{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "grad_norm": 0.014710677460232696,
      "learning_rate": 5.333333333333334e-06,
      "loss": 0.1815,
      "step": 1
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.013275550898261514,
      "learning_rate": 1.0666666666666667e-05,
      "loss": 0.1744,
      "step": 2
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.01207940598404248,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.1744,
      "step": 3
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.011708843482684025,
      "learning_rate": 2.1333333333333335e-05,
      "loss": 0.1811,
      "step": 4
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.013249274182238936,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.1774,
      "step": 5
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.015324670652113426,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.1767,
      "step": 6
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.015390915805574031,
      "learning_rate": 3.733333333333334e-05,
      "loss": 0.188,
      "step": 7
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.016912469601107507,
      "learning_rate": 4.266666666666667e-05,
      "loss": 0.1833,
      "step": 8
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.015795881571698464,
      "learning_rate": 4.8e-05,
      "loss": 0.166,
      "step": 9
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.019429255299681352,
      "learning_rate": 5.333333333333333e-05,
      "loss": 0.1843,
      "step": 10
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.020888212688036735,
      "learning_rate": 5.8666666666666665e-05,
      "loss": 0.1705,
      "step": 11
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.019608486394610464,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.166,
      "step": 12
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.01739688294821358,
      "learning_rate": 6.933333333333334e-05,
      "loss": 0.1571,
      "step": 13
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.02190784702215875,
      "learning_rate": 7.466666666666667e-05,
      "loss": 0.1571,
      "step": 14
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.018483885937035593,
      "learning_rate": 8e-05,
      "loss": 0.148,
      "step": 15
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.02129637477185083,
      "learning_rate": 7.998916964717848e-05,
      "loss": 0.1431,
      "step": 16
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.019338780253217773,
      "learning_rate": 7.9956684453541e-05,
      "loss": 0.134,
      "step": 17
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.017239268916425323,
      "learning_rate": 7.990256201039297e-05,
      "loss": 0.1321,
      "step": 18
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.017054093945207252,
      "learning_rate": 7.982683162599218e-05,
      "loss": 0.126,
      "step": 19
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.015676917124896664,
      "learning_rate": 7.972953430967773e-05,
      "loss": 0.1262,
      "step": 20
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.01625498875306702,
      "learning_rate": 7.961072274966282e-05,
      "loss": 0.1136,
      "step": 21
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.015040096281277067,
      "learning_rate": 7.947046128450319e-05,
      "loss": 0.1101,
      "step": 22
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.01298355654644741,
      "learning_rate": 7.930882586825653e-05,
      "loss": 0.1109,
      "step": 23
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.018234879408144975,
      "learning_rate": 7.912590402935223e-05,
      "loss": 0.1163,
      "step": 24
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.01549239719904538,
      "learning_rate": 7.892179482319297e-05,
      "loss": 0.1099,
      "step": 25
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.012883721001143477,
      "learning_rate": 7.869660877851456e-05,
      "loss": 0.0922,
      "step": 26
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.012337387779329646,
      "learning_rate": 7.845046783753276e-05,
      "loss": 0.095,
      "step": 27
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.013940108166119597,
      "learning_rate": 7.818350528990929e-05,
      "loss": 0.0866,
      "step": 28
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.01298628678332191,
      "learning_rate": 7.789586570057317e-05,
      "loss": 0.0847,
      "step": 29
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.012066367131734002,
      "learning_rate": 7.758770483143634e-05,
      "loss": 0.0874,
      "step": 30
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.011754803105467901,
      "learning_rate": 7.72591895570457e-05,
      "loss": 0.0797,
      "step": 31
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.011906095102196715,
      "learning_rate": 7.69104977742177e-05,
      "loss": 0.0805,
      "step": 32
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.011159902094797761,
      "learning_rate": 7.654181830570404e-05,
      "loss": 0.0764,
      "step": 33
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.011798580111175258,
      "learning_rate": 7.615335079794083e-05,
      "loss": 0.0724,
      "step": 34
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.010339759591392507,
      "learning_rate": 7.57453056129365e-05,
      "loss": 0.0667,
      "step": 35
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.009938978187066816,
      "learning_rate": 7.531790371435709e-05,
      "loss": 0.0651,
      "step": 36
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.010181235056145644,
      "learning_rate": 7.48713765478705e-05,
      "loss": 0.0646,
      "step": 37
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.011185173147328833,
      "learning_rate": 7.440596591581463e-05,
      "loss": 0.0618,
      "step": 38
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.011403768823780507,
      "learning_rate": 7.392192384625704e-05,
      "loss": 0.0643,
      "step": 39
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.01276122192531743,
      "learning_rate": 7.341951245651747e-05,
      "loss": 0.0639,
      "step": 40
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.010914665035059508,
      "learning_rate": 7.28990038112265e-05,
      "loss": 0.0606,
      "step": 41
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.011004164162402918,
      "learning_rate": 7.236067977499791e-05,
      "loss": 0.0571,
      "step": 42
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.010796963080910247,
      "learning_rate": 7.180483185979392e-05,
      "loss": 0.0655,
      "step": 43
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.012653561356055772,
      "learning_rate": 7.123176106706638e-05,
      "loss": 0.0614,
      "step": 44
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.013818254081450885,
      "learning_rate": 7.064177772475912e-05,
      "loss": 0.0547,
      "step": 45
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.014860655429434013,
      "learning_rate": 7.003520131925997e-05,
      "loss": 0.0526,
      "step": 46
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.013228414955155646,
      "learning_rate": 6.941236032239316e-05,
      "loss": 0.0475,
      "step": 47
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.015375687951757642,
      "learning_rate": 6.877359201354606e-05,
      "loss": 0.0524,
      "step": 48
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.01577128460985884,
      "learning_rate": 6.811924229702648e-05,
      "loss": 0.0533,
      "step": 49
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.015166795078791056,
      "learning_rate": 6.744966551474936e-05,
      "loss": 0.0512,
      "step": 50
    },
    {
      "epoch": 1.02,
      "grad_norm": 0.017507605583730556,
      "learning_rate": 6.676522425435433e-05,
      "loss": 0.0561,
      "step": 51
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.016300395006838303,
      "learning_rate": 6.606628915285822e-05,
      "loss": 0.0405,
      "step": 52
    },
    {
      "epoch": 1.06,
      "grad_norm": 0.014846189194985461,
      "learning_rate": 6.53532386959484e-05,
      "loss": 0.0404,
      "step": 53
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.014320313515789142,
      "learning_rate": 6.462645901302633e-05,
      "loss": 0.0478,
      "step": 54
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.014813685814070542,
      "learning_rate": 6.388634366811146e-05,
      "loss": 0.0404,
      "step": 55
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.013293890712711523,
      "learning_rate": 6.313329344671946e-05,
      "loss": 0.0484,
      "step": 56
    },
    {
      "epoch": 1.1400000000000001,
      "grad_norm": 0.02185749002370571,
      "learning_rate": 6.236771613882987e-05,
      "loss": 0.0443,
      "step": 57
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.012360179564130491,
      "learning_rate": 6.159002631806052e-05,
      "loss": 0.0473,
      "step": 58
    },
    {
      "epoch": 1.18,
      "grad_norm": 0.017274617312903254,
      "learning_rate": 6.0800645117168616e-05,
      "loss": 0.0389,
      "step": 59
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.014747179801213546,
      "learning_rate": 6.000000000000001e-05,
      "loss": 0.0419,
      "step": 60
    },
    {
      "epoch": 1.22,
      "grad_norm": 0.012229889958454868,
      "learning_rate": 5.918852453000986e-05,
      "loss": 0.0416,
      "step": 61
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.011166013562191896,
      "learning_rate": 5.836665813548047e-05,
      "loss": 0.0358,
      "step": 62
    },
    {
      "epoch": 1.26,
      "grad_norm": 0.01990702483158937,
      "learning_rate": 5.75348458715631e-05,
      "loss": 0.0405,
      "step": 63
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.010124675086216894,
      "learning_rate": 5.669353817927272e-05,
      "loss": 0.0337,
      "step": 64
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.011931743764099367,
      "learning_rate": 5.584319064156628e-05,
      "loss": 0.0366,
      "step": 65
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.016278557136151433,
      "learning_rate": 5.4984263736636494e-05,
      "loss": 0.0355,
      "step": 66
    },
    {
      "epoch": 1.34,
      "grad_norm": 0.011925585523495121,
      "learning_rate": 5.4117222588554756e-05,
      "loss": 0.0318,
      "step": 67
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 0.008678901727809062,
      "learning_rate": 5.324253671539833e-05,
      "loss": 0.0399,
      "step": 68
    },
    {
      "epoch": 1.38,
      "grad_norm": 0.011205642151287906,
      "learning_rate": 5.23606797749979e-05,
      "loss": 0.0404,
      "step": 69
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.012678260753653327,
      "learning_rate": 5.1472129308443616e-05,
      "loss": 0.0341,
      "step": 70
    },
    {
      "epoch": 1.42,
      "grad_norm": 0.011731088999596854,
      "learning_rate": 5.05773664814881e-05,
      "loss": 0.0399,
      "step": 71
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.012927256706537374,
      "learning_rate": 4.967687582398671e-05,
      "loss": 0.0337,
      "step": 72
    },
    {
      "epoch": 1.46,
      "grad_norm": 0.009401838128986779,
      "learning_rate": 4.877114496751613e-05,
      "loss": 0.0412,
      "step": 73
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.010580857020458983,
      "learning_rate": 4.786066438131321e-05,
      "loss": 0.0386,
      "step": 74
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.01027180063046718,
      "learning_rate": 4.694592710667723e-05,
      "loss": 0.0439,
      "step": 75
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.011227665507764368,
      "learning_rate": 4.602742848997933e-05,
      "loss": 0.034,
      "step": 76
    },
    {
      "epoch": 1.54,
      "grad_norm": 0.011304252083945596,
      "learning_rate": 4.51056659144238e-05,
      "loss": 0.0333,
      "step": 77
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.011126435299093046,
      "learning_rate": 4.418113853070614e-05,
      "loss": 0.0322,
      "step": 78
    },
    {
      "epoch": 1.58,
      "grad_norm": 0.00811610216890556,
      "learning_rate": 4.3254346986714334e-05,
      "loss": 0.0385,
      "step": 79
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.009660536822409894,
      "learning_rate": 4.2325793156419035e-05,
      "loss": 0.0373,
      "step": 80
    },
    {
      "epoch": 1.62,
      "grad_norm": 0.012247343349198626,
      "learning_rate": 4.139597986810005e-05,
      "loss": 0.0424,
      "step": 81
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 0.00949956062234444,
      "learning_rate": 4.046541063205589e-05,
      "loss": 0.0359,
      "step": 82
    },
    {
      "epoch": 1.6600000000000001,
      "grad_norm": 0.008211566504133844,
      "learning_rate": 3.953458936794413e-05,
      "loss": 0.04,
      "step": 83
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 0.00862088942579677,
      "learning_rate": 3.860402013189998e-05,
      "loss": 0.0344,
      "step": 84
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.010458417865000978,
      "learning_rate": 3.767420684358097e-05,
      "loss": 0.0395,
      "step": 85
    },
    {
      "epoch": 1.72,
      "grad_norm": 0.007651341467977927,
      "learning_rate": 3.674565301328568e-05,
      "loss": 0.0399,
      "step": 86
    },
    {
      "epoch": 1.74,
      "grad_norm": 0.008051359031711787,
      "learning_rate": 3.581886146929387e-05,
      "loss": 0.0293,
      "step": 87
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.009184485624535495,
      "learning_rate": 3.4894334085576215e-05,
      "loss": 0.0373,
      "step": 88
    },
    {
      "epoch": 1.78,
      "grad_norm": 0.008969750220048643,
      "learning_rate": 3.397257151002068e-05,
      "loss": 0.0496,
      "step": 89
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.008434083980889533,
      "learning_rate": 3.305407289332279e-05,
      "loss": 0.0299,
      "step": 90
    },
    {
      "epoch": 1.8199999999999998,
      "grad_norm": 0.00784026047924016,
      "learning_rate": 3.213933561868679e-05,
      "loss": 0.0304,
      "step": 91
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 0.008103687367910638,
      "learning_rate": 3.122885503248386e-05,
      "loss": 0.0436,
      "step": 92
    },
    {
      "epoch": 1.8599999999999999,
      "grad_norm": 0.008467672730508868,
      "learning_rate": 3.0323124176013297e-05,
      "loss": 0.0321,
      "step": 93
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.00861086865507992,
      "learning_rate": 2.9422633518511926e-05,
      "loss": 0.0305,
      "step": 94
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.008075900377806443,
      "learning_rate": 2.8527870691556404e-05,
      "loss": 0.0316,
      "step": 95
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.008115978530359329,
      "learning_rate": 2.7639320225002108e-05,
      "loss": 0.0312,
      "step": 96
    },
    {
      "epoch": 1.94,
      "grad_norm": 0.008461228216093337,
      "learning_rate": 2.6757463284601682e-05,
      "loss": 0.0288,
      "step": 97
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.007638529217399345,
      "learning_rate": 2.5882777411445254e-05,
      "loss": 0.0305,
      "step": 98
    },
    {
      "epoch": 1.98,
      "grad_norm": 0.009336523121679683,
      "learning_rate": 2.501573626336352e-05,
      "loss": 0.033,
      "step": 99
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.008106552755580317,
      "learning_rate": 2.4156809358433728e-05,
      "loss": 0.0339,
      "step": 100
    },
    {
      "epoch": 2.02,
      "grad_norm": 0.007082881661631907,
      "learning_rate": 2.330646182072729e-05,
      "loss": 0.0354,
      "step": 101
    },
    {
      "epoch": 2.04,
      "grad_norm": 0.007697481512989457,
      "learning_rate": 2.24651541284369e-05,
      "loss": 0.0403,
      "step": 102
    },
    {
      "epoch": 2.06,
      "grad_norm": 0.007121535747217676,
      "learning_rate": 2.1633341864519526e-05,
      "loss": 0.0337,
      "step": 103
    },
    {
      "epoch": 2.08,
      "grad_norm": 0.00790702913497333,
      "learning_rate": 2.0811475469990167e-05,
      "loss": 0.0327,
      "step": 104
    },
    {
      "epoch": 2.1,
      "grad_norm": 0.008764658811333917,
      "learning_rate": 2.0000000000000012e-05,
      "loss": 0.0351,
      "step": 105
    },
    {
      "epoch": 2.12,
      "grad_norm": 0.008919648827256935,
      "learning_rate": 1.9199354882831387e-05,
      "loss": 0.0292,
      "step": 106
    },
    {
      "epoch": 2.14,
      "grad_norm": 0.008186485009020647,
      "learning_rate": 1.8409973681939498e-05,
      "loss": 0.0323,
      "step": 107
    },
    {
      "epoch": 2.16,
      "grad_norm": 0.007794722813488527,
      "learning_rate": 1.7632283861170135e-05,
      "loss": 0.0307,
      "step": 108
    },
    {
      "epoch": 2.18,
      "grad_norm": 0.007719117811039383,
      "learning_rate": 1.686670655328054e-05,
      "loss": 0.0331,
      "step": 109
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.007310241819341536,
      "learning_rate": 1.6113656331888563e-05,
      "loss": 0.0288,
      "step": 110
    },
    {
      "epoch": 2.22,
      "grad_norm": 0.007571528306863314,
      "learning_rate": 1.537354098697367e-05,
      "loss": 0.0284,
      "step": 111
    },
    {
      "epoch": 2.24,
      "grad_norm": 0.008256048461901356,
      "learning_rate": 1.4646761304051587e-05,
      "loss": 0.0301,
      "step": 112
    },
    {
      "epoch": 2.26,
      "grad_norm": 0.007028066977280104,
      "learning_rate": 1.3933710847141795e-05,
      "loss": 0.0339,
      "step": 113
    },
    {
      "epoch": 2.2800000000000002,
      "grad_norm": 0.007555676769902198,
      "learning_rate": 1.3234775745645684e-05,
      "loss": 0.0375,
      "step": 114
    },
    {
      "epoch": 2.3,
      "grad_norm": 0.008499608872904558,
      "learning_rate": 1.2550334485250661e-05,
      "loss": 0.0275,
      "step": 115
    },
    {
      "epoch": 2.32,
      "grad_norm": 0.008013854835985556,
      "learning_rate": 1.1880757702973531e-05,
      "loss": 0.0359,
      "step": 116
    },
    {
      "epoch": 2.34,
      "grad_norm": 0.008556477071602873,
      "learning_rate": 1.1226407986453963e-05,
      "loss": 0.0381,
      "step": 117
    },
    {
      "epoch": 2.36,
      "grad_norm": 0.007832920693883215,
      "learning_rate": 1.0587639677606857e-05,
      "loss": 0.0344,
      "step": 118
    },
    {
      "epoch": 2.38,
      "grad_norm": 0.007609196196423558,
      "learning_rate": 9.964798680740033e-06,
      "loss": 0.0319,
      "step": 119
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.010740643611552284,
      "learning_rate": 9.358222275240884e-06,
      "loss": 0.0379,
      "step": 120
    },
    {
      "epoch": 2.42,
      "grad_norm": 0.010312015041434402,
      "learning_rate": 8.768238932933632e-06,
      "loss": 0.0421,
      "step": 121
    },
    {
      "epoch": 2.44,
      "grad_norm": 0.008471683253664451,
      "learning_rate": 8.195168140206084e-06,
      "loss": 0.0332,
      "step": 122
    },
    {
      "epoch": 2.46,
      "grad_norm": 0.0074210399106356215,
      "learning_rate": 7.639320225002106e-06,
      "loss": 0.0289,
      "step": 123
    },
    {
      "epoch": 2.48,
      "grad_norm": 0.00735179870041093,
      "learning_rate": 7.1009961887735075e-06,
      "loss": 0.0322,
      "step": 124
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.0075242353335040766,
      "learning_rate": 6.58048754348255e-06,
      "loss": 0.0383,
      "step": 125
    },
    {
      "epoch": 2.52,
      "grad_norm": 0.007729309420039665,
      "learning_rate": 6.078076153742962e-06,
      "loss": 0.0293,
      "step": 126
    },
    {
      "epoch": 2.54,
      "grad_norm": 0.008464093312648984,
      "learning_rate": 5.5940340841853915e-06,
      "loss": 0.0269,
      "step": 127
    },
    {
      "epoch": 2.56,
      "grad_norm": 0.006863091500195714,
      "learning_rate": 5.128623452129508e-06,
      "loss": 0.0389,
      "step": 128
    },
    {
      "epoch": 2.58,
      "grad_norm": 0.007895087731618813,
      "learning_rate": 4.6820962856429205e-06,
      "loss": 0.0392,
      "step": 129
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.007619986693170232,
      "learning_rate": 4.254694387063514e-06,
      "loss": 0.0324,
      "step": 130
    },
    {
      "epoch": 2.62,
      "grad_norm": 0.007943162266708756,
      "learning_rate": 3.846649202059181e-06,
      "loss": 0.0377,
      "step": 131
    },
    {
      "epoch": 2.64,
      "grad_norm": 0.007551878283704844,
      "learning_rate": 3.458181694295961e-06,
      "loss": 0.0283,
      "step": 132
    },
    {
      "epoch": 2.66,
      "grad_norm": 0.008306135332213626,
      "learning_rate": 3.0895022257823083e-06,
      "loss": 0.04,
      "step": 133
    },
    {
      "epoch": 2.68,
      "grad_norm": 0.007520657416309244,
      "learning_rate": 2.7408104429543025e-06,
      "loss": 0.0361,
      "step": 134
    },
    {
      "epoch": 2.7,
      "grad_norm": 0.008111365610476571,
      "learning_rate": 2.4122951685636674e-06,
      "loss": 0.0259,
      "step": 135
    },
    {
      "epoch": 2.7199999999999998,
      "grad_norm": 0.0070217069189199306,
      "learning_rate": 2.104134299426832e-06,
      "loss": 0.0282,
      "step": 136
    },
    {
      "epoch": 2.74,
      "grad_norm": 0.007323631942861919,
      "learning_rate": 1.8164947100907238e-06,
      "loss": 0.0293,
      "step": 137
    },
    {
      "epoch": 2.76,
      "grad_norm": 0.00754692847994923,
      "learning_rate": 1.5495321624672443e-06,
      "loss": 0.0341,
      "step": 138
    },
    {
      "epoch": 2.7800000000000002,
      "grad_norm": 0.008240270275234659,
      "learning_rate": 1.3033912214854482e-06,
      "loss": 0.0272,
      "step": 139
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.007813207109926766,
      "learning_rate": 1.0782051768070477e-06,
      "loss": 0.0367,
      "step": 140
    },
    {
      "epoch": 2.82,
      "grad_norm": 0.00797429292559567,
      "learning_rate": 8.740959706477725e-07,
      "loss": 0.0317,
      "step": 141
    },
    {
      "epoch": 2.84,
      "grad_norm": 0.007510888313468925,
      "learning_rate": 6.911741317434706e-07,
      "loss": 0.0298,
      "step": 142
    },
    {
      "epoch": 2.86,
      "grad_norm": 0.008706846766478742,
      "learning_rate": 5.295387154968312e-07,
      "loss": 0.0304,
      "step": 143
    },
    {
      "epoch": 2.88,
      "grad_norm": 0.008161482820122646,
      "learning_rate": 3.8927725033718553e-07,
      "loss": 0.0405,
      "step": 144
    },
    {
      "epoch": 2.9,
      "grad_norm": 0.008431932977041912,
      "learning_rate": 2.704656903222791e-07,
      "loss": 0.0356,
      "step": 145
    },
    {
      "epoch": 2.92,
      "grad_norm": 0.00859380552765255,
      "learning_rate": 1.7316837400782604e-07,
      "loss": 0.0317,
      "step": 146
    },
    {
      "epoch": 2.94,
      "grad_norm": 0.00754667559190351,
      "learning_rate": 9.74379896070321e-08,
      "loss": 0.0273,
      "step": 147
    },
    {
      "epoch": 2.96,
      "grad_norm": 0.0071967219455463015,
      "learning_rate": 4.331554645901737e-08,
      "loss": 0.0338,
      "step": 148
    },
    {
      "epoch": 2.98,
      "grad_norm": 0.008558634686248607,
      "learning_rate": 1.0830352821531442e-08,
      "loss": 0.0354,
      "step": 149
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.006734822832899019,
      "learning_rate": 0.0,
      "loss": 0.0333,
      "step": 150
    },
    {
      "epoch": 3.0,
      "step": 150,
      "total_flos": 111936666075136.0,
      "train_loss": 0.060392932357887424,
      "train_runtime": 1308.3787,
      "train_samples_per_second": 0.917,
      "train_steps_per_second": 0.115
    }
  ],
  "logging_steps": 1,
  "max_steps": 150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 111936666075136.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}