{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 7.0,
  "eval_steps": 29,
  "global_step": 147,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04938271604938271,
      "grad_norm": 5.25681209564209,
      "learning_rate": 0.0,
      "loss": 1.71002197265625,
      "step": 1
    },
    {
      "epoch": 0.09876543209876543,
      "grad_norm": 4.3470282554626465,
      "learning_rate": 5e-05,
      "loss": 1.547821044921875,
      "step": 2
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 2.8532915115356445,
      "learning_rate": 0.0001,
      "loss": 1.5648193359375,
      "step": 3
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 2.228372573852539,
      "learning_rate": 0.00015,
      "loss": 1.530792236328125,
      "step": 4
    },
    {
      "epoch": 0.24691358024691357,
      "grad_norm": 1.735770583152771,
      "learning_rate": 0.0002,
      "loss": 1.36871337890625,
      "step": 5
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.8590698838233948,
      "learning_rate": 0.00025,
      "loss": 1.2898101806640625,
      "step": 6
    },
    {
      "epoch": 0.345679012345679,
      "grad_norm": 0.8590450286865234,
      "learning_rate": 0.0002499755276685243,
      "loss": 1.46746826171875,
      "step": 7
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.7296649217605591,
      "learning_rate": 0.00024990212265199737,
      "loss": 1.4048614501953125,
      "step": 8
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.6279696226119995,
      "learning_rate": 0.00024977982087825713,
      "loss": 1.3926773071289062,
      "step": 9
    },
    {
      "epoch": 0.49382716049382713,
      "grad_norm": 0.467413067817688,
      "learning_rate": 0.0002496086822074945,
      "loss": 1.190582275390625,
      "step": 10
    },
    {
      "epoch": 0.5432098765432098,
      "grad_norm": 0.40420469641685486,
      "learning_rate": 0.0002493887904029551,
      "loss": 1.397552490234375,
      "step": 11
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.447272390127182,
      "learning_rate": 0.00024912025308994145,
      "loss": 1.1631317138671875,
      "step": 12
    },
    {
      "epoch": 0.6419753086419753,
      "grad_norm": 0.4043784439563751,
      "learning_rate": 0.0002488032017031364,
      "loss": 1.3308563232421875,
      "step": 13
    },
    {
      "epoch": 0.691358024691358,
      "grad_norm": 0.4438956081867218,
      "learning_rate": 0.00024843779142227256,
      "loss": 1.3337440490722656,
      "step": 14
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 0.34970614314079285,
      "learning_rate": 0.0002480242010961803,
      "loss": 1.3263282775878906,
      "step": 15
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.3530415892601013,
      "learning_rate": 0.00024756263315525067,
      "loss": 1.3926849365234375,
      "step": 16
    },
    {
      "epoch": 0.8395061728395061,
      "grad_norm": 0.3591199815273285,
      "learning_rate": 0.00024705331351235676,
      "loss": 1.3209381103515625,
      "step": 17
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.3194695711135864,
      "learning_rate": 0.000246496491452281,
      "loss": 1.2825927734375,
      "step": 18
    },
    {
      "epoch": 0.9382716049382716,
      "grad_norm": 0.3573833405971527,
      "learning_rate": 0.000245892439509704,
      "loss": 1.323028564453125,
      "step": 19
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.3397640585899353,
      "learning_rate": 0.00024524145333581316,
      "loss": 1.2393341064453125,
      "step": 20
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.4994087219238281,
      "learning_rate": 0.00024454385155359707,
      "loss": 1.349365234375,
      "step": 21
    },
    {
      "epoch": 1.0493827160493827,
      "grad_norm": 0.3036208748817444,
      "learning_rate": 0.00024379997560189677,
      "loss": 1.2958526611328125,
      "step": 22
    },
    {
      "epoch": 1.0987654320987654,
      "grad_norm": 0.29232341051101685,
      "learning_rate": 0.00024301018956828963,
      "loss": 1.2221832275390625,
      "step": 23
    },
    {
      "epoch": 1.1481481481481481,
      "grad_norm": 0.31793642044067383,
      "learning_rate": 0.00024217488001088784,
      "loss": 1.290985107421875,
      "step": 24
    },
    {
      "epoch": 1.1975308641975309,
      "grad_norm": 0.2753116190433502,
      "learning_rate": 0.0002412944557691389,
      "loss": 1.31658935546875,
      "step": 25
    },
    {
      "epoch": 1.2469135802469136,
      "grad_norm": 0.274697482585907,
      "learning_rate": 0.00024036934776372037,
      "loss": 1.212890625,
      "step": 26
    },
    {
      "epoch": 1.2962962962962963,
      "grad_norm": 0.23561221361160278,
      "learning_rate": 0.00023940000878562757,
      "loss": 1.15576171875,
      "step": 27
    },
    {
      "epoch": 1.345679012345679,
      "grad_norm": 0.25771093368530273,
      "learning_rate": 0.00023838691327455615,
      "loss": 1.3094940185546875,
      "step": 28
    },
    {
      "epoch": 1.3950617283950617,
      "grad_norm": 0.24315078556537628,
      "learning_rate": 0.00023733055708668926,
      "loss": 1.263580322265625,
      "step": 29
    },
    {
      "epoch": 1.4444444444444444,
      "grad_norm": 0.2666112780570984,
      "learning_rate": 0.0002362314572520028,
      "loss": 1.2547836303710938,
      "step": 30
    },
    {
      "epoch": 1.4938271604938271,
      "grad_norm": 0.23751471936702728,
      "learning_rate": 0.00023509015172120624,
      "loss": 1.1026458740234375,
      "step": 31
    },
    {
      "epoch": 1.4938271604938271,
      "eval_loss": 1.265625,
      "eval_runtime": 0.9594,
      "eval_samples_per_second": 2.085,
      "eval_steps_per_second": 1.042,
      "step": 31
    },
    {
      "epoch": 1.5432098765432098,
      "grad_norm": 0.2607089579105377,
      "learning_rate": 0.0002339071991024449,
      "loss": 1.28887939453125,
      "step": 32
    },
    {
      "epoch": 1.5925925925925926,
      "grad_norm": 0.26426321268081665,
      "learning_rate": 0.00023268317838789088,
      "loss": 1.0847930908203125,
      "step": 33
    },
    {
      "epoch": 1.6419753086419753,
      "grad_norm": 0.27232876420021057,
      "learning_rate": 0.00023141868867035747,
      "loss": 1.2251052856445312,
      "step": 34
    },
    {
      "epoch": 1.691358024691358,
      "grad_norm": 0.24696682393550873,
      "learning_rate": 0.00023011434885007482,
      "loss": 1.2270622253417969,
      "step": 35
    },
    {
      "epoch": 1.7407407407407407,
      "grad_norm": 0.26149365305900574,
      "learning_rate": 0.00022877079733177186,
      "loss": 1.2318115234375,
      "step": 36
    },
    {
      "epoch": 1.7901234567901234,
      "grad_norm": 0.24535240232944489,
      "learning_rate": 0.00022738869171221073,
      "loss": 1.3035202026367188,
      "step": 37
    },
    {
      "epoch": 1.8395061728395061,
      "grad_norm": 0.2595789134502411,
      "learning_rate": 0.00022596870845832852,
      "loss": 1.2228317260742188,
      "step": 38
    },
    {
      "epoch": 1.8888888888888888,
      "grad_norm": 0.31860774755477905,
      "learning_rate": 0.00022451154257614286,
      "loss": 1.1981201171875,
      "step": 39
    },
    {
      "epoch": 1.9382716049382716,
      "grad_norm": 0.307458758354187,
      "learning_rate": 0.00022301790727058347,
      "loss": 1.22918701171875,
      "step": 40
    },
    {
      "epoch": 1.9876543209876543,
      "grad_norm": 0.23014342784881592,
      "learning_rate": 0.00022148853359641623,
      "loss": 1.1669158935546875,
      "step": 41
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.4729158580303192,
      "learning_rate": 0.0002199241701004314,
      "loss": 1.1728515625,
      "step": 42
    },
    {
      "epoch": 2.049382716049383,
      "grad_norm": 0.3366452157497406,
      "learning_rate": 0.00021832558245506935,
      "loss": 1.207427978515625,
      "step": 43
    },
    {
      "epoch": 2.0987654320987654,
      "grad_norm": 0.3107839822769165,
      "learning_rate": 0.00021669355308366506,
      "loss": 1.1574554443359375,
      "step": 44
    },
    {
      "epoch": 2.148148148148148,
      "grad_norm": 0.3020878732204437,
      "learning_rate": 0.00021502888077749372,
      "loss": 1.21209716796875,
      "step": 45
    },
    {
      "epoch": 2.197530864197531,
      "grad_norm": 0.2926070988178253,
      "learning_rate": 0.00021333238030480473,
      "loss": 1.2313995361328125,
      "step": 46
    },
    {
      "epoch": 2.246913580246914,
      "grad_norm": 0.26616376638412476,
      "learning_rate": 0.00021160488201203643,
      "loss": 1.156585693359375,
      "step": 47
    },
    {
      "epoch": 2.2962962962962963,
      "grad_norm": 0.2578714191913605,
      "learning_rate": 0.00020984723141740576,
      "loss": 1.0979995727539062,
      "step": 48
    },
    {
      "epoch": 2.3456790123456788,
      "grad_norm": 0.29350578784942627,
      "learning_rate": 0.00020806028879707212,
      "loss": 1.2372207641601562,
      "step": 49
    },
    {
      "epoch": 2.3950617283950617,
      "grad_norm": 0.29217612743377686,
      "learning_rate": 0.00020624492876407808,
      "loss": 1.2001113891601562,
      "step": 50
    },
    {
      "epoch": 2.4444444444444446,
      "grad_norm": 0.3036291003227234,
      "learning_rate": 0.00020440203984027324,
      "loss": 1.1746063232421875,
      "step": 51
    },
    {
      "epoch": 2.493827160493827,
      "grad_norm": 0.24638646841049194,
      "learning_rate": 0.0002025325240214299,
      "loss": 1.050689697265625,
      "step": 52
    },
    {
      "epoch": 2.5432098765432096,
      "grad_norm": 0.31981024146080017,
      "learning_rate": 0.0002006372963357644,
      "loss": 1.2250442504882812,
      "step": 53
    },
    {
      "epoch": 2.5925925925925926,
      "grad_norm": 0.3018425405025482,
      "learning_rate": 0.00019871728439607966,
      "loss": 1.0356178283691406,
      "step": 54
    },
    {
      "epoch": 2.6419753086419755,
      "grad_norm": 0.29421937465667725,
      "learning_rate": 0.0001967734279457482,
      "loss": 1.1572036743164062,
      "step": 55
    },
    {
      "epoch": 2.691358024691358,
      "grad_norm": 0.26850154995918274,
      "learning_rate": 0.00019480667839875788,
      "loss": 1.1639747619628906,
      "step": 56
    },
    {
      "epoch": 2.7407407407407405,
      "grad_norm": 0.30604299902915955,
      "learning_rate": 0.0001928179983740455,
      "loss": 1.1637630462646484,
      "step": 57
    },
    {
      "epoch": 2.7901234567901234,
      "grad_norm": 0.3135574758052826,
      "learning_rate": 0.00019080836122434646,
      "loss": 1.2458114624023438,
      "step": 58
    },
    {
      "epoch": 2.8395061728395063,
      "grad_norm": 0.2999131381511688,
      "learning_rate": 0.00018877875055979022,
      "loss": 1.1515579223632812,
      "step": 59
    },
    {
      "epoch": 2.888888888888889,
      "grad_norm": 0.29539626836776733,
      "learning_rate": 0.00018673015976647573,
      "loss": 1.1273193359375,
      "step": 60
    },
    {
      "epoch": 2.888888888888889,
      "eval_loss": 1.23828125,
      "eval_runtime": 0.9559,
      "eval_samples_per_second": 2.092,
      "eval_steps_per_second": 1.046,
      "step": 60
    },
    {
      "epoch": 2.9382716049382713,
      "grad_norm": 0.3361843228340149,
      "learning_rate": 0.00018466359152026198,
      "loss": 1.1572113037109375,
      "step": 61
    },
    {
      "epoch": 2.9876543209876543,
      "grad_norm": 0.2982211709022522,
      "learning_rate": 0.0001825800572960118,
      "loss": 1.11712646484375,
      "step": 62
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.6304918527603149,
      "learning_rate": 0.00018048057687252868,
      "loss": 1.011474609375,
      "step": 63
    },
    {
      "epoch": 3.049382716049383,
      "grad_norm": 0.3850592374801636,
      "learning_rate": 0.00017836617783342968,
      "loss": 1.1339263916015625,
      "step": 64
    },
    {
      "epoch": 3.0987654320987654,
      "grad_norm": 0.42818403244018555,
      "learning_rate": 0.0001762378950641979,
      "loss": 1.1064300537109375,
      "step": 65
    },
    {
      "epoch": 3.148148148148148,
      "grad_norm": 0.36842140555381775,
      "learning_rate": 0.00017409677024566146,
      "loss": 1.14141845703125,
      "step": 66
    },
    {
      "epoch": 3.197530864197531,
      "grad_norm": 0.40696412324905396,
      "learning_rate": 0.0001719438513441461,
      "loss": 1.164276123046875,
      "step": 67
    },
    {
      "epoch": 3.246913580246914,
      "grad_norm": 0.3139958381652832,
      "learning_rate": 0.0001697801920985517,
      "loss": 1.1175537109375,
      "step": 68
    },
    {
      "epoch": 3.2962962962962963,
      "grad_norm": 0.3170965909957886,
      "learning_rate": 0.00016760685150460364,
      "loss": 1.0541839599609375,
      "step": 69
    },
    {
      "epoch": 3.3456790123456788,
      "grad_norm": 0.3839226961135864,
      "learning_rate": 0.00016542489329653023,
      "loss": 1.182159423828125,
      "step": 70
    },
    {
      "epoch": 3.3950617283950617,
      "grad_norm": 0.33293765783309937,
      "learning_rate": 0.00016323538542642227,
      "loss": 1.1481399536132812,
      "step": 71
    },
    {
      "epoch": 3.4444444444444446,
      "grad_norm": 0.38391292095184326,
      "learning_rate": 0.00016103939954152703,
      "loss": 1.1070671081542969,
      "step": 72
    },
    {
      "epoch": 3.493827160493827,
      "grad_norm": 0.32796546816825867,
      "learning_rate": 0.00015883801045973425,
      "loss": 1.011688232421875,
      "step": 73
    },
    {
      "epoch": 3.5432098765432096,
      "grad_norm": 0.35083672404289246,
      "learning_rate": 0.00015663229564351038,
      "loss": 1.1720008850097656,
      "step": 74
    },
    {
      "epoch": 3.5925925925925926,
      "grad_norm": 0.3070056438446045,
      "learning_rate": 0.0001544233346725379,
      "loss": 0.9922523498535156,
      "step": 75
    },
    {
      "epoch": 3.6419753086419755,
      "grad_norm": 0.34680983424186707,
      "learning_rate": 0.00015221220871531872,
      "loss": 1.0983657836914062,
      "step": 76
    },
    {
      "epoch": 3.691358024691358,
      "grad_norm": 0.3488447368144989,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.1119155883789062,
      "step": 77
    },
    {
      "epoch": 3.7407407407407405,
      "grad_norm": 0.35251104831695557,
      "learning_rate": 0.00014778779128468133,
      "loss": 1.103586196899414,
      "step": 78
    },
    {
      "epoch": 3.7901234567901234,
      "grad_norm": 0.34638622403144836,
      "learning_rate": 0.00014557666532746214,
      "loss": 1.20166015625,
      "step": 79
    },
    {
      "epoch": 3.8395061728395063,
      "grad_norm": 0.3701181709766388,
      "learning_rate": 0.00014336770435648965,
      "loss": 1.0947341918945312,
      "step": 80
    },
    {
      "epoch": 3.888888888888889,
      "grad_norm": 0.36047980189323425,
      "learning_rate": 0.00014116198954026578,
      "loss": 1.070587158203125,
      "step": 81
    },
    {
      "epoch": 3.9382716049382713,
      "grad_norm": 0.35548630356788635,
      "learning_rate": 0.00013896060045847302,
      "loss": 1.0939178466796875,
      "step": 82
    },
    {
      "epoch": 3.9876543209876543,
      "grad_norm": 0.3634969890117645,
      "learning_rate": 0.00013676461457357776,
      "loss": 1.0791015625,
      "step": 83
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.7552258968353271,
      "learning_rate": 0.00013457510670346977,
      "loss": 0.8719482421875,
      "step": 84
    },
    {
      "epoch": 4.049382716049383,
      "grad_norm": 0.41717907786369324,
      "learning_rate": 0.0001323931484953964,
      "loss": 1.0666046142578125,
      "step": 85
    },
    {
      "epoch": 4.098765432098766,
      "grad_norm": 0.49032023549079895,
      "learning_rate": 0.00013021980790144826,
      "loss": 1.0593414306640625,
      "step": 86
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.40296366810798645,
      "learning_rate": 0.00012805614865585397,
      "loss": 1.07305908203125,
      "step": 87
    },
    {
      "epoch": 4.197530864197531,
      "grad_norm": 0.4764576852321625,
      "learning_rate": 0.00012590322975433856,
      "loss": 1.10174560546875,
      "step": 88
    },
    {
      "epoch": 4.246913580246914,
      "grad_norm": 0.475600004196167,
      "learning_rate": 0.00012376210493580213,
      "loss": 1.0911865234375,
      "step": 89
    },
    {
      "epoch": 4.246913580246914,
      "eval_loss": 1.239013671875,
      "eval_runtime": 0.9267,
      "eval_samples_per_second": 2.158,
      "eval_steps_per_second": 1.079,
      "step": 89
    },
    {
      "epoch": 4.296296296296296,
      "grad_norm": 0.3585899770259857,
      "learning_rate": 0.00012163382216657033,
      "loss": 1.0165557861328125,
      "step": 90
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.43749985098838806,
      "learning_rate": 0.00011951942312747135,
      "loss": 1.1333770751953125,
      "step": 91
    },
    {
      "epoch": 4.395061728395062,
      "grad_norm": 0.4219837188720703,
      "learning_rate": 0.00011741994270398826,
      "loss": 1.1041412353515625,
      "step": 92
    },
    {
      "epoch": 4.444444444444445,
      "grad_norm": 0.49956807494163513,
      "learning_rate": 0.00011533640847973808,
      "loss": 1.0528182983398438,
      "step": 93
    },
    {
      "epoch": 4.493827160493828,
      "grad_norm": 0.31270042061805725,
      "learning_rate": 0.00011326984023352435,
      "loss": 0.976837158203125,
      "step": 94
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.399536669254303,
      "learning_rate": 0.00011122124944020978,
      "loss": 1.1287994384765625,
      "step": 95
    },
    {
      "epoch": 4.592592592592593,
      "grad_norm": 0.33787864446640015,
      "learning_rate": 0.00010919163877565351,
      "loss": 0.959564208984375,
      "step": 96
    },
    {
      "epoch": 4.6419753086419755,
      "grad_norm": 0.4175010621547699,
      "learning_rate": 0.00010718200162595449,
      "loss": 1.0494308471679688,
      "step": 97
    },
    {
      "epoch": 4.6913580246913575,
      "grad_norm": 0.4000602960586548,
      "learning_rate": 0.00010519332160124216,
      "loss": 1.0660667419433594,
      "step": 98
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.3906591236591339,
      "learning_rate": 0.00010322657205425185,
      "loss": 1.0525131225585938,
      "step": 99
    },
    {
      "epoch": 4.790123456790123,
      "grad_norm": 0.40287163853645325,
      "learning_rate": 0.00010128271560392038,
      "loss": 1.1645278930664062,
      "step": 100
    },
    {
      "epoch": 4.839506172839506,
      "grad_norm": 0.4290643632411957,
      "learning_rate": 9.936270366423563e-05,
      "loss": 1.0448684692382812,
      "step": 101
    },
    {
      "epoch": 4.888888888888889,
      "grad_norm": 0.44381940364837646,
      "learning_rate": 9.746747597857014e-05,
      "loss": 1.021392822265625,
      "step": 102
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.4356134235858917,
      "learning_rate": 9.559796015972678e-05,
      "loss": 1.0433349609375,
      "step": 103
    },
    {
      "epoch": 4.987654320987654,
      "grad_norm": 0.34763407707214355,
      "learning_rate": 9.375507123592195e-05,
      "loss": 1.04583740234375,
      "step": 104
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.9103137254714966,
      "learning_rate": 9.193971120292793e-05,
      "loss": 0.7581787109375,
      "step": 105
    },
    {
      "epoch": 5.049382716049383,
      "grad_norm": 0.4677075147628784,
      "learning_rate": 9.015276858259427e-05,
      "loss": 1.01220703125,
      "step": 106
    },
    {
      "epoch": 5.098765432098766,
      "grad_norm": 0.553494930267334,
      "learning_rate": 8.839511798796357e-05,
      "loss": 1.0217132568359375,
      "step": 107
    },
    {
      "epoch": 5.148148148148148,
      "grad_norm": 0.5269855260848999,
      "learning_rate": 8.66676196951953e-05,
      "loss": 1.0179901123046875,
      "step": 108
    },
    {
      "epoch": 5.197530864197531,
      "grad_norm": 0.5712403059005737,
      "learning_rate": 8.497111922250631e-05,
      "loss": 1.04754638671875,
      "step": 109
    },
    {
      "epoch": 5.246913580246914,
      "grad_norm": 0.6944426894187927,
      "learning_rate": 8.330644691633493e-05,
      "loss": 1.072967529296875,
      "step": 110
    },
    {
      "epoch": 5.296296296296296,
      "grad_norm": 0.4847879707813263,
      "learning_rate": 8.167441754493066e-05,
      "loss": 0.9911041259765625,
      "step": 111
    },
    {
      "epoch": 5.345679012345679,
      "grad_norm": 0.5206174254417419,
      "learning_rate": 8.00758298995686e-05,
      "loss": 1.0979385375976562,
      "step": 112
    },
    {
      "epoch": 5.395061728395062,
      "grad_norm": 0.50944584608078,
      "learning_rate": 7.851146640358377e-05,
      "loss": 1.0721282958984375,
      "step": 113
    },
    {
      "epoch": 5.444444444444445,
      "grad_norm": 0.6399138569831848,
      "learning_rate": 7.698209272941658e-05,
      "loss": 1.0106582641601562,
      "step": 114
    },
    {
      "epoch": 5.493827160493828,
      "grad_norm": 0.4612923562526703,
      "learning_rate": 7.548845742385718e-05,
      "loss": 0.9569854736328125,
      "step": 115
    },
    {
      "epoch": 5.54320987654321,
      "grad_norm": 0.4345049560070038,
      "learning_rate": 7.403129154167154e-05,
      "loss": 1.0953178405761719,
      "step": 116
    },
    {
      "epoch": 5.592592592592593,
      "grad_norm": 0.38961249589920044,
      "learning_rate": 7.261130828778935e-05,
      "loss": 0.9322776794433594,
      "step": 117
    },
    {
      "epoch": 5.6419753086419755,
      "grad_norm": 0.4707590639591217,
      "learning_rate": 7.12292026682282e-05,
      "loss": 1.0128402709960938,
      "step": 118
    },
    {
      "epoch": 5.6419753086419755,
      "eval_loss": 1.240234375,
      "eval_runtime": 0.9207,
      "eval_samples_per_second": 2.172,
      "eval_steps_per_second": 1.086,
      "step": 118
    },
    {
      "epoch": 5.6913580246913575,
      "grad_norm": 0.48423728346824646,
      "learning_rate": 6.98856511499252e-05,
      "loss": 1.0358314514160156,
      "step": 119
    },
    {
      "epoch": 5.7407407407407405,
      "grad_norm": 0.4736497700214386,
      "learning_rate": 6.85813113296426e-05,
      "loss": 1.0174751281738281,
      "step": 120
    },
    {
      "epoch": 5.790123456790123,
      "grad_norm": 0.4801523983478546,
      "learning_rate": 6.731682161210913e-05,
      "loss": 1.1348114013671875,
      "step": 121
    },
    {
      "epoch": 5.839506172839506,
      "grad_norm": 0.44162505865097046,
      "learning_rate": 6.609280089755515e-05,
      "loss": 1.0072555541992188,
      "step": 122
    },
    {
      "epoch": 5.888888888888889,
      "grad_norm": 0.44159969687461853,
      "learning_rate": 6.490984827879379e-05,
      "loss": 0.982696533203125,
      "step": 123
    },
    {
      "epoch": 5.938271604938271,
      "grad_norm": 0.457337886095047,
      "learning_rate": 6.376854274799722e-05,
      "loss": 1.0052337646484375,
      "step": 124
    },
    {
      "epoch": 5.987654320987654,
      "grad_norm": 0.4353809356689453,
      "learning_rate": 6.266944291331073e-05,
      "loss": 1.0258636474609375,
      "step": 125
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.9981463551521301,
      "learning_rate": 6.161308672544389e-05,
      "loss": 0.683349609375,
      "step": 126
    },
    {
      "epoch": 6.049382716049383,
      "grad_norm": 0.4959382116794586,
      "learning_rate": 6.059999121437244e-05,
      "loss": 0.975921630859375,
      "step": 127
    },
    {
      "epoch": 6.098765432098766,
      "grad_norm": 0.4520318806171417,
      "learning_rate": 5.963065223627963e-05,
      "loss": 0.9900970458984375,
      "step": 128
    },
    {
      "epoch": 6.148148148148148,
      "grad_norm": 0.47781136631965637,
      "learning_rate": 5.870554423086114e-05,
      "loss": 0.9780731201171875,
      "step": 129
    },
    {
      "epoch": 6.197530864197531,
      "grad_norm": 0.5892452001571655,
      "learning_rate": 5.7825119989112175e-05,
      "loss": 1.005706787109375,
      "step": 130
    },
    {
      "epoch": 6.246913580246914,
      "grad_norm": 0.7322431802749634,
      "learning_rate": 5.698981043171038e-05,
      "loss": 1.05029296875,
      "step": 131
    },
    {
      "epoch": 6.296296296296296,
      "grad_norm": 0.5611432194709778,
      "learning_rate": 5.620002439810326e-05,
      "loss": 0.9683609008789062,
      "step": 132
    },
    {
      "epoch": 6.345679012345679,
      "grad_norm": 0.5940067172050476,
      "learning_rate": 5.545614844640298e-05,
      "loss": 1.0691375732421875,
      "step": 133
    },
    {
      "epoch": 6.395061728395062,
      "grad_norm": 0.5109450221061707,
      "learning_rate": 5.475854666418687e-05,
      "loss": 1.046722412109375,
      "step": 134
    },
    {
      "epoch": 6.444444444444445,
      "grad_norm": 0.5654600262641907,
      "learning_rate": 5.4107560490295996e-05,
      "loss": 0.9742164611816406,
      "step": 135
    },
    {
      "epoch": 6.493827160493828,
      "grad_norm": 0.4135756194591522,
      "learning_rate": 5.350350854771902e-05,
      "loss": 0.940460205078125,
      "step": 136
    },
    {
      "epoch": 6.54320987654321,
      "grad_norm": 0.4793313145637512,
      "learning_rate": 5.294668648764328e-05,
      "loss": 1.0729026794433594,
      "step": 137
    },
    {
      "epoch": 6.592592592592593,
      "grad_norm": 0.4167643189430237,
      "learning_rate": 5.243736684474933e-05,
      "loss": 0.9159736633300781,
      "step": 138
    },
    {
      "epoch": 6.6419753086419755,
      "grad_norm": 0.5435214042663574,
      "learning_rate": 5.1975798903819716e-05,
      "loss": 0.9896240234375,
      "step": 139
    },
    {
      "epoch": 6.6913580246913575,
      "grad_norm": 0.4795510172843933,
      "learning_rate": 5.156220857772745e-05,
      "loss": 1.0148696899414062,
      "step": 140
    },
    {
      "epoch": 6.7407407407407405,
      "grad_norm": 0.48162156343460083,
      "learning_rate": 5.1196798296863607e-05,
      "loss": 0.9907112121582031,
      "step": 141
    },
    {
      "epoch": 6.790123456790123,
      "grad_norm": 0.461369127035141,
      "learning_rate": 5.087974691005855e-05,
      "loss": 1.1144561767578125,
      "step": 142
    },
    {
      "epoch": 6.839506172839506,
      "grad_norm": 0.4630836248397827,
      "learning_rate": 5.0611209597044934e-05,
      "loss": 0.9810867309570312,
      "step": 143
    },
    {
      "epoch": 6.888888888888889,
      "grad_norm": 0.4895261228084564,
      "learning_rate": 5.0391317792505526e-05,
      "loss": 0.9553680419921875,
      "step": 144
    },
    {
      "epoch": 6.938271604938271,
      "grad_norm": 0.5255072712898254,
      "learning_rate": 5.02201791217429e-05,
      "loss": 0.975860595703125,
      "step": 145
    },
    {
      "epoch": 6.987654320987654,
      "grad_norm": 0.4456087648868561,
      "learning_rate": 5.009787734800264e-05,
      "loss": 1.0084686279296875,
      "step": 146
    },
    {
      "epoch": 7.0,
      "grad_norm": 1.0660345554351807,
      "learning_rate": 5.0024472331475704e-05,
      "loss": 0.62939453125,
      "step": 147
    },
    {
      "epoch": 7.0,
      "eval_loss": 1.2626953125,
      "eval_runtime": 0.9239,
      "eval_samples_per_second": 2.165,
      "eval_steps_per_second": 1.082,
      "step": 147
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 147,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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": 1.960408178931794e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}