{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9990049751243781,
  "eval_steps": 100,
  "global_step": 251,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003980099502487562,
      "grad_norm": 3.8580713272094727,
      "learning_rate": 1e-07,
      "loss": 1.266,
      "step": 1
    },
    {
      "epoch": 0.007960199004975124,
      "grad_norm": 3.767099618911743,
      "learning_rate": 1e-07,
      "loss": 1.2058,
      "step": 2
    },
    {
      "epoch": 0.011940298507462687,
      "grad_norm": 3.6648917198181152,
      "learning_rate": 1e-07,
      "loss": 1.1977,
      "step": 3
    },
    {
      "epoch": 0.015920398009950248,
      "grad_norm": 4.032405853271484,
      "learning_rate": 1e-07,
      "loss": 1.3709,
      "step": 4
    },
    {
      "epoch": 0.01990049751243781,
      "grad_norm": 3.6155037879943848,
      "learning_rate": 1e-07,
      "loss": 1.1766,
      "step": 5
    },
    {
      "epoch": 0.023880597014925373,
      "grad_norm": 4.01386022567749,
      "learning_rate": 1e-07,
      "loss": 1.322,
      "step": 6
    },
    {
      "epoch": 0.027860696517412936,
      "grad_norm": 3.610419988632202,
      "learning_rate": 1e-07,
      "loss": 1.2293,
      "step": 7
    },
    {
      "epoch": 0.031840796019900496,
      "grad_norm": 3.849774122238159,
      "learning_rate": 1e-07,
      "loss": 1.2478,
      "step": 8
    },
    {
      "epoch": 0.03582089552238806,
      "grad_norm": 4.040029048919678,
      "learning_rate": 1e-07,
      "loss": 1.3693,
      "step": 9
    },
    {
      "epoch": 0.03980099502487562,
      "grad_norm": 3.2718212604522705,
      "learning_rate": 1e-07,
      "loss": 1.1815,
      "step": 10
    },
    {
      "epoch": 0.04378109452736319,
      "grad_norm": 3.513458490371704,
      "learning_rate": 1e-07,
      "loss": 1.2456,
      "step": 11
    },
    {
      "epoch": 0.04776119402985075,
      "grad_norm": 3.62939453125,
      "learning_rate": 1e-07,
      "loss": 1.2566,
      "step": 12
    },
    {
      "epoch": 0.051741293532338306,
      "grad_norm": 3.0019543170928955,
      "learning_rate": 1e-07,
      "loss": 1.1008,
      "step": 13
    },
    {
      "epoch": 0.05572139303482587,
      "grad_norm": 3.506714105606079,
      "learning_rate": 1e-07,
      "loss": 1.2656,
      "step": 14
    },
    {
      "epoch": 0.05970149253731343,
      "grad_norm": 3.310253858566284,
      "learning_rate": 1e-07,
      "loss": 1.2106,
      "step": 15
    },
    {
      "epoch": 0.06368159203980099,
      "grad_norm": 3.259761095046997,
      "learning_rate": 1e-07,
      "loss": 1.2235,
      "step": 16
    },
    {
      "epoch": 0.06766169154228856,
      "grad_norm": 3.4364163875579834,
      "learning_rate": 1e-07,
      "loss": 1.2248,
      "step": 17
    },
    {
      "epoch": 0.07164179104477612,
      "grad_norm": 3.2793073654174805,
      "learning_rate": 1e-07,
      "loss": 1.2489,
      "step": 18
    },
    {
      "epoch": 0.07562189054726368,
      "grad_norm": 3.304138660430908,
      "learning_rate": 1e-07,
      "loss": 1.2144,
      "step": 19
    },
    {
      "epoch": 0.07960199004975124,
      "grad_norm": 3.531829833984375,
      "learning_rate": 1e-07,
      "loss": 1.2233,
      "step": 20
    },
    {
      "epoch": 0.08358208955223881,
      "grad_norm": 2.7901320457458496,
      "learning_rate": 1e-07,
      "loss": 1.2514,
      "step": 21
    },
    {
      "epoch": 0.08756218905472637,
      "grad_norm": 2.325275182723999,
      "learning_rate": 1e-07,
      "loss": 1.1432,
      "step": 22
    },
    {
      "epoch": 0.09154228855721393,
      "grad_norm": 2.518044948577881,
      "learning_rate": 1e-07,
      "loss": 1.2058,
      "step": 23
    },
    {
      "epoch": 0.0955223880597015,
      "grad_norm": 2.309213161468506,
      "learning_rate": 1e-07,
      "loss": 1.1712,
      "step": 24
    },
    {
      "epoch": 0.09950248756218906,
      "grad_norm": 2.2889468669891357,
      "learning_rate": 1e-07,
      "loss": 1.1712,
      "step": 25
    },
    {
      "epoch": 0.10348258706467661,
      "grad_norm": 2.4013020992279053,
      "learning_rate": 1e-07,
      "loss": 1.1562,
      "step": 26
    },
    {
      "epoch": 0.10746268656716418,
      "grad_norm": 2.434525728225708,
      "learning_rate": 1e-07,
      "loss": 1.2198,
      "step": 27
    },
    {
      "epoch": 0.11144278606965174,
      "grad_norm": 2.251544952392578,
      "learning_rate": 1e-07,
      "loss": 1.1243,
      "step": 28
    },
    {
      "epoch": 0.1154228855721393,
      "grad_norm": 2.2087714672088623,
      "learning_rate": 1e-07,
      "loss": 1.0644,
      "step": 29
    },
    {
      "epoch": 0.11940298507462686,
      "grad_norm": 2.489380359649658,
      "learning_rate": 1e-07,
      "loss": 1.2045,
      "step": 30
    },
    {
      "epoch": 0.12338308457711443,
      "grad_norm": 2.4045751094818115,
      "learning_rate": 1e-07,
      "loss": 1.2104,
      "step": 31
    },
    {
      "epoch": 0.12736318407960198,
      "grad_norm": 2.1436238288879395,
      "learning_rate": 1e-07,
      "loss": 1.0513,
      "step": 32
    },
    {
      "epoch": 0.13134328358208955,
      "grad_norm": 2.2431857585906982,
      "learning_rate": 1e-07,
      "loss": 1.1339,
      "step": 33
    },
    {
      "epoch": 0.13532338308457711,
      "grad_norm": 2.311044454574585,
      "learning_rate": 1e-07,
      "loss": 1.1645,
      "step": 34
    },
    {
      "epoch": 0.13930348258706468,
      "grad_norm": 2.4365642070770264,
      "learning_rate": 1e-07,
      "loss": 1.1917,
      "step": 35
    },
    {
      "epoch": 0.14328358208955225,
      "grad_norm": 2.1745855808258057,
      "learning_rate": 1e-07,
      "loss": 1.1828,
      "step": 36
    },
    {
      "epoch": 0.1472636815920398,
      "grad_norm": 2.0474634170532227,
      "learning_rate": 1e-07,
      "loss": 1.1491,
      "step": 37
    },
    {
      "epoch": 0.15124378109452735,
      "grad_norm": 1.9449026584625244,
      "learning_rate": 1e-07,
      "loss": 1.08,
      "step": 38
    },
    {
      "epoch": 0.15522388059701492,
      "grad_norm": 3.04811692237854,
      "learning_rate": 1e-07,
      "loss": 1.1285,
      "step": 39
    },
    {
      "epoch": 0.15920398009950248,
      "grad_norm": 3.6523616313934326,
      "learning_rate": 1e-07,
      "loss": 1.1066,
      "step": 40
    },
    {
      "epoch": 0.16318407960199005,
      "grad_norm": 3.586474657058716,
      "learning_rate": 1e-07,
      "loss": 1.0668,
      "step": 41
    },
    {
      "epoch": 0.16716417910447762,
      "grad_norm": 3.7307212352752686,
      "learning_rate": 1e-07,
      "loss": 1.0895,
      "step": 42
    },
    {
      "epoch": 0.17114427860696518,
      "grad_norm": 3.6780145168304443,
      "learning_rate": 1e-07,
      "loss": 1.0969,
      "step": 43
    },
    {
      "epoch": 0.17512437810945275,
      "grad_norm": 3.404796600341797,
      "learning_rate": 1e-07,
      "loss": 1.0623,
      "step": 44
    },
    {
      "epoch": 0.1791044776119403,
      "grad_norm": 2.9056687355041504,
      "learning_rate": 1e-07,
      "loss": 1.0852,
      "step": 45
    },
    {
      "epoch": 0.18308457711442785,
      "grad_norm": 2.536485195159912,
      "learning_rate": 1e-07,
      "loss": 1.1154,
      "step": 46
    },
    {
      "epoch": 0.18706467661691542,
      "grad_norm": 2.7943172454833984,
      "learning_rate": 1e-07,
      "loss": 1.1182,
      "step": 47
    },
    {
      "epoch": 0.191044776119403,
      "grad_norm": 2.3565714359283447,
      "learning_rate": 1e-07,
      "loss": 1.0874,
      "step": 48
    },
    {
      "epoch": 0.19502487562189055,
      "grad_norm": 2.36067271232605,
      "learning_rate": 1e-07,
      "loss": 1.0897,
      "step": 49
    },
    {
      "epoch": 0.19900497512437812,
      "grad_norm": 1.958436369895935,
      "learning_rate": 1e-07,
      "loss": 1.0027,
      "step": 50
    },
    {
      "epoch": 0.20298507462686566,
      "grad_norm": 2.0697078704833984,
      "learning_rate": 1e-07,
      "loss": 1.0524,
      "step": 51
    },
    {
      "epoch": 0.20696517412935322,
      "grad_norm": 2.2829782962799072,
      "learning_rate": 1e-07,
      "loss": 1.0981,
      "step": 52
    },
    {
      "epoch": 0.2109452736318408,
      "grad_norm": 2.299952507019043,
      "learning_rate": 1e-07,
      "loss": 1.0779,
      "step": 53
    },
    {
      "epoch": 0.21492537313432836,
      "grad_norm": 2.0332202911376953,
      "learning_rate": 1e-07,
      "loss": 0.9759,
      "step": 54
    },
    {
      "epoch": 0.21890547263681592,
      "grad_norm": 2.410606622695923,
      "learning_rate": 1e-07,
      "loss": 1.0155,
      "step": 55
    },
    {
      "epoch": 0.2228855721393035,
      "grad_norm": 2.6469626426696777,
      "learning_rate": 1e-07,
      "loss": 1.1728,
      "step": 56
    },
    {
      "epoch": 0.22686567164179106,
      "grad_norm": 2.503451347351074,
      "learning_rate": 1e-07,
      "loss": 1.0717,
      "step": 57
    },
    {
      "epoch": 0.2308457711442786,
      "grad_norm": 2.1651253700256348,
      "learning_rate": 1e-07,
      "loss": 1.0946,
      "step": 58
    },
    {
      "epoch": 0.23482587064676616,
      "grad_norm": 2.1998214721679688,
      "learning_rate": 1e-07,
      "loss": 1.0693,
      "step": 59
    },
    {
      "epoch": 0.23880597014925373,
      "grad_norm": 2.221885919570923,
      "learning_rate": 1e-07,
      "loss": 1.0597,
      "step": 60
    },
    {
      "epoch": 0.2427860696517413,
      "grad_norm": 2.011728525161743,
      "learning_rate": 1e-07,
      "loss": 1.0108,
      "step": 61
    },
    {
      "epoch": 0.24676616915422886,
      "grad_norm": 2.034902334213257,
      "learning_rate": 1e-07,
      "loss": 1.0204,
      "step": 62
    },
    {
      "epoch": 0.2507462686567164,
      "grad_norm": 2.29103946685791,
      "learning_rate": 1e-07,
      "loss": 1.0653,
      "step": 63
    },
    {
      "epoch": 0.25472636815920396,
      "grad_norm": 2.3828279972076416,
      "learning_rate": 1e-07,
      "loss": 1.0372,
      "step": 64
    },
    {
      "epoch": 0.25870646766169153,
      "grad_norm": 2.386139392852783,
      "learning_rate": 1e-07,
      "loss": 1.0268,
      "step": 65
    },
    {
      "epoch": 0.2626865671641791,
      "grad_norm": 2.423414707183838,
      "learning_rate": 1e-07,
      "loss": 1.0457,
      "step": 66
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 2.455092191696167,
      "learning_rate": 1e-07,
      "loss": 1.0568,
      "step": 67
    },
    {
      "epoch": 0.27064676616915423,
      "grad_norm": 2.3402390480041504,
      "learning_rate": 1e-07,
      "loss": 1.016,
      "step": 68
    },
    {
      "epoch": 0.2746268656716418,
      "grad_norm": 2.493511199951172,
      "learning_rate": 1e-07,
      "loss": 1.0211,
      "step": 69
    },
    {
      "epoch": 0.27860696517412936,
      "grad_norm": 2.6465377807617188,
      "learning_rate": 1e-07,
      "loss": 1.0279,
      "step": 70
    },
    {
      "epoch": 0.28258706467661693,
      "grad_norm": 3.05757999420166,
      "learning_rate": 1e-07,
      "loss": 0.9864,
      "step": 71
    },
    {
      "epoch": 0.2865671641791045,
      "grad_norm": 2.768735408782959,
      "learning_rate": 1e-07,
      "loss": 1.0058,
      "step": 72
    },
    {
      "epoch": 0.29054726368159206,
      "grad_norm": 2.534254550933838,
      "learning_rate": 1e-07,
      "loss": 0.9786,
      "step": 73
    },
    {
      "epoch": 0.2945273631840796,
      "grad_norm": 1.736907720565796,
      "learning_rate": 1e-07,
      "loss": 0.9466,
      "step": 74
    },
    {
      "epoch": 0.29850746268656714,
      "grad_norm": 1.4108011722564697,
      "learning_rate": 1e-07,
      "loss": 0.9232,
      "step": 75
    },
    {
      "epoch": 0.3024875621890547,
      "grad_norm": 1.571252465248108,
      "learning_rate": 1e-07,
      "loss": 0.9139,
      "step": 76
    },
    {
      "epoch": 0.30646766169154227,
      "grad_norm": 1.639280915260315,
      "learning_rate": 1e-07,
      "loss": 0.9272,
      "step": 77
    },
    {
      "epoch": 0.31044776119402984,
      "grad_norm": 1.46147882938385,
      "learning_rate": 1e-07,
      "loss": 0.8913,
      "step": 78
    },
    {
      "epoch": 0.3144278606965174,
      "grad_norm": 1.1830153465270996,
      "learning_rate": 1e-07,
      "loss": 0.879,
      "step": 79
    },
    {
      "epoch": 0.31840796019900497,
      "grad_norm": 1.535416841506958,
      "learning_rate": 1e-07,
      "loss": 0.8703,
      "step": 80
    },
    {
      "epoch": 0.32238805970149254,
      "grad_norm": 1.8527772426605225,
      "learning_rate": 1e-07,
      "loss": 0.8882,
      "step": 81
    },
    {
      "epoch": 0.3263681592039801,
      "grad_norm": 1.4239050149917603,
      "learning_rate": 1e-07,
      "loss": 0.9042,
      "step": 82
    },
    {
      "epoch": 0.33034825870646767,
      "grad_norm": 1.9072166681289673,
      "learning_rate": 1e-07,
      "loss": 0.9118,
      "step": 83
    },
    {
      "epoch": 0.33432835820895523,
      "grad_norm": 1.8409007787704468,
      "learning_rate": 1e-07,
      "loss": 0.9043,
      "step": 84
    },
    {
      "epoch": 0.3383084577114428,
      "grad_norm": 1.3596872091293335,
      "learning_rate": 1e-07,
      "loss": 0.8902,
      "step": 85
    },
    {
      "epoch": 0.34228855721393037,
      "grad_norm": 1.314673900604248,
      "learning_rate": 1e-07,
      "loss": 0.8509,
      "step": 86
    },
    {
      "epoch": 0.34626865671641793,
      "grad_norm": 1.4804043769836426,
      "learning_rate": 1e-07,
      "loss": 0.8603,
      "step": 87
    },
    {
      "epoch": 0.3502487562189055,
      "grad_norm": 1.3986847400665283,
      "learning_rate": 1e-07,
      "loss": 0.8841,
      "step": 88
    },
    {
      "epoch": 0.354228855721393,
      "grad_norm": 1.3893916606903076,
      "learning_rate": 1e-07,
      "loss": 0.8705,
      "step": 89
    },
    {
      "epoch": 0.3582089552238806,
      "grad_norm": 1.4482388496398926,
      "learning_rate": 1e-07,
      "loss": 0.8706,
      "step": 90
    },
    {
      "epoch": 0.36218905472636814,
      "grad_norm": 1.446069359779358,
      "learning_rate": 1e-07,
      "loss": 0.8445,
      "step": 91
    },
    {
      "epoch": 0.3661691542288557,
      "grad_norm": 1.493567943572998,
      "learning_rate": 1e-07,
      "loss": 0.8823,
      "step": 92
    },
    {
      "epoch": 0.3701492537313433,
      "grad_norm": 1.6904833316802979,
      "learning_rate": 1e-07,
      "loss": 0.8494,
      "step": 93
    },
    {
      "epoch": 0.37412935323383084,
      "grad_norm": 1.469353199005127,
      "learning_rate": 1e-07,
      "loss": 0.8808,
      "step": 94
    },
    {
      "epoch": 0.3781094527363184,
      "grad_norm": 1.498508334159851,
      "learning_rate": 1e-07,
      "loss": 0.8738,
      "step": 95
    },
    {
      "epoch": 0.382089552238806,
      "grad_norm": 1.3189642429351807,
      "learning_rate": 1e-07,
      "loss": 0.8181,
      "step": 96
    },
    {
      "epoch": 0.38606965174129354,
      "grad_norm": 1.2873642444610596,
      "learning_rate": 1e-07,
      "loss": 0.8537,
      "step": 97
    },
    {
      "epoch": 0.3900497512437811,
      "grad_norm": 1.366760492324829,
      "learning_rate": 1e-07,
      "loss": 0.7977,
      "step": 98
    },
    {
      "epoch": 0.3940298507462687,
      "grad_norm": 1.363909125328064,
      "learning_rate": 1e-07,
      "loss": 0.9297,
      "step": 99
    },
    {
      "epoch": 0.39800995024875624,
      "grad_norm": 2.0010488033294678,
      "learning_rate": 1e-07,
      "loss": 0.8176,
      "step": 100
    },
    {
      "epoch": 0.4019900497512438,
      "grad_norm": 1.9680029153823853,
      "learning_rate": 1e-07,
      "loss": 0.818,
      "step": 101
    },
    {
      "epoch": 0.4059701492537313,
      "grad_norm": 1.674877405166626,
      "learning_rate": 1e-07,
      "loss": 0.8414,
      "step": 102
    },
    {
      "epoch": 0.4099502487562189,
      "grad_norm": 1.5867595672607422,
      "learning_rate": 1e-07,
      "loss": 0.7887,
      "step": 103
    },
    {
      "epoch": 0.41393034825870645,
      "grad_norm": 1.6069676876068115,
      "learning_rate": 1e-07,
      "loss": 0.9112,
      "step": 104
    },
    {
      "epoch": 0.417910447761194,
      "grad_norm": 1.5387823581695557,
      "learning_rate": 1e-07,
      "loss": 0.8173,
      "step": 105
    },
    {
      "epoch": 0.4218905472636816,
      "grad_norm": 1.2036306858062744,
      "learning_rate": 1e-07,
      "loss": 0.7781,
      "step": 106
    },
    {
      "epoch": 0.42587064676616915,
      "grad_norm": 1.4114856719970703,
      "learning_rate": 1e-07,
      "loss": 0.8078,
      "step": 107
    },
    {
      "epoch": 0.4298507462686567,
      "grad_norm": 1.2400673627853394,
      "learning_rate": 1e-07,
      "loss": 0.8003,
      "step": 108
    },
    {
      "epoch": 0.4338308457711443,
      "grad_norm": 1.3319138288497925,
      "learning_rate": 1e-07,
      "loss": 0.7651,
      "step": 109
    },
    {
      "epoch": 0.43781094527363185,
      "grad_norm": 1.2857623100280762,
      "learning_rate": 1e-07,
      "loss": 0.7556,
      "step": 110
    },
    {
      "epoch": 0.4417910447761194,
      "grad_norm": 1.5332382917404175,
      "learning_rate": 1e-07,
      "loss": 0.7802,
      "step": 111
    },
    {
      "epoch": 0.445771144278607,
      "grad_norm": 1.331517219543457,
      "learning_rate": 1e-07,
      "loss": 0.7785,
      "step": 112
    },
    {
      "epoch": 0.44975124378109455,
      "grad_norm": 1.271018147468567,
      "learning_rate": 1e-07,
      "loss": 0.7571,
      "step": 113
    },
    {
      "epoch": 0.4537313432835821,
      "grad_norm": 1.3966182470321655,
      "learning_rate": 1e-07,
      "loss": 0.7302,
      "step": 114
    },
    {
      "epoch": 0.4577114427860697,
      "grad_norm": 1.2569191455841064,
      "learning_rate": 1e-07,
      "loss": 0.725,
      "step": 115
    },
    {
      "epoch": 0.4616915422885572,
      "grad_norm": 1.4532155990600586,
      "learning_rate": 1e-07,
      "loss": 0.6981,
      "step": 116
    },
    {
      "epoch": 0.46567164179104475,
      "grad_norm": 1.393580436706543,
      "learning_rate": 1e-07,
      "loss": 0.6814,
      "step": 117
    },
    {
      "epoch": 0.4696517412935323,
      "grad_norm": 1.4711062908172607,
      "learning_rate": 1e-07,
      "loss": 0.6821,
      "step": 118
    },
    {
      "epoch": 0.4736318407960199,
      "grad_norm": 2.436079740524292,
      "learning_rate": 1e-07,
      "loss": 0.8096,
      "step": 119
    },
    {
      "epoch": 0.47761194029850745,
      "grad_norm": 1.2138607501983643,
      "learning_rate": 1e-07,
      "loss": 0.7009,
      "step": 120
    },
    {
      "epoch": 0.481592039800995,
      "grad_norm": 1.053438425064087,
      "learning_rate": 1e-07,
      "loss": 0.6848,
      "step": 121
    },
    {
      "epoch": 0.4855721393034826,
      "grad_norm": 1.3829809427261353,
      "learning_rate": 1e-07,
      "loss": 0.7276,
      "step": 122
    },
    {
      "epoch": 0.48955223880597015,
      "grad_norm": 1.6276544332504272,
      "learning_rate": 1e-07,
      "loss": 0.7052,
      "step": 123
    },
    {
      "epoch": 0.4935323383084577,
      "grad_norm": 1.399953007698059,
      "learning_rate": 1e-07,
      "loss": 0.7116,
      "step": 124
    },
    {
      "epoch": 0.4975124378109453,
      "grad_norm": 1.118137001991272,
      "learning_rate": 1e-07,
      "loss": 0.6912,
      "step": 125
    },
    {
      "epoch": 0.5014925373134328,
      "grad_norm": 0.9562084674835205,
      "learning_rate": 1e-07,
      "loss": 0.6726,
      "step": 126
    },
    {
      "epoch": 0.5054726368159204,
      "grad_norm": 1.0179568529129028,
      "learning_rate": 1e-07,
      "loss": 0.6047,
      "step": 127
    },
    {
      "epoch": 0.5094527363184079,
      "grad_norm": 0.950977087020874,
      "learning_rate": 1e-07,
      "loss": 0.6962,
      "step": 128
    },
    {
      "epoch": 0.5134328358208955,
      "grad_norm": 0.7613106966018677,
      "learning_rate": 1e-07,
      "loss": 0.6381,
      "step": 129
    },
    {
      "epoch": 0.5174129353233831,
      "grad_norm": 0.9950020909309387,
      "learning_rate": 1e-07,
      "loss": 0.6478,
      "step": 130
    },
    {
      "epoch": 0.5213930348258706,
      "grad_norm": 1.0094377994537354,
      "learning_rate": 1e-07,
      "loss": 0.6558,
      "step": 131
    },
    {
      "epoch": 0.5253731343283582,
      "grad_norm": 1.064998745918274,
      "learning_rate": 1e-07,
      "loss": 0.6483,
      "step": 132
    },
    {
      "epoch": 0.5293532338308458,
      "grad_norm": 0.7481135725975037,
      "learning_rate": 1e-07,
      "loss": 0.6469,
      "step": 133
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.9318634867668152,
      "learning_rate": 1e-07,
      "loss": 0.6822,
      "step": 134
    },
    {
      "epoch": 0.5373134328358209,
      "grad_norm": 0.7420485615730286,
      "learning_rate": 1e-07,
      "loss": 0.5645,
      "step": 135
    },
    {
      "epoch": 0.5412935323383085,
      "grad_norm": 0.7259682416915894,
      "learning_rate": 1e-07,
      "loss": 0.6168,
      "step": 136
    },
    {
      "epoch": 0.545273631840796,
      "grad_norm": 0.6080716252326965,
      "learning_rate": 1e-07,
      "loss": 0.5775,
      "step": 137
    },
    {
      "epoch": 0.5492537313432836,
      "grad_norm": 0.7300984263420105,
      "learning_rate": 1e-07,
      "loss": 0.6141,
      "step": 138
    },
    {
      "epoch": 0.5532338308457712,
      "grad_norm": 0.8576564192771912,
      "learning_rate": 1e-07,
      "loss": 0.5893,
      "step": 139
    },
    {
      "epoch": 0.5572139303482587,
      "grad_norm": 0.9741348624229431,
      "learning_rate": 1e-07,
      "loss": 0.6059,
      "step": 140
    },
    {
      "epoch": 0.5611940298507463,
      "grad_norm": 1.1145509481430054,
      "learning_rate": 1e-07,
      "loss": 0.6597,
      "step": 141
    },
    {
      "epoch": 0.5651741293532339,
      "grad_norm": 0.8707802891731262,
      "learning_rate": 1e-07,
      "loss": 0.6206,
      "step": 142
    },
    {
      "epoch": 0.5691542288557214,
      "grad_norm": 1.1013362407684326,
      "learning_rate": 1e-07,
      "loss": 0.6066,
      "step": 143
    },
    {
      "epoch": 0.573134328358209,
      "grad_norm": 1.1516404151916504,
      "learning_rate": 1e-07,
      "loss": 0.6594,
      "step": 144
    },
    {
      "epoch": 0.5771144278606966,
      "grad_norm": 0.7887628078460693,
      "learning_rate": 1e-07,
      "loss": 0.5577,
      "step": 145
    },
    {
      "epoch": 0.5810945273631841,
      "grad_norm": 0.8240315318107605,
      "learning_rate": 1e-07,
      "loss": 0.5911,
      "step": 146
    },
    {
      "epoch": 0.5850746268656717,
      "grad_norm": 0.6422097682952881,
      "learning_rate": 1e-07,
      "loss": 0.5345,
      "step": 147
    },
    {
      "epoch": 0.5890547263681593,
      "grad_norm": 0.6938869953155518,
      "learning_rate": 1e-07,
      "loss": 0.5884,
      "step": 148
    },
    {
      "epoch": 0.5930348258706468,
      "grad_norm": 1.2094863653182983,
      "learning_rate": 1e-07,
      "loss": 0.6102,
      "step": 149
    },
    {
      "epoch": 0.5970149253731343,
      "grad_norm": 0.876981258392334,
      "learning_rate": 1e-07,
      "loss": 0.6256,
      "step": 150
    },
    {
      "epoch": 0.6009950248756218,
      "grad_norm": 0.6353152394294739,
      "learning_rate": 1e-07,
      "loss": 0.5946,
      "step": 151
    },
    {
      "epoch": 0.6049751243781094,
      "grad_norm": 0.7054216265678406,
      "learning_rate": 1e-07,
      "loss": 0.5915,
      "step": 152
    },
    {
      "epoch": 0.608955223880597,
      "grad_norm": 0.6976187229156494,
      "learning_rate": 1e-07,
      "loss": 0.5769,
      "step": 153
    },
    {
      "epoch": 0.6129353233830845,
      "grad_norm": 0.727631688117981,
      "learning_rate": 1e-07,
      "loss": 0.6159,
      "step": 154
    },
    {
      "epoch": 0.6169154228855721,
      "grad_norm": 0.5325585007667542,
      "learning_rate": 1e-07,
      "loss": 0.6424,
      "step": 155
    },
    {
      "epoch": 0.6208955223880597,
      "grad_norm": 0.7219927906990051,
      "learning_rate": 1e-07,
      "loss": 0.599,
      "step": 156
    },
    {
      "epoch": 0.6248756218905472,
      "grad_norm": 0.4903685748577118,
      "learning_rate": 1e-07,
      "loss": 0.5413,
      "step": 157
    },
    {
      "epoch": 0.6288557213930348,
      "grad_norm": 0.6661394238471985,
      "learning_rate": 1e-07,
      "loss": 0.5479,
      "step": 158
    },
    {
      "epoch": 0.6328358208955224,
      "grad_norm": 0.9018793702125549,
      "learning_rate": 1e-07,
      "loss": 0.5804,
      "step": 159
    },
    {
      "epoch": 0.6368159203980099,
      "grad_norm": 0.5995965600013733,
      "learning_rate": 1e-07,
      "loss": 0.596,
      "step": 160
    },
    {
      "epoch": 0.6407960199004975,
      "grad_norm": 0.5746481418609619,
      "learning_rate": 1e-07,
      "loss": 0.5606,
      "step": 161
    },
    {
      "epoch": 0.6447761194029851,
      "grad_norm": 0.9206658005714417,
      "learning_rate": 1e-07,
      "loss": 0.6063,
      "step": 162
    },
    {
      "epoch": 0.6487562189054726,
      "grad_norm": 0.47769197821617126,
      "learning_rate": 1e-07,
      "loss": 0.5873,
      "step": 163
    },
    {
      "epoch": 0.6527363184079602,
      "grad_norm": 0.5097990036010742,
      "learning_rate": 1e-07,
      "loss": 0.6004,
      "step": 164
    },
    {
      "epoch": 0.6567164179104478,
      "grad_norm": 0.5074031949043274,
      "learning_rate": 1e-07,
      "loss": 0.6,
      "step": 165
    },
    {
      "epoch": 0.6606965174129353,
      "grad_norm": 0.45879438519477844,
      "learning_rate": 1e-07,
      "loss": 0.5441,
      "step": 166
    },
    {
      "epoch": 0.6646766169154229,
      "grad_norm": 0.6278098821640015,
      "learning_rate": 1e-07,
      "loss": 0.5243,
      "step": 167
    },
    {
      "epoch": 0.6686567164179105,
      "grad_norm": 0.6123387217521667,
      "learning_rate": 1e-07,
      "loss": 0.5989,
      "step": 168
    },
    {
      "epoch": 0.672636815920398,
      "grad_norm": 0.6250973343849182,
      "learning_rate": 1e-07,
      "loss": 0.5789,
      "step": 169
    },
    {
      "epoch": 0.6766169154228856,
      "grad_norm": 0.8891845941543579,
      "learning_rate": 1e-07,
      "loss": 0.5517,
      "step": 170
    },
    {
      "epoch": 0.6805970149253732,
      "grad_norm": 0.6342730522155762,
      "learning_rate": 1e-07,
      "loss": 0.5602,
      "step": 171
    },
    {
      "epoch": 0.6845771144278607,
      "grad_norm": 0.7926033735275269,
      "learning_rate": 1e-07,
      "loss": 0.5956,
      "step": 172
    },
    {
      "epoch": 0.6885572139303483,
      "grad_norm": 0.45265182852745056,
      "learning_rate": 1e-07,
      "loss": 0.5617,
      "step": 173
    },
    {
      "epoch": 0.6925373134328359,
      "grad_norm": 0.5704881548881531,
      "learning_rate": 1e-07,
      "loss": 0.5962,
      "step": 174
    },
    {
      "epoch": 0.6965174129353234,
      "grad_norm": 0.5954543352127075,
      "learning_rate": 1e-07,
      "loss": 0.5436,
      "step": 175
    },
    {
      "epoch": 0.700497512437811,
      "grad_norm": 0.5004026293754578,
      "learning_rate": 1e-07,
      "loss": 0.5666,
      "step": 176
    },
    {
      "epoch": 0.7044776119402985,
      "grad_norm": 0.5121272206306458,
      "learning_rate": 1e-07,
      "loss": 0.5977,
      "step": 177
    },
    {
      "epoch": 0.708457711442786,
      "grad_norm": 0.5957807898521423,
      "learning_rate": 1e-07,
      "loss": 0.5512,
      "step": 178
    },
    {
      "epoch": 0.7124378109452736,
      "grad_norm": 0.6544281840324402,
      "learning_rate": 1e-07,
      "loss": 0.5805,
      "step": 179
    },
    {
      "epoch": 0.7164179104477612,
      "grad_norm": 0.4494013786315918,
      "learning_rate": 1e-07,
      "loss": 0.537,
      "step": 180
    },
    {
      "epoch": 0.7203980099502487,
      "grad_norm": 0.497487336397171,
      "learning_rate": 1e-07,
      "loss": 0.5499,
      "step": 181
    },
    {
      "epoch": 0.7243781094527363,
      "grad_norm": 0.7070022225379944,
      "learning_rate": 1e-07,
      "loss": 0.545,
      "step": 182
    },
    {
      "epoch": 0.7283582089552239,
      "grad_norm": 0.7148118615150452,
      "learning_rate": 1e-07,
      "loss": 0.5912,
      "step": 183
    },
    {
      "epoch": 0.7323383084577114,
      "grad_norm": 0.4213866889476776,
      "learning_rate": 1e-07,
      "loss": 0.5878,
      "step": 184
    },
    {
      "epoch": 0.736318407960199,
      "grad_norm": 0.4360056221485138,
      "learning_rate": 1e-07,
      "loss": 0.6289,
      "step": 185
    },
    {
      "epoch": 0.7402985074626866,
      "grad_norm": 0.5059033632278442,
      "learning_rate": 1e-07,
      "loss": 0.5813,
      "step": 186
    },
    {
      "epoch": 0.7442786069651741,
      "grad_norm": 0.6717720031738281,
      "learning_rate": 1e-07,
      "loss": 0.5539,
      "step": 187
    },
    {
      "epoch": 0.7482587064676617,
      "grad_norm": 0.736268162727356,
      "learning_rate": 1e-07,
      "loss": 0.5862,
      "step": 188
    },
    {
      "epoch": 0.7522388059701492,
      "grad_norm": 0.5463230609893799,
      "learning_rate": 1e-07,
      "loss": 0.5603,
      "step": 189
    },
    {
      "epoch": 0.7562189054726368,
      "grad_norm": 0.4267301857471466,
      "learning_rate": 1e-07,
      "loss": 0.5204,
      "step": 190
    },
    {
      "epoch": 0.7601990049751244,
      "grad_norm": 0.5766838192939758,
      "learning_rate": 1e-07,
      "loss": 0.5404,
      "step": 191
    },
    {
      "epoch": 0.764179104477612,
      "grad_norm": 0.47452178597450256,
      "learning_rate": 1e-07,
      "loss": 0.5719,
      "step": 192
    },
    {
      "epoch": 0.7681592039800995,
      "grad_norm": 0.496635377407074,
      "learning_rate": 1e-07,
      "loss": 0.5583,
      "step": 193
    },
    {
      "epoch": 0.7721393034825871,
      "grad_norm": 0.6146615147590637,
      "learning_rate": 1e-07,
      "loss": 0.5705,
      "step": 194
    },
    {
      "epoch": 0.7761194029850746,
      "grad_norm": 0.4717157781124115,
      "learning_rate": 1e-07,
      "loss": 0.5237,
      "step": 195
    },
    {
      "epoch": 0.7800995024875622,
      "grad_norm": 0.5160589218139648,
      "learning_rate": 1e-07,
      "loss": 0.5903,
      "step": 196
    },
    {
      "epoch": 0.7840796019900498,
      "grad_norm": 0.5136131644248962,
      "learning_rate": 1e-07,
      "loss": 0.5902,
      "step": 197
    },
    {
      "epoch": 0.7880597014925373,
      "grad_norm": 0.46506819128990173,
      "learning_rate": 1e-07,
      "loss": 0.5339,
      "step": 198
    },
    {
      "epoch": 0.7920398009950249,
      "grad_norm": 0.39230668544769287,
      "learning_rate": 1e-07,
      "loss": 0.5582,
      "step": 199
    },
    {
      "epoch": 0.7960199004975125,
      "grad_norm": 0.4060211777687073,
      "learning_rate": 1e-07,
      "loss": 0.5464,
      "step": 200
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.4357733428478241,
      "learning_rate": 1e-07,
      "loss": 0.5187,
      "step": 201
    },
    {
      "epoch": 0.8039800995024876,
      "grad_norm": 0.5215465426445007,
      "learning_rate": 1e-07,
      "loss": 0.576,
      "step": 202
    },
    {
      "epoch": 0.8079601990049752,
      "grad_norm": 0.41915613412857056,
      "learning_rate": 1e-07,
      "loss": 0.5453,
      "step": 203
    },
    {
      "epoch": 0.8119402985074626,
      "grad_norm": 0.4252179265022278,
      "learning_rate": 1e-07,
      "loss": 0.6138,
      "step": 204
    },
    {
      "epoch": 0.8159203980099502,
      "grad_norm": 0.5336969494819641,
      "learning_rate": 1e-07,
      "loss": 0.6403,
      "step": 205
    },
    {
      "epoch": 0.8199004975124378,
      "grad_norm": 0.655704915523529,
      "learning_rate": 1e-07,
      "loss": 0.5871,
      "step": 206
    },
    {
      "epoch": 0.8238805970149253,
      "grad_norm": 0.5526642203330994,
      "learning_rate": 1e-07,
      "loss": 0.5848,
      "step": 207
    },
    {
      "epoch": 0.8278606965174129,
      "grad_norm": 0.3965601623058319,
      "learning_rate": 1e-07,
      "loss": 0.5439,
      "step": 208
    },
    {
      "epoch": 0.8318407960199005,
      "grad_norm": 0.3756254017353058,
      "learning_rate": 1e-07,
      "loss": 0.544,
      "step": 209
    },
    {
      "epoch": 0.835820895522388,
      "grad_norm": 0.5047779083251953,
      "learning_rate": 1e-07,
      "loss": 0.5752,
      "step": 210
    },
    {
      "epoch": 0.8398009950248756,
      "grad_norm": 0.389487624168396,
      "learning_rate": 1e-07,
      "loss": 0.5365,
      "step": 211
    },
    {
      "epoch": 0.8437810945273632,
      "grad_norm": 0.46802979707717896,
      "learning_rate": 1e-07,
      "loss": 0.6019,
      "step": 212
    },
    {
      "epoch": 0.8477611940298507,
      "grad_norm": 0.5024377703666687,
      "learning_rate": 1e-07,
      "loss": 0.5073,
      "step": 213
    },
    {
      "epoch": 0.8517412935323383,
      "grad_norm": 0.5403252243995667,
      "learning_rate": 1e-07,
      "loss": 0.5839,
      "step": 214
    },
    {
      "epoch": 0.8557213930348259,
      "grad_norm": 0.3976481556892395,
      "learning_rate": 1e-07,
      "loss": 0.5703,
      "step": 215
    },
    {
      "epoch": 0.8597014925373134,
      "grad_norm": 0.44842153787612915,
      "learning_rate": 1e-07,
      "loss": 0.539,
      "step": 216
    },
    {
      "epoch": 0.863681592039801,
      "grad_norm": 0.5411170721054077,
      "learning_rate": 1e-07,
      "loss": 0.572,
      "step": 217
    },
    {
      "epoch": 0.8676616915422886,
      "grad_norm": 0.7187299728393555,
      "learning_rate": 1e-07,
      "loss": 0.5798,
      "step": 218
    },
    {
      "epoch": 0.8716417910447761,
      "grad_norm": 0.5184516310691833,
      "learning_rate": 1e-07,
      "loss": 0.5325,
      "step": 219
    },
    {
      "epoch": 0.8756218905472637,
      "grad_norm": 0.3858243525028229,
      "learning_rate": 1e-07,
      "loss": 0.5687,
      "step": 220
    },
    {
      "epoch": 0.8796019900497513,
      "grad_norm": 0.3441164493560791,
      "learning_rate": 1e-07,
      "loss": 0.5146,
      "step": 221
    },
    {
      "epoch": 0.8835820895522388,
      "grad_norm": 0.4126099944114685,
      "learning_rate": 1e-07,
      "loss": 0.5639,
      "step": 222
    },
    {
      "epoch": 0.8875621890547264,
      "grad_norm": 0.6766132712364197,
      "learning_rate": 1e-07,
      "loss": 0.5536,
      "step": 223
    },
    {
      "epoch": 0.891542288557214,
      "grad_norm": 0.38082340359687805,
      "learning_rate": 1e-07,
      "loss": 0.5399,
      "step": 224
    },
    {
      "epoch": 0.8955223880597015,
      "grad_norm": 0.46175238490104675,
      "learning_rate": 1e-07,
      "loss": 0.5954,
      "step": 225
    },
    {
      "epoch": 0.8995024875621891,
      "grad_norm": 0.49846476316452026,
      "learning_rate": 1e-07,
      "loss": 0.5369,
      "step": 226
    },
    {
      "epoch": 0.9034825870646767,
      "grad_norm": 0.4804675877094269,
      "learning_rate": 1e-07,
      "loss": 0.5606,
      "step": 227
    },
    {
      "epoch": 0.9074626865671642,
      "grad_norm": 0.4761047959327698,
      "learning_rate": 1e-07,
      "loss": 0.5435,
      "step": 228
    },
    {
      "epoch": 0.9114427860696518,
      "grad_norm": 0.6701684594154358,
      "learning_rate": 1e-07,
      "loss": 0.5366,
      "step": 229
    },
    {
      "epoch": 0.9154228855721394,
      "grad_norm": 0.3914811909198761,
      "learning_rate": 1e-07,
      "loss": 0.5536,
      "step": 230
    },
    {
      "epoch": 0.9194029850746268,
      "grad_norm": 0.8211656212806702,
      "learning_rate": 1e-07,
      "loss": 0.5245,
      "step": 231
    },
    {
      "epoch": 0.9233830845771144,
      "grad_norm": 0.6509301066398621,
      "learning_rate": 1e-07,
      "loss": 0.5995,
      "step": 232
    },
    {
      "epoch": 0.9273631840796019,
      "grad_norm": 0.5072076916694641,
      "learning_rate": 1e-07,
      "loss": 0.5317,
      "step": 233
    },
    {
      "epoch": 0.9313432835820895,
      "grad_norm": 0.6173104047775269,
      "learning_rate": 1e-07,
      "loss": 0.548,
      "step": 234
    },
    {
      "epoch": 0.9353233830845771,
      "grad_norm": 0.45433592796325684,
      "learning_rate": 1e-07,
      "loss": 0.5083,
      "step": 235
    },
    {
      "epoch": 0.9393034825870646,
      "grad_norm": 0.40389034152030945,
      "learning_rate": 1e-07,
      "loss": 0.5363,
      "step": 236
    },
    {
      "epoch": 0.9432835820895522,
      "grad_norm": 0.3999645709991455,
      "learning_rate": 1e-07,
      "loss": 0.5291,
      "step": 237
    },
    {
      "epoch": 0.9472636815920398,
      "grad_norm": 0.4328477084636688,
      "learning_rate": 1e-07,
      "loss": 0.5549,
      "step": 238
    },
    {
      "epoch": 0.9512437810945273,
      "grad_norm": 0.529513955116272,
      "learning_rate": 1e-07,
      "loss": 0.5208,
      "step": 239
    },
    {
      "epoch": 0.9552238805970149,
      "grad_norm": 0.41321346163749695,
      "learning_rate": 1e-07,
      "loss": 0.5135,
      "step": 240
    },
    {
      "epoch": 0.9592039800995025,
      "grad_norm": 0.42416515946388245,
      "learning_rate": 1e-07,
      "loss": 0.4893,
      "step": 241
    },
    {
      "epoch": 0.96318407960199,
      "grad_norm": 0.8604540228843689,
      "learning_rate": 1e-07,
      "loss": 0.5321,
      "step": 242
    },
    {
      "epoch": 0.9671641791044776,
      "grad_norm": 0.4030352830886841,
      "learning_rate": 1e-07,
      "loss": 0.5037,
      "step": 243
    },
    {
      "epoch": 0.9711442786069652,
      "grad_norm": 0.45229312777519226,
      "learning_rate": 1e-07,
      "loss": 0.5289,
      "step": 244
    },
    {
      "epoch": 0.9751243781094527,
      "grad_norm": 0.4864250719547272,
      "learning_rate": 1e-07,
      "loss": 0.5453,
      "step": 245
    },
    {
      "epoch": 0.9791044776119403,
      "grad_norm": 0.3489474058151245,
      "learning_rate": 1e-07,
      "loss": 0.5357,
      "step": 246
    },
    {
      "epoch": 0.9830845771144279,
      "grad_norm": 0.4253968894481659,
      "learning_rate": 1e-07,
      "loss": 0.5415,
      "step": 247
    },
    {
      "epoch": 0.9870646766169154,
      "grad_norm": 0.4792375862598419,
      "learning_rate": 1e-07,
      "loss": 0.4918,
      "step": 248
    },
    {
      "epoch": 0.991044776119403,
      "grad_norm": 0.5180811285972595,
      "learning_rate": 1e-07,
      "loss": 0.4897,
      "step": 249
    },
    {
      "epoch": 0.9950248756218906,
      "grad_norm": 0.5927690863609314,
      "learning_rate": 1e-07,
      "loss": 0.5214,
      "step": 250
    },
    {
      "epoch": 0.9990049751243781,
      "grad_norm": 0.3848709166049957,
      "learning_rate": 1e-07,
      "loss": 0.5349,
      "step": 251
    },
    {
      "epoch": 0.9990049751243781,
      "step": 251,
      "total_flos": 2.785366857660498e+17,
      "train_loss": 0.7864806888350453,
      "train_runtime": 27405.4608,
      "train_samples_per_second": 0.44,
      "train_steps_per_second": 0.009
    }
  ],
  "logging_steps": 1,
  "max_steps": 251,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.785366857660498e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}