{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9993192648059904,
  "eval_steps": 92,
  "global_step": 367,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 0.17789718508720398,
      "learning_rate": 2e-05,
      "loss": 2.3216,
      "step": 1
    },
    {
      "epoch": 0.0,
      "eval_loss": 2.256117105484009,
      "eval_runtime": 52.5552,
      "eval_samples_per_second": 95.081,
      "eval_steps_per_second": 23.785,
      "step": 1
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.1491609364748001,
      "learning_rate": 4e-05,
      "loss": 2.2689,
      "step": 2
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.16114787757396698,
      "learning_rate": 6e-05,
      "loss": 2.1799,
      "step": 3
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.17484058439731598,
      "learning_rate": 8e-05,
      "loss": 2.2857,
      "step": 4
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.16328556835651398,
      "learning_rate": 0.0001,
      "loss": 2.1805,
      "step": 5
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.2006424516439438,
      "learning_rate": 0.00012,
      "loss": 2.3171,
      "step": 6
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.15052957832813263,
      "learning_rate": 0.00014,
      "loss": 2.2048,
      "step": 7
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.1444414258003235,
      "learning_rate": 0.00016,
      "loss": 2.181,
      "step": 8
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.174555703997612,
      "learning_rate": 0.00018,
      "loss": 2.0824,
      "step": 9
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.20063771307468414,
      "learning_rate": 0.0002,
      "loss": 2.1274,
      "step": 10
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.19133329391479492,
      "learning_rate": 0.00019999958540892524,
      "loss": 2.2436,
      "step": 11
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.19068902730941772,
      "learning_rate": 0.00019999834163913867,
      "loss": 2.0865,
      "step": 12
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.12937726080417633,
      "learning_rate": 0.00019999626870095333,
      "loss": 1.9834,
      "step": 13
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.12377699464559555,
      "learning_rate": 0.0001999933666115578,
      "loss": 2.0084,
      "step": 14
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.11349006742238998,
      "learning_rate": 0.00019998963539501557,
      "loss": 2.0472,
      "step": 15
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.10255803167819977,
      "learning_rate": 0.00019998507508226524,
      "loss": 2.0017,
      "step": 16
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.1226801723241806,
      "learning_rate": 0.00019997968571112013,
      "loss": 2.0241,
      "step": 17
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.09784600138664246,
      "learning_rate": 0.00019997346732626795,
      "loss": 1.9264,
      "step": 18
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.0987139344215393,
      "learning_rate": 0.00019996641997927043,
      "loss": 2.0021,
      "step": 19
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.1008625328540802,
      "learning_rate": 0.0001999585437285629,
      "loss": 1.9401,
      "step": 20
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.11675934493541718,
      "learning_rate": 0.00019994983863945388,
      "loss": 2.0533,
      "step": 21
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.1078399121761322,
      "learning_rate": 0.0001999403047841243,
      "loss": 2.067,
      "step": 22
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.10346037149429321,
      "learning_rate": 0.00019992994224162728,
      "loss": 1.9767,
      "step": 23
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.11017748713493347,
      "learning_rate": 0.0001999187510978872,
      "loss": 1.9501,
      "step": 24
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.11317062377929688,
      "learning_rate": 0.00019990673144569892,
      "loss": 1.9425,
      "step": 25
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.10313500463962555,
      "learning_rate": 0.0001998938833847273,
      "loss": 1.9594,
      "step": 26
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.1095932349562645,
      "learning_rate": 0.00019988020702150618,
      "loss": 1.951,
      "step": 27
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.11742599308490753,
      "learning_rate": 0.00019986570246943754,
      "loss": 2.0445,
      "step": 28
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.14208655059337616,
      "learning_rate": 0.00019985036984879052,
      "loss": 1.9932,
      "step": 29
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.10696502774953842,
      "learning_rate": 0.00019983420928670044,
      "loss": 1.9076,
      "step": 30
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.10935875028371811,
      "learning_rate": 0.00019981722091716783,
      "loss": 1.8718,
      "step": 31
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.11814530938863754,
      "learning_rate": 0.00019979940488105722,
      "loss": 1.8591,
      "step": 32
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.12232942134141922,
      "learning_rate": 0.00019978076132609599,
      "loss": 1.9379,
      "step": 33
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.11652842909097672,
      "learning_rate": 0.00019976129040687318,
      "loss": 1.9731,
      "step": 34
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.1147683709859848,
      "learning_rate": 0.0001997409922848381,
      "loss": 1.8994,
      "step": 35
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.1180400475859642,
      "learning_rate": 0.00019971986712829932,
      "loss": 1.8678,
      "step": 36
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.13028429448604584,
      "learning_rate": 0.0001996979151124227,
      "loss": 1.9853,
      "step": 37
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.11380694806575775,
      "learning_rate": 0.00019967513641923056,
      "loss": 1.8388,
      "step": 38
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.13089893758296967,
      "learning_rate": 0.00019965153123759966,
      "loss": 1.8802,
      "step": 39
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.12069398909807205,
      "learning_rate": 0.00019962709976326,
      "loss": 1.9847,
      "step": 40
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.12704235315322876,
      "learning_rate": 0.00019960184219879303,
      "loss": 2.0103,
      "step": 41
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.15785923600196838,
      "learning_rate": 0.00019957575875362993,
      "loss": 1.9266,
      "step": 42
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.137678325176239,
      "learning_rate": 0.00019954884964404996,
      "loss": 1.827,
      "step": 43
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.12916652858257294,
      "learning_rate": 0.0001995211150931787,
      "loss": 1.8881,
      "step": 44
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.14117199182510376,
      "learning_rate": 0.00019949255533098604,
      "loss": 1.9003,
      "step": 45
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.122989721596241,
      "learning_rate": 0.00019946317059428448,
      "loss": 1.7859,
      "step": 46
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.14118267595767975,
      "learning_rate": 0.00019943296112672696,
      "loss": 1.9206,
      "step": 47
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.14580337703227997,
      "learning_rate": 0.00019940192717880502,
      "loss": 2.0004,
      "step": 48
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.1319318562746048,
      "learning_rate": 0.00019937006900784665,
      "loss": 1.9288,
      "step": 49
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.13234923779964447,
      "learning_rate": 0.00019933738687801403,
      "loss": 1.8757,
      "step": 50
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.13480357825756073,
      "learning_rate": 0.00019930388106030166,
      "loss": 1.773,
      "step": 51
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.15075266361236572,
      "learning_rate": 0.00019926955183253374,
      "loss": 1.9003,
      "step": 52
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.2747078537940979,
      "learning_rate": 0.00019923439947936204,
      "loss": 1.8076,
      "step": 53
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.14992934465408325,
      "learning_rate": 0.00019919842429226372,
      "loss": 1.9598,
      "step": 54
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.15926502645015717,
      "learning_rate": 0.0001991616265695385,
      "loss": 1.8815,
      "step": 55
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.18423113226890564,
      "learning_rate": 0.00019912400661630658,
      "loss": 2.0042,
      "step": 56
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.15437527000904083,
      "learning_rate": 0.00019908556474450593,
      "loss": 1.8524,
      "step": 57
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.15860721468925476,
      "learning_rate": 0.0001990463012728896,
      "loss": 1.9301,
      "step": 58
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.1519562005996704,
      "learning_rate": 0.00019900621652702336,
      "loss": 1.8769,
      "step": 59
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.13514740765094757,
      "learning_rate": 0.00019896531083928273,
      "loss": 1.7548,
      "step": 60
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.15928471088409424,
      "learning_rate": 0.00019892358454885042,
      "loss": 1.8667,
      "step": 61
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.15786142647266388,
      "learning_rate": 0.00019888103800171333,
      "loss": 1.8641,
      "step": 62
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.1386164277791977,
      "learning_rate": 0.00019883767155065986,
      "loss": 1.8872,
      "step": 63
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.14870542287826538,
      "learning_rate": 0.00019879348555527687,
      "loss": 1.8602,
      "step": 64
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.14343470335006714,
      "learning_rate": 0.00019874848038194673,
      "loss": 1.8312,
      "step": 65
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.15904268622398376,
      "learning_rate": 0.00019870265640384435,
      "loss": 1.9288,
      "step": 66
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.1546896994113922,
      "learning_rate": 0.00019865601400093395,
      "loss": 1.9167,
      "step": 67
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.15036776661872864,
      "learning_rate": 0.000198608553559966,
      "loss": 1.8157,
      "step": 68
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.155603289604187,
      "learning_rate": 0.000198560275474474,
      "loss": 1.8193,
      "step": 69
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.14846371114253998,
      "learning_rate": 0.00019851118014477126,
      "loss": 1.7431,
      "step": 70
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.15555807948112488,
      "learning_rate": 0.00019846126797794743,
      "loss": 1.9226,
      "step": 71
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.14305201172828674,
      "learning_rate": 0.00019841053938786534,
      "loss": 1.8991,
      "step": 72
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.14723321795463562,
      "learning_rate": 0.00019835899479515737,
      "loss": 1.881,
      "step": 73
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.14168229699134827,
      "learning_rate": 0.00019830663462722207,
      "loss": 1.9365,
      "step": 74
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.16648411750793457,
      "learning_rate": 0.00019825345931822068,
      "loss": 1.764,
      "step": 75
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.13298211991786957,
      "learning_rate": 0.00019819946930907332,
      "loss": 1.8581,
      "step": 76
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.15933053195476532,
      "learning_rate": 0.00019814466504745548,
      "loss": 1.8043,
      "step": 77
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.15350531041622162,
      "learning_rate": 0.00019808904698779433,
      "loss": 1.7964,
      "step": 78
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.17690815031528473,
      "learning_rate": 0.00019803261559126492,
      "loss": 1.8173,
      "step": 79
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.14556676149368286,
      "learning_rate": 0.0001979753713257863,
      "loss": 1.9111,
      "step": 80
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.14608439803123474,
      "learning_rate": 0.00019791731466601773,
      "loss": 1.8583,
      "step": 81
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.15660099685192108,
      "learning_rate": 0.0001978584460933546,
      "loss": 1.8686,
      "step": 82
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.2378729283809662,
      "learning_rate": 0.00019779876609592471,
      "loss": 1.7445,
      "step": 83
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.17274336516857147,
      "learning_rate": 0.00019773827516858386,
      "loss": 1.9353,
      "step": 84
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.15144622325897217,
      "learning_rate": 0.00019767697381291202,
      "loss": 1.8179,
      "step": 85
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.1504279226064682,
      "learning_rate": 0.00019761486253720915,
      "loss": 1.787,
      "step": 86
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.14772076904773712,
      "learning_rate": 0.0001975519418564908,
      "loss": 1.8928,
      "step": 87
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.16531221568584442,
      "learning_rate": 0.00019748821229248405,
      "loss": 1.7052,
      "step": 88
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.15720781683921814,
      "learning_rate": 0.00019742367437362306,
      "loss": 1.8116,
      "step": 89
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.15642230212688446,
      "learning_rate": 0.00019735832863504476,
      "loss": 1.7233,
      "step": 90
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.13698022067546844,
      "learning_rate": 0.00019729217561858433,
      "loss": 1.7699,
      "step": 91
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.16550354659557343,
      "learning_rate": 0.00019722521587277076,
      "loss": 1.7379,
      "step": 92
    },
    {
      "epoch": 0.25,
      "eval_loss": 1.785460114479065,
      "eval_runtime": 54.2174,
      "eval_samples_per_second": 92.166,
      "eval_steps_per_second": 23.055,
      "step": 92
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.1539517045021057,
      "learning_rate": 0.00019715744995282234,
      "loss": 1.7921,
      "step": 93
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.1603965014219284,
      "learning_rate": 0.00019708887842064194,
      "loss": 1.7856,
      "step": 94
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.14334900677204132,
      "learning_rate": 0.0001970195018448125,
      "loss": 1.8048,
      "step": 95
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.17852160334587097,
      "learning_rate": 0.00019694932080059217,
      "loss": 1.7513,
      "step": 96
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.15032339096069336,
      "learning_rate": 0.00019687833586990973,
      "loss": 1.7011,
      "step": 97
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.1456947922706604,
      "learning_rate": 0.00019680654764135945,
      "loss": 1.7992,
      "step": 98
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.14242622256278992,
      "learning_rate": 0.00019673395671019654,
      "loss": 1.8617,
      "step": 99
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.15148206055164337,
      "learning_rate": 0.00019666056367833204,
      "loss": 1.8464,
      "step": 100
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.15412554144859314,
      "learning_rate": 0.00019658636915432788,
      "loss": 1.8757,
      "step": 101
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.1881706863641739,
      "learning_rate": 0.0001965113737533918,
      "loss": 1.7233,
      "step": 102
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.16812562942504883,
      "learning_rate": 0.0001964355780973723,
      "loss": 1.769,
      "step": 103
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.14640142023563385,
      "learning_rate": 0.00019635898281475346,
      "loss": 1.8155,
      "step": 104
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.16034264862537384,
      "learning_rate": 0.00019628158854064956,
      "loss": 1.7034,
      "step": 105
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.14522109925746918,
      "learning_rate": 0.00019620339591680023,
      "loss": 1.8194,
      "step": 106
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.1690577268600464,
      "learning_rate": 0.0001961244055915647,
      "loss": 1.7467,
      "step": 107
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.17564715445041656,
      "learning_rate": 0.00019604461821991667,
      "loss": 1.8696,
      "step": 108
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.1871030628681183,
      "learning_rate": 0.00019596403446343877,
      "loss": 1.8975,
      "step": 109
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.18129503726959229,
      "learning_rate": 0.0001958826549903171,
      "loss": 1.8295,
      "step": 110
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.16357164084911346,
      "learning_rate": 0.00019580048047533578,
      "loss": 1.813,
      "step": 111
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.15929792821407318,
      "learning_rate": 0.00019571751159987115,
      "loss": 1.7072,
      "step": 112
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.14020949602127075,
      "learning_rate": 0.00019563374905188637,
      "loss": 1.8245,
      "step": 113
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.14771193265914917,
      "learning_rate": 0.0001955491935259255,
      "loss": 1.7532,
      "step": 114
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.1625107079744339,
      "learning_rate": 0.0001954638457231079,
      "loss": 1.7653,
      "step": 115
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.15289072692394257,
      "learning_rate": 0.0001953777063511223,
      "loss": 1.7301,
      "step": 116
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.15066611766815186,
      "learning_rate": 0.00019529077612422103,
      "loss": 1.7909,
      "step": 117
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.16926345229148865,
      "learning_rate": 0.00019520305576321395,
      "loss": 1.7426,
      "step": 118
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.16127844154834747,
      "learning_rate": 0.00019511454599546268,
      "loss": 1.7841,
      "step": 119
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.14246778190135956,
      "learning_rate": 0.0001950252475548744,
      "loss": 1.7545,
      "step": 120
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.15499025583267212,
      "learning_rate": 0.00019493516118189582,
      "loss": 1.7749,
      "step": 121
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.16287535429000854,
      "learning_rate": 0.00019484428762350708,
      "loss": 1.7878,
      "step": 122
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.14317578077316284,
      "learning_rate": 0.00019475262763321552,
      "loss": 1.8787,
      "step": 123
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.15122784674167633,
      "learning_rate": 0.00019466018197104946,
      "loss": 1.8259,
      "step": 124
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.1579144448041916,
      "learning_rate": 0.00019456695140355172,
      "loss": 1.8568,
      "step": 125
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.15908168256282806,
      "learning_rate": 0.0001944729367037736,
      "loss": 1.7898,
      "step": 126
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.17988181114196777,
      "learning_rate": 0.0001943781386512682,
      "loss": 1.8017,
      "step": 127
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.16047564148902893,
      "learning_rate": 0.000194282558032084,
      "loss": 1.6842,
      "step": 128
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.2199389785528183,
      "learning_rate": 0.0001941861956387585,
      "loss": 1.7777,
      "step": 129
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.17500443756580353,
      "learning_rate": 0.00019408905227031142,
      "loss": 1.817,
      "step": 130
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.16257035732269287,
      "learning_rate": 0.00019399112873223824,
      "loss": 1.7822,
      "step": 131
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.1655006855726242,
      "learning_rate": 0.0001938924258365035,
      "loss": 1.7835,
      "step": 132
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.1625986397266388,
      "learning_rate": 0.00019379294440153392,
      "loss": 1.739,
      "step": 133
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.1542993187904358,
      "learning_rate": 0.00019369268525221185,
      "loss": 1.8484,
      "step": 134
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.16408205032348633,
      "learning_rate": 0.00019359164921986825,
      "loss": 1.7889,
      "step": 135
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.1816944181919098,
      "learning_rate": 0.00019348983714227583,
      "loss": 1.8592,
      "step": 136
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.1641003042459488,
      "learning_rate": 0.00019338724986364222,
      "loss": 1.7293,
      "step": 137
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.14509302377700806,
      "learning_rate": 0.00019328388823460283,
      "loss": 1.653,
      "step": 138
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.14293956756591797,
      "learning_rate": 0.00019317975311221373,
      "loss": 1.8303,
      "step": 139
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.17679671943187714,
      "learning_rate": 0.00019307484535994492,
      "loss": 1.7262,
      "step": 140
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.142549067735672,
      "learning_rate": 0.00019296916584767262,
      "loss": 1.8038,
      "step": 141
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.17163245379924774,
      "learning_rate": 0.00019286271545167254,
      "loss": 1.7815,
      "step": 142
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.1682298481464386,
      "learning_rate": 0.0001927554950546124,
      "loss": 1.7159,
      "step": 143
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.17430084943771362,
      "learning_rate": 0.00019264750554554453,
      "loss": 1.8462,
      "step": 144
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.1589604616165161,
      "learning_rate": 0.00019253874781989864,
      "loss": 1.7369,
      "step": 145
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.15902858972549438,
      "learning_rate": 0.00019242922277947448,
      "loss": 1.8005,
      "step": 146
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.15692317485809326,
      "learning_rate": 0.00019231893133243405,
      "loss": 1.7759,
      "step": 147
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.15179891884326935,
      "learning_rate": 0.00019220787439329438,
      "loss": 1.8517,
      "step": 148
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.14860700070858002,
      "learning_rate": 0.00019209605288291978,
      "loss": 1.7751,
      "step": 149
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.1454017162322998,
      "learning_rate": 0.0001919834677285142,
      "loss": 1.6579,
      "step": 150
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.16802151501178741,
      "learning_rate": 0.00019187011986361374,
      "loss": 1.7853,
      "step": 151
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.16814345121383667,
      "learning_rate": 0.0001917560102280786,
      "loss": 1.7162,
      "step": 152
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.15314815938472748,
      "learning_rate": 0.0001916411397680855,
      "loss": 1.7066,
      "step": 153
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.16011942923069,
      "learning_rate": 0.00019152550943611987,
      "loss": 1.7655,
      "step": 154
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.15423813462257385,
      "learning_rate": 0.00019140912019096766,
      "loss": 1.8106,
      "step": 155
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.1538185477256775,
      "learning_rate": 0.0001912919729977078,
      "loss": 1.7952,
      "step": 156
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.16051077842712402,
      "learning_rate": 0.00019117406882770388,
      "loss": 1.7182,
      "step": 157
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.15189512073993683,
      "learning_rate": 0.00019105540865859623,
      "loss": 1.6282,
      "step": 158
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.16353580355644226,
      "learning_rate": 0.0001909359934742938,
      "loss": 1.7374,
      "step": 159
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.16629937291145325,
      "learning_rate": 0.00019081582426496598,
      "loss": 1.6122,
      "step": 160
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.16899485886096954,
      "learning_rate": 0.00019069490202703438,
      "loss": 1.6817,
      "step": 161
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.1827431470155716,
      "learning_rate": 0.00019057322776316467,
      "loss": 1.7633,
      "step": 162
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.17833983898162842,
      "learning_rate": 0.00019045080248225805,
      "loss": 1.6124,
      "step": 163
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.1423504501581192,
      "learning_rate": 0.00019032762719944316,
      "loss": 1.7344,
      "step": 164
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.1658603847026825,
      "learning_rate": 0.0001902037029360674,
      "loss": 1.6874,
      "step": 165
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.16833803057670593,
      "learning_rate": 0.00019007903071968868,
      "loss": 1.7291,
      "step": 166
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.16885894536972046,
      "learning_rate": 0.00018995361158406676,
      "loss": 1.77,
      "step": 167
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.16659806668758392,
      "learning_rate": 0.00018982744656915475,
      "loss": 1.8441,
      "step": 168
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.18617461621761322,
      "learning_rate": 0.00018970053672109037,
      "loss": 1.8355,
      "step": 169
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.17858782410621643,
      "learning_rate": 0.00018957288309218745,
      "loss": 1.7093,
      "step": 170
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.1546701192855835,
      "learning_rate": 0.00018944448674092714,
      "loss": 1.6651,
      "step": 171
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.16935370862483978,
      "learning_rate": 0.000189315348731949,
      "loss": 1.7196,
      "step": 172
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.17772410809993744,
      "learning_rate": 0.0001891854701360424,
      "loss": 1.7215,
      "step": 173
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.16293296217918396,
      "learning_rate": 0.00018905485203013744,
      "loss": 1.7094,
      "step": 174
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.1712435483932495,
      "learning_rate": 0.00018892349549729615,
      "loss": 1.7627,
      "step": 175
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.19540230929851532,
      "learning_rate": 0.00018879140162670347,
      "loss": 1.7626,
      "step": 176
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.16615939140319824,
      "learning_rate": 0.00018865857151365814,
      "loss": 1.6614,
      "step": 177
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.14994904398918152,
      "learning_rate": 0.0001885250062595638,
      "loss": 1.8007,
      "step": 178
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.17429371178150177,
      "learning_rate": 0.0001883907069719197,
      "loss": 1.5822,
      "step": 179
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.1600300520658493,
      "learning_rate": 0.0001882556747643115,
      "loss": 1.7315,
      "step": 180
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.16705308854579926,
      "learning_rate": 0.00018811991075640223,
      "loss": 1.6875,
      "step": 181
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.1432919055223465,
      "learning_rate": 0.00018798341607392276,
      "loss": 1.662,
      "step": 182
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.1693781316280365,
      "learning_rate": 0.00018784619184866267,
      "loss": 1.6294,
      "step": 183
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.16618549823760986,
      "learning_rate": 0.0001877082392184607,
      "loss": 1.6935,
      "step": 184
    },
    {
      "epoch": 0.5,
      "eval_loss": 1.707476258277893,
      "eval_runtime": 53.476,
      "eval_samples_per_second": 93.444,
      "eval_steps_per_second": 23.375,
      "step": 184
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.19029615819454193,
      "learning_rate": 0.00018756955932719546,
      "loss": 1.6409,
      "step": 185
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.15953810513019562,
      "learning_rate": 0.00018743015332477588,
      "loss": 1.7592,
      "step": 186
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.1445915549993515,
      "learning_rate": 0.0001872900223671316,
      "loss": 1.7382,
      "step": 187
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.1905539631843567,
      "learning_rate": 0.0001871491676162035,
      "loss": 1.7496,
      "step": 188
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.19065023958683014,
      "learning_rate": 0.0001870075902399341,
      "loss": 1.7459,
      "step": 189
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.15250128507614136,
      "learning_rate": 0.00018686529141225767,
      "loss": 1.7847,
      "step": 190
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.16181302070617676,
      "learning_rate": 0.00018672227231309068,
      "loss": 1.6404,
      "step": 191
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.15402203798294067,
      "learning_rate": 0.00018657853412832202,
      "loss": 1.7612,
      "step": 192
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.16924121975898743,
      "learning_rate": 0.00018643407804980303,
      "loss": 1.7262,
      "step": 193
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.1564388871192932,
      "learning_rate": 0.00018628890527533777,
      "loss": 1.7721,
      "step": 194
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.17039404809474945,
      "learning_rate": 0.00018614301700867287,
      "loss": 1.6788,
      "step": 195
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.1548219621181488,
      "learning_rate": 0.0001859964144594879,
      "loss": 1.7128,
      "step": 196
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.16957992315292358,
      "learning_rate": 0.000185849098843385,
      "loss": 1.8554,
      "step": 197
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.15887251496315002,
      "learning_rate": 0.00018570107138187893,
      "loss": 1.691,
      "step": 198
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.1746351420879364,
      "learning_rate": 0.000185552333302387,
      "loss": 1.6902,
      "step": 199
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.15400560200214386,
      "learning_rate": 0.00018540288583821882,
      "loss": 1.7756,
      "step": 200
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.163401260972023,
      "learning_rate": 0.00018525273022856607,
      "loss": 1.6391,
      "step": 201
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.14885050058364868,
      "learning_rate": 0.0001851018677184923,
      "loss": 1.7449,
      "step": 202
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.15566030144691467,
      "learning_rate": 0.00018495029955892248,
      "loss": 1.7574,
      "step": 203
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.16466747224330902,
      "learning_rate": 0.00018479802700663268,
      "loss": 1.7116,
      "step": 204
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.15742923319339752,
      "learning_rate": 0.00018464505132423983,
      "loss": 1.6491,
      "step": 205
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.15772201120853424,
      "learning_rate": 0.00018449137378019094,
      "loss": 1.7971,
      "step": 206
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.17034031450748444,
      "learning_rate": 0.00018433699564875274,
      "loss": 1.7036,
      "step": 207
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.1637440025806427,
      "learning_rate": 0.0001841819182100012,
      "loss": 1.5544,
      "step": 208
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.18623477220535278,
      "learning_rate": 0.00018402614274981073,
      "loss": 1.632,
      "step": 209
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.16553111374378204,
      "learning_rate": 0.0001838696705598436,
      "loss": 1.7081,
      "step": 210
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.15178020298480988,
      "learning_rate": 0.0001837125029375393,
      "loss": 1.679,
      "step": 211
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.16419006884098053,
      "learning_rate": 0.00018355464118610372,
      "loss": 1.7082,
      "step": 212
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.1607130765914917,
      "learning_rate": 0.00018339608661449832,
      "loss": 1.6493,
      "step": 213
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.17754729092121124,
      "learning_rate": 0.00018323684053742932,
      "loss": 1.7558,
      "step": 214
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.16623522341251373,
      "learning_rate": 0.00018307690427533672,
      "loss": 1.7677,
      "step": 215
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.16194763779640198,
      "learning_rate": 0.00018291627915438348,
      "loss": 1.7749,
      "step": 216
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.17232032120227814,
      "learning_rate": 0.00018275496650644444,
      "loss": 1.8273,
      "step": 217
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.16804206371307373,
      "learning_rate": 0.00018259296766909527,
      "loss": 1.7504,
      "step": 218
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.1571667343378067,
      "learning_rate": 0.00018243028398560142,
      "loss": 1.7331,
      "step": 219
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.16855494678020477,
      "learning_rate": 0.00018226691680490694,
      "loss": 1.694,
      "step": 220
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.18118086457252502,
      "learning_rate": 0.00018210286748162336,
      "loss": 1.7338,
      "step": 221
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.16491609811782837,
      "learning_rate": 0.00018193813737601834,
      "loss": 1.5984,
      "step": 222
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.15478603541851044,
      "learning_rate": 0.00018177272785400455,
      "loss": 1.7077,
      "step": 223
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.14907459914684296,
      "learning_rate": 0.0001816066402871282,
      "loss": 1.6867,
      "step": 224
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.16465577483177185,
      "learning_rate": 0.00018143987605255774,
      "loss": 1.7904,
      "step": 225
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.1661553680896759,
      "learning_rate": 0.00018127243653307248,
      "loss": 1.7439,
      "step": 226
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.15185391902923584,
      "learning_rate": 0.00018110432311705096,
      "loss": 1.6711,
      "step": 227
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.15746577084064484,
      "learning_rate": 0.00018093553719845967,
      "loss": 1.7139,
      "step": 228
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.16057291626930237,
      "learning_rate": 0.00018076608017684128,
      "loss": 1.6659,
      "step": 229
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.17637218534946442,
      "learning_rate": 0.00018059595345730318,
      "loss": 1.7832,
      "step": 230
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.16048584878444672,
      "learning_rate": 0.00018042515845050576,
      "loss": 1.8092,
      "step": 231
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.1690172702074051,
      "learning_rate": 0.00018025369657265075,
      "loss": 1.6495,
      "step": 232
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.1493247002363205,
      "learning_rate": 0.0001800815692454694,
      "loss": 1.6867,
      "step": 233
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.1496494710445404,
      "learning_rate": 0.00017990877789621082,
      "loss": 1.6808,
      "step": 234
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.1575721800327301,
      "learning_rate": 0.00017973532395763,
      "loss": 1.7341,
      "step": 235
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.16140134632587433,
      "learning_rate": 0.00017956120886797604,
      "loss": 1.7025,
      "step": 236
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.1708807647228241,
      "learning_rate": 0.0001793864340709802,
      "loss": 1.7168,
      "step": 237
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.1652187556028366,
      "learning_rate": 0.00017921100101584388,
      "loss": 1.6333,
      "step": 238
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.15541191399097443,
      "learning_rate": 0.00017903491115722666,
      "loss": 1.6765,
      "step": 239
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.15625408291816711,
      "learning_rate": 0.00017885816595523423,
      "loss": 1.7528,
      "step": 240
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.171896293759346,
      "learning_rate": 0.00017868076687540624,
      "loss": 1.6741,
      "step": 241
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.1624470204114914,
      "learning_rate": 0.00017850271538870423,
      "loss": 1.5913,
      "step": 242
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.163376584649086,
      "learning_rate": 0.00017832401297149928,
      "loss": 1.6242,
      "step": 243
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.1690063625574112,
      "learning_rate": 0.00017814466110555998,
      "loss": 1.6997,
      "step": 244
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.18232744932174683,
      "learning_rate": 0.00017796466127804,
      "loss": 1.7033,
      "step": 245
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.16556936502456665,
      "learning_rate": 0.0001777840149814657,
      "loss": 1.8036,
      "step": 246
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.1530187577009201,
      "learning_rate": 0.00017760272371372402,
      "loss": 1.7847,
      "step": 247
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.17229686677455902,
      "learning_rate": 0.00017742078897804974,
      "loss": 1.6999,
      "step": 248
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.1453051120042801,
      "learning_rate": 0.00017723821228301322,
      "loss": 1.7255,
      "step": 249
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.1597098410129547,
      "learning_rate": 0.00017705499514250784,
      "loss": 1.7228,
      "step": 250
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.20154576003551483,
      "learning_rate": 0.0001768711390757374,
      "loss": 1.6099,
      "step": 251
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.17710669338703156,
      "learning_rate": 0.0001766866456072036,
      "loss": 1.6167,
      "step": 252
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.15468710660934448,
      "learning_rate": 0.00017650151626669337,
      "loss": 1.6875,
      "step": 253
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.18249762058258057,
      "learning_rate": 0.0001763157525892661,
      "loss": 1.5819,
      "step": 254
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.16782326996326447,
      "learning_rate": 0.0001761293561152411,
      "loss": 1.626,
      "step": 255
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.16319702565670013,
      "learning_rate": 0.0001759423283901846,
      "loss": 1.6173,
      "step": 256
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.15339410305023193,
      "learning_rate": 0.00017575467096489717,
      "loss": 1.7897,
      "step": 257
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.15668465197086334,
      "learning_rate": 0.00017556638539540067,
      "loss": 1.6749,
      "step": 258
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.1564616560935974,
      "learning_rate": 0.00017537747324292542,
      "loss": 1.6263,
      "step": 259
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.15310418605804443,
      "learning_rate": 0.00017518793607389723,
      "loss": 1.7237,
      "step": 260
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.1633821427822113,
      "learning_rate": 0.00017499777545992452,
      "loss": 1.7156,
      "step": 261
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.18414661288261414,
      "learning_rate": 0.00017480699297778518,
      "loss": 1.6333,
      "step": 262
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.18508172035217285,
      "learning_rate": 0.00017461559020941341,
      "loss": 1.681,
      "step": 263
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.17592370510101318,
      "learning_rate": 0.0001744235687418869,
      "loss": 1.7787,
      "step": 264
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.22177156805992126,
      "learning_rate": 0.00017423093016741333,
      "loss": 1.6066,
      "step": 265
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.1583690643310547,
      "learning_rate": 0.00017403767608331733,
      "loss": 1.7423,
      "step": 266
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.17558494210243225,
      "learning_rate": 0.00017384380809202737,
      "loss": 1.7306,
      "step": 267
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.1737305372953415,
      "learning_rate": 0.00017364932780106212,
      "loss": 1.8139,
      "step": 268
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.15237008035182953,
      "learning_rate": 0.00017345423682301755,
      "loss": 1.7415,
      "step": 269
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.1741713285446167,
      "learning_rate": 0.00017325853677555312,
      "loss": 1.73,
      "step": 270
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.1688138246536255,
      "learning_rate": 0.00017306222928137875,
      "loss": 1.774,
      "step": 271
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.16588321328163147,
      "learning_rate": 0.00017286531596824112,
      "loss": 1.758,
      "step": 272
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.17456404864788055,
      "learning_rate": 0.00017266779846891029,
      "loss": 1.7528,
      "step": 273
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.15763048827648163,
      "learning_rate": 0.00017246967842116605,
      "loss": 1.661,
      "step": 274
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.1601736843585968,
      "learning_rate": 0.00017227095746778456,
      "loss": 1.7317,
      "step": 275
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.17678223550319672,
      "learning_rate": 0.00017207163725652445,
      "loss": 1.7016,
      "step": 276
    },
    {
      "epoch": 0.75,
      "eval_loss": 1.666338324546814,
      "eval_runtime": 53.3064,
      "eval_samples_per_second": 93.741,
      "eval_steps_per_second": 23.449,
      "step": 276
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.1592448651790619,
      "learning_rate": 0.00017187171944011329,
      "loss": 1.6313,
      "step": 277
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.1765425056219101,
      "learning_rate": 0.000171671205676234,
      "loss": 1.5646,
      "step": 278
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.14587025344371796,
      "learning_rate": 0.00017147009762751085,
      "loss": 1.7655,
      "step": 279
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.15663780272006989,
      "learning_rate": 0.00017126839696149596,
      "loss": 1.6468,
      "step": 280
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.15041159093379974,
      "learning_rate": 0.00017106610535065517,
      "loss": 1.6655,
      "step": 281
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.18636269867420197,
      "learning_rate": 0.0001708632244723545,
      "loss": 1.7274,
      "step": 282
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.2026071399450302,
      "learning_rate": 0.00017065975600884584,
      "loss": 1.7669,
      "step": 283
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.16321098804473877,
      "learning_rate": 0.00017045570164725348,
      "loss": 1.5634,
      "step": 284
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.17123541235923767,
      "learning_rate": 0.00017025106307955973,
      "loss": 1.6881,
      "step": 285
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.17135639488697052,
      "learning_rate": 0.00017004584200259107,
      "loss": 1.5511,
      "step": 286
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.149318128824234,
      "learning_rate": 0.00016984004011800404,
      "loss": 1.7526,
      "step": 287
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.17461049556732178,
      "learning_rate": 0.0001696336591322711,
      "loss": 1.7297,
      "step": 288
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.22167545557022095,
      "learning_rate": 0.00016942670075666656,
      "loss": 1.5982,
      "step": 289
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.17257270216941833,
      "learning_rate": 0.00016921916670725233,
      "loss": 1.6988,
      "step": 290
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.16062453389167786,
      "learning_rate": 0.00016901105870486372,
      "loss": 1.621,
      "step": 291
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.18726034462451935,
      "learning_rate": 0.00016880237847509514,
      "loss": 1.6037,
      "step": 292
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.1890726536512375,
      "learning_rate": 0.00016859312774828578,
      "loss": 1.6991,
      "step": 293
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.1621987223625183,
      "learning_rate": 0.0001683833082595053,
      "loss": 1.6365,
      "step": 294
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.15142592787742615,
      "learning_rate": 0.0001681729217485395,
      "loss": 1.5566,
      "step": 295
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.15878473222255707,
      "learning_rate": 0.0001679619699598757,
      "loss": 1.6339,
      "step": 296
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.19840176403522491,
      "learning_rate": 0.00016775045464268855,
      "loss": 1.7045,
      "step": 297
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.15840516984462738,
      "learning_rate": 0.00016753837755082527,
      "loss": 1.7066,
      "step": 298
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.14891847968101501,
      "learning_rate": 0.00016732574044279122,
      "loss": 1.6095,
      "step": 299
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.1543874889612198,
      "learning_rate": 0.0001671125450817354,
      "loss": 1.6635,
      "step": 300
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.1737508326768875,
      "learning_rate": 0.00016689879323543566,
      "loss": 1.7243,
      "step": 301
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.1600562036037445,
      "learning_rate": 0.00016668448667628418,
      "loss": 1.6657,
      "step": 302
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.16577617824077606,
      "learning_rate": 0.00016646962718127264,
      "loss": 1.6408,
      "step": 303
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.1584424525499344,
      "learning_rate": 0.00016625421653197766,
      "loss": 1.7327,
      "step": 304
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.16025269031524658,
      "learning_rate": 0.00016603825651454588,
      "loss": 1.7496,
      "step": 305
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.1708802878856659,
      "learning_rate": 0.0001658217489196792,
      "loss": 1.6233,
      "step": 306
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.17108985781669617,
      "learning_rate": 0.00016560469554262,
      "loss": 1.675,
      "step": 307
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.17331109941005707,
      "learning_rate": 0.00016538709818313604,
      "loss": 1.6796,
      "step": 308
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.15554888546466827,
      "learning_rate": 0.0001651689586455059,
      "loss": 1.6977,
      "step": 309
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.16161341965198517,
      "learning_rate": 0.0001649502787385036,
      "loss": 1.5421,
      "step": 310
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.16354724764823914,
      "learning_rate": 0.00016473106027538393,
      "loss": 1.6105,
      "step": 311
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.16034872829914093,
      "learning_rate": 0.0001645113050738673,
      "loss": 1.7455,
      "step": 312
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.15332373976707458,
      "learning_rate": 0.00016429101495612453,
      "loss": 1.5715,
      "step": 313
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.18118220567703247,
      "learning_rate": 0.00016407019174876196,
      "loss": 1.6783,
      "step": 314
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.16754361987113953,
      "learning_rate": 0.00016384883728280626,
      "loss": 1.596,
      "step": 315
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.1616910696029663,
      "learning_rate": 0.00016362695339368913,
      "loss": 1.699,
      "step": 316
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.1674581617116928,
      "learning_rate": 0.00016340454192123217,
      "loss": 1.6238,
      "step": 317
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.1575167030096054,
      "learning_rate": 0.00016318160470963158,
      "loss": 1.7563,
      "step": 318
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.15855339169502258,
      "learning_rate": 0.00016295814360744296,
      "loss": 1.6587,
      "step": 319
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.16675756871700287,
      "learning_rate": 0.00016273416046756585,
      "loss": 1.5694,
      "step": 320
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.17339494824409485,
      "learning_rate": 0.0001625096571472285,
      "loss": 1.6924,
      "step": 321
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.16791300475597382,
      "learning_rate": 0.00016228463550797234,
      "loss": 1.6103,
      "step": 322
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.1806572824716568,
      "learning_rate": 0.00016205909741563663,
      "loss": 1.7016,
      "step": 323
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.18338143825531006,
      "learning_rate": 0.00016183304474034303,
      "loss": 1.6367,
      "step": 324
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.17175601422786713,
      "learning_rate": 0.00016160647935647987,
      "loss": 1.6221,
      "step": 325
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.1569746434688568,
      "learning_rate": 0.00016137940314268695,
      "loss": 1.6587,
      "step": 326
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.16621094942092896,
      "learning_rate": 0.00016115181798183968,
      "loss": 1.7476,
      "step": 327
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.1589597761631012,
      "learning_rate": 0.00016092372576103362,
      "loss": 1.608,
      "step": 328
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.1526154726743698,
      "learning_rate": 0.00016069512837156867,
      "loss": 1.6524,
      "step": 329
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.16909892857074738,
      "learning_rate": 0.00016046602770893365,
      "loss": 1.7135,
      "step": 330
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.16316530108451843,
      "learning_rate": 0.00016023642567279033,
      "loss": 1.645,
      "step": 331
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.15762114524841309,
      "learning_rate": 0.00016000632416695782,
      "loss": 1.6342,
      "step": 332
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.15512891113758087,
      "learning_rate": 0.0001597757250993967,
      "loss": 1.6937,
      "step": 333
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.1490001082420349,
      "learning_rate": 0.0001595446303821933,
      "loss": 1.6558,
      "step": 334
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.167209193110466,
      "learning_rate": 0.00015931304193154375,
      "loss": 1.7354,
      "step": 335
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.15756173431873322,
      "learning_rate": 0.00015908096166773817,
      "loss": 1.6624,
      "step": 336
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.35730743408203125,
      "learning_rate": 0.0001588483915151447,
      "loss": 1.7502,
      "step": 337
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.17207658290863037,
      "learning_rate": 0.00015861533340219347,
      "loss": 1.7045,
      "step": 338
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.1688750982284546,
      "learning_rate": 0.00015838178926136078,
      "loss": 1.7443,
      "step": 339
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.15904007852077484,
      "learning_rate": 0.00015814776102915295,
      "loss": 1.6744,
      "step": 340
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.15581969916820526,
      "learning_rate": 0.0001579132506460903,
      "loss": 1.6926,
      "step": 341
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.1648828089237213,
      "learning_rate": 0.0001576782600566911,
      "loss": 1.6929,
      "step": 342
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.16498371958732605,
      "learning_rate": 0.00015744279120945534,
      "loss": 1.7607,
      "step": 343
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.1721397489309311,
      "learning_rate": 0.00015720684605684864,
      "loss": 1.7413,
      "step": 344
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.20110780000686646,
      "learning_rate": 0.00015697042655528617,
      "loss": 1.7579,
      "step": 345
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.17458587884902954,
      "learning_rate": 0.00015673353466511618,
      "loss": 1.557,
      "step": 346
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.1674317717552185,
      "learning_rate": 0.00015649617235060395,
      "loss": 1.7079,
      "step": 347
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.17642170190811157,
      "learning_rate": 0.0001562583415799154,
      "loss": 1.7137,
      "step": 348
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.17334245145320892,
      "learning_rate": 0.00015602004432510084,
      "loss": 1.6618,
      "step": 349
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.19081345200538635,
      "learning_rate": 0.00015578128256207857,
      "loss": 1.6069,
      "step": 350
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.1641138792037964,
      "learning_rate": 0.00015554205827061855,
      "loss": 1.7307,
      "step": 351
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.18359099328517914,
      "learning_rate": 0.0001553023734343258,
      "loss": 1.6646,
      "step": 352
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.15749670565128326,
      "learning_rate": 0.00015506223004062427,
      "loss": 1.6696,
      "step": 353
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.15676377713680267,
      "learning_rate": 0.00015482163008074016,
      "loss": 1.6257,
      "step": 354
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.1613236665725708,
      "learning_rate": 0.00015458057554968533,
      "loss": 1.6906,
      "step": 355
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.15893089771270752,
      "learning_rate": 0.0001543390684462409,
      "loss": 1.7515,
      "step": 356
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.16093188524246216,
      "learning_rate": 0.00015409711077294066,
      "loss": 1.7285,
      "step": 357
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.1732104867696762,
      "learning_rate": 0.00015385470453605456,
      "loss": 1.728,
      "step": 358
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.18478652834892273,
      "learning_rate": 0.0001536118517455717,
      "loss": 1.6798,
      "step": 359
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.1561679095029831,
      "learning_rate": 0.00015336855441518414,
      "loss": 1.4988,
      "step": 360
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.16175530850887299,
      "learning_rate": 0.00015312481456226986,
      "loss": 1.5661,
      "step": 361
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.15828688442707062,
      "learning_rate": 0.0001528806342078763,
      "loss": 1.6894,
      "step": 362
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.1670212745666504,
      "learning_rate": 0.00015263601537670332,
      "loss": 1.6946,
      "step": 363
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.15261001884937286,
      "learning_rate": 0.00015239096009708665,
      "loss": 1.647,
      "step": 364
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.15754546225070953,
      "learning_rate": 0.00015214547040098082,
      "loss": 1.65,
      "step": 365
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.15401124954223633,
      "learning_rate": 0.00015189954832394266,
      "loss": 1.6826,
      "step": 366
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.15601174533367157,
      "learning_rate": 0.00015165319590511412,
      "loss": 1.7028,
      "step": 367
    }
  ],
  "logging_steps": 1,
  "max_steps": 1101,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 367,
  "total_flos": 1.0951433437776445e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}