{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.9235668789808917,
  "eval_steps": 40,
  "global_step": 628,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006369426751592357,
      "grad_norm": 0.1806156039237976,
      "learning_rate": 1e-05,
      "loss": 1.3031,
      "step": 1
    },
    {
      "epoch": 0.006369426751592357,
      "eval_loss": 1.5003942251205444,
      "eval_runtime": 19.6641,
      "eval_samples_per_second": 55.533,
      "eval_steps_per_second": 0.915,
      "step": 1
    },
    {
      "epoch": 0.012738853503184714,
      "grad_norm": 0.1688886284828186,
      "learning_rate": 2e-05,
      "loss": 1.3305,
      "step": 2
    },
    {
      "epoch": 0.01910828025477707,
      "grad_norm": 0.20123907923698425,
      "learning_rate": 3e-05,
      "loss": 1.324,
      "step": 3
    },
    {
      "epoch": 0.025477707006369428,
      "grad_norm": 0.18879620730876923,
      "learning_rate": 4e-05,
      "loss": 1.3638,
      "step": 4
    },
    {
      "epoch": 0.03184713375796178,
      "grad_norm": 0.20348915457725525,
      "learning_rate": 5e-05,
      "loss": 1.3686,
      "step": 5
    },
    {
      "epoch": 0.03821656050955414,
      "grad_norm": 0.212239071726799,
      "learning_rate": 6e-05,
      "loss": 1.2865,
      "step": 6
    },
    {
      "epoch": 0.044585987261146494,
      "grad_norm": 0.19280897080898285,
      "learning_rate": 7e-05,
      "loss": 1.313,
      "step": 7
    },
    {
      "epoch": 0.050955414012738856,
      "grad_norm": 0.1767151653766632,
      "learning_rate": 8e-05,
      "loss": 1.3207,
      "step": 8
    },
    {
      "epoch": 0.05732484076433121,
      "grad_norm": 0.20014327764511108,
      "learning_rate": 9e-05,
      "loss": 1.3143,
      "step": 9
    },
    {
      "epoch": 0.06369426751592357,
      "grad_norm": 0.18035855889320374,
      "learning_rate": 0.0001,
      "loss": 1.252,
      "step": 10
    },
    {
      "epoch": 0.07006369426751592,
      "grad_norm": 0.19993054866790771,
      "learning_rate": 0.00011000000000000002,
      "loss": 1.302,
      "step": 11
    },
    {
      "epoch": 0.07643312101910828,
      "grad_norm": 0.18973341584205627,
      "learning_rate": 0.00012,
      "loss": 1.2608,
      "step": 12
    },
    {
      "epoch": 0.08280254777070063,
      "grad_norm": 0.19669465720653534,
      "learning_rate": 0.00013000000000000002,
      "loss": 1.2329,
      "step": 13
    },
    {
      "epoch": 0.08917197452229299,
      "grad_norm": 0.1886417716741562,
      "learning_rate": 0.00014,
      "loss": 1.241,
      "step": 14
    },
    {
      "epoch": 0.09554140127388536,
      "grad_norm": 0.19076582789421082,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.2539,
      "step": 15
    },
    {
      "epoch": 0.10191082802547771,
      "grad_norm": 0.16027267277240753,
      "learning_rate": 0.00016,
      "loss": 1.2123,
      "step": 16
    },
    {
      "epoch": 0.10828025477707007,
      "grad_norm": 0.16112814843654633,
      "learning_rate": 0.00017,
      "loss": 1.2465,
      "step": 17
    },
    {
      "epoch": 0.11464968152866242,
      "grad_norm": 0.15539830923080444,
      "learning_rate": 0.00018,
      "loss": 1.1717,
      "step": 18
    },
    {
      "epoch": 0.12101910828025478,
      "grad_norm": 0.15739695727825165,
      "learning_rate": 0.00019,
      "loss": 1.1412,
      "step": 19
    },
    {
      "epoch": 0.12738853503184713,
      "grad_norm": 0.15658576786518097,
      "learning_rate": 0.0002,
      "loss": 1.1731,
      "step": 20
    },
    {
      "epoch": 0.1337579617834395,
      "grad_norm": 0.1474328637123108,
      "learning_rate": 0.00019999866506037345,
      "loss": 1.2051,
      "step": 21
    },
    {
      "epoch": 0.14012738853503184,
      "grad_norm": 0.11234907805919647,
      "learning_rate": 0.00019999466027713507,
      "loss": 1.1803,
      "step": 22
    },
    {
      "epoch": 0.1464968152866242,
      "grad_norm": 0.1053839772939682,
      "learning_rate": 0.00019998798575720776,
      "loss": 1.1436,
      "step": 23
    },
    {
      "epoch": 0.15286624203821655,
      "grad_norm": 0.1049942821264267,
      "learning_rate": 0.00019997864167879312,
      "loss": 1.1881,
      "step": 24
    },
    {
      "epoch": 0.1592356687898089,
      "grad_norm": 0.11039146035909653,
      "learning_rate": 0.00019996662829136676,
      "loss": 1.1528,
      "step": 25
    },
    {
      "epoch": 0.16560509554140126,
      "grad_norm": 0.09678228944540024,
      "learning_rate": 0.0001999519459156716,
      "loss": 1.1496,
      "step": 26
    },
    {
      "epoch": 0.17197452229299362,
      "grad_norm": 0.09857058525085449,
      "learning_rate": 0.0001999345949437094,
      "loss": 1.1304,
      "step": 27
    },
    {
      "epoch": 0.17834394904458598,
      "grad_norm": 0.10835567116737366,
      "learning_rate": 0.0001999145758387301,
      "loss": 1.2262,
      "step": 28
    },
    {
      "epoch": 0.18471337579617833,
      "grad_norm": 0.09927600622177124,
      "learning_rate": 0.0001998918891352197,
      "loss": 1.1382,
      "step": 29
    },
    {
      "epoch": 0.1910828025477707,
      "grad_norm": 0.09861327707767487,
      "learning_rate": 0.00019986653543888568,
      "loss": 1.1987,
      "step": 30
    },
    {
      "epoch": 0.19745222929936307,
      "grad_norm": 0.09174010157585144,
      "learning_rate": 0.00019983851542664126,
      "loss": 1.127,
      "step": 31
    },
    {
      "epoch": 0.20382165605095542,
      "grad_norm": 0.08863182365894318,
      "learning_rate": 0.00019980782984658683,
      "loss": 1.211,
      "step": 32
    },
    {
      "epoch": 0.21019108280254778,
      "grad_norm": 0.08810263872146606,
      "learning_rate": 0.00019977447951799034,
      "loss": 1.1476,
      "step": 33
    },
    {
      "epoch": 0.21656050955414013,
      "grad_norm": 0.08641776442527771,
      "learning_rate": 0.00019973846533126533,
      "loss": 1.1497,
      "step": 34
    },
    {
      "epoch": 0.2229299363057325,
      "grad_norm": 0.09637051075696945,
      "learning_rate": 0.00019969978824794707,
      "loss": 1.1471,
      "step": 35
    },
    {
      "epoch": 0.22929936305732485,
      "grad_norm": 0.09402573108673096,
      "learning_rate": 0.000199658449300667,
      "loss": 1.0976,
      "step": 36
    },
    {
      "epoch": 0.2356687898089172,
      "grad_norm": 0.09077832847833633,
      "learning_rate": 0.00019961444959312508,
      "loss": 1.1119,
      "step": 37
    },
    {
      "epoch": 0.24203821656050956,
      "grad_norm": 0.08864310383796692,
      "learning_rate": 0.0001995677903000604,
      "loss": 1.1157,
      "step": 38
    },
    {
      "epoch": 0.2484076433121019,
      "grad_norm": 0.09867957979440689,
      "learning_rate": 0.0001995184726672197,
      "loss": 1.1656,
      "step": 39
    },
    {
      "epoch": 0.25477707006369427,
      "grad_norm": 0.09343115240335464,
      "learning_rate": 0.00019946649801132427,
      "loss": 1.1084,
      "step": 40
    },
    {
      "epoch": 0.25477707006369427,
      "eval_loss": 1.1224156618118286,
      "eval_runtime": 19.2915,
      "eval_samples_per_second": 56.605,
      "eval_steps_per_second": 0.933,
      "step": 40
    },
    {
      "epoch": 0.2611464968152866,
      "grad_norm": 0.09474795311689377,
      "learning_rate": 0.00019941186772003464,
      "loss": 1.1486,
      "step": 41
    },
    {
      "epoch": 0.267515923566879,
      "grad_norm": 0.09726471453905106,
      "learning_rate": 0.00019935458325191365,
      "loss": 1.1499,
      "step": 42
    },
    {
      "epoch": 0.27388535031847133,
      "grad_norm": 0.09273070096969604,
      "learning_rate": 0.0001992946461363874,
      "loss": 1.1361,
      "step": 43
    },
    {
      "epoch": 0.2802547770700637,
      "grad_norm": 0.10344096273183823,
      "learning_rate": 0.0001992320579737045,
      "loss": 1.0999,
      "step": 44
    },
    {
      "epoch": 0.28662420382165604,
      "grad_norm": 0.09499648213386536,
      "learning_rate": 0.00019916682043489336,
      "loss": 1.0919,
      "step": 45
    },
    {
      "epoch": 0.2929936305732484,
      "grad_norm": 0.09483088552951813,
      "learning_rate": 0.00019909893526171745,
      "loss": 1.0992,
      "step": 46
    },
    {
      "epoch": 0.29936305732484075,
      "grad_norm": 0.10382100939750671,
      "learning_rate": 0.00019902840426662895,
      "loss": 1.1093,
      "step": 47
    },
    {
      "epoch": 0.3057324840764331,
      "grad_norm": 0.10187891870737076,
      "learning_rate": 0.00019895522933272028,
      "loss": 1.1063,
      "step": 48
    },
    {
      "epoch": 0.31210191082802546,
      "grad_norm": 0.1022520437836647,
      "learning_rate": 0.00019887941241367377,
      "loss": 1.1095,
      "step": 49
    },
    {
      "epoch": 0.3184713375796178,
      "grad_norm": 0.11470162868499756,
      "learning_rate": 0.00019880095553370967,
      "loss": 1.0859,
      "step": 50
    },
    {
      "epoch": 0.3248407643312102,
      "grad_norm": 0.09845008701086044,
      "learning_rate": 0.0001987198607875319,
      "loss": 1.0941,
      "step": 51
    },
    {
      "epoch": 0.33121019108280253,
      "grad_norm": 0.1080709770321846,
      "learning_rate": 0.00019863613034027224,
      "loss": 1.084,
      "step": 52
    },
    {
      "epoch": 0.3375796178343949,
      "grad_norm": 0.11064234375953674,
      "learning_rate": 0.0001985497664274326,
      "loss": 1.1018,
      "step": 53
    },
    {
      "epoch": 0.34394904458598724,
      "grad_norm": 0.10099776834249496,
      "learning_rate": 0.0001984607713548251,
      "loss": 1.0881,
      "step": 54
    },
    {
      "epoch": 0.3503184713375796,
      "grad_norm": 0.11960357427597046,
      "learning_rate": 0.0001983691474985108,
      "loss": 1.0845,
      "step": 55
    },
    {
      "epoch": 0.35668789808917195,
      "grad_norm": 0.10840114951133728,
      "learning_rate": 0.00019827489730473596,
      "loss": 1.131,
      "step": 56
    },
    {
      "epoch": 0.3630573248407643,
      "grad_norm": 0.10177604109048843,
      "learning_rate": 0.00019817802328986697,
      "loss": 1.079,
      "step": 57
    },
    {
      "epoch": 0.36942675159235666,
      "grad_norm": 0.11752859503030777,
      "learning_rate": 0.00019807852804032305,
      "loss": 1.0833,
      "step": 58
    },
    {
      "epoch": 0.37579617834394907,
      "grad_norm": 0.11149834841489792,
      "learning_rate": 0.00019797641421250725,
      "loss": 1.1009,
      "step": 59
    },
    {
      "epoch": 0.3821656050955414,
      "grad_norm": 0.10446681827306747,
      "learning_rate": 0.00019787168453273544,
      "loss": 1.1211,
      "step": 60
    },
    {
      "epoch": 0.3885350318471338,
      "grad_norm": 0.12820479273796082,
      "learning_rate": 0.00019776434179716366,
      "loss": 1.1455,
      "step": 61
    },
    {
      "epoch": 0.39490445859872614,
      "grad_norm": 0.10011500865221024,
      "learning_rate": 0.00019765438887171327,
      "loss": 1.0779,
      "step": 62
    },
    {
      "epoch": 0.4012738853503185,
      "grad_norm": 0.11496227979660034,
      "learning_rate": 0.0001975418286919947,
      "loss": 1.1174,
      "step": 63
    },
    {
      "epoch": 0.40764331210191085,
      "grad_norm": 0.10938404500484467,
      "learning_rate": 0.00019742666426322876,
      "loss": 1.0576,
      "step": 64
    },
    {
      "epoch": 0.4140127388535032,
      "grad_norm": 0.12636032700538635,
      "learning_rate": 0.0001973088986601667,
      "loss": 1.083,
      "step": 65
    },
    {
      "epoch": 0.42038216560509556,
      "grad_norm": 0.10620423406362534,
      "learning_rate": 0.00019718853502700783,
      "loss": 1.0728,
      "step": 66
    },
    {
      "epoch": 0.4267515923566879,
      "grad_norm": 0.11206210404634476,
      "learning_rate": 0.0001970655765773159,
      "loss": 1.1107,
      "step": 67
    },
    {
      "epoch": 0.43312101910828027,
      "grad_norm": 0.12613879144191742,
      "learning_rate": 0.00019694002659393305,
      "loss": 1.1065,
      "step": 68
    },
    {
      "epoch": 0.4394904458598726,
      "grad_norm": 0.10636976361274719,
      "learning_rate": 0.00019681188842889222,
      "loss": 1.1192,
      "step": 69
    },
    {
      "epoch": 0.445859872611465,
      "grad_norm": 0.11036239564418793,
      "learning_rate": 0.00019668116550332766,
      "loss": 1.1362,
      "step": 70
    },
    {
      "epoch": 0.45222929936305734,
      "grad_norm": 0.11907072365283966,
      "learning_rate": 0.0001965478613073837,
      "loss": 1.1009,
      "step": 71
    },
    {
      "epoch": 0.4585987261146497,
      "grad_norm": 0.11267364770174026,
      "learning_rate": 0.00019641197940012137,
      "loss": 1.0694,
      "step": 72
    },
    {
      "epoch": 0.46496815286624205,
      "grad_norm": 0.10659351199865341,
      "learning_rate": 0.00019627352340942353,
      "loss": 1.0844,
      "step": 73
    },
    {
      "epoch": 0.4713375796178344,
      "grad_norm": 0.12426211684942245,
      "learning_rate": 0.00019613249703189796,
      "loss": 1.1203,
      "step": 74
    },
    {
      "epoch": 0.47770700636942676,
      "grad_norm": 0.11883872747421265,
      "learning_rate": 0.00019598890403277864,
      "loss": 1.0879,
      "step": 75
    },
    {
      "epoch": 0.4840764331210191,
      "grad_norm": 0.11355262994766235,
      "learning_rate": 0.0001958427482458253,
      "loss": 1.1045,
      "step": 76
    },
    {
      "epoch": 0.49044585987261147,
      "grad_norm": 0.11006154865026474,
      "learning_rate": 0.0001956940335732209,
      "loss": 1.1058,
      "step": 77
    },
    {
      "epoch": 0.4968152866242038,
      "grad_norm": 0.11379122734069824,
      "learning_rate": 0.00019554276398546768,
      "loss": 1.1224,
      "step": 78
    },
    {
      "epoch": 0.5031847133757962,
      "grad_norm": 0.11065732687711716,
      "learning_rate": 0.000195388943521281,
      "loss": 1.1033,
      "step": 79
    },
    {
      "epoch": 0.5095541401273885,
      "grad_norm": 0.11113402247428894,
      "learning_rate": 0.00019523257628748146,
      "loss": 1.0912,
      "step": 80
    },
    {
      "epoch": 0.5095541401273885,
      "eval_loss": 1.0586377382278442,
      "eval_runtime": 19.2899,
      "eval_samples_per_second": 56.61,
      "eval_steps_per_second": 0.933,
      "step": 80
    },
    {
      "epoch": 0.5159235668789809,
      "grad_norm": 0.11783529818058014,
      "learning_rate": 0.00019507366645888543,
      "loss": 1.0938,
      "step": 81
    },
    {
      "epoch": 0.5222929936305732,
      "grad_norm": 0.12089723348617554,
      "learning_rate": 0.00019491221827819347,
      "loss": 1.1068,
      "step": 82
    },
    {
      "epoch": 0.5286624203821656,
      "grad_norm": 0.10991813987493515,
      "learning_rate": 0.00019474823605587703,
      "loss": 1.1393,
      "step": 83
    },
    {
      "epoch": 0.535031847133758,
      "grad_norm": 0.11100416630506516,
      "learning_rate": 0.00019458172417006347,
      "loss": 1.1081,
      "step": 84
    },
    {
      "epoch": 0.5414012738853503,
      "grad_norm": 0.11886284500360489,
      "learning_rate": 0.00019441268706641907,
      "loss": 1.1168,
      "step": 85
    },
    {
      "epoch": 0.5477707006369427,
      "grad_norm": 0.11771067976951599,
      "learning_rate": 0.00019424112925803039,
      "loss": 1.098,
      "step": 86
    },
    {
      "epoch": 0.554140127388535,
      "grad_norm": 0.11022554337978363,
      "learning_rate": 0.00019406705532528374,
      "loss": 1.1179,
      "step": 87
    },
    {
      "epoch": 0.5605095541401274,
      "grad_norm": 0.11891311407089233,
      "learning_rate": 0.00019389046991574298,
      "loss": 1.0866,
      "step": 88
    },
    {
      "epoch": 0.5668789808917197,
      "grad_norm": 0.11594802141189575,
      "learning_rate": 0.00019371137774402527,
      "loss": 1.1146,
      "step": 89
    },
    {
      "epoch": 0.5732484076433121,
      "grad_norm": 0.1181577518582344,
      "learning_rate": 0.0001935297835916754,
      "loss": 1.1213,
      "step": 90
    },
    {
      "epoch": 0.5796178343949044,
      "grad_norm": 0.10821503400802612,
      "learning_rate": 0.00019334569230703794,
      "loss": 1.1121,
      "step": 91
    },
    {
      "epoch": 0.5859872611464968,
      "grad_norm": 0.118013896048069,
      "learning_rate": 0.0001931591088051279,
      "loss": 1.117,
      "step": 92
    },
    {
      "epoch": 0.5923566878980892,
      "grad_norm": 0.11678043752908707,
      "learning_rate": 0.0001929700380674995,
      "loss": 1.0974,
      "step": 93
    },
    {
      "epoch": 0.5987261146496815,
      "grad_norm": 0.11073200404644012,
      "learning_rate": 0.00019277848514211317,
      "loss": 1.1059,
      "step": 94
    },
    {
      "epoch": 0.6050955414012739,
      "grad_norm": 0.11440474539995193,
      "learning_rate": 0.00019258445514320065,
      "loss": 1.0913,
      "step": 95
    },
    {
      "epoch": 0.6114649681528662,
      "grad_norm": 0.11020273715257645,
      "learning_rate": 0.0001923879532511287,
      "loss": 1.0836,
      "step": 96
    },
    {
      "epoch": 0.6178343949044586,
      "grad_norm": 0.11285867542028427,
      "learning_rate": 0.0001921889847122605,
      "loss": 1.0842,
      "step": 97
    },
    {
      "epoch": 0.6242038216560509,
      "grad_norm": 0.11981746554374695,
      "learning_rate": 0.00019198755483881583,
      "loss": 1.1062,
      "step": 98
    },
    {
      "epoch": 0.6305732484076433,
      "grad_norm": 0.11882256716489792,
      "learning_rate": 0.0001917836690087291,
      "loss": 1.1012,
      "step": 99
    },
    {
      "epoch": 0.6369426751592356,
      "grad_norm": 0.11642686277627945,
      "learning_rate": 0.00019157733266550575,
      "loss": 1.0823,
      "step": 100
    },
    {
      "epoch": 0.643312101910828,
      "grad_norm": 0.11980683356523514,
      "learning_rate": 0.00019136855131807705,
      "loss": 1.105,
      "step": 101
    },
    {
      "epoch": 0.6496815286624203,
      "grad_norm": 0.1147085651755333,
      "learning_rate": 0.0001911573305406528,
      "loss": 1.0794,
      "step": 102
    },
    {
      "epoch": 0.6560509554140127,
      "grad_norm": 0.12037765234708786,
      "learning_rate": 0.00019094367597257282,
      "loss": 1.1059,
      "step": 103
    },
    {
      "epoch": 0.6624203821656051,
      "grad_norm": 0.12135636061429977,
      "learning_rate": 0.000190727593318156,
      "loss": 1.118,
      "step": 104
    },
    {
      "epoch": 0.6687898089171974,
      "grad_norm": 0.13285911083221436,
      "learning_rate": 0.00019050908834654834,
      "loss": 1.0817,
      "step": 105
    },
    {
      "epoch": 0.6751592356687898,
      "grad_norm": 0.11360063403844833,
      "learning_rate": 0.00019028816689156878,
      "loss": 1.0711,
      "step": 106
    },
    {
      "epoch": 0.6815286624203821,
      "grad_norm": 0.13178926706314087,
      "learning_rate": 0.00019006483485155338,
      "loss": 1.1266,
      "step": 107
    },
    {
      "epoch": 0.6878980891719745,
      "grad_norm": 0.1290571093559265,
      "learning_rate": 0.0001898390981891979,
      "loss": 1.0776,
      "step": 108
    },
    {
      "epoch": 0.6942675159235668,
      "grad_norm": 0.11376259475946426,
      "learning_rate": 0.0001896109629313987,
      "loss": 1.1026,
      "step": 109
    },
    {
      "epoch": 0.7006369426751592,
      "grad_norm": 0.12076874077320099,
      "learning_rate": 0.0001893804351690917,
      "loss": 1.104,
      "step": 110
    },
    {
      "epoch": 0.7070063694267515,
      "grad_norm": 0.12165362387895584,
      "learning_rate": 0.0001891475210570898,
      "loss": 1.0884,
      "step": 111
    },
    {
      "epoch": 0.7133757961783439,
      "grad_norm": 0.10634943842887878,
      "learning_rate": 0.00018891222681391851,
      "loss": 1.0844,
      "step": 112
    },
    {
      "epoch": 0.7197452229299363,
      "grad_norm": 0.11928383260965347,
      "learning_rate": 0.00018867455872165008,
      "loss": 1.1205,
      "step": 113
    },
    {
      "epoch": 0.7261146496815286,
      "grad_norm": 0.1243489533662796,
      "learning_rate": 0.00018843452312573554,
      "loss": 1.0704,
      "step": 114
    },
    {
      "epoch": 0.732484076433121,
      "grad_norm": 0.11439479887485504,
      "learning_rate": 0.0001881921264348355,
      "loss": 1.0809,
      "step": 115
    },
    {
      "epoch": 0.7388535031847133,
      "grad_norm": 0.1184995099902153,
      "learning_rate": 0.0001879473751206489,
      "loss": 1.1619,
      "step": 116
    },
    {
      "epoch": 0.7452229299363057,
      "grad_norm": 0.11846223473548889,
      "learning_rate": 0.00018770027571774031,
      "loss": 1.0835,
      "step": 117
    },
    {
      "epoch": 0.7515923566878981,
      "grad_norm": 0.11566226184368134,
      "learning_rate": 0.00018745083482336544,
      "loss": 1.0658,
      "step": 118
    },
    {
      "epoch": 0.7579617834394905,
      "grad_norm": 0.11553015559911728,
      "learning_rate": 0.00018719905909729494,
      "loss": 1.0773,
      "step": 119
    },
    {
      "epoch": 0.7643312101910829,
      "grad_norm": 0.13605500757694244,
      "learning_rate": 0.0001869449552616367,
      "loss": 1.0727,
      "step": 120
    },
    {
      "epoch": 0.7643312101910829,
      "eval_loss": 1.0301120281219482,
      "eval_runtime": 19.2781,
      "eval_samples_per_second": 56.645,
      "eval_steps_per_second": 0.934,
      "step": 120
    },
    {
      "epoch": 0.7707006369426752,
      "grad_norm": 0.1149601861834526,
      "learning_rate": 0.00018668853010065634,
      "loss": 1.0745,
      "step": 121
    },
    {
      "epoch": 0.7770700636942676,
      "grad_norm": 0.11904130131006241,
      "learning_rate": 0.00018642979046059593,
      "loss": 1.0574,
      "step": 122
    },
    {
      "epoch": 0.7834394904458599,
      "grad_norm": 0.11868870258331299,
      "learning_rate": 0.00018616874324949159,
      "loss": 1.0681,
      "step": 123
    },
    {
      "epoch": 0.7898089171974523,
      "grad_norm": 0.11400648951530457,
      "learning_rate": 0.00018590539543698854,
      "loss": 1.0874,
      "step": 124
    },
    {
      "epoch": 0.7961783439490446,
      "grad_norm": 0.12247481942176819,
      "learning_rate": 0.0001856397540541554,
      "loss": 1.0832,
      "step": 125
    },
    {
      "epoch": 0.802547770700637,
      "grad_norm": 0.11855783313512802,
      "learning_rate": 0.0001853718261932964,
      "loss": 1.0775,
      "step": 126
    },
    {
      "epoch": 0.8089171974522293,
      "grad_norm": 0.11434577405452728,
      "learning_rate": 0.00018510161900776187,
      "loss": 1.048,
      "step": 127
    },
    {
      "epoch": 0.8152866242038217,
      "grad_norm": 0.12175115942955017,
      "learning_rate": 0.00018482913971175737,
      "loss": 1.0776,
      "step": 128
    },
    {
      "epoch": 0.821656050955414,
      "grad_norm": 0.1237318217754364,
      "learning_rate": 0.00018455439558015115,
      "loss": 1.0977,
      "step": 129
    },
    {
      "epoch": 0.8280254777070064,
      "grad_norm": 0.12041562050580978,
      "learning_rate": 0.00018427739394827973,
      "loss": 1.0477,
      "step": 130
    },
    {
      "epoch": 0.8343949044585988,
      "grad_norm": 0.11855332553386688,
      "learning_rate": 0.00018399814221175227,
      "loss": 1.1026,
      "step": 131
    },
    {
      "epoch": 0.8407643312101911,
      "grad_norm": 0.12020997703075409,
      "learning_rate": 0.00018371664782625287,
      "loss": 1.0484,
      "step": 132
    },
    {
      "epoch": 0.8471337579617835,
      "grad_norm": 0.1116231232881546,
      "learning_rate": 0.00018343291830734176,
      "loss": 1.0772,
      "step": 133
    },
    {
      "epoch": 0.8535031847133758,
      "grad_norm": 0.12280379235744476,
      "learning_rate": 0.00018314696123025454,
      "loss": 1.0829,
      "step": 134
    },
    {
      "epoch": 0.8598726114649682,
      "grad_norm": 0.11589805781841278,
      "learning_rate": 0.00018285878422969983,
      "loss": 1.0636,
      "step": 135
    },
    {
      "epoch": 0.8662420382165605,
      "grad_norm": 0.11667989194393158,
      "learning_rate": 0.0001825683949996556,
      "loss": 1.0783,
      "step": 136
    },
    {
      "epoch": 0.8726114649681529,
      "grad_norm": 0.11666262894868851,
      "learning_rate": 0.00018227580129316366,
      "loss": 1.0587,
      "step": 137
    },
    {
      "epoch": 0.8789808917197452,
      "grad_norm": 0.11791834235191345,
      "learning_rate": 0.00018198101092212267,
      "loss": 1.0955,
      "step": 138
    },
    {
      "epoch": 0.8853503184713376,
      "grad_norm": 0.12023093551397324,
      "learning_rate": 0.00018168403175707954,
      "loss": 1.1133,
      "step": 139
    },
    {
      "epoch": 0.89171974522293,
      "grad_norm": 0.12082846462726593,
      "learning_rate": 0.0001813848717270195,
      "loss": 1.1083,
      "step": 140
    },
    {
      "epoch": 0.8980891719745223,
      "grad_norm": 0.1259888857603073,
      "learning_rate": 0.00018108353881915402,
      "loss": 1.0931,
      "step": 141
    },
    {
      "epoch": 0.9044585987261147,
      "grad_norm": 0.11900565028190613,
      "learning_rate": 0.00018078004107870797,
      "loss": 1.0955,
      "step": 142
    },
    {
      "epoch": 0.910828025477707,
      "grad_norm": 0.11422552168369293,
      "learning_rate": 0.00018047438660870446,
      "loss": 1.0473,
      "step": 143
    },
    {
      "epoch": 0.9171974522292994,
      "grad_norm": 0.13001863658428192,
      "learning_rate": 0.00018016658356974884,
      "loss": 1.0273,
      "step": 144
    },
    {
      "epoch": 0.9235668789808917,
      "grad_norm": 0.11941977590322495,
      "learning_rate": 0.0001798566401798106,
      "loss": 1.0774,
      "step": 145
    },
    {
      "epoch": 0.9299363057324841,
      "grad_norm": 0.12032714486122131,
      "learning_rate": 0.00017954456471400393,
      "loss": 1.1162,
      "step": 146
    },
    {
      "epoch": 0.9363057324840764,
      "grad_norm": 0.13784518837928772,
      "learning_rate": 0.00017923036550436704,
      "loss": 1.095,
      "step": 147
    },
    {
      "epoch": 0.9426751592356688,
      "grad_norm": 0.12085068970918655,
      "learning_rate": 0.00017891405093963938,
      "loss": 1.1024,
      "step": 148
    },
    {
      "epoch": 0.9490445859872612,
      "grad_norm": 0.11120469868183136,
      "learning_rate": 0.00017859562946503788,
      "loss": 1.0502,
      "step": 149
    },
    {
      "epoch": 0.9554140127388535,
      "grad_norm": 0.1275676190853119,
      "learning_rate": 0.00017827510958203147,
      "loss": 1.0875,
      "step": 150
    },
    {
      "epoch": 0.9617834394904459,
      "grad_norm": 0.13544359803199768,
      "learning_rate": 0.00017795249984811396,
      "loss": 1.0985,
      "step": 151
    },
    {
      "epoch": 0.9681528662420382,
      "grad_norm": 0.11840228736400604,
      "learning_rate": 0.00017762780887657574,
      "loss": 1.059,
      "step": 152
    },
    {
      "epoch": 0.9745222929936306,
      "grad_norm": 0.12622268497943878,
      "learning_rate": 0.0001773010453362737,
      "loss": 1.1034,
      "step": 153
    },
    {
      "epoch": 0.9808917197452229,
      "grad_norm": 0.11485569179058075,
      "learning_rate": 0.0001769722179513998,
      "loss": 1.0639,
      "step": 154
    },
    {
      "epoch": 0.9872611464968153,
      "grad_norm": 0.11948831379413605,
      "learning_rate": 0.00017664133550124815,
      "loss": 1.0635,
      "step": 155
    },
    {
      "epoch": 0.9936305732484076,
      "grad_norm": 0.1214427575469017,
      "learning_rate": 0.00017630840681998066,
      "loss": 1.1361,
      "step": 156
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.11713624000549316,
      "learning_rate": 0.00017597344079639112,
      "loss": 1.0619,
      "step": 157
    },
    {
      "epoch": 1.0063694267515924,
      "grad_norm": 0.11573248356580734,
      "learning_rate": 0.00017563644637366788,
      "loss": 1.1141,
      "step": 158
    },
    {
      "epoch": 1.0127388535031847,
      "grad_norm": 0.11592724919319153,
      "learning_rate": 0.00017529743254915512,
      "loss": 1.0569,
      "step": 159
    },
    {
      "epoch": 1.019108280254777,
      "grad_norm": 0.12063013017177582,
      "learning_rate": 0.0001749564083741126,
      "loss": 1.0438,
      "step": 160
    },
    {
      "epoch": 1.019108280254777,
      "eval_loss": 1.012627124786377,
      "eval_runtime": 19.2811,
      "eval_samples_per_second": 56.636,
      "eval_steps_per_second": 0.934,
      "step": 160
    },
    {
      "epoch": 1.0254777070063694,
      "grad_norm": 1.0452429056167603,
      "learning_rate": 0.00017461338295347406,
      "loss": 1.1776,
      "step": 161
    },
    {
      "epoch": 1.0063694267515924,
      "grad_norm": 0.13684259355068207,
      "learning_rate": 0.000174268365445604,
      "loss": 1.0491,
      "step": 162
    },
    {
      "epoch": 1.0127388535031847,
      "grad_norm": 0.13602878153324127,
      "learning_rate": 0.0001739213650620533,
      "loss": 1.0311,
      "step": 163
    },
    {
      "epoch": 1.019108280254777,
      "grad_norm": 0.1506141573190689,
      "learning_rate": 0.00017357239106731317,
      "loss": 1.0233,
      "step": 164
    },
    {
      "epoch": 1.0254777070063694,
      "grad_norm": 0.13961653411388397,
      "learning_rate": 0.00017322145277856794,
      "loss": 1.0515,
      "step": 165
    },
    {
      "epoch": 1.0318471337579618,
      "grad_norm": 0.12875933945178986,
      "learning_rate": 0.00017286855956544613,
      "loss": 1.0643,
      "step": 166
    },
    {
      "epoch": 1.0382165605095541,
      "grad_norm": 0.13839364051818848,
      "learning_rate": 0.0001725137208497705,
      "loss": 1.0853,
      "step": 167
    },
    {
      "epoch": 1.0445859872611465,
      "grad_norm": 0.1401708722114563,
      "learning_rate": 0.0001721569461053062,
      "loss": 1.0608,
      "step": 168
    },
    {
      "epoch": 1.0509554140127388,
      "grad_norm": 0.13666324317455292,
      "learning_rate": 0.0001717982448575082,
      "loss": 1.0186,
      "step": 169
    },
    {
      "epoch": 1.0573248407643312,
      "grad_norm": 0.13511985540390015,
      "learning_rate": 0.00017143762668326667,
      "loss": 1.0775,
      "step": 170
    },
    {
      "epoch": 1.0636942675159236,
      "grad_norm": 0.13401229679584503,
      "learning_rate": 0.00017107510121065138,
      "loss": 1.0587,
      "step": 171
    },
    {
      "epoch": 1.070063694267516,
      "grad_norm": 0.13937029242515564,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.0655,
      "step": 172
    },
    {
      "epoch": 1.0764331210191083,
      "grad_norm": 0.13978822529315948,
      "learning_rate": 0.0001703443671369333,
      "loss": 1.0417,
      "step": 173
    },
    {
      "epoch": 1.0828025477707006,
      "grad_norm": 0.1328263282775879,
      "learning_rate": 0.00016997617804554796,
      "loss": 1.0609,
      "step": 174
    },
    {
      "epoch": 1.089171974522293,
      "grad_norm": 0.13478587567806244,
      "learning_rate": 0.00016960612067470288,
      "loss": 1.0314,
      "step": 175
    },
    {
      "epoch": 1.0955414012738853,
      "grad_norm": 0.12482774257659912,
      "learning_rate": 0.00016923420490448296,
      "loss": 1.0173,
      "step": 176
    },
    {
      "epoch": 1.1019108280254777,
      "grad_norm": 0.12970109283924103,
      "learning_rate": 0.0001688604406645903,
      "loss": 1.0904,
      "step": 177
    },
    {
      "epoch": 1.10828025477707,
      "grad_norm": 0.12363622337579727,
      "learning_rate": 0.00016848483793407873,
      "loss": 1.0434,
      "step": 178
    },
    {
      "epoch": 1.1146496815286624,
      "grad_norm": 0.13114579021930695,
      "learning_rate": 0.00016810740674108764,
      "loss": 1.0456,
      "step": 179
    },
    {
      "epoch": 1.1210191082802548,
      "grad_norm": 0.13814528286457062,
      "learning_rate": 0.00016772815716257412,
      "loss": 1.0845,
      "step": 180
    },
    {
      "epoch": 1.127388535031847,
      "grad_norm": 0.12670482695102692,
      "learning_rate": 0.00016734709932404403,
      "loss": 1.0392,
      "step": 181
    },
    {
      "epoch": 1.1337579617834395,
      "grad_norm": 0.13344614207744598,
      "learning_rate": 0.00016696424339928152,
      "loss": 1.0429,
      "step": 182
    },
    {
      "epoch": 1.1401273885350318,
      "grad_norm": 0.14558671414852142,
      "learning_rate": 0.00016657959961007747,
      "loss": 1.0615,
      "step": 183
    },
    {
      "epoch": 1.1464968152866242,
      "grad_norm": 0.13091522455215454,
      "learning_rate": 0.00016619317822595667,
      "loss": 1.0816,
      "step": 184
    },
    {
      "epoch": 1.1528662420382165,
      "grad_norm": 0.1288042962551117,
      "learning_rate": 0.00016580498956390342,
      "loss": 1.0114,
      "step": 185
    },
    {
      "epoch": 1.1592356687898089,
      "grad_norm": 0.12748295068740845,
      "learning_rate": 0.00016541504398808631,
      "loss": 1.096,
      "step": 186
    },
    {
      "epoch": 1.1656050955414012,
      "grad_norm": 0.13045403361320496,
      "learning_rate": 0.00016502335190958135,
      "loss": 0.9977,
      "step": 187
    },
    {
      "epoch": 1.1719745222929936,
      "grad_norm": 0.14281457662582397,
      "learning_rate": 0.00016462992378609407,
      "loss": 1.0434,
      "step": 188
    },
    {
      "epoch": 1.178343949044586,
      "grad_norm": 0.1320338100194931,
      "learning_rate": 0.00016423477012168038,
      "loss": 1.0554,
      "step": 189
    },
    {
      "epoch": 1.1847133757961783,
      "grad_norm": 0.12324702739715576,
      "learning_rate": 0.00016383790146646588,
      "loss": 1.0416,
      "step": 190
    },
    {
      "epoch": 1.1910828025477707,
      "grad_norm": 0.1301770806312561,
      "learning_rate": 0.00016343932841636456,
      "loss": 1.0613,
      "step": 191
    },
    {
      "epoch": 1.197452229299363,
      "grad_norm": 0.14009694755077362,
      "learning_rate": 0.0001630390616127955,
      "loss": 1.0139,
      "step": 192
    },
    {
      "epoch": 1.2038216560509554,
      "grad_norm": 0.13656193017959595,
      "learning_rate": 0.00016263711174239914,
      "loss": 1.0632,
      "step": 193
    },
    {
      "epoch": 1.2101910828025477,
      "grad_norm": 0.12946204841136932,
      "learning_rate": 0.00016223348953675162,
      "loss": 1.0458,
      "step": 194
    },
    {
      "epoch": 1.21656050955414,
      "grad_norm": 0.1356847584247589,
      "learning_rate": 0.00016182820577207842,
      "loss": 1.0928,
      "step": 195
    },
    {
      "epoch": 1.2229299363057324,
      "grad_norm": 0.1389479786157608,
      "learning_rate": 0.0001614212712689668,
      "loss": 1.0577,
      "step": 196
    },
    {
      "epoch": 1.2292993630573248,
      "grad_norm": 0.1340690702199936,
      "learning_rate": 0.00016101269689207655,
      "loss": 1.0572,
      "step": 197
    },
    {
      "epoch": 1.2356687898089171,
      "grad_norm": 0.13188521564006805,
      "learning_rate": 0.00016060249354985025,
      "loss": 1.0775,
      "step": 198
    },
    {
      "epoch": 1.2420382165605095,
      "grad_norm": 0.12922795116901398,
      "learning_rate": 0.00016019067219422178,
      "loss": 1.0434,
      "step": 199
    },
    {
      "epoch": 1.2484076433121019,
      "grad_norm": 0.12612590193748474,
      "learning_rate": 0.0001597772438203241,
      "loss": 1.0126,
      "step": 200
    },
    {
      "epoch": 1.2484076433121019,
      "eval_loss": 1.00348961353302,
      "eval_runtime": 19.3163,
      "eval_samples_per_second": 56.533,
      "eval_steps_per_second": 0.932,
      "step": 200
    },
    {
      "epoch": 1.2547770700636942,
      "grad_norm": 0.1387277990579605,
      "learning_rate": 0.0001593622194661956,
      "loss": 1.0421,
      "step": 201
    },
    {
      "epoch": 1.2611464968152866,
      "grad_norm": 0.13583126664161682,
      "learning_rate": 0.00015894561021248535,
      "loss": 1.0441,
      "step": 202
    },
    {
      "epoch": 1.267515923566879,
      "grad_norm": 0.12996627390384674,
      "learning_rate": 0.00015852742718215743,
      "loss": 1.0342,
      "step": 203
    },
    {
      "epoch": 1.2738853503184713,
      "grad_norm": 0.13653862476348877,
      "learning_rate": 0.00015810768154019385,
      "loss": 1.0108,
      "step": 204
    },
    {
      "epoch": 1.2802547770700636,
      "grad_norm": 0.1289973258972168,
      "learning_rate": 0.0001576863844932963,
      "loss": 1.0523,
      "step": 205
    },
    {
      "epoch": 1.286624203821656,
      "grad_norm": 0.13348506391048431,
      "learning_rate": 0.00015726354728958736,
      "loss": 1.0564,
      "step": 206
    },
    {
      "epoch": 1.2929936305732483,
      "grad_norm": 0.12048185616731644,
      "learning_rate": 0.0001568391812183097,
      "loss": 1.0457,
      "step": 207
    },
    {
      "epoch": 1.2993630573248407,
      "grad_norm": 0.12991134822368622,
      "learning_rate": 0.00015641329760952513,
      "loss": 1.05,
      "step": 208
    },
    {
      "epoch": 1.305732484076433,
      "grad_norm": 0.13280436396598816,
      "learning_rate": 0.00015598590783381163,
      "loss": 1.0747,
      "step": 209
    },
    {
      "epoch": 1.3121019108280254,
      "grad_norm": 0.13099676370620728,
      "learning_rate": 0.00015555702330196023,
      "loss": 1.0764,
      "step": 210
    },
    {
      "epoch": 1.3184713375796178,
      "grad_norm": 0.1397230178117752,
      "learning_rate": 0.00015512665546467007,
      "loss": 1.0716,
      "step": 211
    },
    {
      "epoch": 1.3248407643312101,
      "grad_norm": 0.13324333727359772,
      "learning_rate": 0.00015469481581224272,
      "loss": 1.0926,
      "step": 212
    },
    {
      "epoch": 1.3312101910828025,
      "grad_norm": 0.1313484162092209,
      "learning_rate": 0.00015426151587427547,
      "loss": 1.0533,
      "step": 213
    },
    {
      "epoch": 1.3375796178343948,
      "grad_norm": 0.1433049589395523,
      "learning_rate": 0.00015382676721935345,
      "loss": 1.055,
      "step": 214
    },
    {
      "epoch": 1.3439490445859872,
      "grad_norm": 0.1309911012649536,
      "learning_rate": 0.00015339058145474085,
      "loss": 1.0536,
      "step": 215
    },
    {
      "epoch": 1.3503184713375795,
      "grad_norm": 0.13482902944087982,
      "learning_rate": 0.00015295297022607088,
      "loss": 1.0176,
      "step": 216
    },
    {
      "epoch": 1.356687898089172,
      "grad_norm": 0.13102853298187256,
      "learning_rate": 0.00015251394521703494,
      "loss": 1.0849,
      "step": 217
    },
    {
      "epoch": 1.3630573248407643,
      "grad_norm": 0.13901150226593018,
      "learning_rate": 0.00015207351814907068,
      "loss": 1.0452,
      "step": 218
    },
    {
      "epoch": 1.3694267515923566,
      "grad_norm": 0.13824929296970367,
      "learning_rate": 0.000151631700781049,
      "loss": 1.0083,
      "step": 219
    },
    {
      "epoch": 1.3757961783439492,
      "grad_norm": 0.1309863179922104,
      "learning_rate": 0.00015118850490896012,
      "loss": 1.0517,
      "step": 220
    },
    {
      "epoch": 1.3821656050955413,
      "grad_norm": 0.1359570473432541,
      "learning_rate": 0.0001507439423655987,
      "loss": 1.0452,
      "step": 221
    },
    {
      "epoch": 1.388535031847134,
      "grad_norm": 0.13473795354366302,
      "learning_rate": 0.00015029802502024788,
      "loss": 1.0234,
      "step": 222
    },
    {
      "epoch": 1.394904458598726,
      "grad_norm": 0.13787756860256195,
      "learning_rate": 0.0001498507647783623,
      "loss": 1.0811,
      "step": 223
    },
    {
      "epoch": 1.4012738853503186,
      "grad_norm": 0.1334763914346695,
      "learning_rate": 0.00014940217358125042,
      "loss": 1.0363,
      "step": 224
    },
    {
      "epoch": 1.4076433121019107,
      "grad_norm": 0.13535600900650024,
      "learning_rate": 0.0001489522634057555,
      "loss": 1.059,
      "step": 225
    },
    {
      "epoch": 1.4140127388535033,
      "grad_norm": 0.1335124969482422,
      "learning_rate": 0.00014850104626393598,
      "loss": 1.0602,
      "step": 226
    },
    {
      "epoch": 1.4203821656050954,
      "grad_norm": 0.13075490295886993,
      "learning_rate": 0.00014804853420274472,
      "loss": 1.0344,
      "step": 227
    },
    {
      "epoch": 1.426751592356688,
      "grad_norm": 0.13887614011764526,
      "learning_rate": 0.00014759473930370736,
      "loss": 1.0728,
      "step": 228
    },
    {
      "epoch": 1.4331210191082802,
      "grad_norm": 0.12808558344841003,
      "learning_rate": 0.0001471396736825998,
      "loss": 1.0158,
      "step": 229
    },
    {
      "epoch": 1.4394904458598727,
      "grad_norm": 0.1339128464460373,
      "learning_rate": 0.00014668334948912453,
      "loss": 1.0647,
      "step": 230
    },
    {
      "epoch": 1.4458598726114649,
      "grad_norm": 0.13178490102291107,
      "learning_rate": 0.00014622577890658665,
      "loss": 1.0684,
      "step": 231
    },
    {
      "epoch": 1.4522292993630574,
      "grad_norm": 0.13547855615615845,
      "learning_rate": 0.00014576697415156817,
      "loss": 1.0712,
      "step": 232
    },
    {
      "epoch": 1.4585987261146496,
      "grad_norm": 0.13795921206474304,
      "learning_rate": 0.00014530694747360204,
      "loss": 1.0776,
      "step": 233
    },
    {
      "epoch": 1.4649681528662422,
      "grad_norm": 0.13771343231201172,
      "learning_rate": 0.00014484571115484508,
      "loss": 1.0517,
      "step": 234
    },
    {
      "epoch": 1.4713375796178343,
      "grad_norm": 0.13231024146080017,
      "learning_rate": 0.0001443832775097501,
      "loss": 1.0776,
      "step": 235
    },
    {
      "epoch": 1.4777070063694269,
      "grad_norm": 0.1319817453622818,
      "learning_rate": 0.00014391965888473703,
      "loss": 1.0494,
      "step": 236
    },
    {
      "epoch": 1.484076433121019,
      "grad_norm": 0.13426139950752258,
      "learning_rate": 0.0001434548676578634,
      "loss": 1.001,
      "step": 237
    },
    {
      "epoch": 1.4904458598726116,
      "grad_norm": 0.13087789714336395,
      "learning_rate": 0.0001429889162384937,
      "loss": 1.0588,
      "step": 238
    },
    {
      "epoch": 1.4968152866242037,
      "grad_norm": 0.13652274012565613,
      "learning_rate": 0.00014252181706696817,
      "loss": 1.0124,
      "step": 239
    },
    {
      "epoch": 1.5031847133757963,
      "grad_norm": 0.13933531939983368,
      "learning_rate": 0.00014205358261427074,
      "loss": 1.048,
      "step": 240
    },
    {
      "epoch": 1.5031847133757963,
      "eval_loss": 0.9937697052955627,
      "eval_runtime": 19.2892,
      "eval_samples_per_second": 56.612,
      "eval_steps_per_second": 0.933,
      "step": 240
    },
    {
      "epoch": 1.5095541401273884,
      "grad_norm": 0.13970831036567688,
      "learning_rate": 0.00014158422538169596,
      "loss": 1.0433,
      "step": 241
    },
    {
      "epoch": 1.515923566878981,
      "grad_norm": 0.13193373382091522,
      "learning_rate": 0.0001411137579005151,
      "loss": 1.0726,
      "step": 242
    },
    {
      "epoch": 1.5222929936305731,
      "grad_norm": 0.14291027188301086,
      "learning_rate": 0.0001406421927316419,
      "loss": 1.0825,
      "step": 243
    },
    {
      "epoch": 1.5286624203821657,
      "grad_norm": 0.14268159866333008,
      "learning_rate": 0.00014016954246529696,
      "loss": 1.0887,
      "step": 244
    },
    {
      "epoch": 1.5350318471337578,
      "grad_norm": 0.13607299327850342,
      "learning_rate": 0.00013969581972067164,
      "loss": 1.0644,
      "step": 245
    },
    {
      "epoch": 1.5414012738853504,
      "grad_norm": 0.13732877373695374,
      "learning_rate": 0.0001392210371455913,
      "loss": 1.0339,
      "step": 246
    },
    {
      "epoch": 1.5477707006369426,
      "grad_norm": 0.13315479457378387,
      "learning_rate": 0.00013874520741617735,
      "loss": 1.0284,
      "step": 247
    },
    {
      "epoch": 1.5541401273885351,
      "grad_norm": 0.13376399874687195,
      "learning_rate": 0.000138268343236509,
      "loss": 1.0279,
      "step": 248
    },
    {
      "epoch": 1.5605095541401273,
      "grad_norm": 0.13698357343673706,
      "learning_rate": 0.00013779045733828407,
      "loss": 1.0884,
      "step": 249
    },
    {
      "epoch": 1.5668789808917198,
      "grad_norm": 0.13575707376003265,
      "learning_rate": 0.00013731156248047904,
      "loss": 1.0383,
      "step": 250
    },
    {
      "epoch": 1.573248407643312,
      "grad_norm": 0.14258643984794617,
      "learning_rate": 0.00013683167144900834,
      "loss": 1.0812,
      "step": 251
    },
    {
      "epoch": 1.5796178343949046,
      "grad_norm": 0.1422533541917801,
      "learning_rate": 0.00013635079705638298,
      "loss": 1.0259,
      "step": 252
    },
    {
      "epoch": 1.5859872611464967,
      "grad_norm": 0.13875292241573334,
      "learning_rate": 0.00013586895214136874,
      "loss": 1.0507,
      "step": 253
    },
    {
      "epoch": 1.5923566878980893,
      "grad_norm": 0.1358788013458252,
      "learning_rate": 0.00013538614956864296,
      "loss": 1.066,
      "step": 254
    },
    {
      "epoch": 1.5987261146496814,
      "grad_norm": 0.13774985074996948,
      "learning_rate": 0.0001349024022284514,
      "loss": 1.0485,
      "step": 255
    },
    {
      "epoch": 1.605095541401274,
      "grad_norm": 0.13040746748447418,
      "learning_rate": 0.00013441772303626387,
      "loss": 1.0173,
      "step": 256
    },
    {
      "epoch": 1.611464968152866,
      "grad_norm": 0.1312469244003296,
      "learning_rate": 0.00013393212493242963,
      "loss": 1.0489,
      "step": 257
    },
    {
      "epoch": 1.6178343949044587,
      "grad_norm": 0.14885447919368744,
      "learning_rate": 0.00013344562088183165,
      "loss": 1.0403,
      "step": 258
    },
    {
      "epoch": 1.6242038216560508,
      "grad_norm": 0.12916652858257294,
      "learning_rate": 0.00013295822387354071,
      "loss": 1.024,
      "step": 259
    },
    {
      "epoch": 1.6305732484076434,
      "grad_norm": 0.14133484661579132,
      "learning_rate": 0.00013246994692046836,
      "loss": 1.0708,
      "step": 260
    },
    {
      "epoch": 1.6369426751592355,
      "grad_norm": 0.1382388323545456,
      "learning_rate": 0.0001319808030590197,
      "loss": 1.0245,
      "step": 261
    },
    {
      "epoch": 1.643312101910828,
      "grad_norm": 0.133922278881073,
      "learning_rate": 0.0001314908053487452,
      "loss": 1.0811,
      "step": 262
    },
    {
      "epoch": 1.6496815286624202,
      "grad_norm": 0.13291525840759277,
      "learning_rate": 0.00013099996687199203,
      "loss": 1.0158,
      "step": 263
    },
    {
      "epoch": 1.6560509554140128,
      "grad_norm": 0.13765017688274384,
      "learning_rate": 0.00013050830073355488,
      "loss": 1.051,
      "step": 264
    },
    {
      "epoch": 1.662420382165605,
      "grad_norm": 0.13831576704978943,
      "learning_rate": 0.000130015820060326,
      "loss": 1.0277,
      "step": 265
    },
    {
      "epoch": 1.6687898089171975,
      "grad_norm": 0.13770005106925964,
      "learning_rate": 0.00012952253800094468,
      "loss": 1.0982,
      "step": 266
    },
    {
      "epoch": 1.6751592356687897,
      "grad_norm": 0.13507647812366486,
      "learning_rate": 0.00012902846772544624,
      "loss": 0.9961,
      "step": 267
    },
    {
      "epoch": 1.6815286624203822,
      "grad_norm": 0.13365790247917175,
      "learning_rate": 0.00012853362242491053,
      "loss": 1.0191,
      "step": 268
    },
    {
      "epoch": 1.6878980891719744,
      "grad_norm": 0.13307291269302368,
      "learning_rate": 0.00012803801531110955,
      "loss": 1.0709,
      "step": 269
    },
    {
      "epoch": 1.694267515923567,
      "grad_norm": 0.1397312730550766,
      "learning_rate": 0.0001275416596161548,
      "loss": 1.0412,
      "step": 270
    },
    {
      "epoch": 1.700636942675159,
      "grad_norm": 0.14555448293685913,
      "learning_rate": 0.00012704456859214397,
      "loss": 1.0675,
      "step": 271
    },
    {
      "epoch": 1.7070063694267517,
      "grad_norm": 0.14011207222938538,
      "learning_rate": 0.00012654675551080724,
      "loss": 1.0632,
      "step": 272
    },
    {
      "epoch": 1.7133757961783438,
      "grad_norm": 0.14120171964168549,
      "learning_rate": 0.00012604823366315273,
      "loss": 1.0307,
      "step": 273
    },
    {
      "epoch": 1.7197452229299364,
      "grad_norm": 0.13699355721473694,
      "learning_rate": 0.00012554901635911187,
      "loss": 1.0482,
      "step": 274
    },
    {
      "epoch": 1.7261146496815285,
      "grad_norm": 0.14194992184638977,
      "learning_rate": 0.00012504911692718385,
      "loss": 1.0944,
      "step": 275
    },
    {
      "epoch": 1.732484076433121,
      "grad_norm": 0.13791659474372864,
      "learning_rate": 0.00012454854871407994,
      "loss": 1.0276,
      "step": 276
    },
    {
      "epoch": 1.7388535031847132,
      "grad_norm": 0.1348312497138977,
      "learning_rate": 0.0001240473250843669,
      "loss": 1.0388,
      "step": 277
    },
    {
      "epoch": 1.7452229299363058,
      "grad_norm": 0.13901084661483765,
      "learning_rate": 0.00012354545942011057,
      "loss": 1.0605,
      "step": 278
    },
    {
      "epoch": 1.7515923566878981,
      "grad_norm": 0.13213810324668884,
      "learning_rate": 0.00012304296512051814,
      "loss": 1.0163,
      "step": 279
    },
    {
      "epoch": 1.7579617834394905,
      "grad_norm": 0.13962963223457336,
      "learning_rate": 0.00012253985560158062,
      "loss": 1.0839,
      "step": 280
    },
    {
      "epoch": 1.7579617834394905,
      "eval_loss": 0.9859278202056885,
      "eval_runtime": 19.3296,
      "eval_samples_per_second": 56.494,
      "eval_steps_per_second": 0.931,
      "step": 280
    },
    {
      "epoch": 1.7643312101910829,
      "grad_norm": 0.13637703657150269,
      "learning_rate": 0.00012203614429571475,
      "loss": 1.0466,
      "step": 281
    },
    {
      "epoch": 1.7707006369426752,
      "grad_norm": 0.13617432117462158,
      "learning_rate": 0.00012153184465140413,
      "loss": 1.086,
      "step": 282
    },
    {
      "epoch": 1.7770700636942676,
      "grad_norm": 0.1326834112405777,
      "learning_rate": 0.00012102697013284034,
      "loss": 1.0692,
      "step": 283
    },
    {
      "epoch": 1.78343949044586,
      "grad_norm": 0.1359279453754425,
      "learning_rate": 0.00012052153421956342,
      "loss": 1.0337,
      "step": 284
    },
    {
      "epoch": 1.7898089171974523,
      "grad_norm": 0.13754823803901672,
      "learning_rate": 0.00012001555040610197,
      "loss": 1.0377,
      "step": 285
    },
    {
      "epoch": 1.7961783439490446,
      "grad_norm": 0.1381075084209442,
      "learning_rate": 0.00011950903220161285,
      "loss": 1.0311,
      "step": 286
    },
    {
      "epoch": 1.802547770700637,
      "grad_norm": 0.14102081954479218,
      "learning_rate": 0.00011900199312952047,
      "loss": 1.0645,
      "step": 287
    },
    {
      "epoch": 1.8089171974522293,
      "grad_norm": 0.14201205968856812,
      "learning_rate": 0.00011849444672715586,
      "loss": 1.043,
      "step": 288
    },
    {
      "epoch": 1.8152866242038217,
      "grad_norm": 0.13808976113796234,
      "learning_rate": 0.0001179864065453951,
      "loss": 1.0263,
      "step": 289
    },
    {
      "epoch": 1.821656050955414,
      "grad_norm": 0.13844111561775208,
      "learning_rate": 0.00011747788614829758,
      "loss": 1.0483,
      "step": 290
    },
    {
      "epoch": 1.8280254777070064,
      "grad_norm": 0.13990408182144165,
      "learning_rate": 0.00011696889911274393,
      "loss": 1.0591,
      "step": 291
    },
    {
      "epoch": 1.8343949044585988,
      "grad_norm": 0.14219453930854797,
      "learning_rate": 0.00011645945902807341,
      "loss": 1.0702,
      "step": 292
    },
    {
      "epoch": 1.8407643312101911,
      "grad_norm": 0.13736915588378906,
      "learning_rate": 0.0001159495794957211,
      "loss": 1.0457,
      "step": 293
    },
    {
      "epoch": 1.8471337579617835,
      "grad_norm": 0.1305588185787201,
      "learning_rate": 0.00011543927412885489,
      "loss": 1.0006,
      "step": 294
    },
    {
      "epoch": 1.8535031847133758,
      "grad_norm": 0.1360785961151123,
      "learning_rate": 0.0001149285565520119,
      "loss": 1.0055,
      "step": 295
    },
    {
      "epoch": 1.8598726114649682,
      "grad_norm": 0.13506443798542023,
      "learning_rate": 0.00011441744040073468,
      "loss": 1.0519,
      "step": 296
    },
    {
      "epoch": 1.8662420382165605,
      "grad_norm": 0.1369323432445526,
      "learning_rate": 0.0001139059393212074,
      "loss": 1.0547,
      "step": 297
    },
    {
      "epoch": 1.872611464968153,
      "grad_norm": 0.13333867490291595,
      "learning_rate": 0.00011339406696989128,
      "loss": 1.0537,
      "step": 298
    },
    {
      "epoch": 1.8789808917197452,
      "grad_norm": 0.13622106611728668,
      "learning_rate": 0.00011288183701315995,
      "loss": 1.0517,
      "step": 299
    },
    {
      "epoch": 1.8853503184713376,
      "grad_norm": 0.14023956656455994,
      "learning_rate": 0.00011236926312693479,
      "loss": 1.0559,
      "step": 300
    },
    {
      "epoch": 1.89171974522293,
      "grad_norm": 0.1363711655139923,
      "learning_rate": 0.00011185635899631963,
      "loss": 1.0291,
      "step": 301
    },
    {
      "epoch": 1.8980891719745223,
      "grad_norm": 0.13854017853736877,
      "learning_rate": 0.00011134313831523547,
      "loss": 1.0605,
      "step": 302
    },
    {
      "epoch": 1.9044585987261147,
      "grad_norm": 0.13852174580097198,
      "learning_rate": 0.00011082961478605475,
      "loss": 1.0553,
      "step": 303
    },
    {
      "epoch": 1.910828025477707,
      "grad_norm": 0.14662423729896545,
      "learning_rate": 0.00011031580211923571,
      "loss": 1.0619,
      "step": 304
    },
    {
      "epoch": 1.9171974522292994,
      "grad_norm": 0.14127817749977112,
      "learning_rate": 0.0001098017140329561,
      "loss": 1.0698,
      "step": 305
    },
    {
      "epoch": 1.9235668789808917,
      "grad_norm": 0.1394420862197876,
      "learning_rate": 0.00010928736425274701,
      "loss": 1.0433,
      "step": 306
    },
    {
      "epoch": 1.929936305732484,
      "grad_norm": 0.1438218653202057,
      "learning_rate": 0.00010877276651112662,
      "loss": 1.0498,
      "step": 307
    },
    {
      "epoch": 1.9363057324840764,
      "grad_norm": 0.1500382274389267,
      "learning_rate": 0.00010825793454723325,
      "loss": 1.0613,
      "step": 308
    },
    {
      "epoch": 1.9426751592356688,
      "grad_norm": 0.14135834574699402,
      "learning_rate": 0.00010774288210645862,
      "loss": 1.0435,
      "step": 309
    },
    {
      "epoch": 1.9490445859872612,
      "grad_norm": 0.1469028890132904,
      "learning_rate": 0.00010722762294008106,
      "loss": 1.0064,
      "step": 310
    },
    {
      "epoch": 1.9554140127388535,
      "grad_norm": 0.14101552963256836,
      "learning_rate": 0.00010671217080489814,
      "loss": 1.0485,
      "step": 311
    },
    {
      "epoch": 1.9617834394904459,
      "grad_norm": 0.1395803987979889,
      "learning_rate": 0.00010619653946285947,
      "loss": 1.0405,
      "step": 312
    },
    {
      "epoch": 1.9681528662420382,
      "grad_norm": 0.1441717892885208,
      "learning_rate": 0.00010568074268069928,
      "loss": 1.0183,
      "step": 313
    },
    {
      "epoch": 1.9745222929936306,
      "grad_norm": 0.14449232816696167,
      "learning_rate": 0.00010516479422956882,
      "loss": 1.035,
      "step": 314
    },
    {
      "epoch": 1.980891719745223,
      "grad_norm": 0.14461494982242584,
      "learning_rate": 0.00010464870788466873,
      "loss": 1.0911,
      "step": 315
    },
    {
      "epoch": 1.9872611464968153,
      "grad_norm": 0.13796767592430115,
      "learning_rate": 0.00010413249742488131,
      "loss": 1.0425,
      "step": 316
    },
    {
      "epoch": 1.9936305732484076,
      "grad_norm": 0.1377556025981903,
      "learning_rate": 0.00010361617663240253,
      "loss": 1.0773,
      "step": 317
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.14611703157424927,
      "learning_rate": 0.00010309975929237408,
      "loss": 1.0333,
      "step": 318
    },
    {
      "epoch": 2.0063694267515926,
      "grad_norm": 0.1386556774377823,
      "learning_rate": 0.00010258325919251537,
      "loss": 0.9997,
      "step": 319
    },
    {
      "epoch": 2.0127388535031847,
      "grad_norm": 0.13707421720027924,
      "learning_rate": 0.00010206669012275545,
      "loss": 1.0817,
      "step": 320
    },
    {
      "epoch": 2.0127388535031847,
      "eval_loss": 0.9801168441772461,
      "eval_runtime": 19.3185,
      "eval_samples_per_second": 56.526,
      "eval_steps_per_second": 0.932,
      "step": 320
    },
    {
      "epoch": 2.019108280254777,
      "grad_norm": 0.13602325320243835,
      "learning_rate": 0.00010155006587486469,
      "loss": 1.0337,
      "step": 321
    },
    {
      "epoch": 2.0254777070063694,
      "grad_norm": 0.6095888018608093,
      "learning_rate": 0.00010103340024208674,
      "loss": 1.1783,
      "step": 322
    },
    {
      "epoch": 2.0063694267515926,
      "grad_norm": 0.1478217989206314,
      "learning_rate": 0.00010051670701877012,
      "loss": 1.0114,
      "step": 323
    },
    {
      "epoch": 2.0127388535031847,
      "grad_norm": 0.1493089348077774,
      "learning_rate": 0.0001,
      "loss": 1.0167,
      "step": 324
    },
    {
      "epoch": 2.0191082802547773,
      "grad_norm": 0.15172579884529114,
      "learning_rate": 9.948329298122988e-05,
      "loss": 1.0161,
      "step": 325
    },
    {
      "epoch": 2.0254777070063694,
      "grad_norm": 0.14516572654247284,
      "learning_rate": 9.89665997579133e-05,
      "loss": 1.0375,
      "step": 326
    },
    {
      "epoch": 2.031847133757962,
      "grad_norm": 0.15873479843139648,
      "learning_rate": 9.844993412513532e-05,
      "loss": 1.0214,
      "step": 327
    },
    {
      "epoch": 2.038216560509554,
      "grad_norm": 0.1409904658794403,
      "learning_rate": 9.793330987724459e-05,
      "loss": 1.001,
      "step": 328
    },
    {
      "epoch": 2.0445859872611467,
      "grad_norm": 0.15463833510875702,
      "learning_rate": 9.741674080748464e-05,
      "loss": 1.0325,
      "step": 329
    },
    {
      "epoch": 2.050955414012739,
      "grad_norm": 0.15082892775535583,
      "learning_rate": 9.690024070762596e-05,
      "loss": 1.0292,
      "step": 330
    },
    {
      "epoch": 2.0573248407643314,
      "grad_norm": 0.1486956775188446,
      "learning_rate": 9.638382336759749e-05,
      "loss": 0.9867,
      "step": 331
    },
    {
      "epoch": 2.0636942675159236,
      "grad_norm": 0.14457155764102936,
      "learning_rate": 9.586750257511867e-05,
      "loss": 1.0255,
      "step": 332
    },
    {
      "epoch": 2.070063694267516,
      "grad_norm": 0.15076091885566711,
      "learning_rate": 9.535129211533129e-05,
      "loss": 1.005,
      "step": 333
    },
    {
      "epoch": 2.0764331210191083,
      "grad_norm": 0.1533278077840805,
      "learning_rate": 9.483520577043121e-05,
      "loss": 0.9923,
      "step": 334
    },
    {
      "epoch": 2.082802547770701,
      "grad_norm": 0.14563091099262238,
      "learning_rate": 9.431925731930078e-05,
      "loss": 1.0548,
      "step": 335
    },
    {
      "epoch": 2.089171974522293,
      "grad_norm": 0.14984974265098572,
      "learning_rate": 9.380346053714055e-05,
      "loss": 1.0417,
      "step": 336
    },
    {
      "epoch": 2.0955414012738856,
      "grad_norm": 0.14393095672130585,
      "learning_rate": 9.328782919510185e-05,
      "loss": 1.0163,
      "step": 337
    },
    {
      "epoch": 2.1019108280254777,
      "grad_norm": 0.14722150564193726,
      "learning_rate": 9.277237705991894e-05,
      "loss": 1.0418,
      "step": 338
    },
    {
      "epoch": 2.1082802547770703,
      "grad_norm": 0.1614050716161728,
      "learning_rate": 9.225711789354137e-05,
      "loss": 0.9721,
      "step": 339
    },
    {
      "epoch": 2.1146496815286624,
      "grad_norm": 0.15309081971645355,
      "learning_rate": 9.174206545276677e-05,
      "loss": 1.0198,
      "step": 340
    },
    {
      "epoch": 2.121019108280255,
      "grad_norm": 0.1521766036748886,
      "learning_rate": 9.122723348887339e-05,
      "loss": 1.0196,
      "step": 341
    },
    {
      "epoch": 2.127388535031847,
      "grad_norm": 0.15561290085315704,
      "learning_rate": 9.0712635747253e-05,
      "loss": 1.0537,
      "step": 342
    },
    {
      "epoch": 2.1337579617834397,
      "grad_norm": 0.1435907781124115,
      "learning_rate": 9.019828596704394e-05,
      "loss": 0.9999,
      "step": 343
    },
    {
      "epoch": 2.140127388535032,
      "grad_norm": 0.15161436796188354,
      "learning_rate": 8.968419788076431e-05,
      "loss": 1.0154,
      "step": 344
    },
    {
      "epoch": 2.1464968152866244,
      "grad_norm": 0.14869481325149536,
      "learning_rate": 8.917038521394526e-05,
      "loss": 0.9847,
      "step": 345
    },
    {
      "epoch": 2.1528662420382165,
      "grad_norm": 0.14515374600887299,
      "learning_rate": 8.865686168476457e-05,
      "loss": 1.0069,
      "step": 346
    },
    {
      "epoch": 2.159235668789809,
      "grad_norm": 0.14634117484092712,
      "learning_rate": 8.81436410036804e-05,
      "loss": 1.008,
      "step": 347
    },
    {
      "epoch": 2.1656050955414012,
      "grad_norm": 0.15083561837673187,
      "learning_rate": 8.763073687306524e-05,
      "loss": 0.9891,
      "step": 348
    },
    {
      "epoch": 2.171974522292994,
      "grad_norm": 0.16083382070064545,
      "learning_rate": 8.71181629868401e-05,
      "loss": 1.0291,
      "step": 349
    },
    {
      "epoch": 2.178343949044586,
      "grad_norm": 0.14988526701927185,
      "learning_rate": 8.660593303010876e-05,
      "loss": 1.0217,
      "step": 350
    },
    {
      "epoch": 2.1847133757961785,
      "grad_norm": 0.15332889556884766,
      "learning_rate": 8.609406067879258e-05,
      "loss": 1.0502,
      "step": 351
    },
    {
      "epoch": 2.1910828025477707,
      "grad_norm": 0.1509145349264145,
      "learning_rate": 8.558255959926533e-05,
      "loss": 1.0021,
      "step": 352
    },
    {
      "epoch": 2.1974522292993632,
      "grad_norm": 0.14952103793621063,
      "learning_rate": 8.507144344798814e-05,
      "loss": 1.0052,
      "step": 353
    },
    {
      "epoch": 2.2038216560509554,
      "grad_norm": 0.14787828922271729,
      "learning_rate": 8.456072587114515e-05,
      "loss": 0.929,
      "step": 354
    },
    {
      "epoch": 2.210191082802548,
      "grad_norm": 0.1580924093723297,
      "learning_rate": 8.405042050427891e-05,
      "loss": 1.0071,
      "step": 355
    },
    {
      "epoch": 2.21656050955414,
      "grad_norm": 0.15078537166118622,
      "learning_rate": 8.35405409719266e-05,
      "loss": 0.999,
      "step": 356
    },
    {
      "epoch": 2.2229299363057327,
      "grad_norm": 0.1510494202375412,
      "learning_rate": 8.303110088725608e-05,
      "loss": 1.0222,
      "step": 357
    },
    {
      "epoch": 2.229299363057325,
      "grad_norm": 0.15881799161434174,
      "learning_rate": 8.252211385170242e-05,
      "loss": 1.0053,
      "step": 358
    },
    {
      "epoch": 2.2356687898089174,
      "grad_norm": 0.15945011377334595,
      "learning_rate": 8.201359345460496e-05,
      "loss": 1.0145,
      "step": 359
    },
    {
      "epoch": 2.2420382165605095,
      "grad_norm": 0.15022100508213043,
      "learning_rate": 8.150555327284417e-05,
      "loss": 1.0115,
      "step": 360
    },
    {
      "epoch": 2.2420382165605095,
      "eval_loss": 0.9787687659263611,
      "eval_runtime": 19.3111,
      "eval_samples_per_second": 56.548,
      "eval_steps_per_second": 0.932,
      "step": 360
    },
    {
      "epoch": 2.248407643312102,
      "grad_norm": 0.15681840479373932,
      "learning_rate": 8.099800687047958e-05,
      "loss": 1.0398,
      "step": 361
    },
    {
      "epoch": 2.254777070063694,
      "grad_norm": 0.14988869428634644,
      "learning_rate": 8.049096779838719e-05,
      "loss": 0.9828,
      "step": 362
    },
    {
      "epoch": 2.261146496815287,
      "grad_norm": 0.1477968841791153,
      "learning_rate": 7.998444959389803e-05,
      "loss": 1.0276,
      "step": 363
    },
    {
      "epoch": 2.267515923566879,
      "grad_norm": 0.1529729813337326,
      "learning_rate": 7.947846578043659e-05,
      "loss": 1.0172,
      "step": 364
    },
    {
      "epoch": 2.2738853503184715,
      "grad_norm": 0.15440192818641663,
      "learning_rate": 7.897302986715967e-05,
      "loss": 1.0387,
      "step": 365
    },
    {
      "epoch": 2.2802547770700636,
      "grad_norm": 0.16899262368679047,
      "learning_rate": 7.846815534859591e-05,
      "loss": 1.0352,
      "step": 366
    },
    {
      "epoch": 2.286624203821656,
      "grad_norm": 0.15240244567394257,
      "learning_rate": 7.796385570428526e-05,
      "loss": 1.0264,
      "step": 367
    },
    {
      "epoch": 2.2929936305732483,
      "grad_norm": 0.15043969452381134,
      "learning_rate": 7.74601443984194e-05,
      "loss": 0.9838,
      "step": 368
    },
    {
      "epoch": 2.299363057324841,
      "grad_norm": 0.16128422319889069,
      "learning_rate": 7.695703487948189e-05,
      "loss": 1.0317,
      "step": 369
    },
    {
      "epoch": 2.305732484076433,
      "grad_norm": 0.159554123878479,
      "learning_rate": 7.645454057988942e-05,
      "loss": 1.0122,
      "step": 370
    },
    {
      "epoch": 2.3121019108280256,
      "grad_norm": 0.15471342206001282,
      "learning_rate": 7.59526749156331e-05,
      "loss": 1.0077,
      "step": 371
    },
    {
      "epoch": 2.3184713375796178,
      "grad_norm": 0.1584528684616089,
      "learning_rate": 7.54514512859201e-05,
      "loss": 1.0074,
      "step": 372
    },
    {
      "epoch": 2.3248407643312103,
      "grad_norm": 0.16024437546730042,
      "learning_rate": 7.495088307281618e-05,
      "loss": 1.0066,
      "step": 373
    },
    {
      "epoch": 2.3312101910828025,
      "grad_norm": 0.15269304811954498,
      "learning_rate": 7.445098364088815e-05,
      "loss": 1.0083,
      "step": 374
    },
    {
      "epoch": 2.337579617834395,
      "grad_norm": 0.15843960642814636,
      "learning_rate": 7.395176633684726e-05,
      "loss": 0.982,
      "step": 375
    },
    {
      "epoch": 2.343949044585987,
      "grad_norm": 0.155010387301445,
      "learning_rate": 7.34532444891928e-05,
      "loss": 1.019,
      "step": 376
    },
    {
      "epoch": 2.3503184713375798,
      "grad_norm": 0.16114681959152222,
      "learning_rate": 7.295543140785603e-05,
      "loss": 1.0056,
      "step": 377
    },
    {
      "epoch": 2.356687898089172,
      "grad_norm": 0.15911327302455902,
      "learning_rate": 7.245834038384522e-05,
      "loss": 1.0172,
      "step": 378
    },
    {
      "epoch": 2.3630573248407645,
      "grad_norm": 0.1528182476758957,
      "learning_rate": 7.196198468889047e-05,
      "loss": 0.989,
      "step": 379
    },
    {
      "epoch": 2.3694267515923566,
      "grad_norm": 0.1665172576904297,
      "learning_rate": 7.146637757508949e-05,
      "loss": 1.0249,
      "step": 380
    },
    {
      "epoch": 2.375796178343949,
      "grad_norm": 0.16792528331279755,
      "learning_rate": 7.097153227455379e-05,
      "loss": 1.0017,
      "step": 381
    },
    {
      "epoch": 2.3821656050955413,
      "grad_norm": 0.15666238963603973,
      "learning_rate": 7.047746199905536e-05,
      "loss": 1.021,
      "step": 382
    },
    {
      "epoch": 2.388535031847134,
      "grad_norm": 0.15589690208435059,
      "learning_rate": 6.998417993967403e-05,
      "loss": 1.0325,
      "step": 383
    },
    {
      "epoch": 2.394904458598726,
      "grad_norm": 0.15027858316898346,
      "learning_rate": 6.949169926644514e-05,
      "loss": 1.0215,
      "step": 384
    },
    {
      "epoch": 2.4012738853503186,
      "grad_norm": 0.15848621726036072,
      "learning_rate": 6.9000033128008e-05,
      "loss": 1.0324,
      "step": 385
    },
    {
      "epoch": 2.4076433121019107,
      "grad_norm": 0.15717780590057373,
      "learning_rate": 6.850919465125482e-05,
      "loss": 0.9591,
      "step": 386
    },
    {
      "epoch": 2.4140127388535033,
      "grad_norm": 0.16189338266849518,
      "learning_rate": 6.801919694098033e-05,
      "loss": 0.9963,
      "step": 387
    },
    {
      "epoch": 2.4203821656050954,
      "grad_norm": 0.16102810204029083,
      "learning_rate": 6.753005307953167e-05,
      "loss": 1.0205,
      "step": 388
    },
    {
      "epoch": 2.426751592356688,
      "grad_norm": 0.15888215601444244,
      "learning_rate": 6.70417761264593e-05,
      "loss": 0.9904,
      "step": 389
    },
    {
      "epoch": 2.43312101910828,
      "grad_norm": 0.16042260825634003,
      "learning_rate": 6.655437911816838e-05,
      "loss": 1.0394,
      "step": 390
    },
    {
      "epoch": 2.4394904458598727,
      "grad_norm": 0.17097777128219604,
      "learning_rate": 6.60678750675704e-05,
      "loss": 1.0279,
      "step": 391
    },
    {
      "epoch": 2.445859872611465,
      "grad_norm": 0.1708676666021347,
      "learning_rate": 6.558227696373616e-05,
      "loss": 0.9913,
      "step": 392
    },
    {
      "epoch": 2.4522292993630574,
      "grad_norm": 0.16568711400032043,
      "learning_rate": 6.509759777154864e-05,
      "loss": 1.0058,
      "step": 393
    },
    {
      "epoch": 2.4585987261146496,
      "grad_norm": 0.16431483626365662,
      "learning_rate": 6.461385043135704e-05,
      "loss": 1.0528,
      "step": 394
    },
    {
      "epoch": 2.464968152866242,
      "grad_norm": 0.15568807721138,
      "learning_rate": 6.413104785863128e-05,
      "loss": 1.044,
      "step": 395
    },
    {
      "epoch": 2.4713375796178343,
      "grad_norm": 0.1519811451435089,
      "learning_rate": 6.3649202943617e-05,
      "loss": 1.0269,
      "step": 396
    },
    {
      "epoch": 2.477707006369427,
      "grad_norm": 0.159037247300148,
      "learning_rate": 6.316832855099173e-05,
      "loss": 1.0221,
      "step": 397
    },
    {
      "epoch": 2.484076433121019,
      "grad_norm": 0.15528284013271332,
      "learning_rate": 6.2688437519521e-05,
      "loss": 0.985,
      "step": 398
    },
    {
      "epoch": 2.4904458598726116,
      "grad_norm": 0.15442180633544922,
      "learning_rate": 6.220954266171596e-05,
      "loss": 1.0071,
      "step": 399
    },
    {
      "epoch": 2.4968152866242037,
      "grad_norm": 0.15721610188484192,
      "learning_rate": 6.173165676349103e-05,
      "loss": 1.0356,
      "step": 400
    },
    {
      "epoch": 2.4968152866242037,
      "eval_loss": 0.9729906916618347,
      "eval_runtime": 19.5681,
      "eval_samples_per_second": 55.805,
      "eval_steps_per_second": 0.92,
      "step": 400
    },
    {
      "epoch": 2.5031847133757963,
      "grad_norm": 0.16139522194862366,
      "learning_rate": 6.125479258382268e-05,
      "loss": 1.0247,
      "step": 401
    },
    {
      "epoch": 2.5095541401273884,
      "grad_norm": 0.16305910050868988,
      "learning_rate": 6.077896285440874e-05,
      "loss": 1.0617,
      "step": 402
    },
    {
      "epoch": 2.515923566878981,
      "grad_norm": 0.1648111492395401,
      "learning_rate": 6.030418027932835e-05,
      "loss": 1.0367,
      "step": 403
    },
    {
      "epoch": 2.522292993630573,
      "grad_norm": 0.1614786684513092,
      "learning_rate": 5.983045753470308e-05,
      "loss": 1.0159,
      "step": 404
    },
    {
      "epoch": 2.5286624203821657,
      "grad_norm": 0.15744082629680634,
      "learning_rate": 5.935780726835811e-05,
      "loss": 1.0317,
      "step": 405
    },
    {
      "epoch": 2.535031847133758,
      "grad_norm": 0.16021069884300232,
      "learning_rate": 5.888624209948495e-05,
      "loss": 1.0468,
      "step": 406
    },
    {
      "epoch": 2.5414012738853504,
      "grad_norm": 0.16327615082263947,
      "learning_rate": 5.841577461830407e-05,
      "loss": 1.0017,
      "step": 407
    },
    {
      "epoch": 2.5477707006369426,
      "grad_norm": 0.16415022313594818,
      "learning_rate": 5.794641738572925e-05,
      "loss": 0.9745,
      "step": 408
    },
    {
      "epoch": 2.554140127388535,
      "grad_norm": 0.16266576945781708,
      "learning_rate": 5.747818293303184e-05,
      "loss": 0.9881,
      "step": 409
    },
    {
      "epoch": 2.5605095541401273,
      "grad_norm": 0.1699274182319641,
      "learning_rate": 5.7011083761506344e-05,
      "loss": 1.041,
      "step": 410
    },
    {
      "epoch": 2.56687898089172,
      "grad_norm": 0.16479632258415222,
      "learning_rate": 5.6545132342136634e-05,
      "loss": 0.9983,
      "step": 411
    },
    {
      "epoch": 2.573248407643312,
      "grad_norm": 0.1586018204689026,
      "learning_rate": 5.608034111526298e-05,
      "loss": 1.0322,
      "step": 412
    },
    {
      "epoch": 2.5796178343949046,
      "grad_norm": 0.16549105942249298,
      "learning_rate": 5.561672249024988e-05,
      "loss": 0.9938,
      "step": 413
    },
    {
      "epoch": 2.5859872611464967,
      "grad_norm": 0.16589821875095367,
      "learning_rate": 5.515428884515494e-05,
      "loss": 1.0039,
      "step": 414
    },
    {
      "epoch": 2.5923566878980893,
      "grad_norm": 0.16915416717529297,
      "learning_rate": 5.469305252639796e-05,
      "loss": 1.0109,
      "step": 415
    },
    {
      "epoch": 2.5987261146496814,
      "grad_norm": 0.1557624787092209,
      "learning_rate": 5.423302584843186e-05,
      "loss": 0.9918,
      "step": 416
    },
    {
      "epoch": 2.605095541401274,
      "grad_norm": 0.16412273049354553,
      "learning_rate": 5.377422109341332e-05,
      "loss": 1.016,
      "step": 417
    },
    {
      "epoch": 2.611464968152866,
      "grad_norm": 0.163206547498703,
      "learning_rate": 5.331665051087549e-05,
      "loss": 1.0528,
      "step": 418
    },
    {
      "epoch": 2.6178343949044587,
      "grad_norm": 0.16450117528438568,
      "learning_rate": 5.286032631740023e-05,
      "loss": 1.0314,
      "step": 419
    },
    {
      "epoch": 2.624203821656051,
      "grad_norm": 0.16499797999858856,
      "learning_rate": 5.240526069629265e-05,
      "loss": 0.985,
      "step": 420
    },
    {
      "epoch": 2.6305732484076434,
      "grad_norm": 0.17124028503894806,
      "learning_rate": 5.19514657972553e-05,
      "loss": 0.9932,
      "step": 421
    },
    {
      "epoch": 2.6369426751592355,
      "grad_norm": 0.1563197821378708,
      "learning_rate": 5.149895373606405e-05,
      "loss": 1.0221,
      "step": 422
    },
    {
      "epoch": 2.643312101910828,
      "grad_norm": 0.16314244270324707,
      "learning_rate": 5.104773659424453e-05,
      "loss": 1.0274,
      "step": 423
    },
    {
      "epoch": 2.6496815286624202,
      "grad_norm": 0.16842271387577057,
      "learning_rate": 5.059782641874962e-05,
      "loss": 0.9844,
      "step": 424
    },
    {
      "epoch": 2.656050955414013,
      "grad_norm": 0.16713784635066986,
      "learning_rate": 5.0149235221637724e-05,
      "loss": 1.0368,
      "step": 425
    },
    {
      "epoch": 2.662420382165605,
      "grad_norm": 0.16381680965423584,
      "learning_rate": 4.970197497975216e-05,
      "loss": 0.9824,
      "step": 426
    },
    {
      "epoch": 2.6687898089171975,
      "grad_norm": 0.15927736461162567,
      "learning_rate": 4.92560576344013e-05,
      "loss": 1.0187,
      "step": 427
    },
    {
      "epoch": 2.6751592356687897,
      "grad_norm": 0.17020700871944427,
      "learning_rate": 4.8811495091039926e-05,
      "loss": 1.0174,
      "step": 428
    },
    {
      "epoch": 2.6815286624203822,
      "grad_norm": 0.1601068079471588,
      "learning_rate": 4.836829921895103e-05,
      "loss": 1.0177,
      "step": 429
    },
    {
      "epoch": 2.6878980891719744,
      "grad_norm": 0.15823066234588623,
      "learning_rate": 4.792648185092937e-05,
      "loss": 1.0062,
      "step": 430
    },
    {
      "epoch": 2.694267515923567,
      "grad_norm": 0.15921784937381744,
      "learning_rate": 4.748605478296507e-05,
      "loss": 1.0211,
      "step": 431
    },
    {
      "epoch": 2.700636942675159,
      "grad_norm": 0.1611403077840805,
      "learning_rate": 4.704702977392914e-05,
      "loss": 0.9955,
      "step": 432
    },
    {
      "epoch": 2.7070063694267517,
      "grad_norm": 0.16314539313316345,
      "learning_rate": 4.660941854525917e-05,
      "loss": 0.9749,
      "step": 433
    },
    {
      "epoch": 2.713375796178344,
      "grad_norm": 0.161176398396492,
      "learning_rate": 4.617323278064657e-05,
      "loss": 1.0242,
      "step": 434
    },
    {
      "epoch": 2.7197452229299364,
      "grad_norm": 0.16189491748809814,
      "learning_rate": 4.573848412572458e-05,
      "loss": 1.0461,
      "step": 435
    },
    {
      "epoch": 2.7261146496815285,
      "grad_norm": 0.16615349054336548,
      "learning_rate": 4.530518418775733e-05,
      "loss": 1.0072,
      "step": 436
    },
    {
      "epoch": 2.732484076433121,
      "grad_norm": 0.16004875302314758,
      "learning_rate": 4.4873344535329976e-05,
      "loss": 0.9512,
      "step": 437
    },
    {
      "epoch": 2.738853503184713,
      "grad_norm": 0.16015282273292542,
      "learning_rate": 4.444297669803981e-05,
      "loss": 1.0274,
      "step": 438
    },
    {
      "epoch": 2.745222929936306,
      "grad_norm": 0.16400328278541565,
      "learning_rate": 4.401409216618837e-05,
      "loss": 1.0202,
      "step": 439
    },
    {
      "epoch": 2.7515923566878984,
      "grad_norm": 0.16385433077812195,
      "learning_rate": 4.35867023904749e-05,
      "loss": 0.992,
      "step": 440
    },
    {
      "epoch": 2.7515923566878984,
      "eval_loss": 0.9724947810173035,
      "eval_runtime": 19.3397,
      "eval_samples_per_second": 56.464,
      "eval_steps_per_second": 0.931,
      "step": 440
    },
    {
      "epoch": 2.7579617834394905,
      "grad_norm": 0.15915533900260925,
      "learning_rate": 4.316081878169028e-05,
      "loss": 0.9942,
      "step": 441
    },
    {
      "epoch": 2.7643312101910826,
      "grad_norm": 0.1640160232782364,
      "learning_rate": 4.273645271041265e-05,
      "loss": 1.0249,
      "step": 442
    },
    {
      "epoch": 2.770700636942675,
      "grad_norm": 0.16595910489559174,
      "learning_rate": 4.231361550670368e-05,
      "loss": 0.9731,
      "step": 443
    },
    {
      "epoch": 2.777070063694268,
      "grad_norm": 0.16304102540016174,
      "learning_rate": 4.189231845980618e-05,
      "loss": 0.9744,
      "step": 444
    },
    {
      "epoch": 2.78343949044586,
      "grad_norm": 0.16614365577697754,
      "learning_rate": 4.147257281784257e-05,
      "loss": 1.0322,
      "step": 445
    },
    {
      "epoch": 2.789808917197452,
      "grad_norm": 0.16803008317947388,
      "learning_rate": 4.105438978751465e-05,
      "loss": 1.0433,
      "step": 446
    },
    {
      "epoch": 2.7961783439490446,
      "grad_norm": 0.16848289966583252,
      "learning_rate": 4.063778053380446e-05,
      "loss": 1.0024,
      "step": 447
    },
    {
      "epoch": 2.802547770700637,
      "grad_norm": 0.1626000553369522,
      "learning_rate": 4.022275617967591e-05,
      "loss": 1.0139,
      "step": 448
    },
    {
      "epoch": 2.8089171974522293,
      "grad_norm": 0.16323398053646088,
      "learning_rate": 3.980932780577826e-05,
      "loss": 0.9812,
      "step": 449
    },
    {
      "epoch": 2.8152866242038215,
      "grad_norm": 0.16567878425121307,
      "learning_rate": 3.939750645014977e-05,
      "loss": 1.0059,
      "step": 450
    },
    {
      "epoch": 2.821656050955414,
      "grad_norm": 0.16283658146858215,
      "learning_rate": 3.8987303107923456e-05,
      "loss": 0.975,
      "step": 451
    },
    {
      "epoch": 2.8280254777070066,
      "grad_norm": 0.162727952003479,
      "learning_rate": 3.857872873103322e-05,
      "loss": 1.0087,
      "step": 452
    },
    {
      "epoch": 2.8343949044585988,
      "grad_norm": 0.16250313818454742,
      "learning_rate": 3.817179422792159e-05,
      "loss": 1.0225,
      "step": 453
    },
    {
      "epoch": 2.840764331210191,
      "grad_norm": 0.17140831053256989,
      "learning_rate": 3.776651046324843e-05,
      "loss": 1.0445,
      "step": 454
    },
    {
      "epoch": 2.8471337579617835,
      "grad_norm": 0.16704216599464417,
      "learning_rate": 3.7362888257600895e-05,
      "loss": 1.0108,
      "step": 455
    },
    {
      "epoch": 2.853503184713376,
      "grad_norm": 0.16444292664527893,
      "learning_rate": 3.69609383872045e-05,
      "loss": 1.0357,
      "step": 456
    },
    {
      "epoch": 2.859872611464968,
      "grad_norm": 0.163473442196846,
      "learning_rate": 3.6560671583635467e-05,
      "loss": 1.0211,
      "step": 457
    },
    {
      "epoch": 2.8662420382165603,
      "grad_norm": 0.1613229364156723,
      "learning_rate": 3.616209853353409e-05,
      "loss": 1.0095,
      "step": 458
    },
    {
      "epoch": 2.872611464968153,
      "grad_norm": 0.16236041486263275,
      "learning_rate": 3.576522987831965e-05,
      "loss": 1.0443,
      "step": 459
    },
    {
      "epoch": 2.8789808917197455,
      "grad_norm": 0.1598891168832779,
      "learning_rate": 3.53700762139059e-05,
      "loss": 1.0239,
      "step": 460
    },
    {
      "epoch": 2.8853503184713376,
      "grad_norm": 0.159934863448143,
      "learning_rate": 3.4976648090418685e-05,
      "loss": 0.9633,
      "step": 461
    },
    {
      "epoch": 2.8917197452229297,
      "grad_norm": 0.16620267927646637,
      "learning_rate": 3.4584956011913696e-05,
      "loss": 1.0087,
      "step": 462
    },
    {
      "epoch": 2.8980891719745223,
      "grad_norm": 0.15960000455379486,
      "learning_rate": 3.419501043609662e-05,
      "loss": 1.0176,
      "step": 463
    },
    {
      "epoch": 2.904458598726115,
      "grad_norm": 0.16119760274887085,
      "learning_rate": 3.380682177404335e-05,
      "loss": 0.9979,
      "step": 464
    },
    {
      "epoch": 2.910828025477707,
      "grad_norm": 0.16766443848609924,
      "learning_rate": 3.342040038992253e-05,
      "loss": 1.0253,
      "step": 465
    },
    {
      "epoch": 2.917197452229299,
      "grad_norm": 0.16117678582668304,
      "learning_rate": 3.303575660071852e-05,
      "loss": 0.9819,
      "step": 466
    },
    {
      "epoch": 2.9235668789808917,
      "grad_norm": 0.16629359126091003,
      "learning_rate": 3.2652900675956e-05,
      "loss": 1.0317,
      "step": 467
    },
    {
      "epoch": 2.9299363057324843,
      "grad_norm": 0.15698491036891937,
      "learning_rate": 3.227184283742591e-05,
      "loss": 1.0077,
      "step": 468
    },
    {
      "epoch": 2.9363057324840764,
      "grad_norm": 0.16256022453308105,
      "learning_rate": 3.1892593258912406e-05,
      "loss": 1.0033,
      "step": 469
    },
    {
      "epoch": 2.9426751592356686,
      "grad_norm": 0.16279557347297668,
      "learning_rate": 3.1515162065921276e-05,
      "loss": 1.0041,
      "step": 470
    },
    {
      "epoch": 2.949044585987261,
      "grad_norm": 0.1671912968158722,
      "learning_rate": 3.113955933540973e-05,
      "loss": 1.02,
      "step": 471
    },
    {
      "epoch": 2.9554140127388537,
      "grad_norm": 0.16780363023281097,
      "learning_rate": 3.076579509551703e-05,
      "loss": 1.0619,
      "step": 472
    },
    {
      "epoch": 2.961783439490446,
      "grad_norm": 0.17170728743076324,
      "learning_rate": 3.0393879325297138e-05,
      "loss": 1.0145,
      "step": 473
    },
    {
      "epoch": 2.968152866242038,
      "grad_norm": 0.15957629680633545,
      "learning_rate": 3.0023821954452035e-05,
      "loss": 1.0177,
      "step": 474
    },
    {
      "epoch": 2.9745222929936306,
      "grad_norm": 0.16020749509334564,
      "learning_rate": 2.9655632863066697e-05,
      "loss": 0.9716,
      "step": 475
    },
    {
      "epoch": 2.980891719745223,
      "grad_norm": 0.1645825058221817,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 1.029,
      "step": 476
    },
    {
      "epoch": 2.9872611464968153,
      "grad_norm": 0.161189004778862,
      "learning_rate": 2.892489878934864e-05,
      "loss": 0.9965,
      "step": 477
    },
    {
      "epoch": 2.9936305732484074,
      "grad_norm": 0.1658092737197876,
      "learning_rate": 2.856237331673336e-05,
      "loss": 0.9981,
      "step": 478
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.16803456842899323,
      "learning_rate": 2.8201755142491814e-05,
      "loss": 1.015,
      "step": 479
    },
    {
      "epoch": 3.0063694267515926,
      "grad_norm": 0.17741180956363678,
      "learning_rate": 2.7843053894693803e-05,
      "loss": 1.0219,
      "step": 480
    },
    {
      "epoch": 3.0063694267515926,
      "eval_loss": 0.9682163596153259,
      "eval_runtime": 19.3149,
      "eval_samples_per_second": 56.537,
      "eval_steps_per_second": 0.932,
      "step": 480
    },
    {
      "epoch": 3.0127388535031847,
      "grad_norm": 0.1747114509344101,
      "learning_rate": 2.74862791502295e-05,
      "loss": 1.0609,
      "step": 481
    },
    {
      "epoch": 3.019108280254777,
      "grad_norm": 0.15900041162967682,
      "learning_rate": 2.7131440434553877e-05,
      "loss": 0.9802,
      "step": 482
    },
    {
      "epoch": 3.0254777070063694,
      "grad_norm": 2.304769277572632,
      "learning_rate": 2.677854722143206e-05,
      "loss": 0.9589,
      "step": 483
    },
    {
      "epoch": 3.0063694267515926,
      "grad_norm": 0.17182937264442444,
      "learning_rate": 2.6427608932686843e-05,
      "loss": 0.9908,
      "step": 484
    },
    {
      "epoch": 3.0127388535031847,
      "grad_norm": 0.1753534972667694,
      "learning_rate": 2.6078634937946722e-05,
      "loss": 0.9786,
      "step": 485
    },
    {
      "epoch": 3.0191082802547773,
      "grad_norm": 0.1778535693883896,
      "learning_rate": 2.5731634554396012e-05,
      "loss": 1.0258,
      "step": 486
    },
    {
      "epoch": 3.0254777070063694,
      "grad_norm": 0.17605502903461456,
      "learning_rate": 2.5386617046525953e-05,
      "loss": 1.0155,
      "step": 487
    },
    {
      "epoch": 3.031847133757962,
      "grad_norm": 0.1721024513244629,
      "learning_rate": 2.5043591625887407e-05,
      "loss": 1.0124,
      "step": 488
    },
    {
      "epoch": 3.038216560509554,
      "grad_norm": 0.16322346031665802,
      "learning_rate": 2.4702567450844883e-05,
      "loss": 0.9821,
      "step": 489
    },
    {
      "epoch": 3.0445859872611467,
      "grad_norm": 0.1648981124162674,
      "learning_rate": 2.436355362633216e-05,
      "loss": 0.9439,
      "step": 490
    },
    {
      "epoch": 3.050955414012739,
      "grad_norm": 0.16538694500923157,
      "learning_rate": 2.4026559203608888e-05,
      "loss": 0.9736,
      "step": 491
    },
    {
      "epoch": 3.0573248407643314,
      "grad_norm": 0.16382743418216705,
      "learning_rate": 2.3691593180019366e-05,
      "loss": 1.0069,
      "step": 492
    },
    {
      "epoch": 3.0636942675159236,
      "grad_norm": 0.15727005898952484,
      "learning_rate": 2.3358664498751846e-05,
      "loss": 0.9977,
      "step": 493
    },
    {
      "epoch": 3.070063694267516,
      "grad_norm": 0.1762123703956604,
      "learning_rate": 2.3027782048600244e-05,
      "loss": 0.993,
      "step": 494
    },
    {
      "epoch": 3.0764331210191083,
      "grad_norm": 0.1813836246728897,
      "learning_rate": 2.26989546637263e-05,
      "loss": 1.0405,
      "step": 495
    },
    {
      "epoch": 3.082802547770701,
      "grad_norm": 0.17147143185138702,
      "learning_rate": 2.237219112342426e-05,
      "loss": 0.9779,
      "step": 496
    },
    {
      "epoch": 3.089171974522293,
      "grad_norm": 0.1784360706806183,
      "learning_rate": 2.2047500151886047e-05,
      "loss": 1.02,
      "step": 497
    },
    {
      "epoch": 3.0955414012738856,
      "grad_norm": 0.1728549301624298,
      "learning_rate": 2.172489041796856e-05,
      "loss": 1.0202,
      "step": 498
    },
    {
      "epoch": 3.1019108280254777,
      "grad_norm": 0.17218239605426788,
      "learning_rate": 2.1404370534962136e-05,
      "loss": 1.0291,
      "step": 499
    },
    {
      "epoch": 3.1082802547770703,
      "grad_norm": 0.17259548604488373,
      "learning_rate": 2.1085949060360654e-05,
      "loss": 1.0283,
      "step": 500
    },
    {
      "epoch": 3.1146496815286624,
      "grad_norm": 0.16972696781158447,
      "learning_rate": 2.0769634495632982e-05,
      "loss": 0.992,
      "step": 501
    },
    {
      "epoch": 3.121019108280255,
      "grad_norm": 0.16903145611286163,
      "learning_rate": 2.0455435285996073e-05,
      "loss": 0.9997,
      "step": 502
    },
    {
      "epoch": 3.127388535031847,
      "grad_norm": 0.17022161185741425,
      "learning_rate": 2.01433598201894e-05,
      "loss": 0.9703,
      "step": 503
    },
    {
      "epoch": 3.1337579617834397,
      "grad_norm": 0.1719067245721817,
      "learning_rate": 1.9833416430251174e-05,
      "loss": 1.0198,
      "step": 504
    },
    {
      "epoch": 3.140127388535032,
      "grad_norm": 0.16758742928504944,
      "learning_rate": 1.9525613391295537e-05,
      "loss": 0.9912,
      "step": 505
    },
    {
      "epoch": 3.1464968152866244,
      "grad_norm": 0.16615444421768188,
      "learning_rate": 1.921995892129208e-05,
      "loss": 0.9506,
      "step": 506
    },
    {
      "epoch": 3.1528662420382165,
      "grad_norm": 0.1669171005487442,
      "learning_rate": 1.8916461180845967e-05,
      "loss": 0.9803,
      "step": 507
    },
    {
      "epoch": 3.159235668789809,
      "grad_norm": 0.16725566983222961,
      "learning_rate": 1.861512827298051e-05,
      "loss": 1.0108,
      "step": 508
    },
    {
      "epoch": 3.1656050955414012,
      "grad_norm": 0.1675242781639099,
      "learning_rate": 1.8315968242920445e-05,
      "loss": 0.9707,
      "step": 509
    },
    {
      "epoch": 3.171974522292994,
      "grad_norm": 0.17284801602363586,
      "learning_rate": 1.801898907787737e-05,
      "loss": 0.9574,
      "step": 510
    },
    {
      "epoch": 3.178343949044586,
      "grad_norm": 0.16599050164222717,
      "learning_rate": 1.772419870683637e-05,
      "loss": 0.9987,
      "step": 511
    },
    {
      "epoch": 3.1847133757961785,
      "grad_norm": 0.171804279088974,
      "learning_rate": 1.7431605000344432e-05,
      "loss": 1.0202,
      "step": 512
    },
    {
      "epoch": 3.1910828025477707,
      "grad_norm": 0.16461063921451569,
      "learning_rate": 1.71412157703002e-05,
      "loss": 0.9701,
      "step": 513
    },
    {
      "epoch": 3.1974522292993632,
      "grad_norm": 0.1710847169160843,
      "learning_rate": 1.6853038769745467e-05,
      "loss": 0.9814,
      "step": 514
    },
    {
      "epoch": 3.2038216560509554,
      "grad_norm": 0.16813382506370544,
      "learning_rate": 1.656708169265824e-05,
      "loss": 1.0044,
      "step": 515
    },
    {
      "epoch": 3.210191082802548,
      "grad_norm": 0.17343468964099884,
      "learning_rate": 1.6283352173747145e-05,
      "loss": 1.0351,
      "step": 516
    },
    {
      "epoch": 3.21656050955414,
      "grad_norm": 0.16783036291599274,
      "learning_rate": 1.6001857788247755e-05,
      "loss": 0.9955,
      "step": 517
    },
    {
      "epoch": 3.2229299363057327,
      "grad_norm": 0.17076148092746735,
      "learning_rate": 1.572260605172027e-05,
      "loss": 0.9835,
      "step": 518
    },
    {
      "epoch": 3.229299363057325,
      "grad_norm": 0.16569438576698303,
      "learning_rate": 1.544560441984886e-05,
      "loss": 0.9771,
      "step": 519
    },
    {
      "epoch": 3.2356687898089174,
      "grad_norm": 0.1622813194990158,
      "learning_rate": 1.5170860288242638e-05,
      "loss": 0.9637,
      "step": 520
    },
    {
      "epoch": 3.2356687898089174,
      "eval_loss": 0.9707406163215637,
      "eval_runtime": 19.3319,
      "eval_samples_per_second": 56.487,
      "eval_steps_per_second": 0.931,
      "step": 520
    },
    {
      "epoch": 3.2420382165605095,
      "grad_norm": 0.1739708036184311,
      "learning_rate": 1.4898380992238159e-05,
      "loss": 1.0275,
      "step": 521
    },
    {
      "epoch": 3.248407643312102,
      "grad_norm": 0.1697636991739273,
      "learning_rate": 1.4628173806703594e-05,
      "loss": 0.9941,
      "step": 522
    },
    {
      "epoch": 3.254777070063694,
      "grad_norm": 0.16739317774772644,
      "learning_rate": 1.4360245945844607e-05,
      "loss": 1.0066,
      "step": 523
    },
    {
      "epoch": 3.261146496815287,
      "grad_norm": 0.17184241116046906,
      "learning_rate": 1.4094604563011472e-05,
      "loss": 0.986,
      "step": 524
    },
    {
      "epoch": 3.267515923566879,
      "grad_norm": 0.16427680850028992,
      "learning_rate": 1.3831256750508448e-05,
      "loss": 1.0012,
      "step": 525
    },
    {
      "epoch": 3.2738853503184715,
      "grad_norm": 0.1750555783510208,
      "learning_rate": 1.3570209539404066e-05,
      "loss": 1.0168,
      "step": 526
    },
    {
      "epoch": 3.2802547770700636,
      "grad_norm": 0.1664997935295105,
      "learning_rate": 1.3311469899343698e-05,
      "loss": 0.9548,
      "step": 527
    },
    {
      "epoch": 3.286624203821656,
      "grad_norm": 0.16923880577087402,
      "learning_rate": 1.305504473836331e-05,
      "loss": 1.004,
      "step": 528
    },
    {
      "epoch": 3.2929936305732483,
      "grad_norm": 0.16449087858200073,
      "learning_rate": 1.2800940902705071e-05,
      "loss": 0.9584,
      "step": 529
    },
    {
      "epoch": 3.299363057324841,
      "grad_norm": 0.16462044417858124,
      "learning_rate": 1.254916517663458e-05,
      "loss": 0.9887,
      "step": 530
    },
    {
      "epoch": 3.305732484076433,
      "grad_norm": 0.17136213183403015,
      "learning_rate": 1.2299724282259683e-05,
      "loss": 1.0142,
      "step": 531
    },
    {
      "epoch": 3.3121019108280256,
      "grad_norm": 0.17270217835903168,
      "learning_rate": 1.2052624879351104e-05,
      "loss": 1.0288,
      "step": 532
    },
    {
      "epoch": 3.3184713375796178,
      "grad_norm": 0.16447976231575012,
      "learning_rate": 1.1807873565164506e-05,
      "loss": 0.9987,
      "step": 533
    },
    {
      "epoch": 3.3248407643312103,
      "grad_norm": 0.1747192144393921,
      "learning_rate": 1.1565476874264447e-05,
      "loss": 0.9685,
      "step": 534
    },
    {
      "epoch": 3.3312101910828025,
      "grad_norm": 0.17412638664245605,
      "learning_rate": 1.1325441278349935e-05,
      "loss": 0.9749,
      "step": 535
    },
    {
      "epoch": 3.337579617834395,
      "grad_norm": 0.15683028101921082,
      "learning_rate": 1.1087773186081473e-05,
      "loss": 1.0045,
      "step": 536
    },
    {
      "epoch": 3.343949044585987,
      "grad_norm": 0.16948175430297852,
      "learning_rate": 1.0852478942910227e-05,
      "loss": 1.0147,
      "step": 537
    },
    {
      "epoch": 3.3503184713375798,
      "grad_norm": 0.16688252985477448,
      "learning_rate": 1.0619564830908302e-05,
      "loss": 1.0057,
      "step": 538
    },
    {
      "epoch": 3.356687898089172,
      "grad_norm": 0.16838929057121277,
      "learning_rate": 1.0389037068601327e-05,
      "loss": 0.9369,
      "step": 539
    },
    {
      "epoch": 3.3630573248407645,
      "grad_norm": 0.17098736763000488,
      "learning_rate": 1.0160901810802115e-05,
      "loss": 0.9592,
      "step": 540
    },
    {
      "epoch": 3.3694267515923566,
      "grad_norm": 0.16877111792564392,
      "learning_rate": 9.935165148446656e-06,
      "loss": 1.009,
      "step": 541
    },
    {
      "epoch": 3.375796178343949,
      "grad_norm": 0.1681944876909256,
      "learning_rate": 9.711833108431235e-06,
      "loss": 0.9559,
      "step": 542
    },
    {
      "epoch": 3.3821656050955413,
      "grad_norm": 0.1644127368927002,
      "learning_rate": 9.49091165345165e-06,
      "loss": 0.9992,
      "step": 543
    },
    {
      "epoch": 3.388535031847134,
      "grad_norm": 0.1731218695640564,
      "learning_rate": 9.272406681844015e-06,
      "loss": 0.985,
      "step": 544
    },
    {
      "epoch": 3.394904458598726,
      "grad_norm": 0.16682636737823486,
      "learning_rate": 9.05632402742721e-06,
      "loss": 0.985,
      "step": 545
    },
    {
      "epoch": 3.4012738853503186,
      "grad_norm": 0.17283613979816437,
      "learning_rate": 8.842669459347186e-06,
      "loss": 0.9896,
      "step": 546
    },
    {
      "epoch": 3.4076433121019107,
      "grad_norm": 0.1709265261888504,
      "learning_rate": 8.631448681922993e-06,
      "loss": 0.989,
      "step": 547
    },
    {
      "epoch": 3.4140127388535033,
      "grad_norm": 0.1714629977941513,
      "learning_rate": 8.422667334494249e-06,
      "loss": 1.0109,
      "step": 548
    },
    {
      "epoch": 3.4203821656050954,
      "grad_norm": 0.1788371056318283,
      "learning_rate": 8.216330991270915e-06,
      "loss": 0.9917,
      "step": 549
    },
    {
      "epoch": 3.426751592356688,
      "grad_norm": 0.17009298503398895,
      "learning_rate": 8.01244516118418e-06,
      "loss": 0.9808,
      "step": 550
    },
    {
      "epoch": 3.43312101910828,
      "grad_norm": 0.169687420129776,
      "learning_rate": 7.81101528773951e-06,
      "loss": 0.9929,
      "step": 551
    },
    {
      "epoch": 3.4394904458598727,
      "grad_norm": 0.1677922010421753,
      "learning_rate": 7.612046748871327e-06,
      "loss": 0.9672,
      "step": 552
    },
    {
      "epoch": 3.445859872611465,
      "grad_norm": 0.16882313787937164,
      "learning_rate": 7.415544856799362e-06,
      "loss": 0.988,
      "step": 553
    },
    {
      "epoch": 3.4522292993630574,
      "grad_norm": 0.17867511510849,
      "learning_rate": 7.221514857886857e-06,
      "loss": 1.0228,
      "step": 554
    },
    {
      "epoch": 3.4585987261146496,
      "grad_norm": 0.17309780418872833,
      "learning_rate": 7.029961932500506e-06,
      "loss": 0.996,
      "step": 555
    },
    {
      "epoch": 3.464968152866242,
      "grad_norm": 0.17159916460514069,
      "learning_rate": 6.840891194872112e-06,
      "loss": 0.9828,
      "step": 556
    },
    {
      "epoch": 3.4713375796178343,
      "grad_norm": 0.17444610595703125,
      "learning_rate": 6.65430769296207e-06,
      "loss": 1.0101,
      "step": 557
    },
    {
      "epoch": 3.477707006369427,
      "grad_norm": 0.16815635561943054,
      "learning_rate": 6.470216408324625e-06,
      "loss": 0.9956,
      "step": 558
    },
    {
      "epoch": 3.484076433121019,
      "grad_norm": 0.16845732927322388,
      "learning_rate": 6.288622255974741e-06,
      "loss": 0.9634,
      "step": 559
    },
    {
      "epoch": 3.4904458598726116,
      "grad_norm": 0.1707555055618286,
      "learning_rate": 6.109530084257042e-06,
      "loss": 1.0085,
      "step": 560
    },
    {
      "epoch": 3.4904458598726116,
      "eval_loss": 0.9698290824890137,
      "eval_runtime": 19.3395,
      "eval_samples_per_second": 56.465,
      "eval_steps_per_second": 0.931,
      "step": 560
    },
    {
      "epoch": 3.4968152866242037,
      "grad_norm": 0.1713126003742218,
      "learning_rate": 5.932944674716279e-06,
      "loss": 1.0164,
      "step": 561
    },
    {
      "epoch": 3.5031847133757963,
      "grad_norm": 0.169924795627594,
      "learning_rate": 5.7588707419696356e-06,
      "loss": 0.9877,
      "step": 562
    },
    {
      "epoch": 3.5095541401273884,
      "grad_norm": 0.17244820296764374,
      "learning_rate": 5.587312933580946e-06,
      "loss": 1.0098,
      "step": 563
    },
    {
      "epoch": 3.515923566878981,
      "grad_norm": 0.17052321135997772,
      "learning_rate": 5.418275829936537e-06,
      "loss": 0.9738,
      "step": 564
    },
    {
      "epoch": 3.522292993630573,
      "grad_norm": 0.1753830909729004,
      "learning_rate": 5.251763944122956e-06,
      "loss": 0.9983,
      "step": 565
    },
    {
      "epoch": 3.5286624203821657,
      "grad_norm": 0.1730627566576004,
      "learning_rate": 5.0877817218065396e-06,
      "loss": 1.0572,
      "step": 566
    },
    {
      "epoch": 3.535031847133758,
      "grad_norm": 0.17786502838134766,
      "learning_rate": 4.926333541114558e-06,
      "loss": 0.9898,
      "step": 567
    },
    {
      "epoch": 3.5414012738853504,
      "grad_norm": 0.174746572971344,
      "learning_rate": 4.767423712518559e-06,
      "loss": 0.9733,
      "step": 568
    },
    {
      "epoch": 3.5477707006369426,
      "grad_norm": 0.16890431940555573,
      "learning_rate": 4.611056478719022e-06,
      "loss": 1.0472,
      "step": 569
    },
    {
      "epoch": 3.554140127388535,
      "grad_norm": 0.16655953228473663,
      "learning_rate": 4.45723601453234e-06,
      "loss": 0.9786,
      "step": 570
    },
    {
      "epoch": 3.5605095541401273,
      "grad_norm": 0.16709204018115997,
      "learning_rate": 4.305966426779118e-06,
      "loss": 0.9831,
      "step": 571
    },
    {
      "epoch": 3.56687898089172,
      "grad_norm": 0.17446470260620117,
      "learning_rate": 4.1572517541747294e-06,
      "loss": 0.9943,
      "step": 572
    },
    {
      "epoch": 3.573248407643312,
      "grad_norm": 0.1702784299850464,
      "learning_rate": 4.011095967221368e-06,
      "loss": 1.0134,
      "step": 573
    },
    {
      "epoch": 3.5796178343949046,
      "grad_norm": 0.1690012663602829,
      "learning_rate": 3.867502968102054e-06,
      "loss": 0.9992,
      "step": 574
    },
    {
      "epoch": 3.5859872611464967,
      "grad_norm": 0.17440934479236603,
      "learning_rate": 3.7264765905764777e-06,
      "loss": 0.9594,
      "step": 575
    },
    {
      "epoch": 3.5923566878980893,
      "grad_norm": 0.17466022074222565,
      "learning_rate": 3.5880205998786388e-06,
      "loss": 0.9614,
      "step": 576
    },
    {
      "epoch": 3.5987261146496814,
      "grad_norm": 0.1677061766386032,
      "learning_rate": 3.4521386926163136e-06,
      "loss": 0.9791,
      "step": 577
    },
    {
      "epoch": 3.605095541401274,
      "grad_norm": 0.16942261159420013,
      "learning_rate": 3.3188344966723515e-06,
      "loss": 1.0008,
      "step": 578
    },
    {
      "epoch": 3.611464968152866,
      "grad_norm": 0.17275391519069672,
      "learning_rate": 3.188111571107799e-06,
      "loss": 0.9451,
      "step": 579
    },
    {
      "epoch": 3.6178343949044587,
      "grad_norm": 0.17021973431110382,
      "learning_rate": 3.059973406066963e-06,
      "loss": 1.0412,
      "step": 580
    },
    {
      "epoch": 3.624203821656051,
      "grad_norm": 0.16870969533920288,
      "learning_rate": 2.9344234226840963e-06,
      "loss": 0.9993,
      "step": 581
    },
    {
      "epoch": 3.6305732484076434,
      "grad_norm": 0.1715007871389389,
      "learning_rate": 2.811464972992195e-06,
      "loss": 0.9862,
      "step": 582
    },
    {
      "epoch": 3.6369426751592355,
      "grad_norm": 0.16849824786186218,
      "learning_rate": 2.6911013398333464e-06,
      "loss": 0.9741,
      "step": 583
    },
    {
      "epoch": 3.643312101910828,
      "grad_norm": 0.16762219369411469,
      "learning_rate": 2.573335736771254e-06,
      "loss": 1.0199,
      "step": 584
    },
    {
      "epoch": 3.6496815286624202,
      "grad_norm": 0.17826132476329803,
      "learning_rate": 2.458171308005308e-06,
      "loss": 1.0265,
      "step": 585
    },
    {
      "epoch": 3.656050955414013,
      "grad_norm": 0.17342117428779602,
      "learning_rate": 2.345611128286718e-06,
      "loss": 1.002,
      "step": 586
    },
    {
      "epoch": 3.662420382165605,
      "grad_norm": 0.16714730858802795,
      "learning_rate": 2.2356582028363547e-06,
      "loss": 1.0481,
      "step": 587
    },
    {
      "epoch": 3.6687898089171975,
      "grad_norm": 0.1712888777256012,
      "learning_rate": 2.128315467264552e-06,
      "loss": 0.9947,
      "step": 588
    },
    {
      "epoch": 3.6751592356687897,
      "grad_norm": 0.1652042120695114,
      "learning_rate": 2.0235857874927654e-06,
      "loss": 0.9969,
      "step": 589
    },
    {
      "epoch": 3.6815286624203822,
      "grad_norm": 0.16838863492012024,
      "learning_rate": 1.921471959676957e-06,
      "loss": 1.0021,
      "step": 590
    },
    {
      "epoch": 3.6878980891719744,
      "grad_norm": 0.17278355360031128,
      "learning_rate": 1.8219767101330442e-06,
      "loss": 1.0179,
      "step": 591
    },
    {
      "epoch": 3.694267515923567,
      "grad_norm": 0.1679522544145584,
      "learning_rate": 1.725102695264058e-06,
      "loss": 0.9612,
      "step": 592
    },
    {
      "epoch": 3.700636942675159,
      "grad_norm": 0.16865026950836182,
      "learning_rate": 1.6308525014892218e-06,
      "loss": 0.9528,
      "step": 593
    },
    {
      "epoch": 3.7070063694267517,
      "grad_norm": 0.17630663514137268,
      "learning_rate": 1.539228645174895e-06,
      "loss": 0.9658,
      "step": 594
    },
    {
      "epoch": 3.713375796178344,
      "grad_norm": 0.17260049283504486,
      "learning_rate": 1.4502335725674165e-06,
      "loss": 0.9856,
      "step": 595
    },
    {
      "epoch": 3.7197452229299364,
      "grad_norm": 0.1704285889863968,
      "learning_rate": 1.3638696597277679e-06,
      "loss": 0.9627,
      "step": 596
    },
    {
      "epoch": 3.7261146496815285,
      "grad_norm": 0.1693270057439804,
      "learning_rate": 1.2801392124681233e-06,
      "loss": 0.9666,
      "step": 597
    },
    {
      "epoch": 3.732484076433121,
      "grad_norm": 0.1699259728193283,
      "learning_rate": 1.1990444662903445e-06,
      "loss": 1.0123,
      "step": 598
    },
    {
      "epoch": 3.738853503184713,
      "grad_norm": 0.17042875289916992,
      "learning_rate": 1.120587586326227e-06,
      "loss": 0.989,
      "step": 599
    },
    {
      "epoch": 3.745222929936306,
      "grad_norm": 0.17394761741161346,
      "learning_rate": 1.0447706672797264e-06,
      "loss": 0.9547,
      "step": 600
    },
    {
      "epoch": 3.745222929936306,
      "eval_loss": 0.9696974158287048,
      "eval_runtime": 19.3313,
      "eval_samples_per_second": 56.489,
      "eval_steps_per_second": 0.931,
      "step": 600
    },
    {
      "epoch": 3.7515923566878984,
      "grad_norm": 0.16741351783275604,
      "learning_rate": 9.715957333710445e-07,
      "loss": 0.9619,
      "step": 601
    },
    {
      "epoch": 3.7579617834394905,
      "grad_norm": 0.1668492704629898,
      "learning_rate": 9.010647382825422e-07,
      "loss": 0.9454,
      "step": 602
    },
    {
      "epoch": 3.7643312101910826,
      "grad_norm": 0.1694195717573166,
      "learning_rate": 8.331795651066454e-07,
      "loss": 1.0132,
      "step": 603
    },
    {
      "epoch": 3.770700636942675,
      "grad_norm": 0.17245754599571228,
      "learning_rate": 7.679420262954984e-07,
      "loss": 0.9499,
      "step": 604
    },
    {
      "epoch": 3.777070063694268,
      "grad_norm": 0.1733883023262024,
      "learning_rate": 7.053538636126122e-07,
      "loss": 1.044,
      "step": 605
    },
    {
      "epoch": 3.78343949044586,
      "grad_norm": 0.17213398218154907,
      "learning_rate": 6.454167480863693e-07,
      "loss": 0.996,
      "step": 606
    },
    {
      "epoch": 3.789808917197452,
      "grad_norm": 0.16396255791187286,
      "learning_rate": 5.881322799653699e-07,
      "loss": 0.9806,
      "step": 607
    },
    {
      "epoch": 3.7961783439490446,
      "grad_norm": 0.17321285605430603,
      "learning_rate": 5.335019886757442e-07,
      "loss": 1.0015,
      "step": 608
    },
    {
      "epoch": 3.802547770700637,
      "grad_norm": 0.17517811059951782,
      "learning_rate": 4.815273327803182e-07,
      "loss": 1.0114,
      "step": 609
    },
    {
      "epoch": 3.8089171974522293,
      "grad_norm": 0.16443413496017456,
      "learning_rate": 4.32209699939623e-07,
      "loss": 0.9686,
      "step": 610
    },
    {
      "epoch": 3.8152866242038215,
      "grad_norm": 0.17695996165275574,
      "learning_rate": 3.8555040687493495e-07,
      "loss": 1.0224,
      "step": 611
    },
    {
      "epoch": 3.821656050955414,
      "grad_norm": 0.1697298139333725,
      "learning_rate": 3.415506993330153e-07,
      "loss": 0.9631,
      "step": 612
    },
    {
      "epoch": 3.8280254777070066,
      "grad_norm": 0.17097443342208862,
      "learning_rate": 3.0021175205294794e-07,
      "loss": 0.9932,
      "step": 613
    },
    {
      "epoch": 3.8343949044585988,
      "grad_norm": 0.16865070164203644,
      "learning_rate": 2.6153466873468645e-07,
      "loss": 1.0147,
      "step": 614
    },
    {
      "epoch": 3.840764331210191,
      "grad_norm": 0.16992445290088654,
      "learning_rate": 2.255204820096668e-07,
      "loss": 0.9813,
      "step": 615
    },
    {
      "epoch": 3.8471337579617835,
      "grad_norm": 0.16435334086418152,
      "learning_rate": 1.921701534131848e-07,
      "loss": 0.9731,
      "step": 616
    },
    {
      "epoch": 3.853503184713376,
      "grad_norm": 0.17002373933792114,
      "learning_rate": 1.614845733587611e-07,
      "loss": 0.995,
      "step": 617
    },
    {
      "epoch": 3.859872611464968,
      "grad_norm": 0.1735718846321106,
      "learning_rate": 1.3346456111430483e-07,
      "loss": 0.9918,
      "step": 618
    },
    {
      "epoch": 3.8662420382165603,
      "grad_norm": 0.17651690542697906,
      "learning_rate": 1.0811086478031974e-07,
      "loss": 1.0215,
      "step": 619
    },
    {
      "epoch": 3.872611464968153,
      "grad_norm": 0.1678246557712555,
      "learning_rate": 8.542416126989805e-08,
      "loss": 0.9948,
      "step": 620
    },
    {
      "epoch": 3.8789808917197455,
      "grad_norm": 0.1722279042005539,
      "learning_rate": 6.540505629061278e-08,
      "loss": 0.982,
      "step": 621
    },
    {
      "epoch": 3.8853503184713376,
      "grad_norm": 0.1686953455209732,
      "learning_rate": 4.8054084328397197e-08,
      "loss": 0.9858,
      "step": 622
    },
    {
      "epoch": 3.8917197452229297,
      "grad_norm": 0.16943636536598206,
      "learning_rate": 3.337170863326744e-08,
      "loss": 0.9501,
      "step": 623
    },
    {
      "epoch": 3.8980891719745223,
      "grad_norm": 0.1638282835483551,
      "learning_rate": 2.135832120689907e-08,
      "loss": 0.9817,
      "step": 624
    },
    {
      "epoch": 3.904458598726115,
      "grad_norm": 0.17025518417358398,
      "learning_rate": 1.20142427922465e-08,
      "loss": 1.009,
      "step": 625
    },
    {
      "epoch": 3.910828025477707,
      "grad_norm": 0.17140662670135498,
      "learning_rate": 5.339722864927676e-09,
      "loss": 1.0027,
      "step": 626
    },
    {
      "epoch": 3.917197452229299,
      "grad_norm": 0.17177358269691467,
      "learning_rate": 1.3349396265516234e-09,
      "loss": 1.007,
      "step": 627
    },
    {
      "epoch": 3.9235668789808917,
      "grad_norm": 0.16751153767108917,
      "learning_rate": 0.0,
      "loss": 0.9767,
      "step": 628
    }
  ],
  "logging_steps": 1,
  "max_steps": 628,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 157,
  "total_flos": 8.188237172922778e+17,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}