_rate": 0.0002972346055878956,
      "loss": 0.90716552734375,
      "step": 69
    },
    {
      "epoch": 0.6002143622722401,
      "grad_norm": 0.09558821469545364,
      "learning_rate": 0.0002970877427170186,
      "loss": 0.8636474609375,
      "step": 70
    },
    {
      "epoch": 0.6087888531618435,
      "grad_norm": 0.08061610162258148,
      "learning_rate": 0.00029693712818112993,
      "loss": 0.86627197265625,
      "step": 71
    },
    {
      "epoch": 0.617363344051447,
      "grad_norm": 0.04875899478793144,
      "learning_rate": 0.00029678276680614293,
      "loss": 0.885284423828125,
      "step": 72
    },
    {
      "epoch": 0.6259378349410504,
      "grad_norm": 0.0811656042933464,
      "learning_rate": 0.000296624663538025,
      "loss": 0.9207763671875,
      "step": 73
    },
    {
      "epoch": 0.6345123258306538,
      "grad_norm": 0.0647500529885292,
      "learning_rate": 0.0002964628234426394,
      "loss": 0.823272705078125,
      "step": 74
    },
    {
      "epoch": 0.6430868167202572,
      "grad_norm": 0.0845179408788681,
      "learning_rate": 0.0002962972517055829,
      "loss": 0.83587646484375,
      "step": 75
    },
    {
      "epoch": 0.6516613076098606,
      "grad_norm": 0.09018101543188095,
      "learning_rate": 0.00029612795363201985,
      "loss": 0.800537109375,
      "step": 76
    },
    {
      "epoch": 0.6602357984994641,
      "grad_norm": 0.04811553284525871,
      "learning_rate": 0.0002959549346465115,
      "loss": 0.827850341796875,
      "step": 77
    },
    {
      "epoch": 0.6688102893890675,
      "grad_norm": 0.07204996794462204,
      "learning_rate": 0.000295778200292843,
      "loss": 0.85418701171875,
      "step": 78
    },
    {
      "epoch": 0.677384780278671,
      "grad_norm": 0.057989247143268585,
      "learning_rate": 0.0002955977562338453,
      "loss": 0.77484130859375,
      "step": 79
    },
    {
      "epoch": 0.6859592711682744,
      "grad_norm": 0.05479753389954567,
      "learning_rate": 0.0002954136082512136,
      "loss": 0.7538833618164062,
      "step": 80
    },
    {
      "epoch": 0.6945337620578779,
      "grad_norm": 0.058230139315128326,
      "learning_rate": 0.0002952257622453227,
      "loss": 0.888916015625,
      "step": 81
    },
    {
      "epoch": 0.7031082529474812,
      "grad_norm": 0.07324634492397308,
      "learning_rate": 0.00029503422423503734,
      "loss": 0.91754150390625,
      "step": 82
    },
    {
      "epoch": 0.7116827438370846,
      "grad_norm": 0.05922788009047508,
      "learning_rate": 0.00029483900035751943,
      "loss": 0.84820556640625,
      "step": 83
    },
    {
      "epoch": 0.7202572347266881,
      "grad_norm": 0.06309138983488083,
      "learning_rate": 0.0002946400968680318,
      "loss": 0.900634765625,
      "step": 84
    },
    {
      "epoch": 0.7288317256162915,
      "grad_norm": 0.05868224799633026,
      "learning_rate": 0.0002944375201397375,
      "loss": 0.8677978515625,
      "step": 85
    },
    {
      "epoch": 0.737406216505895,
      "grad_norm": 0.07041683048009872,
      "learning_rate": 0.0002942312766634951,
      "loss": 0.8905029296875,
      "step": 86
    },
    {
      "epoch": 0.7459807073954984,
      "grad_norm": 0.06062329560518265,
      "learning_rate": 0.000294021373047652,
      "loss": 0.93408203125,
      "step": 87
    },
    {
      "epoch": 0.7545551982851019,
      "grad_norm": 0.06239849701523781,
      "learning_rate": 0.0002938078160178314,
      "loss": 0.8695068359375,
      "step": 88
    },
    {
      "epoch": 0.7631296891747053,
      "grad_norm": 0.05498891696333885,
      "learning_rate": 0.00029359061241671737,
      "loss": 0.82501220703125,
      "step": 89
    },
    {
      "epoch": 0.7717041800643086,
      "grad_norm": 0.06226081773638725,
      "learning_rate": 0.0002933697692038355,
      "loss": 0.758880615234375,
      "step": 90
    },
    {
      "epoch": 0.7802786709539121,
      "grad_norm": 0.0528423972427845,
      "learning_rate": 0.00029314529345533005,
      "loss": 0.93792724609375,
      "step": 91
    },
    {
      "epoch": 0.7888531618435155,
      "grad_norm": 0.06362111866474152,
      "learning_rate": 0.0002929171923637372,
      "loss": 0.86083984375,
      "step": 92
    },
    {
      "epoch": 0.797427652733119,
      "grad_norm": 0.07624952495098114,
      "learning_rate": 0.0002926854732377543,
      "loss": 0.840301513671875,
      "step": 93
    },
    {
      "epoch": 0.8060021436227224,
      "grad_norm": 0.06764503568410873,
      "learning_rate": 0.000292450143502006,
      "loss": 0.734405517578125,
      "step": 94
    },
    {
      "epoch": 0.8145766345123259,
      "grad_norm": 0.06352157890796661,
      "learning_rate": 0.00029221121069680615,
      "loss": 0.765594482421875,
      "step": 95
    },
    {
      "epoch": 0.8231511254019293,
      "grad_norm": 0.071375772356987,
      "learning_rate": 0.0002919686824779165,
      "loss": 0.90155029296875,
      "step": 96
    },
    {
      "epoch": 0.8317256162915327,
      "grad_norm": 0.0634688213467598,
      "learning_rate": 0.00029172256661630087,
      "loss": 0.850830078125,
      "step": 97
    },
    {
      "epoch": 0.8403001071811361,
      "grad_norm": 0.05408760532736778,
      "learning_rate": 0.00029147287099787677,
      "loss": 0.85162353515625,
      "step": 98
    },
    {
      "epoch": 0.8488745980707395,
      "grad_norm": 0.07730305939912796,
      "learning_rate": 0.00029121960362326216,
      "loss": 0.7837905883789062,
      "step": 99
    },
    {
      "epoch": 0.857449088960343,
      "grad_norm": 0.06315551698207855,
      "learning_rate": 0.00029096277260751976,
      "loss": 0.7328109741210938,
      "step": 100
    },
    {
      "epoch": 0.8660235798499464,
      "grad_norm": 0.07862366735935211,
      "learning_rate": 0.0002907023861798962,
      "loss": 0.791473388671875,
      "step": 101
    },
    {
      "epoch": 0.8745980707395499,
      "grad_norm": 0.1041983962059021,
      "learning_rate": 0.0002904384526835591,
      "loss": 0.7735595703125,
      "step": 102
    },
    {
      "epoch": 0.8831725616291533,
      "grad_norm": 0.08728644996881485,
      "learning_rate": 0.00029017098057532934,
      "loss": 0.858917236328125,
      "step": 103
    },
    {
      "epoch": 0.8917470525187567,
      "grad_norm": 0.0771179050207138,
      "learning_rate": 0.00028989997842540996,
      "loss": 0.7494583129882812,
      "step": 104
    },
    {
      "epoch": 0.9003215434083601,
      "grad_norm": 0.13863396644592285,
      "learning_rate": 0.00028962545491711207,
      "loss": 0.8082275390625,
      "step": 105
    },
    {
      "epoch": 0.9088960342979635,
      "grad_norm": 0.10024130344390869,
      "learning_rate": 0.00028934741884657626,
      "loss": 0.8466796875,
      "step": 106
    },
    {
      "epoch": 0.917470525187567,
      "grad_norm": 0.10893175005912781,
      "learning_rate": 0.00028906587912249076,
      "loss": 0.784088134765625,
      "step": 107
    },
    {
      "epoch": 0.9260450160771704,
      "grad_norm": 0.12274371832609177,
      "learning_rate": 0.000288780844765806,
      "loss": 0.9058380126953125,
      "step": 108
    },
    {
      "epoch": 0.9346195069667739,
      "grad_norm": 0.10705537348985672,
      "learning_rate": 0.00028849232490944576,
      "loss": 0.92242431640625,
      "step": 109
    },
    {
      "epoch": 0.9431939978563773,
      "grad_norm": 0.09761575609445572,
      "learning_rate": 0.00028820032879801427,
      "loss": 0.7996826171875,
      "step": 110
    },
    {
      "epoch": 0.9517684887459807,
      "grad_norm": 0.1217934712767601,
      "learning_rate": 0.0002879048657875004,
      "loss": 0.8170166015625,
      "step": 111
    },
    {
      "epoch": 0.9603429796355841,
      "grad_norm": 0.10129762440919876,
      "learning_rate": 0.0002876059453449772,
      "loss": 0.8052978515625,
      "step": 112
    },
    {
      "epoch": 0.9689174705251876,
      "grad_norm": 0.08620790392160416,
      "learning_rate": 0.0002873035770482993,
      "loss": 0.87689208984375,
      "step": 113
    },
    {
      "epoch": 0.977491961414791,
      "grad_norm": 0.10425687581300735,
      "learning_rate": 0.0002869977705857956,
      "loss": 0.8160400390625,
      "step": 114
    },
    {
      "epoch": 0.9860664523043944,
      "grad_norm": 0.07878941297531128,
      "learning_rate": 0.0002866885357559588,
      "loss": 0.8316650390625,
      "step": 115
    },
    {
      "epoch": 0.9946409431939979,
      "grad_norm": 0.08002115041017532,
      "learning_rate": 0.0002863758824671318,
      "loss": 0.7108508944511414,
      "step": 116
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.07355567067861557,
      "learning_rate": 0.0002860598207371899,
      "loss": 0.7896728515625,
      "step": 117
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.8277994990348816,
      "eval_runtime": 1.4754,
      "eval_samples_per_second": 2.033,
      "eval_steps_per_second": 0.678,
      "step": 117
    },
    {
      "epoch": 1.0085744908896035,
      "grad_norm": 0.05929425731301308,
      "learning_rate": 0.0002857403606932198,
      "loss": 0.8380889892578125,
      "step": 118
    },
    {
      "epoch": 1.0171489817792068,
      "grad_norm": 0.07085801661014557,
      "learning_rate": 0.00028541751257119534,
      "loss": 0.8604736328125,
      "step": 119
    },
    {
      "epoch": 1.0257234726688103,
      "grad_norm": 0.06762248277664185,
      "learning_rate": 0.00028509128671564944,
      "loss": 0.771453857421875,
      "step": 120
    },
    {
      "epoch": 1.0342979635584137,
      "grad_norm": 0.07855992764234543,
      "learning_rate": 0.0002847616935793426,
      "loss": 0.780792236328125,
      "step": 121
    },
    {
      "epoch": 1.0428724544480172,
      "grad_norm": 0.0672563686966896,
      "learning_rate": 0.00028442874372292784,
      "loss": 0.86285400390625,
      "step": 122
    },
    {
      "epoch": 1.0514469453376205,
      "grad_norm": 0.056726086884737015,
      "learning_rate": 0.00028409244781461276,
      "loss": 0.7861785888671875,
      "step": 123
    },
    {
      "epoch": 1.060021436227224,
      "grad_norm": 0.06638378649950027,
      "learning_rate": 0.000283752816629817,
      "loss": 0.8045654296875,
      "step": 124
    },
    {
      "epoch": 1.0685959271168275,
      "grad_norm": 0.07196249067783356,
      "learning_rate": 0.00028340986105082795,
      "loss": 0.81085205078125,
      "step": 125
    },
    {
      "epoch": 1.077170418006431,
      "grad_norm": 0.04687396064400673,
      "learning_rate": 0.0002830635920664511,
      "loss": 0.828155517578125,
      "step": 126
    },
    {
      "epoch": 1.0857449088960343,
      "grad_norm": 0.05898623913526535,
      "learning_rate": 0.0002827140207716585,
      "loss": 0.788330078125,
      "step": 127
    },
    {
      "epoch": 1.0943193997856377,
      "grad_norm": 0.0508388951420784,
      "learning_rate": 0.0002823611583672332,
      "loss": 0.82696533203125,
      "step": 128
    },
    {
      "epoch": 1.1028938906752412,
      "grad_norm": 0.06546000391244888,
      "learning_rate": 0.0002820050161594101,
      "loss": 0.88861083984375,
      "step": 129
    },
    {
      "epoch": 1.1114683815648445,
      "grad_norm": 0.06226546689867973,
      "learning_rate": 0.0002816456055595141,
      "loss": 0.861083984375,
      "step": 130
    },
    {
      "epoch": 1.120042872454448,
      "grad_norm": 0.04148954525589943,
      "learning_rate": 0.00028128293808359403,
      "loss": 0.770965576171875,
      "step": 131
    },
    {
      "epoch": 1.1286173633440515,
      "grad_norm": 0.07109932601451874,
      "learning_rate": 0.000280917025352054,
      "loss": 0.825927734375,
      "step": 132
    },
    {
      "epoch": 1.137191854233655,
      "grad_norm": 0.055082906037569046,
      "learning_rate": 0.0002805478790892808,
      "loss": 0.737213134765625,
      "step": 133
    },
    {
      "epoch": 1.1457663451232583,
      "grad_norm": 0.06484628468751907,
      "learning_rate": 0.0002801755111232685,
      "loss": 0.78106689453125,
      "step": 134
    },
    {
      "epoch": 1.1543408360128617,
      "grad_norm": 0.07240717858076096,
      "learning_rate": 0.0002797999333852393,
      "loss": 0.80419921875,
      "step": 135
    },
    {
      "epoch": 1.1629153269024652,
      "grad_norm": 0.06135954335331917,
      "learning_rate": 0.00027942115790926105,
      "loss": 0.90692138671875,
      "step": 136
    },
    {
      "epoch": 1.1714898177920685,
      "grad_norm": 0.06270311772823334,
      "learning_rate": 0.00027903919683186214,
      "loss": 0.85650634765625,
      "step": 137
    },
    {
      "epoch": 1.180064308681672,
      "grad_norm": 0.05699096992611885,
      "learning_rate": 0.00027865406239164223,
      "loss": 0.745819091796875,
      "step": 138
    },
    {
      "epoch": 1.1886387995712755,
      "grad_norm": 0.063872791826725,
      "learning_rate": 0.0002782657669288802,
      "loss": 0.7623291015625,
      "step": 139
    },
    {
      "epoch": 1.197213290460879,
      "grad_norm": 0.0701894536614418,
      "learning_rate": 0.00027787432288513893,
      "loss": 0.7799072265625,
      "step": 140
    },
    {
      "epoch": 1.2057877813504823,
      "grad_norm": 0.05413001775741577,
      "learning_rate": 0.00027747974280286627,
      "loss": 0.80010986328125,
      "step": 141
    },
    {
      "epoch": 1.2143622722400857,
      "grad_norm": 0.06028295308351517,
      "learning_rate": 0.00027708203932499373,
      "loss": 0.7904052734375,
      "step": 142
    },
    {
      "epoch": 1.2229367631296892,
      "grad_norm": 0.06690923124551773,
      "learning_rate": 0.00027668122519453064,
      "loss": 0.797607421875,
      "step": 143
    },
    {
      "epoch": 1.2315112540192925,
      "grad_norm": 0.05621356517076492,
      "learning_rate": 0.0002762773132541565,
      "loss": 0.74786376953125,
      "step": 144
    },
    {
      "epoch": 1.240085744908896,
      "grad_norm": 0.06329293549060822,
      "learning_rate": 0.0002758703164458094,
      "loss": 0.83837890625,
      "step": 145
    },
    {
      "epoch": 1.2486602357984995,
      "grad_norm": 0.05104130879044533,
      "learning_rate": 0.0002754602478102708,
      "loss": 0.847015380859375,
      "step": 146
    },
    {
      "epoch": 1.257234726688103,
      "grad_norm": 0.06266576796770096,
      "learning_rate": 0.0002750471204867483,
      "loss": 0.79595947265625,
      "step": 147
    },
    {
      "epoch": 1.2658092175777063,
      "grad_norm": 0.07377156615257263,
      "learning_rate": 0.0002746309477124543,
      "loss": 0.7952880859375,
      "step": 148
    },
    {
      "epoch": 1.2743837084673098,
      "grad_norm": 0.06539032608270645,
      "learning_rate": 0.0002742117428221821,
      "loss": 0.766998291015625,
      "step": 149
    },
    {
      "epoch": 1.2829581993569132,
      "grad_norm": 0.053485672920942307,
      "learning_rate": 0.00027378951924787823,
      "loss": 0.77288818359375,
      "step": 150
    },
    {
      "epoch": 1.2915326902465165,
      "grad_norm": 0.06742583960294724,
      "learning_rate": 0.00027336429051821274,
      "loss": 0.8330078125,
      "step": 151
    },
    {
      "epoch": 1.30010718113612,
      "grad_norm": 0.06384310871362686,
      "learning_rate": 0.0002729360702581449,
      "loss": 0.717010498046875,
      "step": 152
    },
    {
      "epoch": 1.3086816720257235,
      "grad_norm": 0.06598325818777084,
      "learning_rate": 0.00027250487218848736,
      "loss": 0.762939453125,
      "step": 153
    },
    {
      "epoch": 1.317256162915327,
      "grad_norm": 0.08702228218317032,
      "learning_rate": 0.00027207071012546593,
      "loss": 0.80316162109375,
      "step": 154
    },
    {
      "epoch": 1.3258306538049303,
      "grad_norm": 0.07156196236610413,
      "learning_rate": 0.0002716335979802775,
      "loss": 0.834259033203125,
      "step": 155
    },
    {
      "epoch": 1.3344051446945338,
      "grad_norm": 0.059140343219041824,
      "learning_rate": 0.00027119354975864364,
      "loss": 0.8663330078125,
      "step": 156
    },
    {
      "epoch": 1.3429796355841372,
      "grad_norm": 0.09453645348548889,
      "learning_rate": 0.0002707505795603625,
      "loss": 0.81170654296875,
      "step": 157
    },
    {
      "epoch": 1.3515541264737405,
      "grad_norm": 0.09513115882873535,
      "learning_rate": 0.0002703047015788563,
      "loss": 0.79534912109375,
      "step": 158
    },
    {
      "epoch": 1.360128617363344,
      "grad_norm": 0.07016335427761078,
      "learning_rate": 0.00026985593010071725,
      "loss": 0.81170654296875,
      "step": 159
    },
    {
      "epoch": 1.3687031082529475,
      "grad_norm": 0.09872682392597198,
      "learning_rate": 0.0002694042795052494,
      "loss": 0.79547119140625,
      "step": 160
    },
    {
      "epoch": 1.377277599142551,
      "grad_norm": 0.09112469106912613,
      "learning_rate": 0.000268949764264008,
      "loss": 0.77813720703125,
      "step": 161
    },
    {
      "epoch": 1.3858520900321543,
      "grad_norm": 0.05991310998797417,
      "learning_rate": 0.00026849239894033585,
      "loss": 0.822662353515625,
      "step": 162
    },
    {
      "epoch": 1.3944265809217578,
      "grad_norm": 0.07845229655504227,
      "learning_rate": 0.0002680321981888964,
      "loss": 0.84521484375,
      "step": 163
    },
    {
      "epoch": 1.4030010718113612,
      "grad_norm": 0.07303779572248459,
      "learning_rate": 0.0002675691767552047,
      "loss": 0.87017822265625,
      "step": 164
    },
    {
      "epoch": 1.4115755627009645,
      "grad_norm": 0.06155399978160858,
      "learning_rate": 0.0002671033494751544,
      "loss": 0.8074951171875,
      "step": 165
    },
    {
      "epoch": 1.420150053590568,
      "grad_norm": 0.08537966758012772,
      "learning_rate": 0.00026663473127454295,
      "loss": 0.8055419921875,
      "step": 166
    },
    {
      "epoch": 1.4287245444801715,
      "grad_norm": 0.05704428628087044,
      "learning_rate": 0.0002661633371685926,
      "loss": 0.7847900390625,
      "step": 167
    },
    {
      "epoch": 1.437299035369775,
      "grad_norm": 0.07766614109277725,
      "learning_rate": 0.00026568918226147013,
      "loss": 0.771728515625,
      "step": 168
    },
    {
      "epoch": 1.4458735262593785,
      "grad_norm": 0.0640282928943634,
      "learning_rate": 0.0002652122817458022,
      "loss": 0.7595977783203125,
      "step": 169
    },
    {
      "epoch": 1.4544480171489818,
      "grad_norm": 0.06011052057147026,
      "learning_rate": 0.00026473265090218913,
      "loss": 0.759796142578125,
      "step": 170
    },
    {
      "epoch": 1.4630225080385852,
      "grad_norm": 0.0720759853720665,
      "learning_rate": 0.00026425030509871474,
      "loss": 0.7542724609375,
      "step": 171
    },
    {
      "epoch": 1.4715969989281885,
      "grad_norm": 0.05904731899499893,
      "learning_rate": 0.00026376525979045413,
      "loss": 0.7474365234375,
      "step": 172
    },
    {
      "epoch": 1.480171489817792,
      "grad_norm": 0.10963998734951019,
      "learning_rate": 0.0002632775305189788,
      "loss": 0.847412109375,
      "step": 173
    },
    {
      "epoch": 1.4887459807073955,
      "grad_norm": 0.12647877633571625,
      "learning_rate": 0.0002627871329118584,
      "loss": 0.6992645263671875,
      "step": 174
    },
    {
      "epoch": 1.497320471596999,
      "grad_norm": 0.1200147271156311,
      "learning_rate": 0.0002622940826821597,
      "loss": 0.7720947265625,
      "step": 175
    },
    {
      "epoch": 1.5058949624866025,
      "grad_norm": 0.07278607040643692,
      "learning_rate": 0.0002617983956279439,
      "loss": 0.77734375,
      "step": 176
    },
    {
      "epoch": 1.5144694533762058,
      "grad_norm": 0.08829725533723831,
      "learning_rate": 0.00026130008763175955,
      "loss": 0.743316650390625,
      "step": 177
    },
    {
      "epoch": 1.5230439442658092,
      "grad_norm": 0.12078077346086502,
      "learning_rate": 0.0002607991746601343,
      "loss": 0.796844482421875,
      "step": 178
    },
    {
      "epoch": 1.5316184351554125,
      "grad_norm": 0.09794958680868149,
      "learning_rate": 0.000260295672763063,
      "loss": 0.749664306640625,
      "step": 179
    },
    {
      "epoch": 1.540192926045016,
      "grad_norm": 0.05625319853425026,
      "learning_rate": 0.0002597895980734935,
      "loss": 0.79412841796875,
      "step": 180
    },
    {
      "epoch": 1.5487674169346195,
      "grad_norm": 0.07014744728803635,
      "learning_rate": 0.00025928096680680977,
      "loss": 0.899017333984375,
      "step": 181
    },
    {
      "epoch": 1.557341907824223,
      "grad_norm": 0.05856478959321976,
      "learning_rate": 0.0002587697952603124,
      "loss": 0.70751953125,
      "step": 182
    },
    {
      "epoch": 1.5659163987138265,
      "grad_norm": 0.08058498799800873,
      "learning_rate": 0.00025825609981269603,
      "loss": 0.78082275390625,
      "step": 183
    },
    {
      "epoch": 1.5744908896034298,
      "grad_norm": 0.05845610052347183,
      "learning_rate": 0.0002577398969235252,
      "loss": 0.71905517578125,
      "step": 184
    },
    {
      "epoch": 1.5830653804930332,
      "grad_norm": 0.053984519094228745,
      "learning_rate": 0.00025722120313270637,
      "loss": 0.7066650390625,
      "step": 185
    },
    {
      "epoch": 1.5916398713826365,
      "grad_norm": 0.06483911722898483,
      "learning_rate": 0.00025670003505995814,
      "loss": 0.82421875,
      "step": 186
    },
    {
      "epoch": 1.60021436227224,
      "grad_norm": 0.07012197375297546,
      "learning_rate": 0.0002561764094042791,
      "loss": 0.78277587890625,
      "step": 187
    },
    {
      "epoch": 1.6087888531618435,
      "grad_norm": 0.05907281115651131,
      "learning_rate": 0.000255650342943412,
      "loss": 0.78656005859375,
      "step": 188
    },
    {
      "epoch": 1.617363344051447,
      "grad_norm": 0.05288393422961235,
      "learning_rate": 0.00025512185253330683,
      "loss": 0.805755615234375,
      "step": 189
    },
    {
      "epoch": 1.6259378349410505,
      "grad_norm": 0.0588788241147995,
      "learning_rate": 0.00025459095510758066,
      "loss": 0.83673095703125,
      "step": 190
    },
    {
      "epoch": 1.6345123258306538,
      "grad_norm": 0.057739127427339554,
      "learning_rate": 0.00025405766767697466,
      "loss": 0.749908447265625,
      "step": 191
    },
    {
      "epoch": 1.6430868167202572,
      "grad_norm": 0.06372378021478653,
      "learning_rate": 0.00025352200732880933,
      "loss": 0.756103515625,
      "step": 192
    },
    {
      "epoch": 1.6516613076098605,
      "grad_norm": 0.06043267622590065,
      "learning_rate": 0.00025298399122643717,
      "loss": 0.727081298828125,
      "step": 193
    },
    {
      "epoch": 1.660235798499464,
      "grad_norm": 0.06684987992048264,
      "learning_rate": 0.00025244363660869234,
      "loss": 0.75506591796875,
      "step": 194
    },
    {
      "epoch": 1.6688102893890675,
      "grad_norm": 0.057151395827531815,
      "learning_rate": 0.00025190096078933855,
      "loss": 0.780609130859375,
      "step": 195
    },
    {
      "epoch": 1.677384780278671,
      "grad_norm": 0.057108089327812195,
      "learning_rate": 0.0002513559811565144,
      "loss": 0.709991455078125,
      "step": 196
    },
    {
      "epoch": 1.6859592711682745,
      "grad_norm": 0.05186142772436142,
      "learning_rate": 0.0002508087151721758,
      "loss": 0.6963882446289062,
      "step": 197
    },
    {
      "epoch": 1.694533762057878,
      "grad_norm": 0.07331037521362305,
      "learning_rate": 0.000250259180371537,
      "loss": 0.81683349609375,
      "step": 198
    },
    {
      "epoch": 1.7031082529474812,
      "grad_norm": 0.06463269144296646,
      "learning_rate": 0.00024970739436250847,
      "loss": 0.84393310546875,
      "step": 199
    },
    {
      "epoch": 1.7116827438370845,
      "grad_norm": 0.06651589274406433,
      "learning_rate": 0.0002491533748251326,
      "loss": 0.7808837890625,
      "step": 200
    },
    {
      "epoch": 1.720257234726688,
      "grad_norm": 0.0648699477314949,
      "learning_rate": 0.0002485971395110174,
      "loss": 0.82635498046875,
      "step": 201
    },
    {
      "epoch": 1.7288317256162915,
      "grad_norm": 0.0809793621301651,
      "learning_rate": 0.0002480387062427678,
      "loss": 0.801605224609375,
      "step": 202
    },
    {
      "epoch": 1.737406216505895,
      "grad_norm": 0.07216158509254456,
      "learning_rate": 0.0002474780929134142,
      "loss": 0.8221435546875,
      "step": 203
    },
    {
      "epoch": 1.7459807073954985,
      "grad_norm": 0.060233864933252335,
      "learning_rate": 0.00024691531748583954,
      "loss": 0.86334228515625,
      "step": 204
    },
    {
      "epoch": 1.754555198285102,
      "grad_norm": 0.07268873602151871,
      "learning_rate": 0.00024635039799220364,
      "loss": 0.80535888671875,
      "step": 205
    },
    {
      "epoch": 1.7631296891747053,
      "grad_norm": 0.06778984516859055,
      "learning_rate": 0.0002457833525333652,
      "loss": 0.7625732421875,
      "step": 206
    },
    {
      "epoch": 1.7717041800643085,
      "grad_norm": 0.05779169127345085,
      "learning_rate": 0.0002452141992783021,
      "loss": 0.703765869140625,
      "step": 207
    },
    {
      "epoch": 1.780278670953912,
      "grad_norm": 0.062000446021556854,
      "learning_rate": 0.00024464295646352925,
      "loss": 0.8751220703125,
      "step": 208
    },
    {
      "epoch": 1.7888531618435155,
      "grad_norm": 0.05863572657108307,
      "learning_rate": 0.000244069642392514,
      "loss": 0.79736328125,
      "step": 209
    },
    {
      "epoch": 1.797427652733119,
      "grad_norm": 0.0692872405052185,
      "learning_rate": 0.00024349427543508983,
      "loss": 0.77813720703125,
      "step": 210
    },
    {
      "epoch": 1.8060021436227225,
      "grad_norm": 0.06259209662675858,
      "learning_rate": 0.00024291687402686778,
      "loss": 0.68255615234375,
      "step": 211
    },
    {
      "epoch": 1.814576634512326,
      "grad_norm": 0.057895176112651825,
      "learning_rate": 0.00024233745666864582,
      "loss": 0.71221923828125,
      "step": 212
    },
    {
      "epoch": 1.8231511254019293,
      "grad_norm": 0.06580907106399536,
      "learning_rate": 0.00024175604192581572,
      "loss": 0.84161376953125,
      "step": 213
    },
    {
      "epoch": 1.8317256162915327,
      "grad_norm": 0.05801098793745041,
      "learning_rate": 0.00024117264842776862,
      "loss": 0.791473388671875,
      "step": 214
    },
    {
      "epoch": 1.840300107181136,
      "grad_norm": 0.07300081104040146,
      "learning_rate": 0.00024058729486729787,
      "loss": 0.799285888671875,
      "step": 215
    },
    {
      "epoch": 1.8488745980707395,
      "grad_norm": 0.06187094748020172,
      "learning_rate": 0.00023999999999999998,
      "loss": 0.7302398681640625,
      "step": 216
    },
    {
      "epoch": 1.857449088960343,
      "grad_norm": 0.05715322121977806,
      "learning_rate": 0.00023941078264367406,
      "loss": 0.6843795776367188,
      "step": 217
    },
    {
      "epoch": 1.8660235798499465,
      "grad_norm": 0.06947656720876694,
      "learning_rate": 0.0002388196616777184,
      "loss": 0.735931396484375,
      "step": 218
    },
    {
      "epoch": 1.87459807073955,
      "grad_norm": 0.05428263545036316,
      "learning_rate": 0.00023822665604252585,
      "loss": 0.720184326171875,
      "step": 219
    },
    {
      "epoch": 1.8831725616291533,
      "grad_norm": 0.06101204454898834,
      "learning_rate": 0.00023763178473887688,
      "loss": 0.800445556640625,
      "step": 220
    },
    {
      "epoch": 1.8917470525187567,
      "grad_norm": 0.057823944836854935,
      "learning_rate": 0.00023703506682733075,
      "loss": 0.6990814208984375,
      "step": 221
    },
    {
      "epoch": 1.90032154340836,
      "grad_norm": 0.06676323711872101,
      "learning_rate": 0.00023643652142761484,
      "loss": 0.75115966796875,
      "step": 222
    },
    {
      "epoch": 1.9088960342979635,
      "grad_norm": 0.055982571095228195,
      "learning_rate": 0.00023583616771801172,
      "loss": 0.791290283203125,
      "step": 223
    },
    {
      "epoch": 1.917470525187567,
      "grad_norm": 0.06258241087198257,
      "learning_rate": 0.00023523402493474507,
      "loss": 0.729827880859375,
      "step": 224
    },
    {
      "epoch": 1.9260450160771705,
      "grad_norm": 0.05538873374462128,
      "learning_rate": 0.00023463011237136327,
      "loss": 0.8497467041015625,
      "step": 225
    },
    {
      "epoch": 1.934619506966774,
      "grad_norm": 0.0817316472530365,
      "learning_rate": 0.00023402444937812078,
      "loss": 0.86444091796875,
      "step": 226
    },
    {
      "epoch": 1.9431939978563773,
      "grad_norm": 0.0656244158744812,
      "learning_rate": 0.00023341705536135873,
      "loss": 0.747467041015625,
      "step": 227
    },
    {
      "epoch": 1.9517684887459807,
      "grad_norm": 0.0779951885342598,
      "learning_rate": 0.00023280794978288252,
      "loss": 0.7626953125,
      "step": 228
    },
    {
      "epoch": 1.960342979635584,
      "grad_norm": 0.06638413667678833,
      "learning_rate": 0.00023219715215933877,
      "loss": 0.7542724609375,
      "step": 229
    },
    {
      "epoch": 1.9689174705251875,
      "grad_norm": 0.061039846390485764,
      "learning_rate": 0.00023158468206158956,
      "loss": 0.82269287109375,
      "step": 230
    },
    {
      "epoch": 1.977491961414791,
      "grad_norm": 0.07643549144268036,
      "learning_rate": 0.00023097055911408575,
      "loss": 0.76287841796875,
      "step": 231
    },
    {
      "epoch": 1.9860664523043945,
      "grad_norm": 0.06347046047449112,
      "learning_rate": 0.00023035480299423764,
      "loss": 0.77911376953125,
      "step": 232
    },
    {
      "epoch": 1.994640943193998,
      "grad_norm": 0.06625408679246902,
      "learning_rate": 0.00022973743343178516,
      "loss": 0.6657141447067261,
      "step": 233
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.05505237728357315,
      "learning_rate": 0.000229118470208165,
      "loss": 0.7398681640625,
      "step": 234
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.7862955927848816,
      "eval_runtime": 1.4786,
      "eval_samples_per_second": 2.029,
      "eval_steps_per_second": 0.676,
      "step": 234
    },
    {
      "epoch": 2.0085744908896035,
      "grad_norm": 0.06103143468499184,
      "learning_rate": 0.00022849793315587728,
      "loss": 0.790924072265625,
      "step": 235
    },
    {
      "epoch": 2.017148981779207,
      "grad_norm": 0.05422452092170715,
      "learning_rate": 0.00022787584215784996,
      "loss": 0.80841064453125,
      "step": 236
    },
    {
      "epoch": 2.0257234726688105,
      "grad_norm": 0.06267113238573074,
      "learning_rate": 0.00022725221714680162,
      "loss": 0.724853515625,
      "step": 237
    },
    {
      "epoch": 2.0342979635584135,
      "grad_norm": 0.057212475687265396,
      "learning_rate": 0.00022662707810460302,
      "loss": 0.7371826171875,
      "step": 238
    },
    {
      "epoch": 2.042872454448017,
      "grad_norm": 0.06043396517634392,
      "learning_rate": 0.00022600044506163662,
      "loss": 0.8128662109375,
      "step": 239
    },
    {
      "epoch": 2.0514469453376205,
      "grad_norm": 0.056173279881477356,
      "learning_rate": 0.00022537233809615488,
      "loss": 0.744598388671875,
      "step": 240
    },
    {
      "epoch": 2.060021436227224,
      "grad_norm": 0.06675903499126434,
      "learning_rate": 0.00022474277733363702,
      "loss": 0.75701904296875,
      "step": 241
    },
    {
      "epoch": 2.0685959271168275,
      "grad_norm": 0.07741881906986237,
      "learning_rate": 0.000224111782946144,
      "loss": 0.7635498046875,
      "step": 242
    },
    {
      "epoch": 2.077170418006431,
      "grad_norm": 0.0610402449965477,
      "learning_rate": 0.0002234793751516722,
      "loss": 0.783172607421875,
      "step": 243
    },
    {
      "epoch": 2.0857449088960345,
      "grad_norm": 0.06592462211847305,
      "learning_rate": 0.00022284557421350587,
      "loss": 0.74615478515625,
      "step": 244
    },
    {
      "epoch": 2.0943193997856375,
      "grad_norm": 0.06363070011138916,
      "learning_rate": 0.00022221040043956733,
      "loss": 0.78350830078125,
      "step": 245
    },
    {
      "epoch": 2.102893890675241,
      "grad_norm": 0.056576941162347794,
      "learning_rate": 0.00022157387418176682,
      "loss": 0.8416748046875,
      "step": 246
    },
    {
      "epoch": 2.1114683815648445,
      "grad_norm": 0.07927252352237701,
      "learning_rate": 0.00022093601583535018,
      "loss": 0.81671142578125,
      "step": 247
    },
    {
      "epoch": 2.120042872454448,
      "grad_norm": 0.03795560821890831,
      "learning_rate": 0.00022029684583824526,
      "loss": 0.7349853515625,
      "step": 248
    },
    {
      "epoch": 2.1286173633440515,
      "grad_norm": 0.0839502140879631,
      "learning_rate": 0.0002196563846704072,
      "loss": 0.78277587890625,
      "step": 249
    },
    {
      "epoch": 2.137191854233655,
      "grad_norm": 0.06078169494867325,
      "learning_rate": 0.000219014652853162,
      "loss": 0.696929931640625,
      "step": 250
    },
    {
      "epoch": 2.1457663451232585,
      "grad_norm": 0.08530406653881073,
      "learning_rate": 0.00021837167094854943,
      "loss": 0.73931884765625,
      "step": 251
    },
    {
      "epoch": 2.154340836012862,
      "grad_norm": 0.09302239120006561,
      "learning_rate": 0.00021772745955866374,
      "loss": 0.762451171875,
      "step": 252
    },
    {
      "epoch": 2.162915326902465,
      "grad_norm": 0.05976001173257828,
      "learning_rate": 0.00021708203932499365,
      "loss": 0.86273193359375,
      "step": 253
    },
    {
      "epoch": 2.1714898177920685,
      "grad_norm": 0.08482329547405243,
      "learning_rate": 0.0002164354309277613,
      "loss": 0.8148193359375,
      "step": 254
    },
    {
      "epoch": 2.180064308681672,
      "grad_norm": 0.0532805360853672,
      "learning_rate": 0.00021578765508525901,
      "loss": 0.7078857421875,
      "step": 255
    },
    {
      "epoch": 2.1886387995712755,
      "grad_norm": 0.08859632164239883,
      "learning_rate": 0.00021513873255318603,
      "loss": 0.722564697265625,
      "step": 256
    },
    {
      "epoch": 2.197213290460879,
      "grad_norm": 0.07436488568782806,
      "learning_rate": 0.00021448868412398311,
      "loss": 0.73931884765625,
      "step": 257
    },
    {
      "epoch": 2.2057877813504825,
      "grad_norm": 0.05879945307970047,
      "learning_rate": 0.00021383753062616652,
      "loss": 0.760894775390625,
      "step": 258
    },
    {
      "epoch": 2.214362272240086,
      "grad_norm": 0.07403898984193802,
      "learning_rate": 0.00021318529292366052,
      "loss": 0.75128173828125,
      "step": 259
    },
    {
      "epoch": 2.222936763129689,
      "grad_norm": 0.05317135527729988,
      "learning_rate": 0.00021253199191512885,
      "loss": 0.75799560546875,
      "step": 260
    },
    {
      "epoch": 2.2315112540192925,
      "grad_norm": 0.06778088212013245,
      "learning_rate": 0.00021187764853330512,
      "loss": 0.711822509765625,
      "step": 261
    },
    {
      "epoch": 2.240085744908896,
      "grad_norm": 0.05689414218068123,
      "learning_rate": 0.00021122228374432234,
      "loss": 0.799072265625,
      "step": 262
    },
    {
      "epoch": 2.2486602357984995,
      "grad_norm": 0.07835965603590012,
      "learning_rate": 0.00021056591854704077,
      "loss": 0.809661865234375,
      "step": 263
    },
    {
      "epoch": 2.257234726688103,
      "grad_norm": 0.05032290890812874,
      "learning_rate": 0.0002099085739723751,
      "loss": 0.757415771484375,
      "step": 264
    },
    {
      "epoch": 2.2658092175777065,
      "grad_norm": 0.08543003350496292,
      "learning_rate": 0.000209250271082621,
      "loss": 0.755615234375,
      "step": 265
    },
    {
      "epoch": 2.27438370846731,
      "grad_norm": 0.06288940459489822,
      "learning_rate": 0.0002085910309707798,
      "loss": 0.72991943359375,
      "step": 266
    },
    {
      "epoch": 2.282958199356913,
      "grad_norm": 0.06825575977563858,
      "learning_rate": 0.00020793087475988288,
      "loss": 0.73663330078125,
      "step": 267
    },
    {
      "epoch": 2.2915326902465165,
      "grad_norm": 0.07281676679849625,
      "learning_rate": 0.00020726982360231482,
      "loss": 0.79461669921875,
      "step": 268
    },
    {
      "epoch": 2.30010718113612,
      "grad_norm": 0.05141405016183853,
      "learning_rate": 0.00020660789867913546,
      "loss": 0.682525634765625,
      "step": 269
    },
    {
      "epoch": 2.3086816720257235,
      "grad_norm": 0.06086786091327667,
      "learning_rate": 0.00020594512119940164,
      "loss": 0.72991943359375,
      "step": 270
    },
    {
      "epoch": 2.317256162915327,
      "grad_norm": 0.06365898996591568,
      "learning_rate": 0.00020528151239948713,
      "loss": 0.76580810546875,
      "step": 271
    },
    {
      "epoch": 2.3258306538049305,
      "grad_norm": 0.0594882071018219,
      "learning_rate": 0.00020461709354240262,
      "loss": 0.79718017578125,
      "step": 272
    },
    {
      "epoch": 2.334405144694534,
      "grad_norm": 0.06668376177549362,
      "learning_rate": 0.00020395188591711418,
      "loss": 0.828155517578125,
      "step": 273
    },
    {
      "epoch": 2.342979635584137,
      "grad_norm": 0.06848332285881042,
      "learning_rate": 0.00020328591083786102,
      "loss": 0.7747802734375,
      "step": 274
    },
    {
      "epoch": 2.3515541264737405,
      "grad_norm": 0.06711100786924362,
      "learning_rate": 0.00020261918964347296,
      "loss": 0.75750732421875,
      "step": 275
    },
    {
      "epoch": 2.360128617363344,
      "grad_norm": 0.07434961944818497,
      "learning_rate": 0.00020195174369668637,
      "loss": 0.7769775390625,
      "step": 276
    },
    {
      "epoch": 2.3687031082529475,
      "grad_norm": 0.08133561164140701,
      "learning_rate": 0.00020128359438345968,
      "loss": 0.759765625,
      "step": 277
    },
    {
      "epoch": 2.377277599142551,
      "grad_norm": 0.0581471286714077,
      "learning_rate": 0.0002006147631122883,
      "loss": 0.741943359375,
      "step": 278
    },
    {
      "epoch": 2.3858520900321545,
      "grad_norm": 0.05766907334327698,
      "learning_rate": 0.0001999452713135187,
      "loss": 0.788238525390625,
      "step": 279
    },
    {
      "epoch": 2.394426580921758,
      "grad_norm": 0.0559244342148304,
      "learning_rate": 0.00019927514043866125,
      "loss": 0.80804443359375,
      "step": 280
    },
    {
      "epoch": 2.403001071811361,
      "grad_norm": 0.058058515191078186,
      "learning_rate": 0.00019860439195970375,
      "loss": 0.832550048828125,
      "step": 281
    },
    {
      "epoch": 2.4115755627009645,
      "grad_norm": 0.06110988184809685,
      "learning_rate": 0.00019793304736842257,
      "loss": 0.77239990234375,
      "step": 282
    },
    {
      "epoch": 2.420150053590568,
      "grad_norm": 0.05869636312127113,
      "learning_rate": 0.00019726112817569465,
      "loss": 0.7701416015625,
      "step": 283
    },
    {
      "epoch": 2.4287245444801715,
      "grad_norm": 0.05531616508960724,
      "learning_rate": 0.0001965886559108079,
      "loss": 0.75238037109375,
      "step": 284
    },
    {
      "epoch": 2.437299035369775,
      "grad_norm": 0.0565049834549427,
      "learning_rate": 0.00019591565212077148,
      "loss": 0.738189697265625,
      "step": 285
    },
    {
      "epoch": 2.4458735262593785,
      "grad_norm": 0.04328267648816109,
      "learning_rate": 0.00019524213836962542,
      "loss": 0.7292633056640625,
      "step": 286
    },
    {
      "epoch": 2.454448017148982,
      "grad_norm": 0.048756156116724014,
      "learning_rate": 0.00019456813623774973,
      "loss": 0.727874755859375,
      "step": 287
    },
    {
      "epoch": 2.463022508038585,
      "grad_norm": 0.04933273792266846,
      "learning_rate": 0.00019389366732117276,
      "loss": 0.72344970703125,
      "step": 288
    },
    {
      "epoch": 2.4715969989281885,
      "grad_norm": 0.05126006901264191,
      "learning_rate": 0.00019321875323087935,
      "loss": 0.71636962890625,
      "step": 289
    },
    {
      "epoch": 2.480171489817792,
      "grad_norm": 0.04809730127453804,
      "learning_rate": 0.00019254341559211843,
      "loss": 0.80853271484375,
      "step": 290
    },
    {
      "epoch": 2.4887459807073955,
      "grad_norm": 0.05310454219579697,
      "learning_rate": 0.00019186767604370997,
      "loss": 0.6672821044921875,
      "step": 291
    },
    {
      "epoch": 2.497320471596999,
      "grad_norm": 0.057021502405405045,
      "learning_rate": 0.00019119155623735184,
      "loss": 0.73583984375,
      "step": 292
    },
    {
      "epoch": 2.5058949624866025,
      "grad_norm": 0.049270566552877426,
      "learning_rate": 0.00019051507783692575,
      "loss": 0.745330810546875,
      "step": 293
    },
    {
      "epoch": 2.514469453376206,
      "grad_norm": 0.05883350223302841,
      "learning_rate": 0.00018983826251780354,
      "loss": 0.70928955078125,
      "step": 294
    },
    {
      "epoch": 2.523043944265809,
      "grad_norm": 0.05092175304889679,
      "learning_rate": 0.00018916113196615214,
      "loss": 0.759429931640625,
      "step": 295
    },
    {
      "epoch": 2.5316184351554125,
      "grad_norm": 0.07195451110601425,
      "learning_rate": 0.00018848370787823932,
      "loss": 0.715576171875,
      "step": 296
    },
    {
      "epoch": 2.540192926045016,
      "grad_norm": 0.04519352689385414,
      "learning_rate": 0.000187806011959738,
      "loss": 0.7615966796875,
      "step": 297
    },
    {
      "epoch": 2.5487674169346195,
      "grad_norm": 0.052036102861166,
      "learning_rate": 0.0001871280659250308,
      "loss": 0.86529541015625,
      "step": 298
    },
    {
      "epoch": 2.557341907824223,
      "grad_norm": 0.052507560700178146,
      "learning_rate": 0.00018644989149651476,
      "loss": 0.678070068359375,
      "step": 299
    },
    {
      "epoch": 2.5659163987138265,
      "grad_norm": 0.060118742287158966,
      "learning_rate": 0.00018577151040390484,
      "loss": 0.74627685546875,
      "step": 300
    },
    {
      "epoch": 2.57449088960343,
      "grad_norm": 0.06237257272005081,
      "learning_rate": 0.00018509294438353777,
      "loss": 0.689727783203125,
      "step": 301
    },
    {
      "epoch": 2.583065380493033,
      "grad_norm": 0.04105701670050621,
      "learning_rate": 0.00018441421517767577,
      "loss": 0.678955078125,
      "step": 302
    },
    {
      "epoch": 2.5916398713826365,
      "grad_norm": 0.06602825224399567,
      "learning_rate": 0.00018373534453380966,
      "loss": 0.791748046875,
      "step": 303
    },
    {
      "epoch": 2.60021436227224,
      "grad_norm": 0.052285946905612946,
      "learning_rate": 0.0001830563542039621,
      "loss": 0.75091552734375,
      "step": 304
    },
    {
      "epoch": 2.6087888531618435,
      "grad_norm": 0.05906175076961517,
      "learning_rate": 0.0001823772659439909,
      "loss": 0.75640869140625,
      "step": 305
    },
    {
      "epoch": 2.617363344051447,
      "grad_norm": 0.04906484857201576,
      "learning_rate": 0.00018169810151289143,
      "loss": 0.774383544921875,
      "step": 306
    },
    {
      "epoch": 2.6259378349410505,
      "grad_norm": 0.0505952313542366,
      "learning_rate": 0.00018101888267209987,
      "loss": 0.80377197265625,
      "step": 307
    },
    {
      "epoch": 2.634512325830654,
      "grad_norm": 0.06203756108880043,
      "learning_rate": 0.00018033963118479566,
      "loss": 0.7200927734375,
      "step": 308
    },
    {
      "epoch": 2.643086816720257,
      "grad_norm": 0.055566251277923584,
      "learning_rate": 0.00017966036881520437,
      "loss": 0.72406005859375,
      "step": 309
    },
    {
      "epoch": 2.6516613076098605,
      "grad_norm": 0.049531515687704086,
      "learning_rate": 0.00017898111732790012,
      "loss": 0.698394775390625,
      "step": 310
    },
    {
      "epoch": 2.660235798499464,
      "grad_norm": 0.05577662214636803,
      "learning_rate": 0.0001783018984871086,
      "loss": 0.7239990234375,
      "step": 311
    },
    {
      "epoch": 2.6688102893890675,
      "grad_norm": 0.04533509165048599,
      "learning_rate": 0.00017762273405600907,
      "loss": 0.749542236328125,
      "step": 312
    },
    {
      "epoch": 2.677384780278671,
      "grad_norm": 0.05171598494052887,
      "learning_rate": 0.00017694364579603784,
      "loss": 0.682830810546875,
      "step": 313
    },
    {
      "epoch": 2.6859592711682745,
      "grad_norm": 0.039375439286231995,
      "learning_rate": 0.00017626465546619036,
      "loss": 0.6707992553710938,
      "step": 314
    },
    {
      "epoch": 2.694533762057878,
      "grad_norm": 0.0612909272313118,
      "learning_rate": 0.00017558578482232423,
      "loss": 0.785400390625,
      "step": 315
    },
    {
      "epoch": 2.703108252947481,
      "grad_norm": 0.050703588873147964,
      "learning_rate": 0.00017490705561646223,
      "loss": 0.813232421875,
      "step": 316
    },
    {
      "epoch": 2.7116827438370845,
      "grad_norm": 0.05564006417989731,
      "learning_rate": 0.00017422848959609518,
      "loss": 0.75201416015625,
      "step": 317
    },
    {
      "epoch": 2.720257234726688,
      "grad_norm": 0.05210727080702782,
      "learning_rate": 0.00017355010850348519,
      "loss": 0.794677734375,
      "step": 318
    },
    {
      "epoch": 2.7288317256162915,
      "grad_norm": 0.056916072964668274,
      "learning_rate": 0.00017287193407496918,
      "loss": 0.771270751953125,
      "step": 319
    },
    {
      "epoch": 2.737406216505895,
      "grad_norm": 0.05529365688562393,
      "learning_rate": 0.00017219398804026203,
      "loss": 0.79254150390625,
      "step": 320
    },
    {
      "epoch": 2.7459807073954985,
      "grad_norm": 0.05775995925068855,
      "learning_rate": 0.00017151629212176062,
      "loss": 0.83331298828125,
      "step": 321
    },
    {
      "epoch": 2.754555198285102,
      "grad_norm": 0.054613176733255386,
      "learning_rate": 0.0001708388680338478,
      "loss": 0.77593994140625,
      "step": 322
    },
    {
      "epoch": 2.763129689174705,
      "grad_norm": 0.06064334139227867,
      "learning_rate": 0.00017016173748219649,
      "loss": 0.73480224609375,
      "step": 323
    },
    {
      "epoch": 2.7717041800643085,
      "grad_norm": 0.05133575201034546,
      "learning_rate": 0.00016948492216307422,
      "loss": 0.67864990234375,
      "step": 324
    },
    {
      "epoch": 2.780278670953912,
      "grad_norm": 0.05167587846517563,
      "learning_rate": 0.00016880844376264818,
      "loss": 0.846923828125,
      "step": 325
    },
    {
      "epoch": 2.7888531618435155,
      "grad_norm": 0.059591539204120636,
      "learning_rate": 0.00016813232395629003,
      "loss": 0.76953125,
      "step": 326
    },
    {
      "epoch": 2.797427652733119,
      "grad_norm": 0.05196233466267586,
      "learning_rate": 0.0001674565844078816,
      "loss": 0.7489852905273438,
      "step": 327
    },
    {
      "epoch": 2.8060021436227225,
      "grad_norm": 0.0592251718044281,
      "learning_rate": 0.00016678124676912067,
      "loss": 0.65802001953125,
      "step": 328
    },
    {
      "epoch": 2.814576634512326,
      "grad_norm": 0.05577041581273079,
      "learning_rate": 0.00016610633267882726,
      "loss": 0.686981201171875,
      "step": 329
    },
    {
      "epoch": 2.823151125401929,
      "grad_norm": 0.059413522481918335,
      "learning_rate": 0.0001654318637622502,
      "loss": 0.81402587890625,
      "step": 330
    },
    {
      "epoch": 2.831725616291533,
      "grad_norm": 0.056665509939193726,
      "learning_rate": 0.00016475786163037452,
      "loss": 0.764068603515625,
      "step": 331
    },
    {
      "epoch": 2.840300107181136,
      "grad_norm": 0.0652475655078888,
      "learning_rate": 0.0001640843478792285,
      "loss": 0.772918701171875,
      "step": 332
    },
    {
      "epoch": 2.8488745980707395,
      "grad_norm": 0.04707980528473854,
      "learning_rate": 0.00016341134408919211,
      "loss": 0.7040786743164062,
      "step": 333
    },
    {
      "epoch": 2.857449088960343,
      "grad_norm": 0.06293417513370514,
      "learning_rate": 0.00016273887182430535,
      "loss": 0.6616973876953125,
      "step": 334
    },
    {
      "epoch": 2.8660235798499465,
      "grad_norm": 0.05915632098913193,
      "learning_rate": 0.00016206695263157745,
      "loss": 0.709564208984375,
      "step": 335
    },
    {
      "epoch": 2.87459807073955,
      "grad_norm": 0.06776172667741776,
      "learning_rate": 0.00016139560804029625,
      "loss": 0.696533203125,
      "step": 336
    },
    {
      "epoch": 2.883172561629153,
      "grad_norm": 0.04959143325686455,
      "learning_rate": 0.00016072485956133875,
      "loss": 0.772613525390625,
      "step": 337
    },
    {
      "epoch": 2.891747052518757,
      "grad_norm": 0.061431463807821274,
      "learning_rate": 0.00016005472868648132,
      "loss": 0.6756057739257812,
      "step": 338
    },
    {
      "epoch": 2.90032154340836,
      "grad_norm": 0.0535377599298954,
      "learning_rate": 0.00015938523688771163,
      "loss": 0.7255859375,
      "step": 339
    },
    {
      "epoch": 2.9088960342979635,
      "grad_norm": 0.05439278110861778,
      "learning_rate": 0.0001587164056165403,
      "loss": 0.766265869140625,
      "step": 340
    },
    {
      "epoch": 2.917470525187567,
      "grad_norm": 0.061761267483234406,
      "learning_rate": 0.0001580482563033136,
      "loss": 0.70556640625,
      "step": 341
    },
    {
      "epoch": 2.9260450160771705,
      "grad_norm": 0.05385347828269005,
      "learning_rate": 0.00015738081035652699,
      "loss": 0.8263702392578125,
      "step": 342
    },
    {
      "epoch": 2.934619506966774,
      "grad_norm": 0.07960601896047592,
      "learning_rate": 0.00015671408916213895,
      "loss": 0.83782958984375,
      "step": 343
    },
    {
      "epoch": 2.943193997856377,
      "grad_norm": 0.060974545776844025,
      "learning_rate": 0.00015604811408288585,
      "loss": 0.72247314453125,
      "step": 344
    },
    {
      "epoch": 2.951768488745981,
      "grad_norm": 0.0692184716463089,
      "learning_rate": 0.0001553829064575974,
      "loss": 0.7391357421875,
      "step": 345
    },
    {
      "epoch": 2.960342979635584,
      "grad_norm": 0.06272408366203308,
      "learning_rate": 0.0001547184876005129,
      "loss": 0.730377197265625,
      "step": 346
    },
    {
      "epoch": 2.9689174705251875,
      "grad_norm": 0.06329671293497086,
      "learning_rate": 0.00015405487880059839,
      "loss": 0.7974853515625,
      "step": 347
    },
    {
      "epoch": 2.977491961414791,
      "grad_norm": 0.06859585642814636,
      "learning_rate": 0.00015339210132086454,
      "loss": 0.7373046875,
      "step": 348
    },
    {
      "epoch": 2.9860664523043945,
      "grad_norm": 0.06763207167387009,
      "learning_rate": 0.0001527301763976852,
      "loss": 0.75408935546875,
      "step": 349
    },
    {
      "epoch": 2.994640943193998,
      "grad_norm": 0.05929490178823471,
      "learning_rate": 0.0001520691252401171,
      "loss": 0.6444427371025085,
      "step": 350
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.055816713720560074,
      "learning_rate": 0.0001514089690292202,
      "loss": 0.7152099609375,
      "step": 351
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.7686360478401184,
      "eval_runtime": 1.476,
      "eval_samples_per_second": 2.033,
      "eval_steps_per_second": 0.678,
      "step": 351
    },
    {
      "epoch": 3.0085744908896035,
      "grad_norm": 0.05138656497001648,
      "learning_rate": 0.00015074972891737903,
      "loss": 0.7680816650390625,
      "step": 352
    },
    {
      "epoch": 3.017148981779207,
      "grad_norm": 0.05292936787009239,
      "learning_rate": 0.0001500914260276249,
      "loss": 0.784393310546875,
      "step": 353
    },
    {
      "epoch": 3.0257234726688105,
      "grad_norm": 0.05731496214866638,
      "learning_rate": 0.00014943408145295925,
      "loss": 0.701812744140625,
      "step": 354
    },
    {
      "epoch": 3.0342979635584135,
      "grad_norm": 0.050040747970342636,
      "learning_rate": 0.00014877771625567763,
      "loss": 0.716033935546875,
      "step": 355
    },
    {
      "epoch": 3.042872454448017,
      "grad_norm": 0.0620463490486145,
      "learning_rate": 0.00014812235146669485,
      "loss": 0.7880859375,
      "step": 356
    },
    {
      "epoch": 3.0514469453376205,
      "grad_norm": 0.04854311794042587,
      "learning_rate": 0.00014746800808487117,
      "loss": 0.7237091064453125,
      "step": 357
    },
    {
      "epoch": 3.060021436227224,
      "grad_norm": 0.05635051056742668,
      "learning_rate": 0.00014681470707633945,
      "loss": 0.73406982421875,
      "step": 358
    },
    {
      "epoch": 3.0685959271168275,
      "grad_norm": 0.07214803993701935,
      "learning_rate": 0.00014616246937383345,
      "loss": 0.7393798828125,
      "step": 359
    },
    {
      "epoch": 3.077170418006431,
      "grad_norm": 0.058432698249816895,
      "learning_rate": 0.00014551131587601683,
      "loss": 0.760528564453125,
      "step": 360
    },
    {
      "epoch": 3.0857449088960345,
      "grad_norm": 0.056913599371910095,
      "learning_rate": 0.00014486126744681394,
      "loss": 0.724609375,
      "step": 361
    },
    {
      "epoch": 3.0943193997856375,
      "grad_norm": 0.05305374041199684,
      "learning_rate": 0.00014421234491474095,
      "loss": 0.7608642578125,
      "step": 362
    },
    {
      "epoch": 3.102893890675241,
      "grad_norm": 0.06576422601938248,
      "learning_rate": 0.0001435645690722387,
      "loss": 0.81781005859375,
      "step": 363
    },
    {
      "epoch": 3.1114683815648445,
      "grad_norm": 0.055945251137018204,
      "learning_rate": 0.00014291796067500632,
      "loss": 0.79266357421875,
      "step": 364
    },
    {
      "epoch": 3.120042872454448,
      "grad_norm": 0.043631911277770996,
      "learning_rate": 0.00014227254044133628,
      "loss": 0.716552734375,
      "step": 365
    },
    {
      "epoch": 3.1286173633440515,
      "grad_norm": 0.0694379135966301,
      "learning_rate": 0.00014162832905145056,
      "loss": 0.760009765625,
      "step": 366
    },
    {
      "epoch": 3.137191854233655,
      "grad_norm": 0.05540696904063225,
      "learning_rate": 0.00014098534714683796,
      "loss": 0.676116943359375,
      "step": 367
    },
    {
      "epoch": 3.1457663451232585,
      "grad_norm": 0.07162007689476013,
      "learning_rate": 0.00014034361532959283,
      "loss": 0.71685791015625,
      "step": 368
    },
    {
      "epoch": 3.154340836012862,
      "grad_norm": 0.06378567963838577,
      "learning_rate": 0.00013970315416175473,
      "loss": 0.739837646484375,
      "step": 369
    },
    {
      "epoch": 3.162915326902465,
      "grad_norm": 0.06068071350455284,
      "learning_rate": 0.00013906398416464982,
      "loss": 0.840087890625,
      "step": 370
    },
    {
      "epoch": 3.1714898177920685,
      "grad_norm": 0.06196490302681923,
      "learning_rate": 0.0001384261258182332,
      "loss": 0.7926025390625,
      "step": 371
    },
    {
      "epoch": 3.180064308681672,
      "grad_norm": 0.04930365830659866,
      "learning_rate": 0.0001377895995604327,
      "loss": 0.6868896484375,
      "step": 372
    },
    {
      "epoch": 3.1886387995712755,
      "grad_norm": 0.06730048358440399,
      "learning_rate": 0.00013715442578649415,
      "loss": 0.7003173828125,
      "step": 373
    },
    {
      "epoch": 3.197213290460879,
      "grad_norm": 0.04527326300740242,
      "learning_rate": 0.00013652062484832776,
      "loss": 0.7171630859375,
      "step": 374
    },
    {
      "epoch": 3.2057877813504825,
      "grad_norm": 0.059825342148542404,
      "learning_rate": 0.000135888217053856,
      "loss": 0.739715576171875,
      "step": 375
    },
    {
      "epoch": 3.214362272240086,
      "grad_norm": 0.053285226225852966,
      "learning_rate": 0.00013525722266636298,
      "loss": 0.72894287109375,
      "step": 376
    },
    {
      "epoch": 3.222936763129689,
      "grad_norm": 0.06195559725165367,
      "learning_rate": 0.0001346276619038451,
      "loss": 0.7376708984375,
      "step": 377
    },
    {
      "epoch": 3.2315112540192925,
      "grad_norm": 0.05531533062458038,
      "learning_rate": 0.00013399955493836334,
      "loss": 0.692413330078125,
      "step": 378
    },
    {
      "epoch": 3.240085744908896,
      "grad_norm": 0.055787086486816406,
      "learning_rate": 0.00013337292189539695,
      "loss": 0.77734375,
      "step": 379
    },
    {
      "epoch": 3.2486602357984995,
      "grad_norm": 0.05260423570871353,
      "learning_rate": 0.00013274778285319834,
      "loss": 0.7879180908203125,
      "step": 380
    },
    {
      "epoch": 3.257234726688103,
      "grad_norm": 0.05745295435190201,
      "learning_rate": 0.00013212415784215003,
      "loss": 0.7371826171875,
      "step": 381
    },
    {
      "epoch": 3.2658092175777065,
      "grad_norm": 0.058583177626132965,
      "learning_rate": 0.00013150206684412271,
      "loss": 0.73309326171875,
      "step": 382
    },
    {
      "epoch": 3.27438370846731,
      "grad_norm": 0.05085247755050659,
      "learning_rate": 0.00013088152979183503,
      "loss": 0.709320068359375,
      "step": 383
    },
    {
      "epoch": 3.282958199356913,
      "grad_norm": 0.055643390864133835,
      "learning_rate": 0.0001302625665682148,
      "loss": 0.71612548828125,
      "step": 384
    },
    {
      "epoch": 3.2915326902465165,
      "grad_norm": 0.06260328739881516,
      "learning_rate": 0.0001296451970057623,
      "loss": 0.7724609375,
      "step": 385
    },
    {
      "epoch": 3.30010718113612,
      "grad_norm": 0.0570947639644146,
      "learning_rate": 0.00012902944088591424,
      "loss": 0.6644287109375,
      "step": 386
    },
    {
      "epoch": 3.3086816720257235,
      "grad_norm": 0.05135821923613548,
      "learning_rate": 0.0001284153179384104,
      "loss": 0.710906982421875,
      "step": 387
    },
    {
      "epoch": 3.317256162915327,
      "grad_norm": 0.0693868026137352,
      "learning_rate": 0.00012780284784066125,
      "loss": 0.74493408203125,
      "step": 388
    },
    {
      "epoch": 3.3258306538049305,
      "grad_norm": 0.04338880628347397,
      "learning_rate": 0.0001271920502171175,
      "loss": 0.777374267578125,
      "step": 389
    },
    {
      "epoch": 3.334405144694534,
      "grad_norm": 0.07024918496608734,
      "learning_rate": 0.0001265829446386413,
      "loss": 0.807464599609375,
      "step": 390
    },
    {
      "epoch": 3.342979635584137,
      "grad_norm": 0.05625499039888382,
      "learning_rate": 0.00012597555062187919,
      "loss": 0.7550048828125,
      "step": 391
    },
    {
      "epoch": 3.3515541264737405,
      "grad_norm": 0.06183150038123131,
      "learning_rate": 0.00012536988762863673,
      "loss": 0.73748779296875,
      "step": 392
    },
    {
      "epoch": 3.360128617363344,
      "grad_norm": 0.054574184119701385,
      "learning_rate": 0.0001247659750652549,
      "loss": 0.75640869140625,
      "step": 393
    },
    {
      "epoch": 3.3687031082529475,
      "grad_norm": 0.07003854960203171,
      "learning_rate": 0.0001241638322819883,
      "loss": 0.74090576171875,
      "step": 394
    },
    {
      "epoch": 3.377277599142551,
      "grad_norm": 0.05656116083264351,
      "learning_rate": 0.0001235634785723852,
      "loss": 0.72259521484375,
      "step": 395
    },
    {
      "epoch": 3.3858520900321545,
      "grad_norm": 0.05788353458046913,
      "learning_rate": 0.0001229649331726692,
      "loss": 0.768829345703125,
      "step": 396
    },
    {
      "epoch": 3.394426580921758,
      "grad_norm": 0.05563675984740257,
      "learning_rate": 0.00012236821526112309,
      "loss": 0.78729248046875,
      "step": 397
    },
    {
      "epoch": 3.403001071811361,
      "grad_norm": 0.0542960986495018,
      "learning_rate": 0.00012177334395747416,
      "loss": 0.811859130859375,
      "step": 398
    },
    {
      "epoch": 3.4115755627009645,
      "grad_norm": 0.05454206466674805,
      "learning_rate": 0.00012118033832228162,
      "loss": 0.75323486328125,
      "step": 399
    },
    {
      "epoch": 3.420150053590568,
      "grad_norm": 0.05685446783900261,
      "learning_rate": 0.00012058921735632597,
      "loss": 0.75006103515625,
      "step": 400
    },
    {
      "epoch": 3.4287245444801715,
      "grad_norm": 0.05096472427248955,
      "learning_rate": 0.00012000000000000003,
      "loss": 0.7333984375,
      "step": 401
    },
    {
      "epoch": 3.437299035369775,
      "grad_norm": 0.05850978568196297,
      "learning_rate": 0.00011941270513270217,
      "loss": 0.719024658203125,
      "step": 402
    },
    {
      "epoch": 3.4458735262593785,
      "grad_norm": 0.040631793439388275,
      "learning_rate": 0.00011882735157223134,
      "loss": 0.7116241455078125,
      "step": 403
    },
    {
      "epoch": 3.454448017148982,
      "grad_norm": 0.05659075453877449,
      "learning_rate": 0.00011824395807418426,
      "loss": 0.71026611328125,
      "step": 404
    },
    {
      "epoch": 3.463022508038585,
      "grad_norm": 0.048608481884002686,
      "learning_rate": 0.0001176625433313542,
      "loss": 0.70684814453125,
      "step": 405
    },
    {
      "epoch": 3.4715969989281885,
      "grad_norm": 0.04655507206916809,
      "learning_rate": 0.00011708312597313221,
      "loss": 0.6976318359375,
      "step": 406
    },
    {
      "epoch": 3.480171489817792,
      "grad_norm": 0.05062742903828621,
      "learning_rate": 0.0001165057245649102,
      "loss": 0.78924560546875,
      "step": 407
    },
    {
      "epoch": 3.4887459807073955,
      "grad_norm": 0.047387462109327316,
      "learning_rate": 0.00011593035760748603,
      "loss": 0.6509857177734375,
      "step": 408
    },
    {
      "epoch": 3.497320471596999,
      "grad_norm": 0.05388082563877106,
      "learning_rate": 0.00011535704353647073,
      "loss": 0.71783447265625,
      "step": 409
    },
    {
      "epoch": 3.5058949624866025,
      "grad_norm": 0.04968787357211113,
      "learning_rate": 0.00011478580072169787,
      "loss": 0.72930908203125,
      "step": 410
    },
    {
      "epoch": 3.514469453376206,
      "grad_norm": 0.05020741745829582,
      "learning_rate": 0.00011421664746663484,
      "loss": 0.69207763671875,
      "step": 411
    },
    {
      "epoch": 3.523043944265809,
      "grad_norm": 0.053264692425727844,
      "learning_rate": 0.0001136496020077964,
      "loss": 0.7415771484375,
      "step": 412
    },
    {
      "epoch": 3.5316184351554125,
      "grad_norm": 0.05593063309788704,
      "learning_rate": 0.00011308468251416045,
      "loss": 0.698089599609375,
      "step": 413
    },
    {
      "epoch": 3.540192926045016,
      "grad_norm": 0.052051134407520294,
      "learning_rate": 0.00011252190708658582,
      "loss": 0.744354248046875,
      "step": 414
    },
    {
      "epoch": 3.5487674169346195,
      "grad_norm": 0.04472478851675987,
      "learning_rate": 0.0001119612937572322,
      "loss": 0.846527099609375,
      "step": 415
    },
    {
      "epoch": 3.557341907824223,
      "grad_norm": 0.0508098229765892,
      "learning_rate": 0.00011140286048898256,
      "loss": 0.662811279296875,
      "step": 416
    },
    {
      "epoch": 3.5659163987138265,
      "grad_norm": 0.04844518378376961,
      "learning_rate": 0.0001108466251748674,
      "loss": 0.727996826171875,
      "step": 417
    },
    {
      "epoch": 3.57449088960343,
      "grad_norm": 0.05300529673695564,
      "learning_rate": 0.00011029260563749154,
      "loss": 0.6729736328125,
      "step": 418
    },
    {
      "epoch": 3.583065380493033,
      "grad_norm": 0.05097375810146332,
      "learning_rate": 0.00010974081962846298,
      "loss": 0.66473388671875,
      "step": 419
    },
    {
      "epoch": 3.5916398713826365,
      "grad_norm": 0.05159912258386612,
      "learning_rate": 0.00010919128482782423,
      "loss": 0.77410888671875,
      "step": 420
    },
    {
      "epoch": 3.60021436227224,
      "grad_norm": 0.05908460170030594,
      "learning_rate": 0.00010864401884348561,
      "loss": 0.734039306640625,
      "step": 421
    },
    {
      "epoch": 3.6087888531618435,
      "grad_norm": 0.051211923360824585,
      "learning_rate": 0.0001080990392106614,
      "loss": 0.73919677734375,
      "step": 422
    },
    {
      "epoch": 3.617363344051447,
      "grad_norm": 0.05478530004620552,
      "learning_rate": 0.00010755636339130767,
      "loss": 0.7579345703125,
      "step": 423
    },
    {
      "epoch": 3.6259378349410505,
      "grad_norm": 0.050885457545518875,
      "learning_rate": 0.00010701600877356284,
      "loss": 0.785675048828125,
      "step": 424
    },
    {
      "epoch": 3.634512325830654,
      "grad_norm": 0.06410066038370132,
      "learning_rate": 0.00010647799267119068,
      "loss": 0.70391845703125,
      "step": 425
    },
    {
      "epoch": 3.643086816720257,
      "grad_norm": 0.05240744352340698,
      "learning_rate": 0.0001059423323230254,
      "loss": 0.70672607421875,
      "step": 426
    },
    {
      "epoch": 3.6516613076098605,
      "grad_norm": 0.054693736135959625,
      "learning_rate": 0.00010540904489241935,
      "loss": 0.683074951171875,
      "step": 427
    },
    {
      "epoch": 3.660235798499464,
      "grad_norm": 0.056872740387916565,
      "learning_rate": 0.00010487814746669313,
      "loss": 0.707061767578125,
      "step": 428
    },
    {
      "epoch": 3.6688102893890675,
      "grad_norm": 0.04834144935011864,
      "learning_rate": 0.00010434965705658804,
      "loss": 0.733001708984375,
      "step": 429
    },
    {
      "epoch": 3.677384780278671,
      "grad_norm": 0.05322672426700592,
      "learning_rate": 0.00010382359059572093,
      "loss": 0.667694091796875,
      "step": 430
    },
    {
      "epoch": 3.6859592711682745,
      "grad_norm": 0.03898676857352257,
      "learning_rate": 0.00010329996494004184,
      "loss": 0.6569061279296875,
      "step": 431
    },
    {
      "epoch": 3.694533762057878,
      "grad_norm": 0.05350349843502045,
      "learning_rate": 0.00010277879686729367,
      "loss": 0.76824951171875,
      "step": 432
    },
    {
      "epoch": 3.703108252947481,
      "grad_norm": 0.05077127367258072,
      "learning_rate": 0.0001022601030764748,
      "loss": 0.79608154296875,
      "step": 433
    },
    {
      "epoch": 3.7116827438370845,
      "grad_norm": 0.05157258361577988,
      "learning_rate": 0.00010174390018730396,
      "loss": 0.73529052734375,
      "step": 434
    },
    {
      "epoch": 3.720257234726688,
      "grad_norm": 0.05006041377782822,
      "learning_rate": 0.00010123020473968765,
      "loss": 0.77716064453125,
      "step": 435
    },
    {
      "epoch": 3.7288317256162915,
      "grad_norm": 0.05507458373904228,
      "learning_rate": 0.00010071903319319024,
      "loss": 0.75555419921875,
      "step": 436
    },
    {
      "epoch": 3.737406216505895,
      "grad_norm": 0.05242147296667099,
      "learning_rate": 0.00010021040192650655,
      "loss": 0.775634765625,
      "step": 437
    },
    {
      "epoch": 3.7459807073954985,
      "grad_norm": 0.05443510785698891,
      "learning_rate": 9.970432723693704e-05,
      "loss": 0.81634521484375,
      "step": 438
    },
    {
      "epoch": 3.754555198285102,
      "grad_norm": 0.04829897731542587,
      "learning_rate": 9.920082533986568e-05,
      "loss": 0.75970458984375,
      "step": 439
    },
    {
      "epoch": 3.763129689174705,
      "grad_norm": 0.05000029131770134,
      "learning_rate": 9.869991236824042e-05,
      "loss": 0.718902587890625,
      "step": 440
    },
    {
      "epoch": 3.7717041800643085,
      "grad_norm": 0.04309910535812378,
      "learning_rate": 9.820160437205608e-05,
      "loss": 0.66436767578125,
      "step": 441
    },
    {
      "epoch": 3.780278670953912,
      "grad_norm": 0.05324380844831467,
      "learning_rate": 9.770591731784023e-05,
      "loss": 0.82952880859375,
      "step": 442
    },
    {
      "epoch": 3.7888531618435155,
      "grad_norm": 0.05055423080921173,
      "learning_rate": 9.721286708814163e-05,
      "loss": 0.75347900390625,
      "step": 443
    },
    {
      "epoch": 3.797427652733119,
      "grad_norm": 0.057011786848306656,
      "learning_rate": 9.672246948102118e-05,
      "loss": 0.733856201171875,
      "step": 444
    },
    {
      "epoch": 3.8060021436227225,
      "grad_norm": 0.04577447101473808,
      "learning_rate": 9.623474020954587e-05,
      "loss": 0.643707275390625,
      "step": 445
    },
    {
      "epoch": 3.814576634512326,
      "grad_norm": 0.05471675097942352,
      "learning_rate": 9.57496949012853e-05,
      "loss": 0.6719970703125,
      "step": 446
    },
    {
      "epoch": 3.823151125401929,
      "grad_norm": 0.0550396554172039,
      "learning_rate": 9.526734909781083e-05,
      "loss": 0.79815673828125,
      "step": 447
    },
    {
      "epoch": 3.831725616291533,
      "grad_norm": 0.05966958776116371,
      "learning_rate": 9.478771825419771e-05,
      "loss": 0.748687744140625,
      "step": 448
    },
    {
      "epoch": 3.840300107181136,
      "grad_norm": 0.0513051301240921,
      "learning_rate": 9.431081773852985e-05,
      "loss": 0.75811767578125,
      "step": 449
    },
    {
      "epoch": 3.8488745980707395,
      "grad_norm": 0.04967513307929039,
      "learning_rate": 9.383666283140738e-05,
      "loss": 0.6893692016601562,
      "step": 450
    },
    {
      "epoch": 3.857449088960343,
      "grad_norm": 0.043654534965753555,
      "learning_rate": 9.336526872545707e-05,
      "loss": 0.6484603881835938,
      "step": 451
    },
    {
      "epoch": 3.8660235798499465,
      "grad_norm": 0.05421756953001022,
      "learning_rate": 9.289665052484557e-05,
      "loss": 0.694580078125,
      "step": 452
    },
    {
      "epoch": 3.87459807073955,
      "grad_norm": 0.04800517484545708,
      "learning_rate": 9.243082324479534e-05,
      "loss": 0.6819305419921875,
      "step": 453
    },
    {
      "epoch": 3.883172561629153,
      "grad_norm": 0.04926931485533714,
      "learning_rate": 9.196780181110363e-05,
      "loss": 0.75799560546875,
      "step": 454
    },
    {
      "epoch": 3.891747052518757,
      "grad_norm": 0.047687649726867676,
      "learning_rate": 9.150760105966423e-05,
      "loss": 0.660552978515625,
      "step": 455
    },
    {
      "epoch": 3.90032154340836,
      "grad_norm": 0.045551471412181854,
      "learning_rate": 9.105023573599201e-05,
      "loss": 0.7110595703125,
      "step": 456
    },
    {
      "epoch": 3.9088960342979635,
      "grad_norm": 0.04617937654256821,
      "learning_rate": 9.059572049475058e-05,
      "loss": 0.7515869140625,
      "step": 457
    },
    {
      "epoch": 3.917470525187567,
      "grad_norm": 0.04780326038599014,
      "learning_rate": 9.014406989928276e-05,
      "loss": 0.69134521484375,
      "step": 458
    },
    {
      "epoch": 3.9260450160771705,
      "grad_norm": 0.03921288624405861,
      "learning_rate": 8.969529842114374e-05,
      "loss": 0.810821533203125,
      "step": 459
    },
    {
      "epoch": 3.934619506966774,
      "grad_norm": 0.05188051983714104,
      "learning_rate": 8.924942043963753e-05,
      "loss": 0.82061767578125,
      "step": 460
    },
    {
      "epoch": 3.943193997856377,
      "grad_norm": 0.05147204548120499,
      "learning_rate": 8.880645024135633e-05,
      "loss": 0.7080078125,
      "step": 461
    },
    {
      "epoch": 3.951768488745981,
      "grad_norm": 0.05234919488430023,
      "learning_rate": 8.83664020197225e-05,
      "loss": 0.7239990234375,
      "step": 462
    },
    {
      "epoch": 3.960342979635584,
      "grad_norm": 0.05237029865384102,
      "learning_rate": 8.792928987453402e-05,
      "loss": 0.716094970703125,
      "step": 463
    },
    {
      "epoch": 3.9689174705251875,
      "grad_norm": 0.050819944590330124,
      "learning_rate": 8.749512781151265e-05,
      "loss": 0.78216552734375,
      "step": 464
    },
    {
      "epoch": 3.977491961414791,
      "grad_norm": 0.054847560822963715,
      "learning_rate": 8.706392974185508e-05,
      "loss": 0.72222900390625,
      "step": 465
    },
    {
      "epoch": 3.9860664523043945,
      "grad_norm": 0.04899563640356064,
      "learning_rate": 8.663570948178728e-05,
      "loss": 0.73895263671875,
      "step": 466
    },
    {
      "epoch": 3.994640943193998,
      "grad_norm": 0.04511614516377449,
      "learning_rate": 8.621048075212175e-05,
      "loss": 0.6319303512573242,
      "step": 467
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.05584103241562843,
      "learning_rate": 8.578825717781797e-05,
      "loss": 0.69921875,
      "step": 468
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.76025390625,
      "eval_runtime": 1.4788,
      "eval_samples_per_second": 2.029,
      "eval_steps_per_second": 0.676,
      "step": 468
    },
    {
      "epoch": 4.008574490889603,
      "grad_norm": 0.04365234822034836,
      "learning_rate": 8.53690522875457e-05,
      "loss": 0.7537689208984375,
      "step": 469
    },
    {
      "epoch": 4.017148981779207,
      "grad_norm": 0.05667227506637573,
      "learning_rate": 8.495287951325173e-05,
      "loss": 0.769805908203125,
      "step": 470
    },
    {
      "epoch": 4.02572347266881,
      "grad_norm": 0.05286044999957085,
      "learning_rate": 8.453975218972924e-05,
      "loss": 0.688385009765625,
      "step": 471
    },
    {
      "epoch": 4.034297963558414,
      "grad_norm": 0.04600420221686363,
      "learning_rate": 8.412968355419063e-05,
      "loss": 0.70330810546875,
      "step": 472
    },
    {
      "epoch": 4.042872454448017,
      "grad_norm": 0.05683373287320137,
      "learning_rate": 8.372268674584347e-05,
      "loss": 0.77349853515625,
      "step": 473
    },
    {
      "epoch": 4.051446945337621,
      "grad_norm": 0.0434025377035141,
      "learning_rate": 8.331877480546941e-05,
      "loss": 0.7111968994140625,
      "step": 474
    },
    {
      "epoch": 4.060021436227224,
      "grad_norm": 0.05847004055976868,
      "learning_rate": 8.291796067500631e-05,
      "loss": 0.71990966796875,
      "step": 475
    },
    {
      "epoch": 4.068595927116827,
      "grad_norm": 0.05432530492544174,
      "learning_rate": 8.252025719713371e-05,
      "loss": 0.72503662109375,
      "step": 476
    },
    {
      "epoch": 4.077170418006431,
      "grad_norm": 0.05224629491567612,
      "learning_rate": 8.212567711486109e-05,
      "loss": 0.7470703125,
      "step": 477
    },
    {
      "epoch": 4.085744908896034,
      "grad_norm": 0.052483994513750076,
      "learning_rate": 8.17342330711198e-05,
      "loss": 0.711669921875,
      "step": 478
    },
    {
      "epoch": 4.094319399785638,
      "grad_norm": 0.049032311886548996,
      "learning_rate": 8.13459376083578e-05,
      "loss": 0.747711181640625,
      "step": 479
    },
    {
      "epoch": 4.102893890675241,
      "grad_norm": 0.05547500029206276,
      "learning_rate": 8.096080316813787e-05,
      "loss": 0.803466796875,
      "step": 480
    },
    {
      "epoch": 4.111468381564845,
      "grad_norm": 0.05432252213358879,
      "learning_rate": 8.057884209073895e-05,
      "loss": 0.779296875,
      "step": 481
    },
    {
      "epoch": 4.120042872454448,
      "grad_norm": 0.04143486171960831,
      "learning_rate": 8.020006661476073e-05,
      "loss": 0.704742431640625,
      "step": 482
    },
    {
      "epoch": 4.128617363344051,
      "grad_norm": 0.06884818524122238,
      "learning_rate": 7.982448887673147e-05,
      "loss": 0.74639892578125,
      "step": 483
    },
    {
      "epoch": 4.137191854233655,
      "grad_norm": 0.04944215342402458,
      "learning_rate": 7.94521209107192e-05,
      "loss": 0.664031982421875,
      "step": 484
    },
    {
      "epoch": 4.145766345123258,
      "grad_norm": 0.0739644467830658,
      "learning_rate": 7.908297464794601e-05,
      "loss": 0.7034912109375,
      "step": 485
    },
    {
      "epoch": 4.154340836012862,
      "grad_norm": 0.049721743911504745,
      "learning_rate": 7.871706191640596e-05,
      "loss": 0.72613525390625,
      "step": 486
    },
    {
      "epoch": 4.162915326902465,
      "grad_norm": 0.0742981880903244,
      "learning_rate": 7.83543944404859e-05,
      "loss": 0.82672119140625,
      "step": 487
    },
    {
      "epoch": 4.171489817792069,
      "grad_norm": 0.054561156779527664,
      "learning_rate": 7.799498384058989e-05,
      "loss": 0.779296875,
      "step": 488
    },
    {
      "epoch": 4.180064308681672,
      "grad_norm": 0.06064046919345856,
      "learning_rate": 7.763884163276682e-05,
      "loss": 0.67559814453125,
      "step": 489
    },
    {
      "epoch": 4.188638799571275,
      "grad_norm": 0.060892995446920395,
      "learning_rate": 7.728597922834148e-05,
      "loss": 0.687469482421875,
      "step": 490
    },
    {
      "epoch": 4.197213290460879,
      "grad_norm": 0.050845179706811905,
      "learning_rate": 7.693640793354888e-05,
      "loss": 0.7049560546875,
      "step": 491
    },
    {
      "epoch": 4.205787781350482,
      "grad_norm": 0.06286416947841644,
      "learning_rate": 7.659013894917202e-05,
      "loss": 0.7279052734375,
      "step": 492
    },
    {
      "epoch": 4.214362272240086,
      "grad_norm": 0.058105748146772385,
      "learning_rate": 7.624718337018295e-05,
      "loss": 0.717041015625,
      "step": 493
    },
    {
      "epoch": 4.222936763129689,
      "grad_norm": 0.069930300116539,
      "learning_rate": 7.590755218538729e-05,
      "loss": 0.725341796875,
      "step": 494
    },
    {
      "epoch": 4.231511254019293,
      "grad_norm": 0.05379112437367439,
      "learning_rate": 7.557125627707217e-05,
      "loss": 0.68109130859375,
      "step": 495
    },
    {
      "epoch": 4.240085744908896,
      "grad_norm": 0.058652762323617935,
      "learning_rate": 7.523830642065742e-05,
      "loss": 0.76470947265625,
      "step": 496
    },
    {
      "epoch": 4.248660235798499,
      "grad_norm": 0.05279368907213211,
      "learning_rate": 7.490871328435054e-05,
      "loss": 0.7750244140625,
      "step": 497
    },
    {
      "epoch": 4.257234726688103,
      "grad_norm": 0.0474751740694046,
      "learning_rate": 7.458248742880467e-05,
      "loss": 0.72442626953125,
      "step": 498
    },
    {
      "epoch": 4.265809217577706,
      "grad_norm": 0.0655018612742424,
      "learning_rate": 7.425963930678024e-05,
      "loss": 0.720703125,
      "step": 499
    },
    {
      "epoch": 4.27438370846731,
      "grad_norm": 0.04611559957265854,
      "learning_rate": 7.394017926281014e-05,
      "loss": 0.697174072265625,
      "step": 500
    },
    {
      "epoch": 4.282958199356913,
      "grad_norm": 0.0522368848323822,
      "learning_rate": 7.362411753286815e-05,
      "loss": 0.7041015625,
      "step": 501
    },
    {
      "epoch": 4.291532690246517,
      "grad_norm": 0.055782414972782135,
      "learning_rate": 7.331146424404115e-05,
      "loss": 0.759521484375,
      "step": 502
    },
    {
      "epoch": 4.30010718113612,
      "grad_norm": 0.042888134717941284,
      "learning_rate": 7.300222941420438e-05,
      "loss": 0.65264892578125,
      "step": 503
    },
    {
      "epoch": 4.308681672025724,
      "grad_norm": 0.05125903710722923,
      "learning_rate": 7.269642295170065e-05,
      "loss": 0.700286865234375,
      "step": 504
    },
    {
      "epoch": 4.317256162915327,
      "grad_norm": 0.052178867161273956,
      "learning_rate": 7.239405465502276e-05,
      "loss": 0.73260498046875,
      "step": 505
    },
    {
      "epoch": 4.32583065380493,
      "grad_norm": 0.04375027120113373,
      "learning_rate": 7.209513421249957e-05,
      "loss": 0.765228271484375,
      "step": 506
    },
    {
      "epoch": 4.334405144694534,
      "grad_norm": 0.049392566084861755,
      "learning_rate": 7.179967120198566e-05,
      "loss": 0.794464111328125,
      "step": 507
    },
    {
      "epoch": 4.342979635584137,
      "grad_norm": 0.04670102521777153,
      "learning_rate": 7.150767509055424e-05,
      "loss": 0.74334716796875,
      "step": 508
    },
    {
      "epoch": 4.351554126473741,
      "grad_norm": 0.047154515981674194,
      "learning_rate": 7.1219155234194e-05,
      "loss": 0.725341796875,
      "step": 509
    },
    {
      "epoch": 4.360128617363344,
      "grad_norm": 0.04515945911407471,
      "learning_rate": 7.093412087750926e-05,
      "loss": 0.7452392578125,
      "step": 510
    },
    {
      "epoch": 4.368703108252948,
      "grad_norm": 0.04779065027832985,
      "learning_rate": 7.06525811534237e-05,
      "loss": 0.72900390625,
      "step": 511
    },
    {
      "epoch": 4.377277599142551,
      "grad_norm": 0.04777348414063454,
      "learning_rate": 7.037454508288788e-05,
      "loss": 0.710693359375,
      "step": 512
    },
    {
      "epoch": 4.385852090032154,
      "grad_norm": 0.04633750393986702,
      "learning_rate": 7.010002157459002e-05,
      "loss": 0.75750732421875,
      "step": 513
    },
    {
      "epoch": 4.394426580921758,
      "grad_norm": 0.049866750836372375,
      "learning_rate": 6.982901942467069e-05,
      "loss": 0.77532958984375,
      "step": 514
    },
    {
      "epoch": 4.403001071811361,
      "grad_norm": 0.04413531348109245,
      "learning_rate": 6.956154731644087e-05,
      "loss": 0.799285888671875,
      "step": 515
    },
    {
      "epoch": 4.411575562700965,
      "grad_norm": 0.051137540489435196,
      "learning_rate": 6.929761382010377e-05,
      "loss": 0.7412109375,
      "step": 516
    },
    {
      "epoch": 4.420150053590568,
      "grad_norm": 0.04512210935354233,
      "learning_rate": 6.903722739248022e-05,
      "loss": 0.73870849609375,
      "step": 517
    },
    {
      "epoch": 4.428724544480172,
      "grad_norm": 0.043679069727659225,
      "learning_rate": 6.878039637673778e-05,
      "loss": 0.72222900390625,
      "step": 518
    },
    {
      "epoch": 4.437299035369775,
      "grad_norm": 0.04275720939040184,
      "learning_rate": 6.852712900212326e-05,
      "loss": 0.708221435546875,
      "step": 519
    },
    {
      "epoch": 4.445873526259378,
      "grad_norm": 0.03821426257491112,
      "learning_rate": 6.827743338369914e-05,
      "loss": 0.7018280029296875,
      "step": 520
    },
    {
      "epoch": 4.454448017148982,
      "grad_norm": 0.045829422771930695,
      "learning_rate": 6.803131752208352e-05,
      "loss": 0.699188232421875,
      "step": 521
    },
    {
      "epoch": 4.463022508038585,
      "grad_norm": 0.03798821195960045,
      "learning_rate": 6.778878930319379e-05,
      "loss": 0.69696044921875,
      "step": 522
    },
    {
      "epoch": 4.471596998928189,
      "grad_norm": 0.04419054836034775,
      "learning_rate": 6.754985649799395e-05,
      "loss": 0.687408447265625,
      "step": 523
    },
    {
      "epoch": 4.480171489817792,
      "grad_norm": 0.04709318280220032,
      "learning_rate": 6.731452676224564e-05,
      "loss": 0.778594970703125,
      "step": 524
    },
    {
      "epoch": 4.488745980707396,
      "grad_norm": 0.04529687017202377,
      "learning_rate": 6.708280763626275e-05,
      "loss": 0.641815185546875,
      "step": 525
    },
    {
      "epoch": 4.497320471596999,
      "grad_norm": 0.045921169221401215,
      "learning_rate": 6.685470654466989e-05,
      "loss": 0.70697021484375,
      "step": 526
    },
    {
      "epoch": 4.505894962486602,
      "grad_norm": 0.042227499186992645,
      "learning_rate": 6.663023079616452e-05,
      "loss": 0.719024658203125,
      "step": 527
    },
    {
      "epoch": 4.514469453376206,
      "grad_norm": 0.04445791244506836,
      "learning_rate": 6.640938758328267e-05,
      "loss": 0.682037353515625,
      "step": 528
    },
    {
      "epoch": 4.523043944265809,
      "grad_norm": 0.04456387460231781,
      "learning_rate": 6.619218398216858e-05,
      "loss": 0.73101806640625,
      "step": 529
    },
    {
      "epoch": 4.531618435155413,
      "grad_norm": 0.04433625191450119,
      "learning_rate": 6.597862695234792e-05,
      "loss": 0.68719482421875,
      "step": 530
    },
    {
      "epoch": 4.540192926045016,
      "grad_norm": 0.04204265773296356,
      "learning_rate": 6.576872333650481e-05,
      "loss": 0.734893798828125,
      "step": 531
    },
    {
      "epoch": 4.54876741693462,
      "grad_norm": 0.03989989683032036,
      "learning_rate": 6.556247986026255e-05,
      "loss": 0.83648681640625,
      "step": 532
    },
    {
      "epoch": 4.557341907824223,
      "grad_norm": 0.04226313903927803,
      "learning_rate": 6.535990313196815e-05,
      "loss": 0.65362548828125,
      "step": 533
    },
    {
      "epoch": 4.565916398713826,
      "grad_norm": 0.04485386982560158,
      "learning_rate": 6.516099964248053e-05,
      "loss": 0.717681884765625,
      "step": 534
    },
    {
      "epoch": 4.57449088960343,
      "grad_norm": 0.04086388275027275,
      "learning_rate": 6.496577576496266e-05,
      "loss": 0.663238525390625,
      "step": 535
    },
    {
      "epoch": 4.583065380493033,
      "grad_norm": 0.04292574152350426,
      "learning_rate": 6.477423775467726e-05,
      "loss": 0.6556396484375,
      "step": 536
    },
    {
      "epoch": 4.591639871382637,
      "grad_norm": 0.04506971314549446,
      "learning_rate": 6.458639174878636e-05,
      "loss": 0.76336669921875,
      "step": 537
    },
    {
      "epoch": 4.60021436227224,
      "grad_norm": 0.049535319209098816,
      "learning_rate": 6.440224376615473e-05,
      "loss": 0.724395751953125,
      "step": 538
    },
    {
      "epoch": 4.608788853161844,
      "grad_norm": 0.04636030271649361,
      "learning_rate": 6.422179970715696e-05,
      "loss": 0.73016357421875,
      "step": 539
    },
    {
      "epoch": 4.617363344051447,
      "grad_norm": 0.044309113174676895,
      "learning_rate": 6.404506535348845e-05,
      "loss": 0.747650146484375,
      "step": 540
    },
    {
      "epoch": 4.62593783494105,
      "grad_norm": 0.05031096562743187,
      "learning_rate": 6.387204636798014e-05,
      "loss": 0.77557373046875,
      "step": 541
    },
    {
      "epoch": 4.634512325830654,
      "grad_norm": 0.05166783556342125,
      "learning_rate": 6.370274829441704e-05,
      "loss": 0.69378662109375,
      "step": 542
    },
    {
      "epoch": 4.643086816720257,
      "grad_norm": 0.048238057643175125,
      "learning_rate": 6.353717655736061e-05,
      "loss": 0.6966552734375,
      "step": 543
    },
    {
      "epoch": 4.651661307609861,
      "grad_norm": 0.04742105305194855,
      "learning_rate": 6.337533646197503e-05,
      "loss": 0.673797607421875,
      "step": 544
    },
    {
      "epoch": 4.660235798499464,
      "grad_norm": 0.052290815860033035,
      "learning_rate": 6.321723319385706e-05,
      "loss": 0.69696044921875,
      "step": 545
    },
    {
      "epoch": 4.668810289389068,
      "grad_norm": 0.048471227288246155,
      "learning_rate": 6.306287181887001e-05,
      "loss": 0.723388671875,
      "step": 546
    },
    {
      "epoch": 4.677384780278671,
      "grad_norm": 0.04996265470981598,
      "learning_rate": 6.291225728298139e-05,
      "loss": 0.65869140625,
      "step": 547
    },
    {
      "epoch": 4.685959271168274,
      "grad_norm": 0.039980459958314896,
      "learning_rate": 6.276539441210439e-05,
      "loss": 0.6492233276367188,
      "step": 548
    },
    {
      "epoch": 4.694533762057878,
      "grad_norm": 0.05233966186642647,
      "learning_rate": 6.262228791194332e-05,
      "loss": 0.75872802734375,
      "step": 549
    },
    {
      "epoch": 4.703108252947481,
      "grad_norm": 0.051795706152915955,
      "learning_rate": 6.248294236784279e-05,
      "loss": 0.78631591796875,
      "step": 550
    },
    {
      "epoch": 4.711682743837085,
      "grad_norm": 0.04987563565373421,
      "learning_rate": 6.234736224464078e-05,
      "loss": 0.725341796875,
      "step": 551
    },
    {
      "epoch": 4.720257234726688,
      "grad_norm": 0.05183640494942665,
      "learning_rate": 6.221555188652566e-05,
      "loss": 0.766845703125,
      "step": 552
    },
    {
      "epoch": 4.728831725616292,
      "grad_norm": 0.053391359746456146,
      "learning_rate": 6.208751551689681e-05,
      "loss": 0.745849609375,
      "step": 553
    },
    {
      "epoch": 4.737406216505895,
      "grad_norm": 0.05205420404672623,
      "learning_rate": 6.196325723822954e-05,
      "loss": 0.76556396484375,
      "step": 554
    },
    {
      "epoch": 4.745980707395498,
      "grad_norm": 0.04696294665336609,
      "learning_rate": 6.184278103194346e-05,
      "loss": 0.80572509765625,
      "step": 555
    },
    {
      "epoch": 4.754555198285102,
      "grad_norm": 0.049076225608587265,
      "learning_rate": 6.172609075827498e-05,
      "loss": 0.75006103515625,
      "step": 556
    },
    {
      "epoch": 4.763129689174705,
      "grad_norm": 0.050074853003025055,
      "learning_rate": 6.161319015615364e-05,
      "loss": 0.710052490234375,
      "step": 557
    },
    {
      "epoch": 4.771704180064309,
      "grad_norm": 0.04180307686328888,
      "learning_rate": 6.15040828430822e-05,
      "loss": 0.6563873291015625,
      "step": 558
    },
    {
      "epoch": 4.780278670953912,
      "grad_norm": 0.05236335098743439,
      "learning_rate": 6.139877231502092e-05,
      "loss": 0.82098388671875,
      "step": 559
    },
    {
      "epoch": 4.788853161843516,
      "grad_norm": 0.04821524769067764,
      "learning_rate": 6.129726194627536e-05,
      "loss": 0.74407958984375,
      "step": 560
    },
    {
      "epoch": 4.797427652733119,
      "grad_norm": 0.04967579245567322,
      "learning_rate": 6.119955498938834e-05,
      "loss": 0.7240219116210938,
      "step": 561
    },
    {
      "epoch": 4.806002143622722,
      "grad_norm": 0.050489019602537155,
      "learning_rate": 6.110565457503575e-05,
      "loss": 0.635833740234375,
      "step": 562
    },
    {
      "epoch": 4.814576634512326,
      "grad_norm": 0.04605700075626373,
      "learning_rate": 6.101556371192621e-05,
      "loss": 0.664215087890625,
      "step": 563
    },
    {
      "epoch": 4.823151125401929,
      "grad_norm": 0.051928021013736725,
      "learning_rate": 6.092928528670462e-05,
      "loss": 0.7886962890625,
      "step": 564
    },
    {
      "epoch": 4.831725616291533,
      "grad_norm": 0.04701283574104309,
      "learning_rate": 6.0846822063859754e-05,
      "loss": 0.73876953125,
      "step": 565
    },
    {
      "epoch": 4.840300107181136,
      "grad_norm": 0.04480873420834541,
      "learning_rate": 6.076817668563565e-05,
      "loss": 0.749267578125,
      "step": 566
    },
    {
      "epoch": 4.84887459807074,
      "grad_norm": 0.04020781069993973,
      "learning_rate": 6.069335167194689e-05,
      "loss": 0.680572509765625,
      "step": 567
    },
    {
      "epoch": 4.857449088960343,
      "grad_norm": 0.04343302920460701,
      "learning_rate": 6.062234942029797e-05,
      "loss": 0.6403427124023438,
      "step": 568
    },
    {
      "epoch": 4.866023579849946,
      "grad_norm": 0.047655124217271805,
      "learning_rate": 6.055517220570637e-05,
      "loss": 0.685516357421875,
      "step": 569
    },
    {
      "epoch": 4.87459807073955,
      "grad_norm": 0.04417397826910019,
      "learning_rate": 6.049182218062971e-05,
      "loss": 0.6743621826171875,
      "step": 570
    },
    {
      "epoch": 4.883172561629153,
      "grad_norm": 0.04672884941101074,
      "learning_rate": 6.043230137489682e-05,
      "loss": 0.748779296875,
      "step": 571
    },
    {
      "epoch": 4.891747052518757,
      "grad_norm": 0.04711579903960228,
      "learning_rate": 6.037661169564262e-05,
      "loss": 0.6528701782226562,
      "step": 572
    },
    {
      "epoch": 4.90032154340836,
      "grad_norm": 0.048221029341220856,
      "learning_rate": 6.032475492724705e-05,
      "loss": 0.7030029296875,
      "step": 573
    },
    {
      "epoch": 4.908896034297964,
      "grad_norm": 0.04538934677839279,
      "learning_rate": 6.0276732731277946e-05,
      "loss": 0.7435302734375,
      "step": 574
    },
    {
      "epoch": 4.917470525187567,
      "grad_norm": 0.05124829709529877,
      "learning_rate": 6.0232546646437685e-05,
      "loss": 0.68365478515625,
      "step": 575
    },
    {
      "epoch": 4.92604501607717,
      "grad_norm": 0.04275573790073395,
      "learning_rate": 6.019219808851403e-05,
      "loss": 0.8039703369140625,
      "step": 576
    },
    {
      "epoch": 4.934619506966774,
      "grad_norm": 0.04536749795079231,
      "learning_rate": 6.0155688350334614e-05,
      "loss": 0.81207275390625,
      "step": 577
    },
    {
      "epoch": 4.943193997856377,
      "grad_norm": 0.04794101417064667,
      "learning_rate": 6.012301860172563e-05,
      "loss": 0.700103759765625,
      "step": 578
    },
    {
      "epoch": 4.951768488745981,
      "grad_norm": 0.046271175146102905,
      "learning_rate": 6.009418988947432e-05,
      "loss": 0.715789794921875,
      "step": 579
    },
    {
      "epoch": 4.960342979635584,
      "grad_norm": 0.047130003571510315,
      "learning_rate": 6.0069203137295366e-05,
      "loss": 0.708221435546875,
      "step": 580
    },
    {
      "epoch": 4.968917470525188,
      "grad_norm": 0.04532779008150101,
      "learning_rate": 6.0048059145801414e-05,
      "loss": 0.7744140625,
      "step": 581
    },
    {
      "epoch": 4.977491961414791,
      "grad_norm": 0.05076000466942787,
      "learning_rate": 6.003075859247728e-05,
      "loss": 0.714111328125,
      "step": 582
    },
    {
      "epoch": 4.986066452304394,
      "grad_norm": 0.048792798072099686,
      "learning_rate": 6.0017302031658416e-05,
      "loss": 0.73028564453125,
      "step": 583
    },
    {
      "epoch": 4.994640943193998,
      "grad_norm": 0.043757710605859756,
      "learning_rate": 6.000768989451298e-05,
      "loss": 0.6249872446060181,
      "step": 584
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.05427691340446472,
      "learning_rate": 6.000192248902809e-05,
      "loss": 0.68988037109375,
      "step": 585
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.7565104365348816,
      "eval_runtime": 1.4755,
      "eval_samples_per_second": 2.033,
      "eval_steps_per_second": 0.678,
      "step": 585
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 585,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.466845268806205e+19,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}