{
  "best_metric": 0.7289469838142395,
  "best_model_checkpoint": "miner_id_24/checkpoint-400",
  "epoch": 0.08968107168880668,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002242026792220167,
      "grad_norm": 126.1038818359375,
      "learning_rate": 2e-05,
      "loss": 20.535,
      "step": 1
    },
    {
      "epoch": 0.0002242026792220167,
      "eval_loss": 2.3938145637512207,
      "eval_runtime": 698.3723,
      "eval_samples_per_second": 7.16,
      "eval_steps_per_second": 1.79,
      "step": 1
    },
    {
      "epoch": 0.0004484053584440334,
      "grad_norm": 99.99730682373047,
      "learning_rate": 4e-05,
      "loss": 17.4049,
      "step": 2
    },
    {
      "epoch": 0.0006726080376660501,
      "grad_norm": 105.478759765625,
      "learning_rate": 6e-05,
      "loss": 16.535,
      "step": 3
    },
    {
      "epoch": 0.0008968107168880668,
      "grad_norm": 70.27592468261719,
      "learning_rate": 8e-05,
      "loss": 12.5348,
      "step": 4
    },
    {
      "epoch": 0.0011210133961100834,
      "grad_norm": 97.4080810546875,
      "learning_rate": 0.0001,
      "loss": 13.2828,
      "step": 5
    },
    {
      "epoch": 0.0013452160753321001,
      "grad_norm": 113.0913314819336,
      "learning_rate": 0.00012,
      "loss": 12.2028,
      "step": 6
    },
    {
      "epoch": 0.0015694187545541168,
      "grad_norm": 52.263145446777344,
      "learning_rate": 0.00014,
      "loss": 8.7435,
      "step": 7
    },
    {
      "epoch": 0.0017936214337761335,
      "grad_norm": 62.40456008911133,
      "learning_rate": 0.00016,
      "loss": 8.6549,
      "step": 8
    },
    {
      "epoch": 0.0020178241129981504,
      "grad_norm": 65.93408966064453,
      "learning_rate": 0.00018,
      "loss": 9.4705,
      "step": 9
    },
    {
      "epoch": 0.002242026792220167,
      "grad_norm": 43.083744049072266,
      "learning_rate": 0.0002,
      "loss": 7.8587,
      "step": 10
    },
    {
      "epoch": 0.002466229471442184,
      "grad_norm": 49.018985748291016,
      "learning_rate": 0.00019999928367015404,
      "loss": 7.3603,
      "step": 11
    },
    {
      "epoch": 0.0026904321506642003,
      "grad_norm": 29.12760353088379,
      "learning_rate": 0.00019999713469087867,
      "loss": 6.4356,
      "step": 12
    },
    {
      "epoch": 0.002914634829886217,
      "grad_norm": 32.05826950073242,
      "learning_rate": 0.00019999355309296144,
      "loss": 6.271,
      "step": 13
    },
    {
      "epoch": 0.0031388375091082337,
      "grad_norm": 34.21839141845703,
      "learning_rate": 0.00019998853892771453,
      "loss": 8.0705,
      "step": 14
    },
    {
      "epoch": 0.0033630401883302506,
      "grad_norm": 30.485218048095703,
      "learning_rate": 0.00019998209226697376,
      "loss": 8.2374,
      "step": 15
    },
    {
      "epoch": 0.003587242867552267,
      "grad_norm": 31.998018264770508,
      "learning_rate": 0.00019997421320309795,
      "loss": 6.9484,
      "step": 16
    },
    {
      "epoch": 0.003811445546774284,
      "grad_norm": 27.289979934692383,
      "learning_rate": 0.00019996490184896723,
      "loss": 7.0251,
      "step": 17
    },
    {
      "epoch": 0.004035648225996301,
      "grad_norm": 29.063690185546875,
      "learning_rate": 0.00019995415833798158,
      "loss": 7.7886,
      "step": 18
    },
    {
      "epoch": 0.004259850905218318,
      "grad_norm": 32.24039077758789,
      "learning_rate": 0.000199941982824059,
      "loss": 6.4147,
      "step": 19
    },
    {
      "epoch": 0.004484053584440334,
      "grad_norm": 29.33707046508789,
      "learning_rate": 0.00019992837548163316,
      "loss": 6.9304,
      "step": 20
    },
    {
      "epoch": 0.004708256263662351,
      "grad_norm": 35.22611618041992,
      "learning_rate": 0.00019991333650565095,
      "loss": 6.0003,
      "step": 21
    },
    {
      "epoch": 0.004932458942884368,
      "grad_norm": 37.675045013427734,
      "learning_rate": 0.00019989686611156972,
      "loss": 7.9153,
      "step": 22
    },
    {
      "epoch": 0.0051566616221063845,
      "grad_norm": 31.198379516601562,
      "learning_rate": 0.0001998789645353542,
      "loss": 4.9754,
      "step": 23
    },
    {
      "epoch": 0.0053808643013284006,
      "grad_norm": 36.45598602294922,
      "learning_rate": 0.000199859632033473,
      "loss": 7.6056,
      "step": 24
    },
    {
      "epoch": 0.0056050669805504175,
      "grad_norm": 33.72439956665039,
      "learning_rate": 0.00019983886888289514,
      "loss": 6.2217,
      "step": 25
    },
    {
      "epoch": 0.005829269659772434,
      "grad_norm": 31.307844161987305,
      "learning_rate": 0.00019981667538108587,
      "loss": 5.9159,
      "step": 26
    },
    {
      "epoch": 0.006053472338994451,
      "grad_norm": 27.1914119720459,
      "learning_rate": 0.00019979305184600256,
      "loss": 7.7606,
      "step": 27
    },
    {
      "epoch": 0.006277675018216467,
      "grad_norm": 30.91358757019043,
      "learning_rate": 0.00019976799861609008,
      "loss": 6.4419,
      "step": 28
    },
    {
      "epoch": 0.006501877697438484,
      "grad_norm": 31.102294921875,
      "learning_rate": 0.00019974151605027594,
      "loss": 7.3968,
      "step": 29
    },
    {
      "epoch": 0.006726080376660501,
      "grad_norm": 24.997732162475586,
      "learning_rate": 0.00019971360452796522,
      "loss": 7.405,
      "step": 30
    },
    {
      "epoch": 0.006950283055882518,
      "grad_norm": 27.011751174926758,
      "learning_rate": 0.000199684264449035,
      "loss": 6.295,
      "step": 31
    },
    {
      "epoch": 0.007174485735104534,
      "grad_norm": 57.90675354003906,
      "learning_rate": 0.0001996534962338288,
      "loss": 6.6209,
      "step": 32
    },
    {
      "epoch": 0.007398688414326551,
      "grad_norm": 26.843050003051758,
      "learning_rate": 0.00019962130032315044,
      "loss": 6.6557,
      "step": 33
    },
    {
      "epoch": 0.007622891093548568,
      "grad_norm": 38.86860656738281,
      "learning_rate": 0.0001995876771782577,
      "loss": 7.782,
      "step": 34
    },
    {
      "epoch": 0.007847093772770585,
      "grad_norm": 23.273401260375977,
      "learning_rate": 0.0001995526272808559,
      "loss": 5.6526,
      "step": 35
    },
    {
      "epoch": 0.008071296451992602,
      "grad_norm": 31.08440589904785,
      "learning_rate": 0.00019951615113309075,
      "loss": 8.2093,
      "step": 36
    },
    {
      "epoch": 0.008295499131214619,
      "grad_norm": 22.350833892822266,
      "learning_rate": 0.00019947824925754131,
      "loss": 6.028,
      "step": 37
    },
    {
      "epoch": 0.008519701810436636,
      "grad_norm": 27.807506561279297,
      "learning_rate": 0.00019943892219721253,
      "loss": 6.8341,
      "step": 38
    },
    {
      "epoch": 0.00874390448965865,
      "grad_norm": 28.673147201538086,
      "learning_rate": 0.00019939817051552728,
      "loss": 6.8244,
      "step": 39
    },
    {
      "epoch": 0.008968107168880668,
      "grad_norm": 28.544300079345703,
      "learning_rate": 0.0001993559947963185,
      "loss": 6.7331,
      "step": 40
    },
    {
      "epoch": 0.009192309848102685,
      "grad_norm": 35.682701110839844,
      "learning_rate": 0.00019931239564382073,
      "loss": 6.1532,
      "step": 41
    },
    {
      "epoch": 0.009416512527324701,
      "grad_norm": 28.997901916503906,
      "learning_rate": 0.00019926737368266144,
      "loss": 7.4634,
      "step": 42
    },
    {
      "epoch": 0.009640715206546718,
      "grad_norm": 26.42931365966797,
      "learning_rate": 0.00019922092955785217,
      "loss": 6.3474,
      "step": 43
    },
    {
      "epoch": 0.009864917885768735,
      "grad_norm": 28.974231719970703,
      "learning_rate": 0.00019917306393477907,
      "loss": 8.8579,
      "step": 44
    },
    {
      "epoch": 0.010089120564990752,
      "grad_norm": 23.615530014038086,
      "learning_rate": 0.00019912377749919374,
      "loss": 5.4516,
      "step": 45
    },
    {
      "epoch": 0.010313323244212769,
      "grad_norm": 28.568689346313477,
      "learning_rate": 0.00019907307095720303,
      "loss": 7.3263,
      "step": 46
    },
    {
      "epoch": 0.010537525923434784,
      "grad_norm": 26.684173583984375,
      "learning_rate": 0.0001990209450352591,
      "loss": 5.9323,
      "step": 47
    },
    {
      "epoch": 0.010761728602656801,
      "grad_norm": 33.331974029541016,
      "learning_rate": 0.00019896740048014908,
      "loss": 9.5157,
      "step": 48
    },
    {
      "epoch": 0.010985931281878818,
      "grad_norm": 24.288129806518555,
      "learning_rate": 0.0001989124380589842,
      "loss": 6.7932,
      "step": 49
    },
    {
      "epoch": 0.011210133961100835,
      "grad_norm": 23.27587890625,
      "learning_rate": 0.00019885605855918885,
      "loss": 5.9373,
      "step": 50
    },
    {
      "epoch": 0.011434336640322852,
      "grad_norm": 26.940839767456055,
      "learning_rate": 0.0001987982627884895,
      "loss": 6.7137,
      "step": 51
    },
    {
      "epoch": 0.011658539319544869,
      "grad_norm": 28.85309600830078,
      "learning_rate": 0.00019873905157490285,
      "loss": 6.9183,
      "step": 52
    },
    {
      "epoch": 0.011882741998766886,
      "grad_norm": 29.890792846679688,
      "learning_rate": 0.00019867842576672403,
      "loss": 5.5844,
      "step": 53
    },
    {
      "epoch": 0.012106944677988903,
      "grad_norm": 30.305374145507812,
      "learning_rate": 0.0001986163862325146,
      "loss": 5.8588,
      "step": 54
    },
    {
      "epoch": 0.01233114735721092,
      "grad_norm": 32.619354248046875,
      "learning_rate": 0.00019855293386108992,
      "loss": 6.7053,
      "step": 55
    },
    {
      "epoch": 0.012555350036432935,
      "grad_norm": 35.285362243652344,
      "learning_rate": 0.0001984880695615066,
      "loss": 6.6549,
      "step": 56
    },
    {
      "epoch": 0.012779552715654952,
      "grad_norm": 28.37751579284668,
      "learning_rate": 0.00019842179426304924,
      "loss": 5.6804,
      "step": 57
    },
    {
      "epoch": 0.013003755394876968,
      "grad_norm": 36.84033966064453,
      "learning_rate": 0.0001983541089152174,
      "loss": 6.9011,
      "step": 58
    },
    {
      "epoch": 0.013227958074098985,
      "grad_norm": 27.49158477783203,
      "learning_rate": 0.00019828501448771176,
      "loss": 6.4378,
      "step": 59
    },
    {
      "epoch": 0.013452160753321002,
      "grad_norm": 31.058568954467773,
      "learning_rate": 0.00019821451197042026,
      "loss": 7.2063,
      "step": 60
    },
    {
      "epoch": 0.01367636343254302,
      "grad_norm": 28.093948364257812,
      "learning_rate": 0.00019814260237340414,
      "loss": 6.8696,
      "step": 61
    },
    {
      "epoch": 0.013900566111765036,
      "grad_norm": 29.54469108581543,
      "learning_rate": 0.0001980692867268832,
      "loss": 6.4564,
      "step": 62
    },
    {
      "epoch": 0.014124768790987053,
      "grad_norm": 31.518455505371094,
      "learning_rate": 0.00019799456608122107,
      "loss": 6.683,
      "step": 63
    },
    {
      "epoch": 0.014348971470209068,
      "grad_norm": 28.135486602783203,
      "learning_rate": 0.0001979184415069104,
      "loss": 6.2822,
      "step": 64
    },
    {
      "epoch": 0.014573174149431085,
      "grad_norm": 26.87474250793457,
      "learning_rate": 0.00019784091409455728,
      "loss": 7.0468,
      "step": 65
    },
    {
      "epoch": 0.014797376828653102,
      "grad_norm": 33.120967864990234,
      "learning_rate": 0.00019776198495486565,
      "loss": 6.8367,
      "step": 66
    },
    {
      "epoch": 0.015021579507875119,
      "grad_norm": 36.56197738647461,
      "learning_rate": 0.00019768165521862155,
      "loss": 7.4689,
      "step": 67
    },
    {
      "epoch": 0.015245782187097136,
      "grad_norm": 29.483192443847656,
      "learning_rate": 0.00019759992603667667,
      "loss": 7.0864,
      "step": 68
    },
    {
      "epoch": 0.015469984866319153,
      "grad_norm": 26.171871185302734,
      "learning_rate": 0.0001975167985799321,
      "loss": 6.1041,
      "step": 69
    },
    {
      "epoch": 0.01569418754554117,
      "grad_norm": 39.571292877197266,
      "learning_rate": 0.00019743227403932134,
      "loss": 7.6122,
      "step": 70
    },
    {
      "epoch": 0.015918390224763185,
      "grad_norm": 30.298654556274414,
      "learning_rate": 0.0001973463536257935,
      "loss": 7.6106,
      "step": 71
    },
    {
      "epoch": 0.016142592903985203,
      "grad_norm": 43.653106689453125,
      "learning_rate": 0.00019725903857029564,
      "loss": 6.9136,
      "step": 72
    },
    {
      "epoch": 0.01636679558320722,
      "grad_norm": 25.71277618408203,
      "learning_rate": 0.00019717033012375538,
      "loss": 7.5374,
      "step": 73
    },
    {
      "epoch": 0.016590998262429237,
      "grad_norm": 24.647903442382812,
      "learning_rate": 0.00019708022955706292,
      "loss": 4.9617,
      "step": 74
    },
    {
      "epoch": 0.016815200941651252,
      "grad_norm": 25.697256088256836,
      "learning_rate": 0.00019698873816105273,
      "loss": 7.4518,
      "step": 75
    },
    {
      "epoch": 0.01703940362087327,
      "grad_norm": 25.474393844604492,
      "learning_rate": 0.00019689585724648516,
      "loss": 6.4463,
      "step": 76
    },
    {
      "epoch": 0.017263606300095286,
      "grad_norm": 27.94502067565918,
      "learning_rate": 0.00019680158814402762,
      "loss": 6.3231,
      "step": 77
    },
    {
      "epoch": 0.0174878089793173,
      "grad_norm": 32.44084167480469,
      "learning_rate": 0.00019670593220423558,
      "loss": 6.6641,
      "step": 78
    },
    {
      "epoch": 0.01771201165853932,
      "grad_norm": 31.0953426361084,
      "learning_rate": 0.0001966088907975331,
      "loss": 8.3381,
      "step": 79
    },
    {
      "epoch": 0.017936214337761335,
      "grad_norm": 26.307016372680664,
      "learning_rate": 0.00019651046531419332,
      "loss": 7.2786,
      "step": 80
    },
    {
      "epoch": 0.018160417016983354,
      "grad_norm": 27.859359741210938,
      "learning_rate": 0.00019641065716431849,
      "loss": 6.8786,
      "step": 81
    },
    {
      "epoch": 0.01838461969620537,
      "grad_norm": 25.600828170776367,
      "learning_rate": 0.00019630946777781966,
      "loss": 6.2762,
      "step": 82
    },
    {
      "epoch": 0.018608822375427388,
      "grad_norm": 25.116792678833008,
      "learning_rate": 0.00019620689860439647,
      "loss": 6.6437,
      "step": 83
    },
    {
      "epoch": 0.018833025054649403,
      "grad_norm": 30.76014518737793,
      "learning_rate": 0.0001961029511135161,
      "loss": 6.9008,
      "step": 84
    },
    {
      "epoch": 0.01905722773387142,
      "grad_norm": 25.599990844726562,
      "learning_rate": 0.0001959976267943923,
      "loss": 7.0286,
      "step": 85
    },
    {
      "epoch": 0.019281430413093437,
      "grad_norm": 27.448787689208984,
      "learning_rate": 0.00019589092715596417,
      "loss": 7.25,
      "step": 86
    },
    {
      "epoch": 0.019505633092315452,
      "grad_norm": 28.388507843017578,
      "learning_rate": 0.00019578285372687446,
      "loss": 6.6516,
      "step": 87
    },
    {
      "epoch": 0.01972983577153747,
      "grad_norm": 37.779422760009766,
      "learning_rate": 0.00019567340805544758,
      "loss": 6.51,
      "step": 88
    },
    {
      "epoch": 0.019954038450759486,
      "grad_norm": 26.867084503173828,
      "learning_rate": 0.00019556259170966755,
      "loss": 6.532,
      "step": 89
    },
    {
      "epoch": 0.020178241129981504,
      "grad_norm": 24.564254760742188,
      "learning_rate": 0.0001954504062771555,
      "loss": 6.5824,
      "step": 90
    },
    {
      "epoch": 0.02040244380920352,
      "grad_norm": 32.00818634033203,
      "learning_rate": 0.00019533685336514697,
      "loss": 7.4471,
      "step": 91
    },
    {
      "epoch": 0.020626646488425538,
      "grad_norm": 26.054603576660156,
      "learning_rate": 0.00019522193460046864,
      "loss": 6.5195,
      "step": 92
    },
    {
      "epoch": 0.020850849167647553,
      "grad_norm": 25.680438995361328,
      "learning_rate": 0.00019510565162951537,
      "loss": 5.439,
      "step": 93
    },
    {
      "epoch": 0.02107505184686957,
      "grad_norm": 31.208587646484375,
      "learning_rate": 0.00019498800611822645,
      "loss": 6.447,
      "step": 94
    },
    {
      "epoch": 0.021299254526091587,
      "grad_norm": 22.253074645996094,
      "learning_rate": 0.00019486899975206166,
      "loss": 5.865,
      "step": 95
    },
    {
      "epoch": 0.021523457205313602,
      "grad_norm": 30.783687591552734,
      "learning_rate": 0.00019474863423597728,
      "loss": 5.8101,
      "step": 96
    },
    {
      "epoch": 0.02174765988453562,
      "grad_norm": 32.515968322753906,
      "learning_rate": 0.00019462691129440147,
      "loss": 6.9156,
      "step": 97
    },
    {
      "epoch": 0.021971862563757636,
      "grad_norm": 26.716693878173828,
      "learning_rate": 0.00019450383267120982,
      "loss": 7.3049,
      "step": 98
    },
    {
      "epoch": 0.022196065242979655,
      "grad_norm": 34.22292709350586,
      "learning_rate": 0.00019437940012970013,
      "loss": 8.3232,
      "step": 99
    },
    {
      "epoch": 0.02242026792220167,
      "grad_norm": 26.541484832763672,
      "learning_rate": 0.00019425361545256727,
      "loss": 7.7195,
      "step": 100
    },
    {
      "epoch": 0.02242026792220167,
      "eval_loss": 0.8167434334754944,
      "eval_runtime": 704.0365,
      "eval_samples_per_second": 7.102,
      "eval_steps_per_second": 1.775,
      "step": 100
    },
    {
      "epoch": 0.02264447060142369,
      "grad_norm": 34.53705978393555,
      "learning_rate": 0.0001941264804418776,
      "loss": 7.6651,
      "step": 101
    },
    {
      "epoch": 0.022868673280645704,
      "grad_norm": 28.85417366027832,
      "learning_rate": 0.0001939979969190432,
      "loss": 6.902,
      "step": 102
    },
    {
      "epoch": 0.02309287595986772,
      "grad_norm": 22.874216079711914,
      "learning_rate": 0.00019386816672479565,
      "loss": 5.6693,
      "step": 103
    },
    {
      "epoch": 0.023317078639089737,
      "grad_norm": 25.60254669189453,
      "learning_rate": 0.00019373699171915988,
      "loss": 6.4141,
      "step": 104
    },
    {
      "epoch": 0.023541281318311753,
      "grad_norm": 27.99315071105957,
      "learning_rate": 0.00019360447378142728,
      "loss": 6.5433,
      "step": 105
    },
    {
      "epoch": 0.02376548399753377,
      "grad_norm": 22.138385772705078,
      "learning_rate": 0.00019347061481012894,
      "loss": 6.2604,
      "step": 106
    },
    {
      "epoch": 0.023989686676755786,
      "grad_norm": 28.11634063720703,
      "learning_rate": 0.00019333541672300841,
      "loss": 7.7013,
      "step": 107
    },
    {
      "epoch": 0.024213889355977805,
      "grad_norm": 26.298097610473633,
      "learning_rate": 0.00019319888145699415,
      "loss": 6.7254,
      "step": 108
    },
    {
      "epoch": 0.02443809203519982,
      "grad_norm": 32.601802825927734,
      "learning_rate": 0.00019306101096817186,
      "loss": 6.1263,
      "step": 109
    },
    {
      "epoch": 0.02466229471442184,
      "grad_norm": 27.140356063842773,
      "learning_rate": 0.00019292180723175654,
      "loss": 7.0992,
      "step": 110
    },
    {
      "epoch": 0.024886497393643854,
      "grad_norm": 28.598079681396484,
      "learning_rate": 0.00019278127224206396,
      "loss": 5.6771,
      "step": 111
    },
    {
      "epoch": 0.02511070007286587,
      "grad_norm": 36.28137969970703,
      "learning_rate": 0.00019263940801248226,
      "loss": 7.0739,
      "step": 112
    },
    {
      "epoch": 0.025334902752087888,
      "grad_norm": 28.40138053894043,
      "learning_rate": 0.0001924962165754431,
      "loss": 7.7833,
      "step": 113
    },
    {
      "epoch": 0.025559105431309903,
      "grad_norm": 24.93914794921875,
      "learning_rate": 0.0001923516999823925,
      "loss": 6.6856,
      "step": 114
    },
    {
      "epoch": 0.02578330811053192,
      "grad_norm": 27.28483772277832,
      "learning_rate": 0.00019220586030376134,
      "loss": 6.2761,
      "step": 115
    },
    {
      "epoch": 0.026007510789753937,
      "grad_norm": 23.135244369506836,
      "learning_rate": 0.00019205869962893605,
      "loss": 5.8583,
      "step": 116
    },
    {
      "epoch": 0.026231713468975956,
      "grad_norm": 28.643129348754883,
      "learning_rate": 0.0001919102200662282,
      "loss": 6.2237,
      "step": 117
    },
    {
      "epoch": 0.02645591614819797,
      "grad_norm": 25.207122802734375,
      "learning_rate": 0.0001917604237428447,
      "loss": 6.8272,
      "step": 118
    },
    {
      "epoch": 0.02668011882741999,
      "grad_norm": 23.8134765625,
      "learning_rate": 0.00019160931280485702,
      "loss": 5.2492,
      "step": 119
    },
    {
      "epoch": 0.026904321506642005,
      "grad_norm": 26.125720977783203,
      "learning_rate": 0.00019145688941717075,
      "loss": 5.7282,
      "step": 120
    },
    {
      "epoch": 0.02712852418586402,
      "grad_norm": 33.9704704284668,
      "learning_rate": 0.00019130315576349423,
      "loss": 6.9509,
      "step": 121
    },
    {
      "epoch": 0.02735272686508604,
      "grad_norm": 30.981101989746094,
      "learning_rate": 0.00019114811404630762,
      "loss": 6.3979,
      "step": 122
    },
    {
      "epoch": 0.027576929544308054,
      "grad_norm": 22.4842472076416,
      "learning_rate": 0.0001909917664868311,
      "loss": 6.0354,
      "step": 123
    },
    {
      "epoch": 0.027801132223530072,
      "grad_norm": 32.84996795654297,
      "learning_rate": 0.0001908341153249931,
      "loss": 6.4721,
      "step": 124
    },
    {
      "epoch": 0.028025334902752087,
      "grad_norm": 26.951725006103516,
      "learning_rate": 0.00019067516281939825,
      "loss": 6.7431,
      "step": 125
    },
    {
      "epoch": 0.028249537581974106,
      "grad_norm": 23.87074089050293,
      "learning_rate": 0.00019051491124729512,
      "loss": 5.931,
      "step": 126
    },
    {
      "epoch": 0.02847374026119612,
      "grad_norm": 37.152591705322266,
      "learning_rate": 0.00019035336290454334,
      "loss": 7.3899,
      "step": 127
    },
    {
      "epoch": 0.028697942940418136,
      "grad_norm": 32.23517608642578,
      "learning_rate": 0.00019019052010558088,
      "loss": 7.225,
      "step": 128
    },
    {
      "epoch": 0.028922145619640155,
      "grad_norm": 26.25091552734375,
      "learning_rate": 0.00019002638518339087,
      "loss": 5.6054,
      "step": 129
    },
    {
      "epoch": 0.02914634829886217,
      "grad_norm": 28.006101608276367,
      "learning_rate": 0.00018986096048946824,
      "loss": 7.9982,
      "step": 130
    },
    {
      "epoch": 0.02937055097808419,
      "grad_norm": 38.7149772644043,
      "learning_rate": 0.00018969424839378584,
      "loss": 8.4457,
      "step": 131
    },
    {
      "epoch": 0.029594753657306204,
      "grad_norm": 25.91262435913086,
      "learning_rate": 0.0001895262512847607,
      "loss": 6.9604,
      "step": 132
    },
    {
      "epoch": 0.029818956336528223,
      "grad_norm": 21.268983840942383,
      "learning_rate": 0.0001893569715692197,
      "loss": 5.2707,
      "step": 133
    },
    {
      "epoch": 0.030043159015750238,
      "grad_norm": 33.657981872558594,
      "learning_rate": 0.00018918641167236505,
      "loss": 5.9472,
      "step": 134
    },
    {
      "epoch": 0.030267361694972256,
      "grad_norm": 28.115495681762695,
      "learning_rate": 0.00018901457403773967,
      "loss": 7.0108,
      "step": 135
    },
    {
      "epoch": 0.03049156437419427,
      "grad_norm": 25.33727264404297,
      "learning_rate": 0.00018884146112719207,
      "loss": 5.8147,
      "step": 136
    },
    {
      "epoch": 0.030715767053416287,
      "grad_norm": 30.39851188659668,
      "learning_rate": 0.00018866707542084118,
      "loss": 7.2195,
      "step": 137
    },
    {
      "epoch": 0.030939969732638305,
      "grad_norm": 31.78814125061035,
      "learning_rate": 0.00018849141941704067,
      "loss": 6.3176,
      "step": 138
    },
    {
      "epoch": 0.03116417241186032,
      "grad_norm": 28.935474395751953,
      "learning_rate": 0.0001883144956323433,
      "loss": 7.5649,
      "step": 139
    },
    {
      "epoch": 0.03138837509108234,
      "grad_norm": 28.71467399597168,
      "learning_rate": 0.00018813630660146488,
      "loss": 6.115,
      "step": 140
    },
    {
      "epoch": 0.03161257777030436,
      "grad_norm": 26.66712188720703,
      "learning_rate": 0.00018795685487724782,
      "loss": 6.7109,
      "step": 141
    },
    {
      "epoch": 0.03183678044952637,
      "grad_norm": 26.047056198120117,
      "learning_rate": 0.00018777614303062457,
      "loss": 5.4715,
      "step": 142
    },
    {
      "epoch": 0.03206098312874839,
      "grad_norm": 27.34377098083496,
      "learning_rate": 0.000187594173650581,
      "loss": 6.8057,
      "step": 143
    },
    {
      "epoch": 0.03228518580797041,
      "grad_norm": 26.84559440612793,
      "learning_rate": 0.000187410949344119,
      "loss": 6.0385,
      "step": 144
    },
    {
      "epoch": 0.03250938848719242,
      "grad_norm": 22.556068420410156,
      "learning_rate": 0.0001872264727362194,
      "loss": 5.076,
      "step": 145
    },
    {
      "epoch": 0.03273359116641444,
      "grad_norm": 30.990081787109375,
      "learning_rate": 0.00018704074646980415,
      "loss": 8.3495,
      "step": 146
    },
    {
      "epoch": 0.032957793845636456,
      "grad_norm": 24.56372833251953,
      "learning_rate": 0.0001868537732056987,
      "loss": 6.0178,
      "step": 147
    },
    {
      "epoch": 0.033181996524858474,
      "grad_norm": 31.70186424255371,
      "learning_rate": 0.00018666555562259356,
      "loss": 7.7613,
      "step": 148
    },
    {
      "epoch": 0.033406199204080486,
      "grad_norm": 29.10866355895996,
      "learning_rate": 0.0001864760964170062,
      "loss": 5.487,
      "step": 149
    },
    {
      "epoch": 0.033630401883302505,
      "grad_norm": 25.912494659423828,
      "learning_rate": 0.00018628539830324229,
      "loss": 5.9884,
      "step": 150
    },
    {
      "epoch": 0.03385460456252452,
      "grad_norm": 28.45311737060547,
      "learning_rate": 0.00018609346401335684,
      "loss": 6.3458,
      "step": 151
    },
    {
      "epoch": 0.03407880724174654,
      "grad_norm": 24.32749366760254,
      "learning_rate": 0.00018590029629711506,
      "loss": 6.3678,
      "step": 152
    },
    {
      "epoch": 0.034303009920968554,
      "grad_norm": 32.25789260864258,
      "learning_rate": 0.00018570589792195298,
      "loss": 5.7656,
      "step": 153
    },
    {
      "epoch": 0.03452721260019057,
      "grad_norm": 29.06962776184082,
      "learning_rate": 0.00018551027167293768,
      "loss": 5.3993,
      "step": 154
    },
    {
      "epoch": 0.03475141527941259,
      "grad_norm": 27.226818084716797,
      "learning_rate": 0.00018531342035272766,
      "loss": 5.9963,
      "step": 155
    },
    {
      "epoch": 0.0349756179586346,
      "grad_norm": 23.95298194885254,
      "learning_rate": 0.00018511534678153244,
      "loss": 5.9709,
      "step": 156
    },
    {
      "epoch": 0.03519982063785662,
      "grad_norm": 31.9146728515625,
      "learning_rate": 0.0001849160537970722,
      "loss": 6.9961,
      "step": 157
    },
    {
      "epoch": 0.03542402331707864,
      "grad_norm": 25.755165100097656,
      "learning_rate": 0.0001847155442545372,
      "loss": 6.5454,
      "step": 158
    },
    {
      "epoch": 0.03564822599630066,
      "grad_norm": 24.231678009033203,
      "learning_rate": 0.00018451382102654683,
      "loss": 6.6485,
      "step": 159
    },
    {
      "epoch": 0.03587242867552267,
      "grad_norm": 27.726436614990234,
      "learning_rate": 0.00018431088700310844,
      "loss": 6.0035,
      "step": 160
    },
    {
      "epoch": 0.03609663135474469,
      "grad_norm": 29.822324752807617,
      "learning_rate": 0.00018410674509157607,
      "loss": 6.0299,
      "step": 161
    },
    {
      "epoch": 0.03632083403396671,
      "grad_norm": 28.1485538482666,
      "learning_rate": 0.00018390139821660855,
      "loss": 6.3191,
      "step": 162
    },
    {
      "epoch": 0.03654503671318872,
      "grad_norm": 29.311811447143555,
      "learning_rate": 0.00018369484932012777,
      "loss": 6.7074,
      "step": 163
    },
    {
      "epoch": 0.03676923939241074,
      "grad_norm": 32.607913970947266,
      "learning_rate": 0.00018348710136127655,
      "loss": 5.66,
      "step": 164
    },
    {
      "epoch": 0.03699344207163276,
      "grad_norm": 25.113399505615234,
      "learning_rate": 0.00018327815731637612,
      "loss": 6.9365,
      "step": 165
    },
    {
      "epoch": 0.037217644750854775,
      "grad_norm": 31.439462661743164,
      "learning_rate": 0.0001830680201788836,
      "loss": 5.919,
      "step": 166
    },
    {
      "epoch": 0.03744184743007679,
      "grad_norm": 26.15847396850586,
      "learning_rate": 0.0001828566929593491,
      "loss": 6.6313,
      "step": 167
    },
    {
      "epoch": 0.037666050109298806,
      "grad_norm": 35.38442611694336,
      "learning_rate": 0.00018264417868537244,
      "loss": 5.644,
      "step": 168
    },
    {
      "epoch": 0.037890252788520824,
      "grad_norm": 27.612476348876953,
      "learning_rate": 0.00018243048040156003,
      "loss": 7.0993,
      "step": 169
    },
    {
      "epoch": 0.03811445546774284,
      "grad_norm": 25.662029266357422,
      "learning_rate": 0.00018221560116948103,
      "loss": 6.0174,
      "step": 170
    },
    {
      "epoch": 0.038338658146964855,
      "grad_norm": 25.098709106445312,
      "learning_rate": 0.00018199954406762352,
      "loss": 6.5899,
      "step": 171
    },
    {
      "epoch": 0.03856286082618687,
      "grad_norm": 28.130373001098633,
      "learning_rate": 0.0001817823121913506,
      "loss": 6.4024,
      "step": 172
    },
    {
      "epoch": 0.03878706350540889,
      "grad_norm": 31.034496307373047,
      "learning_rate": 0.00018156390865285574,
      "loss": 6.8425,
      "step": 173
    },
    {
      "epoch": 0.039011266184630904,
      "grad_norm": 26.748743057250977,
      "learning_rate": 0.00018134433658111845,
      "loss": 6.3032,
      "step": 174
    },
    {
      "epoch": 0.03923546886385292,
      "grad_norm": 22.752180099487305,
      "learning_rate": 0.00018112359912185924,
      "loss": 6.1072,
      "step": 175
    },
    {
      "epoch": 0.03945967154307494,
      "grad_norm": 31.163314819335938,
      "learning_rate": 0.00018090169943749476,
      "loss": 6.5983,
      "step": 176
    },
    {
      "epoch": 0.03968387422229696,
      "grad_norm": 27.870765686035156,
      "learning_rate": 0.00018067864070709231,
      "loss": 8.1716,
      "step": 177
    },
    {
      "epoch": 0.03990807690151897,
      "grad_norm": 27.21661949157715,
      "learning_rate": 0.00018045442612632444,
      "loss": 6.9641,
      "step": 178
    },
    {
      "epoch": 0.04013227958074099,
      "grad_norm": 26.731801986694336,
      "learning_rate": 0.00018022905890742306,
      "loss": 6.2812,
      "step": 179
    },
    {
      "epoch": 0.04035648225996301,
      "grad_norm": 24.192214965820312,
      "learning_rate": 0.00018000254227913348,
      "loss": 5.758,
      "step": 180
    },
    {
      "epoch": 0.04058068493918502,
      "grad_norm": 30.906335830688477,
      "learning_rate": 0.0001797748794866681,
      "loss": 6.9955,
      "step": 181
    },
    {
      "epoch": 0.04080488761840704,
      "grad_norm": 27.075498580932617,
      "learning_rate": 0.00017954607379166,
      "loss": 6.4733,
      "step": 182
    },
    {
      "epoch": 0.04102909029762906,
      "grad_norm": 22.58766746520996,
      "learning_rate": 0.00017931612847211614,
      "loss": 5.943,
      "step": 183
    },
    {
      "epoch": 0.041253292976851076,
      "grad_norm": 28.564857482910156,
      "learning_rate": 0.00017908504682237047,
      "loss": 6.9913,
      "step": 184
    },
    {
      "epoch": 0.04147749565607309,
      "grad_norm": 27.306659698486328,
      "learning_rate": 0.0001788528321530366,
      "loss": 7.4083,
      "step": 185
    },
    {
      "epoch": 0.041701698335295107,
      "grad_norm": 19.585481643676758,
      "learning_rate": 0.00017861948779096046,
      "loss": 5.2434,
      "step": 186
    },
    {
      "epoch": 0.041925901014517125,
      "grad_norm": 28.687835693359375,
      "learning_rate": 0.00017838501707917277,
      "loss": 6.9779,
      "step": 187
    },
    {
      "epoch": 0.04215010369373914,
      "grad_norm": 22.903833389282227,
      "learning_rate": 0.0001781494233768408,
      "loss": 6.7312,
      "step": 188
    },
    {
      "epoch": 0.042374306372961155,
      "grad_norm": 32.384071350097656,
      "learning_rate": 0.00017791271005922066,
      "loss": 6.044,
      "step": 189
    },
    {
      "epoch": 0.042598509052183174,
      "grad_norm": 31.21797752380371,
      "learning_rate": 0.00017767488051760857,
      "loss": 6.6644,
      "step": 190
    },
    {
      "epoch": 0.04282271173140519,
      "grad_norm": 28.008169174194336,
      "learning_rate": 0.0001774359381592925,
      "loss": 5.4835,
      "step": 191
    },
    {
      "epoch": 0.043046914410627204,
      "grad_norm": 27.017803192138672,
      "learning_rate": 0.00017719588640750336,
      "loss": 6.8772,
      "step": 192
    },
    {
      "epoch": 0.04327111708984922,
      "grad_norm": 22.190126419067383,
      "learning_rate": 0.00017695472870136577,
      "loss": 5.3273,
      "step": 193
    },
    {
      "epoch": 0.04349531976907124,
      "grad_norm": 25.520254135131836,
      "learning_rate": 0.00017671246849584903,
      "loss": 5.2049,
      "step": 194
    },
    {
      "epoch": 0.04371952244829326,
      "grad_norm": 29.884645462036133,
      "learning_rate": 0.00017646910926171747,
      "loss": 6.8554,
      "step": 195
    },
    {
      "epoch": 0.04394372512751527,
      "grad_norm": 22.455238342285156,
      "learning_rate": 0.0001762246544854807,
      "loss": 5.3091,
      "step": 196
    },
    {
      "epoch": 0.04416792780673729,
      "grad_norm": 31.887685775756836,
      "learning_rate": 0.00017597910766934378,
      "loss": 6.7686,
      "step": 197
    },
    {
      "epoch": 0.04439213048595931,
      "grad_norm": 23.880464553833008,
      "learning_rate": 0.00017573247233115694,
      "loss": 4.9694,
      "step": 198
    },
    {
      "epoch": 0.04461633316518132,
      "grad_norm": 25.794836044311523,
      "learning_rate": 0.00017548475200436533,
      "loss": 6.0254,
      "step": 199
    },
    {
      "epoch": 0.04484053584440334,
      "grad_norm": 25.69194221496582,
      "learning_rate": 0.00017523595023795813,
      "loss": 5.0283,
      "step": 200
    },
    {
      "epoch": 0.04484053584440334,
      "eval_loss": 0.7787144780158997,
      "eval_runtime": 703.949,
      "eval_samples_per_second": 7.103,
      "eval_steps_per_second": 1.776,
      "step": 200
    },
    {
      "epoch": 0.04506473852362536,
      "grad_norm": 26.68964385986328,
      "learning_rate": 0.00017498607059641806,
      "loss": 7.7639,
      "step": 201
    },
    {
      "epoch": 0.04528894120284738,
      "grad_norm": 26.825929641723633,
      "learning_rate": 0.00017473511665966993,
      "loss": 6.7804,
      "step": 202
    },
    {
      "epoch": 0.04551314388206939,
      "grad_norm": 23.67875862121582,
      "learning_rate": 0.00017448309202302968,
      "loss": 5.4813,
      "step": 203
    },
    {
      "epoch": 0.04573734656129141,
      "grad_norm": 26.33807373046875,
      "learning_rate": 0.00017423000029715267,
      "loss": 7.3499,
      "step": 204
    },
    {
      "epoch": 0.045961549240513426,
      "grad_norm": 31.40791893005371,
      "learning_rate": 0.0001739758451079821,
      "loss": 7.0488,
      "step": 205
    },
    {
      "epoch": 0.04618575191973544,
      "grad_norm": 30.0040340423584,
      "learning_rate": 0.00017372063009669686,
      "loss": 6.9667,
      "step": 206
    },
    {
      "epoch": 0.046409954598957456,
      "grad_norm": 24.12087059020996,
      "learning_rate": 0.00017346435891965956,
      "loss": 5.6326,
      "step": 207
    },
    {
      "epoch": 0.046634157278179475,
      "grad_norm": 25.19437599182129,
      "learning_rate": 0.00017320703524836405,
      "loss": 6.5727,
      "step": 208
    },
    {
      "epoch": 0.046858359957401494,
      "grad_norm": 25.65641212463379,
      "learning_rate": 0.00017294866276938288,
      "loss": 7.3645,
      "step": 209
    },
    {
      "epoch": 0.047082562636623505,
      "grad_norm": 26.1568546295166,
      "learning_rate": 0.00017268924518431438,
      "loss": 6.4609,
      "step": 210
    },
    {
      "epoch": 0.047306765315845524,
      "grad_norm": 27.86001205444336,
      "learning_rate": 0.00017242878620972972,
      "loss": 5.6512,
      "step": 211
    },
    {
      "epoch": 0.04753096799506754,
      "grad_norm": 30.072603225708008,
      "learning_rate": 0.00017216728957711967,
      "loss": 6.3957,
      "step": 212
    },
    {
      "epoch": 0.047755170674289554,
      "grad_norm": 28.224714279174805,
      "learning_rate": 0.0001719047590328411,
      "loss": 7.073,
      "step": 213
    },
    {
      "epoch": 0.04797937335351157,
      "grad_norm": 25.31119728088379,
      "learning_rate": 0.0001716411983380632,
      "loss": 6.6975,
      "step": 214
    },
    {
      "epoch": 0.04820357603273359,
      "grad_norm": 26.434383392333984,
      "learning_rate": 0.0001713766112687139,
      "loss": 6.2888,
      "step": 215
    },
    {
      "epoch": 0.04842777871195561,
      "grad_norm": 22.03464698791504,
      "learning_rate": 0.00017111100161542545,
      "loss": 5.1292,
      "step": 216
    },
    {
      "epoch": 0.04865198139117762,
      "grad_norm": 28.093812942504883,
      "learning_rate": 0.00017084437318348034,
      "loss": 6.2516,
      "step": 217
    },
    {
      "epoch": 0.04887618407039964,
      "grad_norm": 25.522157669067383,
      "learning_rate": 0.00017057672979275656,
      "loss": 4.3692,
      "step": 218
    },
    {
      "epoch": 0.04910038674962166,
      "grad_norm": 37.885066986083984,
      "learning_rate": 0.00017030807527767318,
      "loss": 8.6422,
      "step": 219
    },
    {
      "epoch": 0.04932458942884368,
      "grad_norm": 23.919164657592773,
      "learning_rate": 0.0001700384134871351,
      "loss": 4.3907,
      "step": 220
    },
    {
      "epoch": 0.04954879210806569,
      "grad_norm": 30.759042739868164,
      "learning_rate": 0.00016976774828447808,
      "loss": 5.7591,
      "step": 221
    },
    {
      "epoch": 0.04977299478728771,
      "grad_norm": 25.29736328125,
      "learning_rate": 0.0001694960835474134,
      "loss": 6.4651,
      "step": 222
    },
    {
      "epoch": 0.04999719746650973,
      "grad_norm": 32.31372833251953,
      "learning_rate": 0.00016922342316797224,
      "loss": 7.5994,
      "step": 223
    },
    {
      "epoch": 0.05022140014573174,
      "grad_norm": 34.49051284790039,
      "learning_rate": 0.00016894977105244997,
      "loss": 5.3788,
      "step": 224
    },
    {
      "epoch": 0.05044560282495376,
      "grad_norm": 27.807523727416992,
      "learning_rate": 0.00016867513112135013,
      "loss": 7.0854,
      "step": 225
    },
    {
      "epoch": 0.050669805504175776,
      "grad_norm": 26.920969009399414,
      "learning_rate": 0.0001683995073093283,
      "loss": 5.4263,
      "step": 226
    },
    {
      "epoch": 0.050894008183397794,
      "grad_norm": 21.783588409423828,
      "learning_rate": 0.00016812290356513576,
      "loss": 5.0984,
      "step": 227
    },
    {
      "epoch": 0.051118210862619806,
      "grad_norm": 28.780790328979492,
      "learning_rate": 0.00016784532385156285,
      "loss": 6.5168,
      "step": 228
    },
    {
      "epoch": 0.051342413541841825,
      "grad_norm": 23.58247184753418,
      "learning_rate": 0.0001675667721453822,
      "loss": 6.3168,
      "step": 229
    },
    {
      "epoch": 0.05156661622106384,
      "grad_norm": 28.736845016479492,
      "learning_rate": 0.0001672872524372919,
      "loss": 6.3998,
      "step": 230
    },
    {
      "epoch": 0.051790818900285855,
      "grad_norm": 26.237924575805664,
      "learning_rate": 0.0001670067687318581,
      "loss": 5.0964,
      "step": 231
    },
    {
      "epoch": 0.052015021579507874,
      "grad_norm": 43.71037673950195,
      "learning_rate": 0.00016672532504745778,
      "loss": 5.4998,
      "step": 232
    },
    {
      "epoch": 0.05223922425872989,
      "grad_norm": 29.2600040435791,
      "learning_rate": 0.00016644292541622118,
      "loss": 6.8491,
      "step": 233
    },
    {
      "epoch": 0.05246342693795191,
      "grad_norm": 21.38605499267578,
      "learning_rate": 0.00016615957388397399,
      "loss": 5.3216,
      "step": 234
    },
    {
      "epoch": 0.05268762961717392,
      "grad_norm": 23.657005310058594,
      "learning_rate": 0.00016587527451017938,
      "loss": 5.0904,
      "step": 235
    },
    {
      "epoch": 0.05291183229639594,
      "grad_norm": 31.94679069519043,
      "learning_rate": 0.00016559003136787988,
      "loss": 6.6094,
      "step": 236
    },
    {
      "epoch": 0.05313603497561796,
      "grad_norm": 24.545034408569336,
      "learning_rate": 0.00016530384854363908,
      "loss": 5.9517,
      "step": 237
    },
    {
      "epoch": 0.05336023765483998,
      "grad_norm": 20.54098892211914,
      "learning_rate": 0.00016501673013748284,
      "loss": 4.7426,
      "step": 238
    },
    {
      "epoch": 0.05358444033406199,
      "grad_norm": 29.30255699157715,
      "learning_rate": 0.0001647286802628409,
      "loss": 5.0767,
      "step": 239
    },
    {
      "epoch": 0.05380864301328401,
      "grad_norm": 25.274873733520508,
      "learning_rate": 0.0001644397030464877,
      "loss": 6.0057,
      "step": 240
    },
    {
      "epoch": 0.05403284569250603,
      "grad_norm": 30.522607803344727,
      "learning_rate": 0.00016414980262848333,
      "loss": 5.4639,
      "step": 241
    },
    {
      "epoch": 0.05425704837172804,
      "grad_norm": 27.17019271850586,
      "learning_rate": 0.00016385898316211426,
      "loss": 8.2,
      "step": 242
    },
    {
      "epoch": 0.05448125105095006,
      "grad_norm": 34.644840240478516,
      "learning_rate": 0.0001635672488138337,
      "loss": 6.2911,
      "step": 243
    },
    {
      "epoch": 0.05470545373017208,
      "grad_norm": 31.783117294311523,
      "learning_rate": 0.0001632746037632021,
      "loss": 7.2176,
      "step": 244
    },
    {
      "epoch": 0.054929656409394095,
      "grad_norm": 26.393400192260742,
      "learning_rate": 0.00016298105220282713,
      "loss": 7.2498,
      "step": 245
    },
    {
      "epoch": 0.05515385908861611,
      "grad_norm": 24.275781631469727,
      "learning_rate": 0.00016268659833830367,
      "loss": 6.0092,
      "step": 246
    },
    {
      "epoch": 0.055378061767838126,
      "grad_norm": 30.19478988647461,
      "learning_rate": 0.00016239124638815357,
      "loss": 5.8394,
      "step": 247
    },
    {
      "epoch": 0.055602264447060144,
      "grad_norm": 28.320449829101562,
      "learning_rate": 0.00016209500058376515,
      "loss": 7.5603,
      "step": 248
    },
    {
      "epoch": 0.055826467126282156,
      "grad_norm": 27.67572784423828,
      "learning_rate": 0.00016179786516933264,
      "loss": 6.5809,
      "step": 249
    },
    {
      "epoch": 0.056050669805504175,
      "grad_norm": 24.7399959564209,
      "learning_rate": 0.00016149984440179537,
      "loss": 5.6449,
      "step": 250
    },
    {
      "epoch": 0.05627487248472619,
      "grad_norm": 24.4751033782959,
      "learning_rate": 0.0001612009425507767,
      "loss": 6.317,
      "step": 251
    },
    {
      "epoch": 0.05649907516394821,
      "grad_norm": 23.211273193359375,
      "learning_rate": 0.00016090116389852306,
      "loss": 5.4623,
      "step": 252
    },
    {
      "epoch": 0.056723277843170224,
      "grad_norm": 35.17152786254883,
      "learning_rate": 0.00016060051273984226,
      "loss": 7.8537,
      "step": 253
    },
    {
      "epoch": 0.05694748052239224,
      "grad_norm": 31.641395568847656,
      "learning_rate": 0.00016029899338204233,
      "loss": 6.8457,
      "step": 254
    },
    {
      "epoch": 0.05717168320161426,
      "grad_norm": 28.683767318725586,
      "learning_rate": 0.00015999661014486956,
      "loss": 7.2325,
      "step": 255
    },
    {
      "epoch": 0.05739588588083627,
      "grad_norm": 26.966703414916992,
      "learning_rate": 0.0001596933673604467,
      "loss": 6.0539,
      "step": 256
    },
    {
      "epoch": 0.05762008856005829,
      "grad_norm": 24.80389976501465,
      "learning_rate": 0.0001593892693732109,
      "loss": 5.9841,
      "step": 257
    },
    {
      "epoch": 0.05784429123928031,
      "grad_norm": 34.446815490722656,
      "learning_rate": 0.00015908432053985143,
      "loss": 6.8646,
      "step": 258
    },
    {
      "epoch": 0.05806849391850233,
      "grad_norm": 21.325645446777344,
      "learning_rate": 0.00015877852522924732,
      "loss": 5.2984,
      "step": 259
    },
    {
      "epoch": 0.05829269659772434,
      "grad_norm": 34.308197021484375,
      "learning_rate": 0.0001584718878224047,
      "loss": 7.5846,
      "step": 260
    },
    {
      "epoch": 0.05851689927694636,
      "grad_norm": 22.28634262084961,
      "learning_rate": 0.00015816441271239415,
      "loss": 6.2673,
      "step": 261
    },
    {
      "epoch": 0.05874110195616838,
      "grad_norm": 25.385961532592773,
      "learning_rate": 0.00015785610430428762,
      "loss": 6.993,
      "step": 262
    },
    {
      "epoch": 0.058965304635390396,
      "grad_norm": 26.998252868652344,
      "learning_rate": 0.00015754696701509533,
      "loss": 5.9968,
      "step": 263
    },
    {
      "epoch": 0.05918950731461241,
      "grad_norm": 29.365854263305664,
      "learning_rate": 0.00015723700527370268,
      "loss": 8.324,
      "step": 264
    },
    {
      "epoch": 0.059413709993834427,
      "grad_norm": 26.02857780456543,
      "learning_rate": 0.00015692622352080662,
      "loss": 5.4796,
      "step": 265
    },
    {
      "epoch": 0.059637912673056445,
      "grad_norm": 29.669628143310547,
      "learning_rate": 0.00015661462620885199,
      "loss": 6.2872,
      "step": 266
    },
    {
      "epoch": 0.05986211535227846,
      "grad_norm": 30.974468231201172,
      "learning_rate": 0.00015630221780196793,
      "loss": 7.349,
      "step": 267
    },
    {
      "epoch": 0.060086318031500476,
      "grad_norm": 22.726001739501953,
      "learning_rate": 0.0001559890027759037,
      "loss": 5.7207,
      "step": 268
    },
    {
      "epoch": 0.060310520710722494,
      "grad_norm": 25.2329158782959,
      "learning_rate": 0.0001556749856179648,
      "loss": 5.8548,
      "step": 269
    },
    {
      "epoch": 0.06053472338994451,
      "grad_norm": 28.854917526245117,
      "learning_rate": 0.00015536017082694846,
      "loss": 8.1974,
      "step": 270
    },
    {
      "epoch": 0.060758926069166524,
      "grad_norm": 27.093841552734375,
      "learning_rate": 0.00015504456291307928,
      "loss": 6.0959,
      "step": 271
    },
    {
      "epoch": 0.06098312874838854,
      "grad_norm": 26.861101150512695,
      "learning_rate": 0.0001547281663979446,
      "loss": 6.3417,
      "step": 272
    },
    {
      "epoch": 0.06120733142761056,
      "grad_norm": 34.58692932128906,
      "learning_rate": 0.0001544109858144298,
      "loss": 5.6725,
      "step": 273
    },
    {
      "epoch": 0.061431534106832573,
      "grad_norm": 30.19547462463379,
      "learning_rate": 0.00015409302570665325,
      "loss": 6.6448,
      "step": 274
    },
    {
      "epoch": 0.06165573678605459,
      "grad_norm": 35.375850677490234,
      "learning_rate": 0.00015377429062990122,
      "loss": 6.586,
      "step": 275
    },
    {
      "epoch": 0.06187993946527661,
      "grad_norm": 32.33896255493164,
      "learning_rate": 0.00015345478515056267,
      "loss": 5.0244,
      "step": 276
    },
    {
      "epoch": 0.06210414214449863,
      "grad_norm": 22.222728729248047,
      "learning_rate": 0.0001531345138460639,
      "loss": 5.1491,
      "step": 277
    },
    {
      "epoch": 0.06232834482372064,
      "grad_norm": 22.69867515563965,
      "learning_rate": 0.00015281348130480272,
      "loss": 6.2111,
      "step": 278
    },
    {
      "epoch": 0.06255254750294266,
      "grad_norm": 31.529678344726562,
      "learning_rate": 0.00015249169212608294,
      "loss": 7.6497,
      "step": 279
    },
    {
      "epoch": 0.06277675018216468,
      "grad_norm": 20.71282196044922,
      "learning_rate": 0.00015216915092004847,
      "loss": 4.4721,
      "step": 280
    },
    {
      "epoch": 0.0630009528613867,
      "grad_norm": 28.865964889526367,
      "learning_rate": 0.0001518458623076171,
      "loss": 6.7895,
      "step": 281
    },
    {
      "epoch": 0.06322515554060872,
      "grad_norm": 37.748802185058594,
      "learning_rate": 0.0001515218309204145,
      "loss": 6.9725,
      "step": 282
    },
    {
      "epoch": 0.06344935821983072,
      "grad_norm": 24.95966148376465,
      "learning_rate": 0.00015119706140070778,
      "loss": 5.2719,
      "step": 283
    },
    {
      "epoch": 0.06367356089905274,
      "grad_norm": 29.674686431884766,
      "learning_rate": 0.00015087155840133888,
      "loss": 6.693,
      "step": 284
    },
    {
      "epoch": 0.06389776357827476,
      "grad_norm": 27.693613052368164,
      "learning_rate": 0.0001505453265856581,
      "loss": 4.8887,
      "step": 285
    },
    {
      "epoch": 0.06412196625749678,
      "grad_norm": 25.27315330505371,
      "learning_rate": 0.00015021837062745714,
      "loss": 4.9784,
      "step": 286
    },
    {
      "epoch": 0.0643461689367188,
      "grad_norm": 27.22920036315918,
      "learning_rate": 0.00014989069521090226,
      "loss": 6.8051,
      "step": 287
    },
    {
      "epoch": 0.06457037161594081,
      "grad_norm": 29.53125,
      "learning_rate": 0.00014956230503046703,
      "loss": 6.1924,
      "step": 288
    },
    {
      "epoch": 0.06479457429516283,
      "grad_norm": 22.533437728881836,
      "learning_rate": 0.00014923320479086523,
      "loss": 3.9074,
      "step": 289
    },
    {
      "epoch": 0.06501877697438484,
      "grad_norm": 27.690608978271484,
      "learning_rate": 0.00014890339920698334,
      "loss": 5.6133,
      "step": 290
    },
    {
      "epoch": 0.06524297965360686,
      "grad_norm": 26.100614547729492,
      "learning_rate": 0.000148572893003813,
      "loss": 6.2221,
      "step": 291
    },
    {
      "epoch": 0.06546718233282887,
      "grad_norm": 27.521034240722656,
      "learning_rate": 0.00014824169091638337,
      "loss": 6.2779,
      "step": 292
    },
    {
      "epoch": 0.06569138501205089,
      "grad_norm": 25.931276321411133,
      "learning_rate": 0.0001479097976896933,
      "loss": 5.497,
      "step": 293
    },
    {
      "epoch": 0.06591558769127291,
      "grad_norm": 25.47264862060547,
      "learning_rate": 0.00014757721807864317,
      "loss": 7.2255,
      "step": 294
    },
    {
      "epoch": 0.06613979037049493,
      "grad_norm": 34.3621940612793,
      "learning_rate": 0.0001472439568479671,
      "loss": 6.2906,
      "step": 295
    },
    {
      "epoch": 0.06636399304971695,
      "grad_norm": 30.048749923706055,
      "learning_rate": 0.0001469100187721644,
      "loss": 7.3081,
      "step": 296
    },
    {
      "epoch": 0.06658819572893897,
      "grad_norm": 25.935880661010742,
      "learning_rate": 0.0001465754086354312,
      "loss": 6.5646,
      "step": 297
    },
    {
      "epoch": 0.06681239840816097,
      "grad_norm": 31.581850051879883,
      "learning_rate": 0.0001462401312315922,
      "loss": 6.317,
      "step": 298
    },
    {
      "epoch": 0.06703660108738299,
      "grad_norm": 30.92125129699707,
      "learning_rate": 0.00014590419136403148,
      "loss": 5.8107,
      "step": 299
    },
    {
      "epoch": 0.06726080376660501,
      "grad_norm": 20.947221755981445,
      "learning_rate": 0.00014556759384562416,
      "loss": 5.4587,
      "step": 300
    },
    {
      "epoch": 0.06726080376660501,
      "eval_loss": 0.7641205787658691,
      "eval_runtime": 703.8737,
      "eval_samples_per_second": 7.104,
      "eval_steps_per_second": 1.776,
      "step": 300
    },
    {
      "epoch": 0.06748500644582703,
      "grad_norm": 22.433246612548828,
      "learning_rate": 0.00014523034349866724,
      "loss": 5.3525,
      "step": 301
    },
    {
      "epoch": 0.06770920912504905,
      "grad_norm": 26.223323822021484,
      "learning_rate": 0.00014489244515481046,
      "loss": 6.456,
      "step": 302
    },
    {
      "epoch": 0.06793341180427107,
      "grad_norm": 27.563039779663086,
      "learning_rate": 0.00014455390365498722,
      "loss": 5.4097,
      "step": 303
    },
    {
      "epoch": 0.06815761448349308,
      "grad_norm": 23.94797706604004,
      "learning_rate": 0.0001442147238493451,
      "loss": 5.0482,
      "step": 304
    },
    {
      "epoch": 0.06838181716271509,
      "grad_norm": 21.291425704956055,
      "learning_rate": 0.00014387491059717652,
      "loss": 5.5756,
      "step": 305
    },
    {
      "epoch": 0.06860601984193711,
      "grad_norm": 24.306989669799805,
      "learning_rate": 0.00014353446876684892,
      "loss": 5.5763,
      "step": 306
    },
    {
      "epoch": 0.06883022252115913,
      "grad_norm": 26.249731063842773,
      "learning_rate": 0.00014319340323573518,
      "loss": 5.3777,
      "step": 307
    },
    {
      "epoch": 0.06905442520038114,
      "grad_norm": 25.386579513549805,
      "learning_rate": 0.0001428517188901437,
      "loss": 4.9775,
      "step": 308
    },
    {
      "epoch": 0.06927862787960316,
      "grad_norm": 28.783363342285156,
      "learning_rate": 0.00014250942062524834,
      "loss": 6.6978,
      "step": 309
    },
    {
      "epoch": 0.06950283055882518,
      "grad_norm": 26.462312698364258,
      "learning_rate": 0.0001421665133450184,
      "loss": 5.6331,
      "step": 310
    },
    {
      "epoch": 0.0697270332380472,
      "grad_norm": 28.439918518066406,
      "learning_rate": 0.00014182300196214829,
      "loss": 5.7064,
      "step": 311
    },
    {
      "epoch": 0.0699512359172692,
      "grad_norm": 25.450496673583984,
      "learning_rate": 0.00014147889139798708,
      "loss": 5.6113,
      "step": 312
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 23.286020278930664,
      "learning_rate": 0.00014113418658246815,
      "loss": 5.6453,
      "step": 313
    },
    {
      "epoch": 0.07039964127571324,
      "grad_norm": 27.5487060546875,
      "learning_rate": 0.00014078889245403844,
      "loss": 7.4498,
      "step": 314
    },
    {
      "epoch": 0.07062384395493526,
      "grad_norm": 24.131595611572266,
      "learning_rate": 0.0001404430139595877,
      "loss": 5.5885,
      "step": 315
    },
    {
      "epoch": 0.07084804663415728,
      "grad_norm": 23.212574005126953,
      "learning_rate": 0.0001400965560543778,
      "loss": 5.4629,
      "step": 316
    },
    {
      "epoch": 0.0710722493133793,
      "grad_norm": 20.374752044677734,
      "learning_rate": 0.0001397495237019714,
      "loss": 5.8839,
      "step": 317
    },
    {
      "epoch": 0.07129645199260132,
      "grad_norm": 30.799087524414062,
      "learning_rate": 0.0001394019218741612,
      "loss": 6.004,
      "step": 318
    },
    {
      "epoch": 0.07152065467182332,
      "grad_norm": 20.440460205078125,
      "learning_rate": 0.00013905375555089844,
      "loss": 5.7907,
      "step": 319
    },
    {
      "epoch": 0.07174485735104534,
      "grad_norm": 27.264223098754883,
      "learning_rate": 0.00013870502972022173,
      "loss": 6.7352,
      "step": 320
    },
    {
      "epoch": 0.07196906003026736,
      "grad_norm": 23.21996307373047,
      "learning_rate": 0.00013835574937818543,
      "loss": 5.2501,
      "step": 321
    },
    {
      "epoch": 0.07219326270948938,
      "grad_norm": 25.04043197631836,
      "learning_rate": 0.00013800591952878825,
      "loss": 4.7605,
      "step": 322
    },
    {
      "epoch": 0.0724174653887114,
      "grad_norm": 23.297082901000977,
      "learning_rate": 0.00013765554518390142,
      "loss": 6.519,
      "step": 323
    },
    {
      "epoch": 0.07264166806793342,
      "grad_norm": 23.292020797729492,
      "learning_rate": 0.00013730463136319692,
      "loss": 5.4929,
      "step": 324
    },
    {
      "epoch": 0.07286587074715543,
      "grad_norm": 24.706947326660156,
      "learning_rate": 0.0001369531830940757,
      "loss": 4.5879,
      "step": 325
    },
    {
      "epoch": 0.07309007342637744,
      "grad_norm": 43.54905319213867,
      "learning_rate": 0.00013660120541159537,
      "loss": 6.0984,
      "step": 326
    },
    {
      "epoch": 0.07331427610559946,
      "grad_norm": 32.5107536315918,
      "learning_rate": 0.00013624870335839835,
      "loss": 5.0921,
      "step": 327
    },
    {
      "epoch": 0.07353847878482148,
      "grad_norm": 26.931394577026367,
      "learning_rate": 0.00013589568198463944,
      "loss": 6.1434,
      "step": 328
    },
    {
      "epoch": 0.0737626814640435,
      "grad_norm": 26.276329040527344,
      "learning_rate": 0.00013554214634791358,
      "loss": 6.5365,
      "step": 329
    },
    {
      "epoch": 0.07398688414326551,
      "grad_norm": 30.379703521728516,
      "learning_rate": 0.0001351881015131833,
      "loss": 6.5844,
      "step": 330
    },
    {
      "epoch": 0.07421108682248753,
      "grad_norm": 28.38410758972168,
      "learning_rate": 0.00013483355255270634,
      "loss": 6.8411,
      "step": 331
    },
    {
      "epoch": 0.07443528950170955,
      "grad_norm": 37.88333511352539,
      "learning_rate": 0.00013447850454596265,
      "loss": 7.4075,
      "step": 332
    },
    {
      "epoch": 0.07465949218093156,
      "grad_norm": 22.149269104003906,
      "learning_rate": 0.0001341229625795819,
      "loss": 4.6868,
      "step": 333
    },
    {
      "epoch": 0.07488369486015357,
      "grad_norm": 26.708667755126953,
      "learning_rate": 0.00013376693174727065,
      "loss": 7.1763,
      "step": 334
    },
    {
      "epoch": 0.07510789753937559,
      "grad_norm": 32.2342643737793,
      "learning_rate": 0.000133410417149739,
      "loss": 5.9916,
      "step": 335
    },
    {
      "epoch": 0.07533210021859761,
      "grad_norm": 23.190683364868164,
      "learning_rate": 0.00013305342389462792,
      "loss": 6.7958,
      "step": 336
    },
    {
      "epoch": 0.07555630289781963,
      "grad_norm": 25.41720199584961,
      "learning_rate": 0.0001326959570964359,
      "loss": 5.9341,
      "step": 337
    },
    {
      "epoch": 0.07578050557704165,
      "grad_norm": 24.89381980895996,
      "learning_rate": 0.00013233802187644566,
      "loss": 5.7459,
      "step": 338
    },
    {
      "epoch": 0.07600470825626367,
      "grad_norm": 26.433286666870117,
      "learning_rate": 0.00013197962336265078,
      "loss": 5.8656,
      "step": 339
    },
    {
      "epoch": 0.07622891093548569,
      "grad_norm": 23.45703887939453,
      "learning_rate": 0.0001316207666896824,
      "loss": 7.2301,
      "step": 340
    },
    {
      "epoch": 0.07645311361470769,
      "grad_norm": 23.478832244873047,
      "learning_rate": 0.00013126145699873532,
      "loss": 6.1818,
      "step": 341
    },
    {
      "epoch": 0.07667731629392971,
      "grad_norm": 26.580644607543945,
      "learning_rate": 0.00013090169943749476,
      "loss": 6.4381,
      "step": 342
    },
    {
      "epoch": 0.07690151897315173,
      "grad_norm": 24.34688377380371,
      "learning_rate": 0.00013054149916006218,
      "loss": 4.9698,
      "step": 343
    },
    {
      "epoch": 0.07712572165237375,
      "grad_norm": 23.483030319213867,
      "learning_rate": 0.00013018086132688184,
      "loss": 6.102,
      "step": 344
    },
    {
      "epoch": 0.07734992433159577,
      "grad_norm": 32.27409744262695,
      "learning_rate": 0.00012981979110466654,
      "loss": 6.3361,
      "step": 345
    },
    {
      "epoch": 0.07757412701081778,
      "grad_norm": 39.28462219238281,
      "learning_rate": 0.0001294582936663239,
      "loss": 6.1558,
      "step": 346
    },
    {
      "epoch": 0.0777983296900398,
      "grad_norm": 20.815690994262695,
      "learning_rate": 0.00012909637419088193,
      "loss": 5.8407,
      "step": 347
    },
    {
      "epoch": 0.07802253236926181,
      "grad_norm": 22.997406005859375,
      "learning_rate": 0.00012873403786341513,
      "loss": 5.0343,
      "step": 348
    },
    {
      "epoch": 0.07824673504848383,
      "grad_norm": 23.768835067749023,
      "learning_rate": 0.00012837128987497,
      "loss": 5.9477,
      "step": 349
    },
    {
      "epoch": 0.07847093772770584,
      "grad_norm": 23.4127140045166,
      "learning_rate": 0.00012800813542249072,
      "loss": 6.3897,
      "step": 350
    },
    {
      "epoch": 0.07869514040692786,
      "grad_norm": 25.958768844604492,
      "learning_rate": 0.00012764457970874474,
      "loss": 5.9002,
      "step": 351
    },
    {
      "epoch": 0.07891934308614988,
      "grad_norm": 23.999540328979492,
      "learning_rate": 0.00012728062794224832,
      "loss": 6.3838,
      "step": 352
    },
    {
      "epoch": 0.0791435457653719,
      "grad_norm": 25.941434860229492,
      "learning_rate": 0.00012691628533719162,
      "loss": 6.0543,
      "step": 353
    },
    {
      "epoch": 0.07936774844459392,
      "grad_norm": 25.38425636291504,
      "learning_rate": 0.0001265515571133643,
      "loss": 5.4367,
      "step": 354
    },
    {
      "epoch": 0.07959195112381592,
      "grad_norm": 29.00336456298828,
      "learning_rate": 0.0001261864484960807,
      "loss": 6.9892,
      "step": 355
    },
    {
      "epoch": 0.07981615380303794,
      "grad_norm": 23.103368759155273,
      "learning_rate": 0.00012582096471610467,
      "loss": 5.6874,
      "step": 356
    },
    {
      "epoch": 0.08004035648225996,
      "grad_norm": 25.465681076049805,
      "learning_rate": 0.00012545511100957513,
      "loss": 7.5541,
      "step": 357
    },
    {
      "epoch": 0.08026455916148198,
      "grad_norm": 22.889604568481445,
      "learning_rate": 0.00012508889261793059,
      "loss": 6.2107,
      "step": 358
    },
    {
      "epoch": 0.080488761840704,
      "grad_norm": 25.460586547851562,
      "learning_rate": 0.00012472231478783432,
      "loss": 5.8195,
      "step": 359
    },
    {
      "epoch": 0.08071296451992602,
      "grad_norm": 23.091257095336914,
      "learning_rate": 0.0001243553827710992,
      "loss": 5.0557,
      "step": 360
    },
    {
      "epoch": 0.08093716719914804,
      "grad_norm": 23.88401985168457,
      "learning_rate": 0.00012398810182461228,
      "loss": 7.0062,
      "step": 361
    },
    {
      "epoch": 0.08116136987837004,
      "grad_norm": 26.319368362426758,
      "learning_rate": 0.00012362047721025968,
      "loss": 6.2851,
      "step": 362
    },
    {
      "epoch": 0.08138557255759206,
      "grad_norm": 23.18193817138672,
      "learning_rate": 0.00012325251419485102,
      "loss": 7.8421,
      "step": 363
    },
    {
      "epoch": 0.08160977523681408,
      "grad_norm": 33.88003921508789,
      "learning_rate": 0.00012288421805004414,
      "loss": 6.9523,
      "step": 364
    },
    {
      "epoch": 0.0818339779160361,
      "grad_norm": 21.98015785217285,
      "learning_rate": 0.00012251559405226941,
      "loss": 5.464,
      "step": 365
    },
    {
      "epoch": 0.08205818059525812,
      "grad_norm": 25.273300170898438,
      "learning_rate": 0.0001221466474826543,
      "loss": 5.6353,
      "step": 366
    },
    {
      "epoch": 0.08228238327448013,
      "grad_norm": 21.41402244567871,
      "learning_rate": 0.00012177738362694757,
      "loss": 4.3776,
      "step": 367
    },
    {
      "epoch": 0.08250658595370215,
      "grad_norm": 26.154260635375977,
      "learning_rate": 0.00012140780777544367,
      "loss": 5.0361,
      "step": 368
    },
    {
      "epoch": 0.08273078863292416,
      "grad_norm": 23.87849998474121,
      "learning_rate": 0.00012103792522290682,
      "loss": 6.1016,
      "step": 369
    },
    {
      "epoch": 0.08295499131214618,
      "grad_norm": 22.090389251708984,
      "learning_rate": 0.00012066774126849529,
      "loss": 6.0558,
      "step": 370
    },
    {
      "epoch": 0.0831791939913682,
      "grad_norm": 26.19266128540039,
      "learning_rate": 0.00012029726121568541,
      "loss": 5.8491,
      "step": 371
    },
    {
      "epoch": 0.08340339667059021,
      "grad_norm": 29.90646743774414,
      "learning_rate": 0.00011992649037219545,
      "loss": 7.2177,
      "step": 372
    },
    {
      "epoch": 0.08362759934981223,
      "grad_norm": 22.093286514282227,
      "learning_rate": 0.00011955543404990994,
      "loss": 4.6878,
      "step": 373
    },
    {
      "epoch": 0.08385180202903425,
      "grad_norm": 23.279293060302734,
      "learning_rate": 0.0001191840975648032,
      "loss": 5.6476,
      "step": 374
    },
    {
      "epoch": 0.08407600470825627,
      "grad_norm": 25.416563034057617,
      "learning_rate": 0.00011881248623686338,
      "loss": 5.1577,
      "step": 375
    },
    {
      "epoch": 0.08430020738747827,
      "grad_norm": 27.834501266479492,
      "learning_rate": 0.00011844060539001618,
      "loss": 6.3812,
      "step": 376
    },
    {
      "epoch": 0.08452441006670029,
      "grad_norm": 22.874313354492188,
      "learning_rate": 0.00011806846035204863,
      "loss": 5.3266,
      "step": 377
    },
    {
      "epoch": 0.08474861274592231,
      "grad_norm": 24.81113052368164,
      "learning_rate": 0.00011769605645453265,
      "loss": 5.7783,
      "step": 378
    },
    {
      "epoch": 0.08497281542514433,
      "grad_norm": 22.971466064453125,
      "learning_rate": 0.00011732339903274878,
      "loss": 6.5039,
      "step": 379
    },
    {
      "epoch": 0.08519701810436635,
      "grad_norm": 25.4050350189209,
      "learning_rate": 0.00011695049342560968,
      "loss": 5.5774,
      "step": 380
    },
    {
      "epoch": 0.08542122078358837,
      "grad_norm": 29.026569366455078,
      "learning_rate": 0.00011657734497558371,
      "loss": 4.7611,
      "step": 381
    },
    {
      "epoch": 0.08564542346281039,
      "grad_norm": 29.733060836791992,
      "learning_rate": 0.00011620395902861822,
      "loss": 6.5835,
      "step": 382
    },
    {
      "epoch": 0.0858696261420324,
      "grad_norm": 29.463947296142578,
      "learning_rate": 0.00011583034093406327,
      "loss": 5.567,
      "step": 383
    },
    {
      "epoch": 0.08609382882125441,
      "grad_norm": 24.28775405883789,
      "learning_rate": 0.00011545649604459466,
      "loss": 6.2566,
      "step": 384
    },
    {
      "epoch": 0.08631803150047643,
      "grad_norm": 20.342971801757812,
      "learning_rate": 0.00011508242971613741,
      "loss": 5.61,
      "step": 385
    },
    {
      "epoch": 0.08654223417969845,
      "grad_norm": 22.342500686645508,
      "learning_rate": 0.00011470814730778905,
      "loss": 6.012,
      "step": 386
    },
    {
      "epoch": 0.08676643685892046,
      "grad_norm": 20.931930541992188,
      "learning_rate": 0.00011433365418174278,
      "loss": 4.7274,
      "step": 387
    },
    {
      "epoch": 0.08699063953814248,
      "grad_norm": 27.429777145385742,
      "learning_rate": 0.00011395895570321064,
      "loss": 7.3026,
      "step": 388
    },
    {
      "epoch": 0.0872148422173645,
      "grad_norm": 25.487855911254883,
      "learning_rate": 0.00011358405724034676,
      "loss": 5.9912,
      "step": 389
    },
    {
      "epoch": 0.08743904489658652,
      "grad_norm": 23.963817596435547,
      "learning_rate": 0.00011320896416417026,
      "loss": 5.2803,
      "step": 390
    },
    {
      "epoch": 0.08766324757580853,
      "grad_norm": 21.640357971191406,
      "learning_rate": 0.00011283368184848842,
      "loss": 6.0277,
      "step": 391
    },
    {
      "epoch": 0.08788745025503054,
      "grad_norm": 24.89389419555664,
      "learning_rate": 0.00011245821566981976,
      "loss": 5.4938,
      "step": 392
    },
    {
      "epoch": 0.08811165293425256,
      "grad_norm": 24.243425369262695,
      "learning_rate": 0.0001120825710073169,
      "loss": 5.557,
      "step": 393
    },
    {
      "epoch": 0.08833585561347458,
      "grad_norm": 24.979612350463867,
      "learning_rate": 0.00011170675324268942,
      "loss": 5.636,
      "step": 394
    },
    {
      "epoch": 0.0885600582926966,
      "grad_norm": 35.96656036376953,
      "learning_rate": 0.000111330767760127,
      "loss": 7.8786,
      "step": 395
    },
    {
      "epoch": 0.08878426097191862,
      "grad_norm": 29.268381118774414,
      "learning_rate": 0.00011095461994622209,
      "loss": 6.1095,
      "step": 396
    },
    {
      "epoch": 0.08900846365114064,
      "grad_norm": 28.387245178222656,
      "learning_rate": 0.0001105783151898928,
      "loss": 5.8353,
      "step": 397
    },
    {
      "epoch": 0.08923266633036264,
      "grad_norm": 34.898292541503906,
      "learning_rate": 0.00011020185888230571,
      "loss": 6.896,
      "step": 398
    },
    {
      "epoch": 0.08945686900958466,
      "grad_norm": 29.814363479614258,
      "learning_rate": 0.00010982525641679859,
      "loss": 5.7637,
      "step": 399
    },
    {
      "epoch": 0.08968107168880668,
      "grad_norm": 24.08759117126465,
      "learning_rate": 0.00010944851318880314,
      "loss": 6.4127,
      "step": 400
    },
    {
      "epoch": 0.08968107168880668,
      "eval_loss": 0.7289469838142395,
      "eval_runtime": 704.3144,
      "eval_samples_per_second": 7.099,
      "eval_steps_per_second": 1.775,
      "step": 400
    }
  ],
  "logging_steps": 1,
  "max_steps": 840,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1250084863803392e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}