{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.806451612903226,
  "eval_steps": 16,
  "global_step": 434,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016129032258064516,
      "grad_norm": 5.020356178283691,
      "learning_rate": 2e-05,
      "loss": 2.1533,
      "step": 1
    },
    {
      "epoch": 0.016129032258064516,
      "eval_loss": 2.183060884475708,
      "eval_runtime": 261.5376,
      "eval_samples_per_second": 4.053,
      "eval_steps_per_second": 0.677,
      "step": 1
    },
    {
      "epoch": 0.03225806451612903,
      "grad_norm": 5.117613315582275,
      "learning_rate": 4e-05,
      "loss": 2.1211,
      "step": 2
    },
    {
      "epoch": 0.04838709677419355,
      "grad_norm": 4.581052303314209,
      "learning_rate": 6e-05,
      "loss": 2.1036,
      "step": 3
    },
    {
      "epoch": 0.06451612903225806,
      "grad_norm": 3.6673312187194824,
      "learning_rate": 8e-05,
      "loss": 2.0632,
      "step": 4
    },
    {
      "epoch": 0.08064516129032258,
      "grad_norm": 3.1003849506378174,
      "learning_rate": 0.0001,
      "loss": 2.021,
      "step": 5
    },
    {
      "epoch": 0.0967741935483871,
      "grad_norm": 2.2640504837036133,
      "learning_rate": 0.00012,
      "loss": 1.9713,
      "step": 6
    },
    {
      "epoch": 0.11290322580645161,
      "grad_norm": 2.594027519226074,
      "learning_rate": 0.00014,
      "loss": 1.8607,
      "step": 7
    },
    {
      "epoch": 0.12903225806451613,
      "grad_norm": 2.064988136291504,
      "learning_rate": 0.00016,
      "loss": 1.8101,
      "step": 8
    },
    {
      "epoch": 0.14516129032258066,
      "grad_norm": 1.8494470119476318,
      "learning_rate": 0.00018,
      "loss": 1.7351,
      "step": 9
    },
    {
      "epoch": 0.16129032258064516,
      "grad_norm": 1.8000997304916382,
      "learning_rate": 0.0002,
      "loss": 1.7415,
      "step": 10
    },
    {
      "epoch": 0.1774193548387097,
      "grad_norm": 1.7077090740203857,
      "learning_rate": 0.0001999986737997063,
      "loss": 1.7155,
      "step": 11
    },
    {
      "epoch": 0.1935483870967742,
      "grad_norm": 1.8839540481567383,
      "learning_rate": 0.00019999469523400122,
      "loss": 1.7474,
      "step": 12
    },
    {
      "epoch": 0.20967741935483872,
      "grad_norm": 1.7330329418182373,
      "learning_rate": 0.00019998806440841234,
      "loss": 1.6775,
      "step": 13
    },
    {
      "epoch": 0.22580645161290322,
      "grad_norm": 1.4584600925445557,
      "learning_rate": 0.00019997878149881574,
      "loss": 1.7176,
      "step": 14
    },
    {
      "epoch": 0.24193548387096775,
      "grad_norm": 1.4614368677139282,
      "learning_rate": 0.0001999668467514313,
      "loss": 1.6047,
      "step": 15
    },
    {
      "epoch": 0.25806451612903225,
      "grad_norm": 1.3776947259902954,
      "learning_rate": 0.0001999522604828164,
      "loss": 1.6416,
      "step": 16
    },
    {
      "epoch": 0.25806451612903225,
      "eval_loss": 1.7332706451416016,
      "eval_runtime": 431.4384,
      "eval_samples_per_second": 2.457,
      "eval_steps_per_second": 0.41,
      "step": 16
    },
    {
      "epoch": 0.27419354838709675,
      "grad_norm": 1.4929783344268799,
      "learning_rate": 0.00019993502307985724,
      "loss": 1.73,
      "step": 17
    },
    {
      "epoch": 0.2903225806451613,
      "grad_norm": 1.3602776527404785,
      "learning_rate": 0.00019991513499975882,
      "loss": 1.6958,
      "step": 18
    },
    {
      "epoch": 0.3064516129032258,
      "grad_norm": 1.4044336080551147,
      "learning_rate": 0.00019989259677003274,
      "loss": 1.6475,
      "step": 19
    },
    {
      "epoch": 0.3225806451612903,
      "grad_norm": 1.3602012395858765,
      "learning_rate": 0.00019986740898848306,
      "loss": 1.7063,
      "step": 20
    },
    {
      "epoch": 0.3387096774193548,
      "grad_norm": 1.3823881149291992,
      "learning_rate": 0.0001998395723231907,
      "loss": 1.7079,
      "step": 21
    },
    {
      "epoch": 0.3548387096774194,
      "grad_norm": 1.3182601928710938,
      "learning_rate": 0.00019980908751249555,
      "loss": 1.672,
      "step": 22
    },
    {
      "epoch": 0.3709677419354839,
      "grad_norm": 1.2420353889465332,
      "learning_rate": 0.00019977595536497687,
      "loss": 1.6393,
      "step": 23
    },
    {
      "epoch": 0.3870967741935484,
      "grad_norm": 1.3861604928970337,
      "learning_rate": 0.00019974017675943192,
      "loss": 1.6904,
      "step": 24
    },
    {
      "epoch": 0.4032258064516129,
      "grad_norm": 1.537832498550415,
      "learning_rate": 0.00019970175264485266,
      "loss": 1.6731,
      "step": 25
    },
    {
      "epoch": 0.41935483870967744,
      "grad_norm": 1.2361652851104736,
      "learning_rate": 0.0001996606840404006,
      "loss": 1.6262,
      "step": 26
    },
    {
      "epoch": 0.43548387096774194,
      "grad_norm": 1.253831148147583,
      "learning_rate": 0.00019961697203537952,
      "loss": 1.6068,
      "step": 27
    },
    {
      "epoch": 0.45161290322580644,
      "grad_norm": 1.306778073310852,
      "learning_rate": 0.00019957061778920701,
      "loss": 1.6397,
      "step": 28
    },
    {
      "epoch": 0.46774193548387094,
      "grad_norm": 1.1258474588394165,
      "learning_rate": 0.0001995216225313833,
      "loss": 1.5656,
      "step": 29
    },
    {
      "epoch": 0.4838709677419355,
      "grad_norm": 1.198811411857605,
      "learning_rate": 0.0001994699875614589,
      "loss": 1.6768,
      "step": 30
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.4581488370895386,
      "learning_rate": 0.00019941571424900013,
      "loss": 1.5823,
      "step": 31
    },
    {
      "epoch": 0.5161290322580645,
      "grad_norm": 1.2790226936340332,
      "learning_rate": 0.00019935880403355253,
      "loss": 1.6154,
      "step": 32
    },
    {
      "epoch": 0.5161290322580645,
      "eval_loss": 1.64582359790802,
      "eval_runtime": 430.558,
      "eval_samples_per_second": 2.462,
      "eval_steps_per_second": 0.411,
      "step": 32
    },
    {
      "epoch": 0.532258064516129,
      "grad_norm": 1.1969035863876343,
      "learning_rate": 0.0001992992584246031,
      "loss": 1.6766,
      "step": 33
    },
    {
      "epoch": 0.5483870967741935,
      "grad_norm": 1.4593340158462524,
      "learning_rate": 0.00019923707900153982,
      "loss": 1.6112,
      "step": 34
    },
    {
      "epoch": 0.5645161290322581,
      "grad_norm": 1.306646704673767,
      "learning_rate": 0.00019917226741361015,
      "loss": 1.5671,
      "step": 35
    },
    {
      "epoch": 0.5806451612903226,
      "grad_norm": 1.3403998613357544,
      "learning_rate": 0.00019910482537987702,
      "loss": 1.6703,
      "step": 36
    },
    {
      "epoch": 0.5967741935483871,
      "grad_norm": 1.1974356174468994,
      "learning_rate": 0.0001990347546891733,
      "loss": 1.586,
      "step": 37
    },
    {
      "epoch": 0.6129032258064516,
      "grad_norm": 1.3454561233520508,
      "learning_rate": 0.0001989620572000544,
      "loss": 1.6023,
      "step": 38
    },
    {
      "epoch": 0.6290322580645161,
      "grad_norm": 1.2124018669128418,
      "learning_rate": 0.000198886734840749,
      "loss": 1.6405,
      "step": 39
    },
    {
      "epoch": 0.6451612903225806,
      "grad_norm": 1.0802409648895264,
      "learning_rate": 0.00019880878960910772,
      "loss": 1.5191,
      "step": 40
    },
    {
      "epoch": 0.6612903225806451,
      "grad_norm": 1.4059436321258545,
      "learning_rate": 0.0001987282235725504,
      "loss": 1.5969,
      "step": 41
    },
    {
      "epoch": 0.6774193548387096,
      "grad_norm": 1.2623989582061768,
      "learning_rate": 0.00019864503886801106,
      "loss": 1.5921,
      "step": 42
    },
    {
      "epoch": 0.6935483870967742,
      "grad_norm": 1.2654995918273926,
      "learning_rate": 0.0001985592377018813,
      "loss": 1.5707,
      "step": 43
    },
    {
      "epoch": 0.7096774193548387,
      "grad_norm": 1.2158616781234741,
      "learning_rate": 0.00019847082234995171,
      "loss": 1.5141,
      "step": 44
    },
    {
      "epoch": 0.7258064516129032,
      "grad_norm": 1.2419042587280273,
      "learning_rate": 0.00019837979515735166,
      "loss": 1.5541,
      "step": 45
    },
    {
      "epoch": 0.7419354838709677,
      "grad_norm": 1.1441471576690674,
      "learning_rate": 0.00019828615853848688,
      "loss": 1.4788,
      "step": 46
    },
    {
      "epoch": 0.7580645161290323,
      "grad_norm": 1.1924492120742798,
      "learning_rate": 0.00019818991497697565,
      "loss": 1.5335,
      "step": 47
    },
    {
      "epoch": 0.7741935483870968,
      "grad_norm": 1.133042812347412,
      "learning_rate": 0.00019809106702558277,
      "loss": 1.5155,
      "step": 48
    },
    {
      "epoch": 0.7741935483870968,
      "eval_loss": 1.5807298421859741,
      "eval_runtime": 433.4129,
      "eval_samples_per_second": 2.446,
      "eval_steps_per_second": 0.408,
      "step": 48
    },
    {
      "epoch": 0.7903225806451613,
      "grad_norm": 1.2338794469833374,
      "learning_rate": 0.0001979896173061518,
      "loss": 1.611,
      "step": 49
    },
    {
      "epoch": 0.8064516129032258,
      "grad_norm": 1.306178331375122,
      "learning_rate": 0.0001978855685095358,
      "loss": 1.5046,
      "step": 50
    },
    {
      "epoch": 0.8225806451612904,
      "grad_norm": 1.174604058265686,
      "learning_rate": 0.00019777892339552559,
      "loss": 1.5431,
      "step": 51
    },
    {
      "epoch": 0.8387096774193549,
      "grad_norm": 1.3554447889328003,
      "learning_rate": 0.00019766968479277683,
      "loss": 1.5713,
      "step": 52
    },
    {
      "epoch": 0.8548387096774194,
      "grad_norm": 1.111693263053894,
      "learning_rate": 0.00019755785559873488,
      "loss": 1.5173,
      "step": 53
    },
    {
      "epoch": 0.8709677419354839,
      "grad_norm": 1.1916875839233398,
      "learning_rate": 0.00019744343877955788,
      "loss": 1.5706,
      "step": 54
    },
    {
      "epoch": 0.8870967741935484,
      "grad_norm": 1.1925556659698486,
      "learning_rate": 0.00019732643737003827,
      "loss": 1.5466,
      "step": 55
    },
    {
      "epoch": 0.9032258064516129,
      "grad_norm": 1.174657940864563,
      "learning_rate": 0.00019720685447352209,
      "loss": 1.5281,
      "step": 56
    },
    {
      "epoch": 0.9193548387096774,
      "grad_norm": 1.1206492185592651,
      "learning_rate": 0.00019708469326182678,
      "loss": 1.5871,
      "step": 57
    },
    {
      "epoch": 0.9354838709677419,
      "grad_norm": 1.089790940284729,
      "learning_rate": 0.0001969599569751571,
      "loss": 1.5988,
      "step": 58
    },
    {
      "epoch": 0.9516129032258065,
      "grad_norm": 1.146849274635315,
      "learning_rate": 0.000196832648922019,
      "loss": 1.5066,
      "step": 59
    },
    {
      "epoch": 0.967741935483871,
      "grad_norm": 1.0739450454711914,
      "learning_rate": 0.00019670277247913205,
      "loss": 1.5486,
      "step": 60
    },
    {
      "epoch": 0.9838709677419355,
      "grad_norm": 1.0958797931671143,
      "learning_rate": 0.00019657033109133975,
      "loss": 1.5212,
      "step": 61
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.134975552558899,
      "learning_rate": 0.0001964353282715183,
      "loss": 1.5581,
      "step": 62
    },
    {
      "epoch": 1.0161290322580645,
      "grad_norm": 1.1783857345581055,
      "learning_rate": 0.0001962977676004832,
      "loss": 1.4905,
      "step": 63
    },
    {
      "epoch": 1.032258064516129,
      "grad_norm": 1.0987132787704468,
      "learning_rate": 0.00019615765272689461,
      "loss": 1.5359,
      "step": 64
    },
    {
      "epoch": 1.032258064516129,
      "eval_loss": 1.5370668172836304,
      "eval_runtime": 379.6837,
      "eval_samples_per_second": 2.792,
      "eval_steps_per_second": 0.466,
      "step": 64
    },
    {
      "epoch": 1.0161290322580645,
      "grad_norm": 1.0743085145950317,
      "learning_rate": 0.00019601498736716017,
      "loss": 1.1431,
      "step": 65
    },
    {
      "epoch": 1.032258064516129,
      "grad_norm": 0.9797853231430054,
      "learning_rate": 0.00019586977530533677,
      "loss": 1.0969,
      "step": 66
    },
    {
      "epoch": 1.0483870967741935,
      "grad_norm": 1.1307501792907715,
      "learning_rate": 0.00019572202039303,
      "loss": 1.0826,
      "step": 67
    },
    {
      "epoch": 1.064516129032258,
      "grad_norm": 1.0152018070220947,
      "learning_rate": 0.00019557172654929196,
      "loss": 1.1224,
      "step": 68
    },
    {
      "epoch": 1.0806451612903225,
      "grad_norm": 1.0957362651824951,
      "learning_rate": 0.0001954188977605175,
      "loss": 1.0978,
      "step": 69
    },
    {
      "epoch": 1.096774193548387,
      "grad_norm": 1.0177264213562012,
      "learning_rate": 0.00019526353808033825,
      "loss": 1.0882,
      "step": 70
    },
    {
      "epoch": 1.1129032258064515,
      "grad_norm": 1.0174063444137573,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.0331,
      "step": 71
    },
    {
      "epoch": 1.129032258064516,
      "grad_norm": 1.0872232913970947,
      "learning_rate": 0.00019494524259582992,
      "loss": 1.0552,
      "step": 72
    },
    {
      "epoch": 1.1451612903225807,
      "grad_norm": 1.0081063508987427,
      "learning_rate": 0.00019478231523397215,
      "loss": 1.023,
      "step": 73
    },
    {
      "epoch": 1.1612903225806452,
      "grad_norm": 1.083362340927124,
      "learning_rate": 0.00019461687386542826,
      "loss": 1.0639,
      "step": 74
    },
    {
      "epoch": 1.1774193548387097,
      "grad_norm": 1.1271260976791382,
      "learning_rate": 0.00019444892287836613,
      "loss": 1.053,
      "step": 75
    },
    {
      "epoch": 1.1935483870967742,
      "grad_norm": 1.1567646265029907,
      "learning_rate": 0.00019427846672751873,
      "loss": 1.0214,
      "step": 76
    },
    {
      "epoch": 1.2096774193548387,
      "grad_norm": 1.1053016185760498,
      "learning_rate": 0.00019410550993406603,
      "loss": 1.0552,
      "step": 77
    },
    {
      "epoch": 1.2258064516129032,
      "grad_norm": 1.0573008060455322,
      "learning_rate": 0.00019393005708551498,
      "loss": 1.0223,
      "step": 78
    },
    {
      "epoch": 1.2419354838709677,
      "grad_norm": 1.081141471862793,
      "learning_rate": 0.00019375211283557798,
      "loss": 1.0422,
      "step": 79
    },
    {
      "epoch": 1.2580645161290323,
      "grad_norm": 1.154768943786621,
      "learning_rate": 0.00019357168190404936,
      "loss": 1.0746,
      "step": 80
    },
    {
      "epoch": 1.2580645161290323,
      "eval_loss": 1.5887596607208252,
      "eval_runtime": 379.2194,
      "eval_samples_per_second": 2.795,
      "eval_steps_per_second": 0.467,
      "step": 80
    },
    {
      "epoch": 1.2741935483870968,
      "grad_norm": 1.0481725931167603,
      "learning_rate": 0.00019338876907668026,
      "loss": 1.0684,
      "step": 81
    },
    {
      "epoch": 1.2903225806451613,
      "grad_norm": 1.1526888608932495,
      "learning_rate": 0.00019320337920505153,
      "loss": 1.104,
      "step": 82
    },
    {
      "epoch": 1.3064516129032258,
      "grad_norm": 1.108069658279419,
      "learning_rate": 0.00019301551720644523,
      "loss": 1.0907,
      "step": 83
    },
    {
      "epoch": 1.3225806451612903,
      "grad_norm": 1.1018728017807007,
      "learning_rate": 0.00019282518806371414,
      "loss": 1.0699,
      "step": 84
    },
    {
      "epoch": 1.3387096774193548,
      "grad_norm": 1.157453179359436,
      "learning_rate": 0.00019263239682514952,
      "loss": 1.0589,
      "step": 85
    },
    {
      "epoch": 1.3548387096774195,
      "grad_norm": 1.116068959236145,
      "learning_rate": 0.0001924371486043473,
      "loss": 1.0847,
      "step": 86
    },
    {
      "epoch": 1.370967741935484,
      "grad_norm": 1.0575870275497437,
      "learning_rate": 0.00019223944858007253,
      "loss": 1.0688,
      "step": 87
    },
    {
      "epoch": 1.3870967741935485,
      "grad_norm": 1.1120954751968384,
      "learning_rate": 0.0001920393019961217,
      "loss": 1.0829,
      "step": 88
    },
    {
      "epoch": 1.403225806451613,
      "grad_norm": 1.0838677883148193,
      "learning_rate": 0.00019183671416118405,
      "loss": 1.0751,
      "step": 89
    },
    {
      "epoch": 1.4193548387096775,
      "grad_norm": 1.1601375341415405,
      "learning_rate": 0.0001916316904487005,
      "loss": 1.0348,
      "step": 90
    },
    {
      "epoch": 1.435483870967742,
      "grad_norm": 1.080993413925171,
      "learning_rate": 0.00019142423629672117,
      "loss": 1.0512,
      "step": 91
    },
    {
      "epoch": 1.4516129032258065,
      "grad_norm": 1.4107691049575806,
      "learning_rate": 0.00019121435720776122,
      "loss": 1.0834,
      "step": 92
    },
    {
      "epoch": 1.467741935483871,
      "grad_norm": 1.10901939868927,
      "learning_rate": 0.00019100205874865485,
      "loss": 1.127,
      "step": 93
    },
    {
      "epoch": 1.4838709677419355,
      "grad_norm": 1.040759563446045,
      "learning_rate": 0.0001907873465504076,
      "loss": 1.0838,
      "step": 94
    },
    {
      "epoch": 1.5,
      "grad_norm": 1.117697834968567,
      "learning_rate": 0.00019057022630804716,
      "loss": 1.094,
      "step": 95
    },
    {
      "epoch": 1.5161290322580645,
      "grad_norm": 1.1124318838119507,
      "learning_rate": 0.00019035070378047204,
      "loss": 1.0806,
      "step": 96
    },
    {
      "epoch": 1.5161290322580645,
      "eval_loss": 1.569594144821167,
      "eval_runtime": 379.9276,
      "eval_samples_per_second": 2.79,
      "eval_steps_per_second": 0.466,
      "step": 96
    },
    {
      "epoch": 1.532258064516129,
      "grad_norm": 1.0274182558059692,
      "learning_rate": 0.00019012878479029906,
      "loss": 1.0322,
      "step": 97
    },
    {
      "epoch": 1.5483870967741935,
      "grad_norm": 1.214774250984192,
      "learning_rate": 0.00018990447522370884,
      "loss": 1.1029,
      "step": 98
    },
    {
      "epoch": 1.564516129032258,
      "grad_norm": 1.146145224571228,
      "learning_rate": 0.00018967778103028967,
      "loss": 1.0939,
      "step": 99
    },
    {
      "epoch": 1.5806451612903225,
      "grad_norm": 1.115272045135498,
      "learning_rate": 0.00018944870822287956,
      "loss": 1.0795,
      "step": 100
    },
    {
      "epoch": 1.596774193548387,
      "grad_norm": 1.0580235719680786,
      "learning_rate": 0.0001892172628774071,
      "loss": 1.0887,
      "step": 101
    },
    {
      "epoch": 1.6129032258064515,
      "grad_norm": 1.1681277751922607,
      "learning_rate": 0.00018898345113272998,
      "loss": 1.0781,
      "step": 102
    },
    {
      "epoch": 1.629032258064516,
      "grad_norm": 1.1023615598678589,
      "learning_rate": 0.00018874727919047227,
      "loss": 1.0679,
      "step": 103
    },
    {
      "epoch": 1.6451612903225805,
      "grad_norm": 1.139622688293457,
      "learning_rate": 0.00018850875331485995,
      "loss": 1.0795,
      "step": 104
    },
    {
      "epoch": 1.661290322580645,
      "grad_norm": 1.0712463855743408,
      "learning_rate": 0.00018826787983255473,
      "loss": 1.11,
      "step": 105
    },
    {
      "epoch": 1.6774193548387095,
      "grad_norm": 1.0515589714050293,
      "learning_rate": 0.00018802466513248632,
      "loss": 1.0896,
      "step": 106
    },
    {
      "epoch": 1.6935483870967742,
      "grad_norm": 1.0597035884857178,
      "learning_rate": 0.00018777911566568282,
      "loss": 1.0761,
      "step": 107
    },
    {
      "epoch": 1.7096774193548387,
      "grad_norm": 1.11446213722229,
      "learning_rate": 0.00018753123794509974,
      "loss": 1.0813,
      "step": 108
    },
    {
      "epoch": 1.7258064516129032,
      "grad_norm": 1.0365442037582397,
      "learning_rate": 0.0001872810385454472,
      "loss": 1.1037,
      "step": 109
    },
    {
      "epoch": 1.7419354838709677,
      "grad_norm": 1.0622906684875488,
      "learning_rate": 0.00018702852410301554,
      "loss": 1.085,
      "step": 110
    },
    {
      "epoch": 1.7580645161290323,
      "grad_norm": 1.0445847511291504,
      "learning_rate": 0.0001867737013154993,
      "loss": 1.1109,
      "step": 111
    },
    {
      "epoch": 1.7741935483870968,
      "grad_norm": 1.066573977470398,
      "learning_rate": 0.0001865165769418196,
      "loss": 1.0348,
      "step": 112
    },
    {
      "epoch": 1.7741935483870968,
      "eval_loss": 1.5535695552825928,
      "eval_runtime": 385.6979,
      "eval_samples_per_second": 2.748,
      "eval_steps_per_second": 0.459,
      "step": 112
    },
    {
      "epoch": 1.7903225806451613,
      "grad_norm": 1.1161065101623535,
      "learning_rate": 0.00018625715780194485,
      "loss": 1.0733,
      "step": 113
    },
    {
      "epoch": 1.8064516129032258,
      "grad_norm": 1.0873162746429443,
      "learning_rate": 0.00018599545077670985,
      "loss": 1.0875,
      "step": 114
    },
    {
      "epoch": 1.8225806451612905,
      "grad_norm": 2.7381904125213623,
      "learning_rate": 0.00018573146280763324,
      "loss": 1.1284,
      "step": 115
    },
    {
      "epoch": 1.838709677419355,
      "grad_norm": 1.0686196088790894,
      "learning_rate": 0.0001854652008967335,
      "loss": 1.064,
      "step": 116
    },
    {
      "epoch": 1.8548387096774195,
      "grad_norm": 1.0897347927093506,
      "learning_rate": 0.0001851966721063431,
      "loss": 1.0418,
      "step": 117
    },
    {
      "epoch": 1.870967741935484,
      "grad_norm": 1.092289686203003,
      "learning_rate": 0.00018492588355892124,
      "loss": 1.1247,
      "step": 118
    },
    {
      "epoch": 1.8870967741935485,
      "grad_norm": 1.1446326971054077,
      "learning_rate": 0.00018465284243686494,
      "loss": 1.0789,
      "step": 119
    },
    {
      "epoch": 1.903225806451613,
      "grad_norm": 1.052269458770752,
      "learning_rate": 0.00018437755598231856,
      "loss": 1.0792,
      "step": 120
    },
    {
      "epoch": 1.9193548387096775,
      "grad_norm": 1.1960537433624268,
      "learning_rate": 0.00018410003149698162,
      "loss": 1.0551,
      "step": 121
    },
    {
      "epoch": 1.935483870967742,
      "grad_norm": 1.2509639263153076,
      "learning_rate": 0.00018382027634191524,
      "loss": 1.1336,
      "step": 122
    },
    {
      "epoch": 1.9516129032258065,
      "grad_norm": 1.1205637454986572,
      "learning_rate": 0.00018353829793734669,
      "loss": 1.082,
      "step": 123
    },
    {
      "epoch": 1.967741935483871,
      "grad_norm": 1.087641954421997,
      "learning_rate": 0.00018325410376247294,
      "loss": 1.0999,
      "step": 124
    },
    {
      "epoch": 1.9838709677419355,
      "grad_norm": 1.141137957572937,
      "learning_rate": 0.0001829677013552619,
      "loss": 1.1358,
      "step": 125
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.1019104719161987,
      "learning_rate": 0.0001826790983122527,
      "loss": 1.0671,
      "step": 126
    },
    {
      "epoch": 2.0161290322580645,
      "grad_norm": 1.0500136613845825,
      "learning_rate": 0.00018238830228835417,
      "loss": 1.1061,
      "step": 127
    },
    {
      "epoch": 2.032258064516129,
      "grad_norm": 1.0191640853881836,
      "learning_rate": 0.00018209532099664174,
      "loss": 1.0769,
      "step": 128
    },
    {
      "epoch": 2.032258064516129,
      "eval_loss": 1.5341366529464722,
      "eval_runtime": 377.1489,
      "eval_samples_per_second": 2.811,
      "eval_steps_per_second": 0.469,
      "step": 128
    },
    {
      "epoch": 2.0161290322580645,
      "grad_norm": 0.8983094692230225,
      "learning_rate": 0.00018180016220815292,
      "loss": 0.6901,
      "step": 129
    },
    {
      "epoch": 2.032258064516129,
      "grad_norm": 0.9102672934532166,
      "learning_rate": 0.00018150283375168114,
      "loss": 0.6643,
      "step": 130
    },
    {
      "epoch": 2.0483870967741935,
      "grad_norm": 0.9043310284614563,
      "learning_rate": 0.00018120334351356813,
      "loss": 0.6813,
      "step": 131
    },
    {
      "epoch": 2.064516129032258,
      "grad_norm": 0.920064389705658,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.6422,
      "step": 132
    },
    {
      "epoch": 2.0806451612903225,
      "grad_norm": 1.0108799934387207,
      "learning_rate": 0.0001805979095242702,
      "loss": 0.6727,
      "step": 133
    },
    {
      "epoch": 2.096774193548387,
      "grad_norm": 0.9978906512260437,
      "learning_rate": 0.00018029198183161998,
      "loss": 0.6705,
      "step": 134
    },
    {
      "epoch": 2.1129032258064515,
      "grad_norm": 0.9658149480819702,
      "learning_rate": 0.00017998392447397197,
      "loss": 0.6519,
      "step": 135
    },
    {
      "epoch": 2.129032258064516,
      "grad_norm": 0.9641355872154236,
      "learning_rate": 0.00017967374562224132,
      "loss": 0.6408,
      "step": 136
    },
    {
      "epoch": 2.1451612903225805,
      "grad_norm": 1.057494878768921,
      "learning_rate": 0.0001793614535036137,
      "loss": 0.6903,
      "step": 137
    },
    {
      "epoch": 2.161290322580645,
      "grad_norm": 1.0118696689605713,
      "learning_rate": 0.00017904705640132718,
      "loss": 0.6606,
      "step": 138
    },
    {
      "epoch": 2.1774193548387095,
      "grad_norm": 0.9846657514572144,
      "learning_rate": 0.0001787305626544523,
      "loss": 0.6712,
      "step": 139
    },
    {
      "epoch": 2.193548387096774,
      "grad_norm": 1.151206374168396,
      "learning_rate": 0.00017841198065767107,
      "loss": 0.6781,
      "step": 140
    },
    {
      "epoch": 2.2096774193548385,
      "grad_norm": 0.9539623856544495,
      "learning_rate": 0.0001780913188610542,
      "loss": 0.6253,
      "step": 141
    },
    {
      "epoch": 2.225806451612903,
      "grad_norm": 1.044904351234436,
      "learning_rate": 0.00017776858576983712,
      "loss": 0.6617,
      "step": 142
    },
    {
      "epoch": 2.241935483870968,
      "grad_norm": 0.9991489052772522,
      "learning_rate": 0.0001774437899441942,
      "loss": 0.6703,
      "step": 143
    },
    {
      "epoch": 2.258064516129032,
      "grad_norm": 1.0453065633773804,
      "learning_rate": 0.0001771169399990119,
      "loss": 0.6608,
      "step": 144
    },
    {
      "epoch": 2.258064516129032,
      "eval_loss": 1.6200847625732422,
      "eval_runtime": 371.4426,
      "eval_samples_per_second": 2.854,
      "eval_steps_per_second": 0.477,
      "step": 144
    },
    {
      "epoch": 2.274193548387097,
      "grad_norm": 0.9984713196754456,
      "learning_rate": 0.00017678804460366,
      "loss": 0.6976,
      "step": 145
    },
    {
      "epoch": 2.2903225806451615,
      "grad_norm": 0.9991441369056702,
      "learning_rate": 0.00017645711248176195,
      "loss": 0.6872,
      "step": 146
    },
    {
      "epoch": 2.306451612903226,
      "grad_norm": 2.5695972442626953,
      "learning_rate": 0.00017612415241096327,
      "loss": 0.6672,
      "step": 147
    },
    {
      "epoch": 2.3225806451612905,
      "grad_norm": 0.9834401607513428,
      "learning_rate": 0.00017578917322269886,
      "loss": 0.6764,
      "step": 148
    },
    {
      "epoch": 2.338709677419355,
      "grad_norm": 1.0587729215621948,
      "learning_rate": 0.00017545218380195864,
      "loss": 0.6741,
      "step": 149
    },
    {
      "epoch": 2.3548387096774195,
      "grad_norm": 1.0295051336288452,
      "learning_rate": 0.00017511319308705198,
      "loss": 0.6963,
      "step": 150
    },
    {
      "epoch": 2.370967741935484,
      "grad_norm": 1.0167349576950073,
      "learning_rate": 0.00017477221006937066,
      "loss": 0.7085,
      "step": 151
    },
    {
      "epoch": 2.3870967741935485,
      "grad_norm": 1.0259524583816528,
      "learning_rate": 0.0001744292437931502,
      "loss": 0.7143,
      "step": 152
    },
    {
      "epoch": 2.403225806451613,
      "grad_norm": 1.0057259798049927,
      "learning_rate": 0.00017408430335523012,
      "loss": 0.708,
      "step": 153
    },
    {
      "epoch": 2.4193548387096775,
      "grad_norm": 0.975724995136261,
      "learning_rate": 0.00017373739790481262,
      "loss": 0.696,
      "step": 154
    },
    {
      "epoch": 2.435483870967742,
      "grad_norm": 1.0695990324020386,
      "learning_rate": 0.00017338853664321992,
      "loss": 0.6734,
      "step": 155
    },
    {
      "epoch": 2.4516129032258065,
      "grad_norm": 1.3752026557922363,
      "learning_rate": 0.00017303772882365016,
      "loss": 0.6976,
      "step": 156
    },
    {
      "epoch": 2.467741935483871,
      "grad_norm": 2.8574488162994385,
      "learning_rate": 0.00017268498375093202,
      "loss": 0.7288,
      "step": 157
    },
    {
      "epoch": 2.4838709677419355,
      "grad_norm": 1.0393046140670776,
      "learning_rate": 0.00017233031078127788,
      "loss": 0.6664,
      "step": 158
    },
    {
      "epoch": 2.5,
      "grad_norm": 1.456668496131897,
      "learning_rate": 0.00017197371932203568,
      "loss": 0.6944,
      "step": 159
    },
    {
      "epoch": 2.5161290322580645,
      "grad_norm": 1.0640977621078491,
      "learning_rate": 0.00017161521883143934,
      "loss": 0.6918,
      "step": 160
    },
    {
      "epoch": 2.5161290322580645,
      "eval_loss": 1.6184865236282349,
      "eval_runtime": 239.7727,
      "eval_samples_per_second": 4.421,
      "eval_steps_per_second": 0.738,
      "step": 160
    },
    {
      "epoch": 2.532258064516129,
      "grad_norm": 1.1856733560562134,
      "learning_rate": 0.000171254818818358,
      "loss": 0.7186,
      "step": 161
    },
    {
      "epoch": 2.5483870967741935,
      "grad_norm": 1.0068649053573608,
      "learning_rate": 0.00017089252884204377,
      "loss": 0.6656,
      "step": 162
    },
    {
      "epoch": 2.564516129032258,
      "grad_norm": 1.055477499961853,
      "learning_rate": 0.00017052835851187804,
      "loss": 0.7235,
      "step": 163
    },
    {
      "epoch": 2.5806451612903225,
      "grad_norm": 1.0402213335037231,
      "learning_rate": 0.0001701623174871168,
      "loss": 0.7212,
      "step": 164
    },
    {
      "epoch": 2.596774193548387,
      "grad_norm": 1.0087556838989258,
      "learning_rate": 0.00016979441547663435,
      "loss": 0.7124,
      "step": 165
    },
    {
      "epoch": 2.6129032258064515,
      "grad_norm": 1.9748854637145996,
      "learning_rate": 0.0001694246622386658,
      "loss": 0.732,
      "step": 166
    },
    {
      "epoch": 2.629032258064516,
      "grad_norm": 1.0986181497573853,
      "learning_rate": 0.0001690530675805482,
      "loss": 0.7063,
      "step": 167
    },
    {
      "epoch": 2.6451612903225805,
      "grad_norm": 0.9828779101371765,
      "learning_rate": 0.00016867964135846043,
      "loss": 0.7026,
      "step": 168
    },
    {
      "epoch": 2.661290322580645,
      "grad_norm": 1.0073943138122559,
      "learning_rate": 0.0001683043934771618,
      "loss": 0.7084,
      "step": 169
    },
    {
      "epoch": 2.6774193548387095,
      "grad_norm": 1.0138689279556274,
      "learning_rate": 0.00016792733388972932,
      "loss": 0.7144,
      "step": 170
    },
    {
      "epoch": 2.693548387096774,
      "grad_norm": 1.0346741676330566,
      "learning_rate": 0.00016754847259729369,
      "loss": 0.686,
      "step": 171
    },
    {
      "epoch": 2.709677419354839,
      "grad_norm": 1.0213960409164429,
      "learning_rate": 0.0001671678196487741,
      "loss": 0.6537,
      "step": 172
    },
    {
      "epoch": 2.725806451612903,
      "grad_norm": 0.9593885540962219,
      "learning_rate": 0.00016678538514061154,
      "loss": 0.7029,
      "step": 173
    },
    {
      "epoch": 2.741935483870968,
      "grad_norm": 1.0341320037841797,
      "learning_rate": 0.00016640117921650117,
      "loss": 0.6969,
      "step": 174
    },
    {
      "epoch": 2.758064516129032,
      "grad_norm": 1.1095786094665527,
      "learning_rate": 0.00016601521206712318,
      "loss": 0.7048,
      "step": 175
    },
    {
      "epoch": 2.774193548387097,
      "grad_norm": 0.9925594329833984,
      "learning_rate": 0.00016562749392987254,
      "loss": 0.7203,
      "step": 176
    },
    {
      "epoch": 2.774193548387097,
      "eval_loss": 1.6154118776321411,
      "eval_runtime": 232.8684,
      "eval_samples_per_second": 4.552,
      "eval_steps_per_second": 0.76,
      "step": 176
    },
    {
      "epoch": 2.790322580645161,
      "grad_norm": 0.9950226545333862,
      "learning_rate": 0.00016523803508858732,
      "loss": 0.6853,
      "step": 177
    },
    {
      "epoch": 2.806451612903226,
      "grad_norm": 1.0214858055114746,
      "learning_rate": 0.0001648468458732762,
      "loss": 0.7098,
      "step": 178
    },
    {
      "epoch": 2.8225806451612905,
      "grad_norm": 1.0195788145065308,
      "learning_rate": 0.00016445393665984417,
      "loss": 0.6775,
      "step": 179
    },
    {
      "epoch": 2.838709677419355,
      "grad_norm": 0.9992055892944336,
      "learning_rate": 0.00016405931786981755,
      "loss": 0.6981,
      "step": 180
    },
    {
      "epoch": 2.8548387096774195,
      "grad_norm": 1.0090147256851196,
      "learning_rate": 0.0001636629999700674,
      "loss": 0.7083,
      "step": 181
    },
    {
      "epoch": 2.870967741935484,
      "grad_norm": 1.0279518365859985,
      "learning_rate": 0.00016326499347253207,
      "loss": 0.7097,
      "step": 182
    },
    {
      "epoch": 2.8870967741935485,
      "grad_norm": 0.9872741103172302,
      "learning_rate": 0.00016286530893393818,
      "loss": 0.7185,
      "step": 183
    },
    {
      "epoch": 2.903225806451613,
      "grad_norm": 1.0596610307693481,
      "learning_rate": 0.00016246395695552085,
      "loss": 0.6818,
      "step": 184
    },
    {
      "epoch": 2.9193548387096775,
      "grad_norm": 5.755076885223389,
      "learning_rate": 0.00016206094818274229,
      "loss": 0.7244,
      "step": 185
    },
    {
      "epoch": 2.935483870967742,
      "grad_norm": 1.0628125667572021,
      "learning_rate": 0.00016165629330500952,
      "loss": 0.7094,
      "step": 186
    },
    {
      "epoch": 2.9516129032258065,
      "grad_norm": 1.0117448568344116,
      "learning_rate": 0.00016125000305539094,
      "loss": 0.7052,
      "step": 187
    },
    {
      "epoch": 2.967741935483871,
      "grad_norm": 1.0038176774978638,
      "learning_rate": 0.0001608420882103315,
      "loss": 0.6832,
      "step": 188
    },
    {
      "epoch": 2.9838709677419355,
      "grad_norm": 1.0732207298278809,
      "learning_rate": 0.00016043255958936693,
      "loss": 0.7367,
      "step": 189
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.056867003440857,
      "learning_rate": 0.00016002142805483685,
      "loss": 0.674,
      "step": 190
    },
    {
      "epoch": 3.0161290322580645,
      "grad_norm": 1.0539047718048096,
      "learning_rate": 0.00015960870451159638,
      "loss": 0.724,
      "step": 191
    },
    {
      "epoch": 3.032258064516129,
      "grad_norm": 1.0756276845932007,
      "learning_rate": 0.0001591943999067273,
      "loss": 0.7172,
      "step": 192
    },
    {
      "epoch": 3.032258064516129,
      "eval_loss": 1.6202313899993896,
      "eval_runtime": 227.1127,
      "eval_samples_per_second": 4.667,
      "eval_steps_per_second": 0.779,
      "step": 192
    },
    {
      "epoch": 3.0161290322580645,
      "grad_norm": 0.8275887966156006,
      "learning_rate": 0.00015877852522924732,
      "loss": 0.4273,
      "step": 193
    },
    {
      "epoch": 3.032258064516129,
      "grad_norm": 0.8425289988517761,
      "learning_rate": 0.00015836109150981886,
      "loss": 0.3975,
      "step": 194
    },
    {
      "epoch": 3.0483870967741935,
      "grad_norm": 0.8054454922676086,
      "learning_rate": 0.00015794210982045636,
      "loss": 0.4053,
      "step": 195
    },
    {
      "epoch": 3.064516129032258,
      "grad_norm": 0.9864973425865173,
      "learning_rate": 0.00015752159127423263,
      "loss": 0.3912,
      "step": 196
    },
    {
      "epoch": 3.0806451612903225,
      "grad_norm": 4.44207763671875,
      "learning_rate": 0.00015709954702498397,
      "loss": 0.4295,
      "step": 197
    },
    {
      "epoch": 3.096774193548387,
      "grad_norm": 1.4279245138168335,
      "learning_rate": 0.0001566759882670146,
      "loss": 0.458,
      "step": 198
    },
    {
      "epoch": 3.1129032258064515,
      "grad_norm": 0.9974954724311829,
      "learning_rate": 0.0001562509262347995,
      "loss": 0.4105,
      "step": 199
    },
    {
      "epoch": 3.129032258064516,
      "grad_norm": 1.0291105508804321,
      "learning_rate": 0.00015582437220268647,
      "loss": 0.3779,
      "step": 200
    },
    {
      "epoch": 3.1451612903225805,
      "grad_norm": 0.9659109711647034,
      "learning_rate": 0.00015539633748459724,
      "loss": 0.4046,
      "step": 201
    },
    {
      "epoch": 3.161290322580645,
      "grad_norm": 1.0539616346359253,
      "learning_rate": 0.0001549668334337271,
      "loss": 0.4101,
      "step": 202
    },
    {
      "epoch": 3.1774193548387095,
      "grad_norm": 1.0015851259231567,
      "learning_rate": 0.00015453587144224407,
      "loss": 0.4184,
      "step": 203
    },
    {
      "epoch": 3.193548387096774,
      "grad_norm": 0.9041028618812561,
      "learning_rate": 0.0001541034629409865,
      "loss": 0.3943,
      "step": 204
    },
    {
      "epoch": 3.2096774193548385,
      "grad_norm": 0.922798216342926,
      "learning_rate": 0.00015366961939916008,
      "loss": 0.3937,
      "step": 205
    },
    {
      "epoch": 3.225806451612903,
      "grad_norm": 0.9305877685546875,
      "learning_rate": 0.00015323435232403337,
      "loss": 0.3796,
      "step": 206
    },
    {
      "epoch": 3.241935483870968,
      "grad_norm": 0.9297038316726685,
      "learning_rate": 0.00015279767326063296,
      "loss": 0.404,
      "step": 207
    },
    {
      "epoch": 3.258064516129032,
      "grad_norm": 0.8899175524711609,
      "learning_rate": 0.00015235959379143678,
      "loss": 0.3914,
      "step": 208
    },
    {
      "epoch": 3.258064516129032,
      "eval_loss": 1.7161870002746582,
      "eval_runtime": 361.1949,
      "eval_samples_per_second": 2.935,
      "eval_steps_per_second": 0.49,
      "step": 208
    },
    {
      "epoch": 3.274193548387097,
      "grad_norm": 0.9059929847717285,
      "learning_rate": 0.0001519201255360673,
      "loss": 0.3761,
      "step": 209
    },
    {
      "epoch": 3.2903225806451615,
      "grad_norm": 1.0878820419311523,
      "learning_rate": 0.0001514792801509831,
      "loss": 0.4018,
      "step": 210
    },
    {
      "epoch": 3.306451612903226,
      "grad_norm": 0.9320698976516724,
      "learning_rate": 0.00015103706932916974,
      "loss": 0.398,
      "step": 211
    },
    {
      "epoch": 3.3225806451612905,
      "grad_norm": 0.8879979252815247,
      "learning_rate": 0.00015059350479982965,
      "loss": 0.3848,
      "step": 212
    },
    {
      "epoch": 3.338709677419355,
      "grad_norm": 0.8591129779815674,
      "learning_rate": 0.00015014859832807105,
      "loss": 0.3935,
      "step": 213
    },
    {
      "epoch": 3.3548387096774195,
      "grad_norm": 0.8328726887702942,
      "learning_rate": 0.0001497023617145958,
      "loss": 0.4025,
      "step": 214
    },
    {
      "epoch": 3.370967741935484,
      "grad_norm": 0.9114816188812256,
      "learning_rate": 0.00014925480679538647,
      "loss": 0.3978,
      "step": 215
    },
    {
      "epoch": 3.3870967741935485,
      "grad_norm": 0.8772809505462646,
      "learning_rate": 0.0001488059454413923,
      "loss": 0.3936,
      "step": 216
    },
    {
      "epoch": 3.403225806451613,
      "grad_norm": 0.96305251121521,
      "learning_rate": 0.00014835578955821457,
      "loss": 0.4098,
      "step": 217
    },
    {
      "epoch": 3.4193548387096775,
      "grad_norm": 0.8828062415122986,
      "learning_rate": 0.00014790435108579048,
      "loss": 0.3994,
      "step": 218
    },
    {
      "epoch": 3.435483870967742,
      "grad_norm": 1.0111607313156128,
      "learning_rate": 0.00014745164199807682,
      "loss": 0.4002,
      "step": 219
    },
    {
      "epoch": 3.4516129032258065,
      "grad_norm": 0.9364872574806213,
      "learning_rate": 0.000146997674302732,
      "loss": 0.4115,
      "step": 220
    },
    {
      "epoch": 3.467741935483871,
      "grad_norm": 0.9206238389015198,
      "learning_rate": 0.00014654246004079793,
      "loss": 0.3979,
      "step": 221
    },
    {
      "epoch": 3.4838709677419355,
      "grad_norm": 0.910442590713501,
      "learning_rate": 0.00014608601128638027,
      "loss": 0.4041,
      "step": 222
    },
    {
      "epoch": 3.5,
      "grad_norm": 0.9023163914680481,
      "learning_rate": 0.00014562834014632853,
      "loss": 0.3936,
      "step": 223
    },
    {
      "epoch": 3.5161290322580645,
      "grad_norm": 1.0501468181610107,
      "learning_rate": 0.00014516945875991472,
      "loss": 0.4111,
      "step": 224
    },
    {
      "epoch": 3.5161290322580645,
      "eval_loss": 1.711409091949463,
      "eval_runtime": 360.3679,
      "eval_samples_per_second": 2.941,
      "eval_steps_per_second": 0.491,
      "step": 224
    },
    {
      "epoch": 3.532258064516129,
      "grad_norm": 1.386006474494934,
      "learning_rate": 0.0001447093792985114,
      "loss": 0.4127,
      "step": 225
    },
    {
      "epoch": 3.5483870967741935,
      "grad_norm": 0.8904193639755249,
      "learning_rate": 0.00014424811396526892,
      "loss": 0.4089,
      "step": 226
    },
    {
      "epoch": 3.564516129032258,
      "grad_norm": 0.8737647533416748,
      "learning_rate": 0.00014378567499479168,
      "loss": 0.3884,
      "step": 227
    },
    {
      "epoch": 3.5806451612903225,
      "grad_norm": 0.914535641670227,
      "learning_rate": 0.00014332207465281364,
      "loss": 0.4217,
      "step": 228
    },
    {
      "epoch": 3.596774193548387,
      "grad_norm": 0.9375549554824829,
      "learning_rate": 0.00014285732523587304,
      "loss": 0.4092,
      "step": 229
    },
    {
      "epoch": 3.6129032258064515,
      "grad_norm": 0.8925461173057556,
      "learning_rate": 0.0001423914390709861,
      "loss": 0.3956,
      "step": 230
    },
    {
      "epoch": 3.629032258064516,
      "grad_norm": 0.8751139640808105,
      "learning_rate": 0.00014192442851532018,
      "loss": 0.413,
      "step": 231
    },
    {
      "epoch": 3.6451612903225805,
      "grad_norm": 0.8749066591262817,
      "learning_rate": 0.00014145630595586607,
      "loss": 0.4015,
      "step": 232
    },
    {
      "epoch": 3.661290322580645,
      "grad_norm": 0.9000979661941528,
      "learning_rate": 0.0001409870838091092,
      "loss": 0.4117,
      "step": 233
    },
    {
      "epoch": 3.6774193548387095,
      "grad_norm": 0.909804105758667,
      "learning_rate": 0.00014051677452070065,
      "loss": 0.3782,
      "step": 234
    },
    {
      "epoch": 3.693548387096774,
      "grad_norm": 1.7925716638565063,
      "learning_rate": 0.00014004539056512667,
      "loss": 0.4451,
      "step": 235
    },
    {
      "epoch": 3.709677419354839,
      "grad_norm": 0.9784117937088013,
      "learning_rate": 0.00013957294444537808,
      "loss": 0.4252,
      "step": 236
    },
    {
      "epoch": 3.725806451612903,
      "grad_norm": 0.9990687370300293,
      "learning_rate": 0.00013909944869261855,
      "loss": 0.4384,
      "step": 237
    },
    {
      "epoch": 3.741935483870968,
      "grad_norm": 1.0078152418136597,
      "learning_rate": 0.0001386249158658522,
      "loss": 0.4193,
      "step": 238
    },
    {
      "epoch": 3.758064516129032,
      "grad_norm": 0.9793704152107239,
      "learning_rate": 0.00013814935855159055,
      "loss": 0.4253,
      "step": 239
    },
    {
      "epoch": 3.774193548387097,
      "grad_norm": 0.9232134819030762,
      "learning_rate": 0.00013767278936351854,
      "loss": 0.4091,
      "step": 240
    },
    {
      "epoch": 3.774193548387097,
      "eval_loss": 1.717702865600586,
      "eval_runtime": 359.9193,
      "eval_samples_per_second": 2.945,
      "eval_steps_per_second": 0.492,
      "step": 240
    },
    {
      "epoch": 3.790322580645161,
      "grad_norm": 1.0362968444824219,
      "learning_rate": 0.00013719522094216013,
      "loss": 0.418,
      "step": 241
    },
    {
      "epoch": 3.806451612903226,
      "grad_norm": 0.9517565369606018,
      "learning_rate": 0.00013671666595454295,
      "loss": 0.4343,
      "step": 242
    },
    {
      "epoch": 3.8225806451612905,
      "grad_norm": 0.9661825895309448,
      "learning_rate": 0.00013623713709386227,
      "loss": 0.3973,
      "step": 243
    },
    {
      "epoch": 3.838709677419355,
      "grad_norm": 0.9564940333366394,
      "learning_rate": 0.00013575664707914448,
      "loss": 0.3935,
      "step": 244
    },
    {
      "epoch": 3.8548387096774195,
      "grad_norm": 0.9845961928367615,
      "learning_rate": 0.0001352752086549095,
      "loss": 0.4374,
      "step": 245
    },
    {
      "epoch": 3.870967741935484,
      "grad_norm": 0.9213180541992188,
      "learning_rate": 0.0001347928345908329,
      "loss": 0.4253,
      "step": 246
    },
    {
      "epoch": 3.8870967741935485,
      "grad_norm": 0.8919222950935364,
      "learning_rate": 0.00013430953768140723,
      "loss": 0.4148,
      "step": 247
    },
    {
      "epoch": 3.903225806451613,
      "grad_norm": 0.899038553237915,
      "learning_rate": 0.00013382533074560255,
      "loss": 0.419,
      "step": 248
    },
    {
      "epoch": 3.9193548387096775,
      "grad_norm": 0.9399131536483765,
      "learning_rate": 0.00013334022662652649,
      "loss": 0.4081,
      "step": 249
    },
    {
      "epoch": 3.935483870967742,
      "grad_norm": 0.8963966965675354,
      "learning_rate": 0.0001328542381910835,
      "loss": 0.4036,
      "step": 250
    },
    {
      "epoch": 3.9516129032258065,
      "grad_norm": 0.8994773626327515,
      "learning_rate": 0.0001323673783296337,
      "loss": 0.4138,
      "step": 251
    },
    {
      "epoch": 3.967741935483871,
      "grad_norm": 0.9611584544181824,
      "learning_rate": 0.00013187965995565098,
      "loss": 0.4416,
      "step": 252
    },
    {
      "epoch": 3.9838709677419355,
      "grad_norm": 0.9271295666694641,
      "learning_rate": 0.00013139109600538028,
      "loss": 0.4009,
      "step": 253
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.9294149875640869,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.4187,
      "step": 254
    },
    {
      "epoch": 4.016129032258064,
      "grad_norm": 0.9005634188652039,
      "learning_rate": 0.0001304114832327518,
      "loss": 0.4068,
      "step": 255
    },
    {
      "epoch": 4.032258064516129,
      "grad_norm": 0.9278081655502319,
      "learning_rate": 0.00012992046039364893,
      "loss": 0.4103,
      "step": 256
    },
    {
      "epoch": 4.032258064516129,
      "eval_loss": 1.719123363494873,
      "eval_runtime": 366.7154,
      "eval_samples_per_second": 2.891,
      "eval_steps_per_second": 0.483,
      "step": 256
    },
    {
      "epoch": 4.016129032258065,
      "grad_norm": 0.6807416677474976,
      "learning_rate": 0.00012942864394407879,
      "loss": 0.2192,
      "step": 257
    },
    {
      "epoch": 4.032258064516129,
      "grad_norm": 0.7075343132019043,
      "learning_rate": 0.0001289360469289838,
      "loss": 0.2174,
      "step": 258
    },
    {
      "epoch": 4.048387096774194,
      "grad_norm": 0.7534266114234924,
      "learning_rate": 0.0001284426824140101,
      "loss": 0.2102,
      "step": 259
    },
    {
      "epoch": 4.064516129032258,
      "grad_norm": 0.80478435754776,
      "learning_rate": 0.00012794856348516095,
      "loss": 0.1996,
      "step": 260
    },
    {
      "epoch": 4.080645161290323,
      "grad_norm": 0.8782503604888916,
      "learning_rate": 0.00012745370324844974,
      "loss": 0.2231,
      "step": 261
    },
    {
      "epoch": 4.096774193548387,
      "grad_norm": 0.9023078083992004,
      "learning_rate": 0.00012695811482955227,
      "loss": 0.2127,
      "step": 262
    },
    {
      "epoch": 4.112903225806452,
      "grad_norm": 1.4141674041748047,
      "learning_rate": 0.0001264618113734587,
      "loss": 0.2308,
      "step": 263
    },
    {
      "epoch": 4.129032258064516,
      "grad_norm": 0.7676845192909241,
      "learning_rate": 0.00012596480604412484,
      "loss": 0.2044,
      "step": 264
    },
    {
      "epoch": 4.145161290322581,
      "grad_norm": 0.7796346545219421,
      "learning_rate": 0.00012546711202412287,
      "loss": 0.2103,
      "step": 265
    },
    {
      "epoch": 4.161290322580645,
      "grad_norm": 0.7459124326705933,
      "learning_rate": 0.000124968742514292,
      "loss": 0.1979,
      "step": 266
    },
    {
      "epoch": 4.17741935483871,
      "grad_norm": 0.7819743156433105,
      "learning_rate": 0.000124469710733388,
      "loss": 0.1989,
      "step": 267
    },
    {
      "epoch": 4.193548387096774,
      "grad_norm": 0.8068183660507202,
      "learning_rate": 0.00012397002991773275,
      "loss": 0.211,
      "step": 268
    },
    {
      "epoch": 4.209677419354839,
      "grad_norm": 0.76580810546875,
      "learning_rate": 0.00012346971332086317,
      "loss": 0.2161,
      "step": 269
    },
    {
      "epoch": 4.225806451612903,
      "grad_norm": 0.7457690238952637,
      "learning_rate": 0.0001229687742131796,
      "loss": 0.2082,
      "step": 270
    },
    {
      "epoch": 4.241935483870968,
      "grad_norm": 0.7540544867515564,
      "learning_rate": 0.0001224672258815938,
      "loss": 0.1897,
      "step": 271
    },
    {
      "epoch": 4.258064516129032,
      "grad_norm": 0.769862174987793,
      "learning_rate": 0.00012196508162917677,
      "loss": 0.1996,
      "step": 272
    },
    {
      "epoch": 4.258064516129032,
      "eval_loss": 1.8386796712875366,
      "eval_runtime": 360.7673,
      "eval_samples_per_second": 2.938,
      "eval_steps_per_second": 0.491,
      "step": 272
    },
    {
      "epoch": 4.274193548387097,
      "grad_norm": 0.7516776919364929,
      "learning_rate": 0.00012146235477480559,
      "loss": 0.2048,
      "step": 273
    },
    {
      "epoch": 4.290322580645161,
      "grad_norm": 0.8582746386528015,
      "learning_rate": 0.00012095905865281025,
      "loss": 0.2017,
      "step": 274
    },
    {
      "epoch": 4.306451612903226,
      "grad_norm": 0.7552902102470398,
      "learning_rate": 0.0001204552066126201,
      "loss": 0.205,
      "step": 275
    },
    {
      "epoch": 4.32258064516129,
      "grad_norm": 0.7861020565032959,
      "learning_rate": 0.00011995081201840956,
      "loss": 0.21,
      "step": 276
    },
    {
      "epoch": 4.338709677419355,
      "grad_norm": 0.8263004422187805,
      "learning_rate": 0.00011944588824874388,
      "loss": 0.2006,
      "step": 277
    },
    {
      "epoch": 4.354838709677419,
      "grad_norm": 3.678614616394043,
      "learning_rate": 0.00011894044869622403,
      "loss": 0.19,
      "step": 278
    },
    {
      "epoch": 4.370967741935484,
      "grad_norm": 0.7940691709518433,
      "learning_rate": 0.0001184345067671317,
      "loss": 0.2141,
      "step": 279
    },
    {
      "epoch": 4.387096774193548,
      "grad_norm": 0.7446163296699524,
      "learning_rate": 0.00011792807588107357,
      "loss": 0.192,
      "step": 280
    },
    {
      "epoch": 4.403225806451613,
      "grad_norm": 0.7419606447219849,
      "learning_rate": 0.00011742116947062545,
      "loss": 0.2085,
      "step": 281
    },
    {
      "epoch": 4.419354838709677,
      "grad_norm": 0.7716213464736938,
      "learning_rate": 0.00011691380098097597,
      "loss": 0.2126,
      "step": 282
    },
    {
      "epoch": 4.435483870967742,
      "grad_norm": 0.9422786831855774,
      "learning_rate": 0.00011640598386956992,
      "loss": 0.2048,
      "step": 283
    },
    {
      "epoch": 4.451612903225806,
      "grad_norm": 0.8216850161552429,
      "learning_rate": 0.0001158977316057513,
      "loss": 0.1977,
      "step": 284
    },
    {
      "epoch": 4.467741935483871,
      "grad_norm": 0.7419984936714172,
      "learning_rate": 0.0001153890576704062,
      "loss": 0.2047,
      "step": 285
    },
    {
      "epoch": 4.483870967741936,
      "grad_norm": 0.7556256651878357,
      "learning_rate": 0.00011487997555560503,
      "loss": 0.2094,
      "step": 286
    },
    {
      "epoch": 4.5,
      "grad_norm": 0.8195300102233887,
      "learning_rate": 0.0001143704987642448,
      "loss": 0.199,
      "step": 287
    },
    {
      "epoch": 4.516129032258064,
      "grad_norm": 0.7117184996604919,
      "learning_rate": 0.00011386064080969094,
      "loss": 0.1932,
      "step": 288
    },
    {
      "epoch": 4.516129032258064,
      "eval_loss": 1.8438739776611328,
      "eval_runtime": 361.0378,
      "eval_samples_per_second": 2.936,
      "eval_steps_per_second": 0.49,
      "step": 288
    },
    {
      "epoch": 4.532258064516129,
      "grad_norm": 0.7270099520683289,
      "learning_rate": 0.00011335041521541885,
      "loss": 0.1916,
      "step": 289
    },
    {
      "epoch": 4.548387096774194,
      "grad_norm": 0.7429494261741638,
      "learning_rate": 0.00011283983551465511,
      "loss": 0.1984,
      "step": 290
    },
    {
      "epoch": 4.564516129032258,
      "grad_norm": 0.7204171419143677,
      "learning_rate": 0.00011232891525001876,
      "loss": 0.1814,
      "step": 291
    },
    {
      "epoch": 4.580645161290323,
      "grad_norm": 0.7861455678939819,
      "learning_rate": 0.0001118176679731619,
      "loss": 0.2097,
      "step": 292
    },
    {
      "epoch": 4.596774193548387,
      "grad_norm": 0.8191571831703186,
      "learning_rate": 0.0001113061072444103,
      "loss": 0.221,
      "step": 293
    },
    {
      "epoch": 4.612903225806452,
      "grad_norm": 1.3524975776672363,
      "learning_rate": 0.00011079424663240372,
      "loss": 0.2066,
      "step": 294
    },
    {
      "epoch": 4.629032258064516,
      "grad_norm": 0.7753690481185913,
      "learning_rate": 0.00011028209971373605,
      "loss": 0.2112,
      "step": 295
    },
    {
      "epoch": 4.645161290322581,
      "grad_norm": 0.7331258654594421,
      "learning_rate": 0.00010976968007259519,
      "loss": 0.1993,
      "step": 296
    },
    {
      "epoch": 4.661290322580645,
      "grad_norm": 0.7499488592147827,
      "learning_rate": 0.00010925700130040266,
      "loss": 0.1937,
      "step": 297
    },
    {
      "epoch": 4.67741935483871,
      "grad_norm": 0.813107967376709,
      "learning_rate": 0.00010874407699545328,
      "loss": 0.2157,
      "step": 298
    },
    {
      "epoch": 4.693548387096774,
      "grad_norm": 0.8471450805664062,
      "learning_rate": 0.0001082309207625543,
      "loss": 0.215,
      "step": 299
    },
    {
      "epoch": 4.709677419354839,
      "grad_norm": 0.7541672587394714,
      "learning_rate": 0.00010771754621266466,
      "loss": 0.1968,
      "step": 300
    },
    {
      "epoch": 4.725806451612903,
      "grad_norm": 0.8032663464546204,
      "learning_rate": 0.00010720396696253393,
      "loss": 0.2161,
      "step": 301
    },
    {
      "epoch": 4.741935483870968,
      "grad_norm": 0.7688977718353271,
      "learning_rate": 0.00010669019663434117,
      "loss": 0.202,
      "step": 302
    },
    {
      "epoch": 4.758064516129032,
      "grad_norm": 0.8105716109275818,
      "learning_rate": 0.00010617624885533356,
      "loss": 0.228,
      "step": 303
    },
    {
      "epoch": 4.774193548387097,
      "grad_norm": 0.7785431146621704,
      "learning_rate": 0.00010566213725746506,
      "loss": 0.2185,
      "step": 304
    },
    {
      "epoch": 4.774193548387097,
      "eval_loss": 1.8509935140609741,
      "eval_runtime": 361.2404,
      "eval_samples_per_second": 2.934,
      "eval_steps_per_second": 0.49,
      "step": 304
    },
    {
      "epoch": 4.790322580645161,
      "grad_norm": 0.865378737449646,
      "learning_rate": 0.00010514787547703466,
      "loss": 0.2095,
      "step": 305
    },
    {
      "epoch": 4.806451612903226,
      "grad_norm": 1.0173976421356201,
      "learning_rate": 0.00010463347715432488,
      "loss": 0.2202,
      "step": 306
    },
    {
      "epoch": 4.82258064516129,
      "grad_norm": 0.7536367774009705,
      "learning_rate": 0.00010411895593323981,
      "loss": 0.2072,
      "step": 307
    },
    {
      "epoch": 4.838709677419355,
      "grad_norm": 0.7996053695678711,
      "learning_rate": 0.00010360432546094341,
      "loss": 0.209,
      "step": 308
    },
    {
      "epoch": 4.854838709677419,
      "grad_norm": 0.8005889654159546,
      "learning_rate": 0.00010308959938749729,
      "loss": 0.217,
      "step": 309
    },
    {
      "epoch": 4.870967741935484,
      "grad_norm": 0.7493289709091187,
      "learning_rate": 0.00010257479136549889,
      "loss": 0.2037,
      "step": 310
    },
    {
      "epoch": 4.887096774193548,
      "grad_norm": 0.8069470524787903,
      "learning_rate": 0.00010205991504971912,
      "loss": 0.2189,
      "step": 311
    },
    {
      "epoch": 4.903225806451613,
      "grad_norm": 0.7922778129577637,
      "learning_rate": 0.00010154498409674051,
      "loss": 0.2241,
      "step": 312
    },
    {
      "epoch": 4.919354838709677,
      "grad_norm": 0.7668143510818481,
      "learning_rate": 0.00010103001216459469,
      "loss": 0.2202,
      "step": 313
    },
    {
      "epoch": 4.935483870967742,
      "grad_norm": 0.7700707316398621,
      "learning_rate": 0.00010051501291240008,
      "loss": 0.2149,
      "step": 314
    },
    {
      "epoch": 4.951612903225806,
      "grad_norm": 0.7833395004272461,
      "learning_rate": 0.0001,
      "loss": 0.2176,
      "step": 315
    },
    {
      "epoch": 4.967741935483871,
      "grad_norm": 0.7745612263679504,
      "learning_rate": 9.948498708759993e-05,
      "loss": 0.2121,
      "step": 316
    },
    {
      "epoch": 4.983870967741936,
      "grad_norm": 0.7606418132781982,
      "learning_rate": 9.896998783540536e-05,
      "loss": 0.1974,
      "step": 317
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.8445224165916443,
      "learning_rate": 9.845501590325948e-05,
      "loss": 0.2194,
      "step": 318
    },
    {
      "epoch": 5.016129032258064,
      "grad_norm": 0.7644294500350952,
      "learning_rate": 9.794008495028087e-05,
      "loss": 0.2037,
      "step": 319
    },
    {
      "epoch": 5.032258064516129,
      "grad_norm": 0.7571164965629578,
      "learning_rate": 9.742520863450115e-05,
      "loss": 0.2221,
      "step": 320
    },
    {
      "epoch": 5.032258064516129,
      "eval_loss": 1.851494550704956,
      "eval_runtime": 366.7021,
      "eval_samples_per_second": 2.891,
      "eval_steps_per_second": 0.483,
      "step": 320
    },
    {
      "epoch": 5.016129032258065,
      "grad_norm": 0.591090977191925,
      "learning_rate": 9.691040061250273e-05,
      "loss": 0.1024,
      "step": 321
    },
    {
      "epoch": 5.032258064516129,
      "grad_norm": 0.5239948630332947,
      "learning_rate": 9.639567453905661e-05,
      "loss": 0.0993,
      "step": 322
    },
    {
      "epoch": 5.048387096774194,
      "grad_norm": 0.4719286561012268,
      "learning_rate": 9.58810440667602e-05,
      "loss": 0.0905,
      "step": 323
    },
    {
      "epoch": 5.064516129032258,
      "grad_norm": 0.5142775177955627,
      "learning_rate": 9.536652284567513e-05,
      "loss": 0.0916,
      "step": 324
    },
    {
      "epoch": 5.080645161290323,
      "grad_norm": 0.6494867205619812,
      "learning_rate": 9.485212452296535e-05,
      "loss": 0.1001,
      "step": 325
    },
    {
      "epoch": 5.096774193548387,
      "grad_norm": 0.6289418935775757,
      "learning_rate": 9.433786274253495e-05,
      "loss": 0.0945,
      "step": 326
    },
    {
      "epoch": 5.112903225806452,
      "grad_norm": 0.6664146780967712,
      "learning_rate": 9.382375114466644e-05,
      "loss": 0.0919,
      "step": 327
    },
    {
      "epoch": 5.129032258064516,
      "grad_norm": 0.6793842911720276,
      "learning_rate": 9.330980336565887e-05,
      "loss": 0.1023,
      "step": 328
    },
    {
      "epoch": 5.145161290322581,
      "grad_norm": 0.6552854776382446,
      "learning_rate": 9.279603303746608e-05,
      "loss": 0.0956,
      "step": 329
    },
    {
      "epoch": 5.161290322580645,
      "grad_norm": 0.5973914861679077,
      "learning_rate": 9.228245378733537e-05,
      "loss": 0.0978,
      "step": 330
    },
    {
      "epoch": 5.17741935483871,
      "grad_norm": 0.5700520277023315,
      "learning_rate": 9.176907923744571e-05,
      "loss": 0.0909,
      "step": 331
    },
    {
      "epoch": 5.193548387096774,
      "grad_norm": 0.5783142447471619,
      "learning_rate": 9.125592300454676e-05,
      "loss": 0.094,
      "step": 332
    },
    {
      "epoch": 5.209677419354839,
      "grad_norm": 0.5391398072242737,
      "learning_rate": 9.074299869959738e-05,
      "loss": 0.0885,
      "step": 333
    },
    {
      "epoch": 5.225806451612903,
      "grad_norm": 0.5473701357841492,
      "learning_rate": 9.023031992740488e-05,
      "loss": 0.0917,
      "step": 334
    },
    {
      "epoch": 5.241935483870968,
      "grad_norm": 0.5759130716323853,
      "learning_rate": 8.971790028626395e-05,
      "loss": 0.1002,
      "step": 335
    },
    {
      "epoch": 5.258064516129032,
      "grad_norm": 0.5708579421043396,
      "learning_rate": 8.920575336759629e-05,
      "loss": 0.0968,
      "step": 336
    },
    {
      "epoch": 5.258064516129032,
      "eval_loss": 2.0317347049713135,
      "eval_runtime": 365.1587,
      "eval_samples_per_second": 2.903,
      "eval_steps_per_second": 0.485,
      "step": 336
    },
    {
      "epoch": 5.274193548387097,
      "grad_norm": 0.6354628205299377,
      "learning_rate": 8.869389275558972e-05,
      "loss": 0.1,
      "step": 337
    },
    {
      "epoch": 5.290322580645161,
      "grad_norm": 0.6346054077148438,
      "learning_rate": 8.818233202683814e-05,
      "loss": 0.097,
      "step": 338
    },
    {
      "epoch": 5.306451612903226,
      "grad_norm": 0.5868246555328369,
      "learning_rate": 8.767108474998128e-05,
      "loss": 0.098,
      "step": 339
    },
    {
      "epoch": 5.32258064516129,
      "grad_norm": 0.5682688355445862,
      "learning_rate": 8.71601644853449e-05,
      "loss": 0.0887,
      "step": 340
    },
    {
      "epoch": 5.338709677419355,
      "grad_norm": 0.643573522567749,
      "learning_rate": 8.664958478458117e-05,
      "loss": 0.0969,
      "step": 341
    },
    {
      "epoch": 5.354838709677419,
      "grad_norm": 1.490026593208313,
      "learning_rate": 8.613935919030907e-05,
      "loss": 0.0983,
      "step": 342
    },
    {
      "epoch": 5.370967741935484,
      "grad_norm": 0.629753828048706,
      "learning_rate": 8.562950123575523e-05,
      "loss": 0.0991,
      "step": 343
    },
    {
      "epoch": 5.387096774193548,
      "grad_norm": 0.6013917326927185,
      "learning_rate": 8.512002444439502e-05,
      "loss": 0.1026,
      "step": 344
    },
    {
      "epoch": 5.403225806451613,
      "grad_norm": 0.5838581323623657,
      "learning_rate": 8.461094232959381e-05,
      "loss": 0.089,
      "step": 345
    },
    {
      "epoch": 5.419354838709677,
      "grad_norm": 0.5835732221603394,
      "learning_rate": 8.410226839424871e-05,
      "loss": 0.0939,
      "step": 346
    },
    {
      "epoch": 5.435483870967742,
      "grad_norm": 0.616823136806488,
      "learning_rate": 8.359401613043012e-05,
      "loss": 0.0936,
      "step": 347
    },
    {
      "epoch": 5.451612903225806,
      "grad_norm": 0.6824636459350586,
      "learning_rate": 8.308619901902406e-05,
      "loss": 0.1023,
      "step": 348
    },
    {
      "epoch": 5.467741935483871,
      "grad_norm": 0.5994443297386169,
      "learning_rate": 8.257883052937456e-05,
      "loss": 0.0975,
      "step": 349
    },
    {
      "epoch": 5.483870967741936,
      "grad_norm": 0.7672178149223328,
      "learning_rate": 8.207192411892646e-05,
      "loss": 0.0983,
      "step": 350
    },
    {
      "epoch": 5.5,
      "grad_norm": 1.1863083839416504,
      "learning_rate": 8.156549323286831e-05,
      "loss": 0.0951,
      "step": 351
    },
    {
      "epoch": 5.516129032258064,
      "grad_norm": 0.5679525136947632,
      "learning_rate": 8.1059551303776e-05,
      "loss": 0.0937,
      "step": 352
    },
    {
      "epoch": 5.516129032258064,
      "eval_loss": 2.013756036758423,
      "eval_runtime": 365.2484,
      "eval_samples_per_second": 2.902,
      "eval_steps_per_second": 0.485,
      "step": 352
    },
    {
      "epoch": 5.532258064516129,
      "grad_norm": 0.5959299802780151,
      "learning_rate": 8.055411175125616e-05,
      "loss": 0.086,
      "step": 353
    },
    {
      "epoch": 5.548387096774194,
      "grad_norm": 0.5877125859260559,
      "learning_rate": 8.004918798159045e-05,
      "loss": 0.0911,
      "step": 354
    },
    {
      "epoch": 5.564516129032258,
      "grad_norm": 0.5466898083686829,
      "learning_rate": 7.954479338737995e-05,
      "loss": 0.0845,
      "step": 355
    },
    {
      "epoch": 5.580645161290323,
      "grad_norm": 0.5609007477760315,
      "learning_rate": 7.904094134718976e-05,
      "loss": 0.0883,
      "step": 356
    },
    {
      "epoch": 5.596774193548387,
      "grad_norm": 0.6323772668838501,
      "learning_rate": 7.853764522519445e-05,
      "loss": 0.0944,
      "step": 357
    },
    {
      "epoch": 5.612903225806452,
      "grad_norm": 0.6980358958244324,
      "learning_rate": 7.803491837082324e-05,
      "loss": 0.1007,
      "step": 358
    },
    {
      "epoch": 5.629032258064516,
      "grad_norm": 0.6050729751586914,
      "learning_rate": 7.753277411840622e-05,
      "loss": 0.0927,
      "step": 359
    },
    {
      "epoch": 5.645161290322581,
      "grad_norm": 0.5835074782371521,
      "learning_rate": 7.703122578682046e-05,
      "loss": 0.0876,
      "step": 360
    },
    {
      "epoch": 5.661290322580645,
      "grad_norm": 0.5104186534881592,
      "learning_rate": 7.653028667913686e-05,
      "loss": 0.084,
      "step": 361
    },
    {
      "epoch": 5.67741935483871,
      "grad_norm": 0.5861672163009644,
      "learning_rate": 7.602997008226726e-05,
      "loss": 0.0932,
      "step": 362
    },
    {
      "epoch": 5.693548387096774,
      "grad_norm": 0.5980664491653442,
      "learning_rate": 7.553028926661201e-05,
      "loss": 0.0833,
      "step": 363
    },
    {
      "epoch": 5.709677419354839,
      "grad_norm": 0.6397245526313782,
      "learning_rate": 7.5031257485708e-05,
      "loss": 0.088,
      "step": 364
    },
    {
      "epoch": 5.725806451612903,
      "grad_norm": 0.6025028228759766,
      "learning_rate": 7.453288797587714e-05,
      "loss": 0.0949,
      "step": 365
    },
    {
      "epoch": 5.741935483870968,
      "grad_norm": 0.6607884168624878,
      "learning_rate": 7.403519395587521e-05,
      "loss": 0.1029,
      "step": 366
    },
    {
      "epoch": 5.758064516129032,
      "grad_norm": 0.6854023933410645,
      "learning_rate": 7.353818862654129e-05,
      "loss": 0.0984,
      "step": 367
    },
    {
      "epoch": 5.774193548387097,
      "grad_norm": 0.5980477929115295,
      "learning_rate": 7.304188517044774e-05,
      "loss": 0.0973,
      "step": 368
    },
    {
      "epoch": 5.774193548387097,
      "eval_loss": 2.027407646179199,
      "eval_runtime": 229.0955,
      "eval_samples_per_second": 4.627,
      "eval_steps_per_second": 0.773,
      "step": 368
    },
    {
      "epoch": 5.790322580645161,
      "grad_norm": 0.5738844871520996,
      "learning_rate": 7.254629675155027e-05,
      "loss": 0.0872,
      "step": 369
    },
    {
      "epoch": 5.806451612903226,
      "grad_norm": 0.6093122363090515,
      "learning_rate": 7.205143651483906e-05,
      "loss": 0.0939,
      "step": 370
    },
    {
      "epoch": 5.82258064516129,
      "grad_norm": 0.5988517999649048,
      "learning_rate": 7.155731758598992e-05,
      "loss": 0.0922,
      "step": 371
    },
    {
      "epoch": 5.838709677419355,
      "grad_norm": 0.6104899644851685,
      "learning_rate": 7.106395307101621e-05,
      "loss": 0.0829,
      "step": 372
    },
    {
      "epoch": 5.854838709677419,
      "grad_norm": 0.8592974543571472,
      "learning_rate": 7.057135605592121e-05,
      "loss": 0.1204,
      "step": 373
    },
    {
      "epoch": 5.870967741935484,
      "grad_norm": 0.5683754682540894,
      "learning_rate": 7.007953960635109e-05,
      "loss": 0.0865,
      "step": 374
    },
    {
      "epoch": 5.887096774193548,
      "grad_norm": 0.5832166075706482,
      "learning_rate": 6.958851676724823e-05,
      "loss": 0.0911,
      "step": 375
    },
    {
      "epoch": 5.903225806451613,
      "grad_norm": 0.534551739692688,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.0861,
      "step": 376
    },
    {
      "epoch": 5.919354838709677,
      "grad_norm": 0.546940803527832,
      "learning_rate": 6.860890399461974e-05,
      "loss": 0.0893,
      "step": 377
    },
    {
      "epoch": 5.935483870967742,
      "grad_norm": 0.5596715211868286,
      "learning_rate": 6.812034004434903e-05,
      "loss": 0.0913,
      "step": 378
    },
    {
      "epoch": 5.951612903225806,
      "grad_norm": 0.6050382852554321,
      "learning_rate": 6.76326216703663e-05,
      "loss": 0.0853,
      "step": 379
    },
    {
      "epoch": 5.967741935483871,
      "grad_norm": 0.563949465751648,
      "learning_rate": 6.714576180891654e-05,
      "loss": 0.0814,
      "step": 380
    },
    {
      "epoch": 5.983870967741936,
      "grad_norm": 0.6186781525611877,
      "learning_rate": 6.665977337347354e-05,
      "loss": 0.1003,
      "step": 381
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.583235502243042,
      "learning_rate": 6.617466925439746e-05,
      "loss": 0.0911,
      "step": 382
    },
    {
      "epoch": 6.016129032258064,
      "grad_norm": 0.6332904696464539,
      "learning_rate": 6.569046231859281e-05,
      "loss": 0.0923,
      "step": 383
    },
    {
      "epoch": 6.032258064516129,
      "grad_norm": 0.6747143864631653,
      "learning_rate": 6.520716540916709e-05,
      "loss": 0.083,
      "step": 384
    },
    {
      "epoch": 6.032258064516129,
      "eval_loss": 2.0257039070129395,
      "eval_runtime": 219.95,
      "eval_samples_per_second": 4.819,
      "eval_steps_per_second": 0.805,
      "step": 384
    },
    {
      "epoch": 6.016129032258065,
      "grad_norm": 0.33682334423065186,
      "learning_rate": 6.472479134509052e-05,
      "loss": 0.0476,
      "step": 385
    },
    {
      "epoch": 6.032258064516129,
      "grad_norm": 0.33974146842956543,
      "learning_rate": 6.424335292085553e-05,
      "loss": 0.0462,
      "step": 386
    },
    {
      "epoch": 6.048387096774194,
      "grad_norm": 0.335627019405365,
      "learning_rate": 6.376286290613776e-05,
      "loss": 0.0437,
      "step": 387
    },
    {
      "epoch": 6.064516129032258,
      "grad_norm": 0.3977552652359009,
      "learning_rate": 6.32833340454571e-05,
      "loss": 0.0446,
      "step": 388
    },
    {
      "epoch": 6.080645161290323,
      "grad_norm": 0.3793430030345917,
      "learning_rate": 6.280477905783988e-05,
      "loss": 0.0437,
      "step": 389
    },
    {
      "epoch": 6.096774193548387,
      "grad_norm": 0.38144728541374207,
      "learning_rate": 6.232721063648148e-05,
      "loss": 0.0388,
      "step": 390
    },
    {
      "epoch": 6.112903225806452,
      "grad_norm": 0.3977310359477997,
      "learning_rate": 6.185064144840948e-05,
      "loss": 0.0412,
      "step": 391
    },
    {
      "epoch": 6.129032258064516,
      "grad_norm": 0.4477882385253906,
      "learning_rate": 6.137508413414784e-05,
      "loss": 0.0422,
      "step": 392
    },
    {
      "epoch": 6.145161290322581,
      "grad_norm": 0.4987168312072754,
      "learning_rate": 6.0900551307381484e-05,
      "loss": 0.0391,
      "step": 393
    },
    {
      "epoch": 6.161290322580645,
      "grad_norm": 0.4499349892139435,
      "learning_rate": 6.0427055554621913e-05,
      "loss": 0.0382,
      "step": 394
    },
    {
      "epoch": 6.17741935483871,
      "grad_norm": 0.39157646894454956,
      "learning_rate": 5.9954609434873344e-05,
      "loss": 0.0368,
      "step": 395
    },
    {
      "epoch": 6.193548387096774,
      "grad_norm": 0.38924601674079895,
      "learning_rate": 5.948322547929939e-05,
      "loss": 0.0406,
      "step": 396
    },
    {
      "epoch": 6.209677419354839,
      "grad_norm": 0.4060990810394287,
      "learning_rate": 5.901291619089081e-05,
      "loss": 0.0453,
      "step": 397
    },
    {
      "epoch": 6.225806451612903,
      "grad_norm": 0.5091999173164368,
      "learning_rate": 5.854369404413398e-05,
      "loss": 0.0415,
      "step": 398
    },
    {
      "epoch": 6.241935483870968,
      "grad_norm": 0.38994643092155457,
      "learning_rate": 5.807557148467984e-05,
      "loss": 0.0429,
      "step": 399
    },
    {
      "epoch": 6.258064516129032,
      "grad_norm": 0.4015688896179199,
      "learning_rate": 5.7608560929013946e-05,
      "loss": 0.0385,
      "step": 400
    },
    {
      "epoch": 6.258064516129032,
      "eval_loss": 2.1730642318725586,
      "eval_runtime": 220.4701,
      "eval_samples_per_second": 4.808,
      "eval_steps_per_second": 0.803,
      "step": 400
    },
    {
      "epoch": 6.274193548387097,
      "grad_norm": 0.41079944372177124,
      "learning_rate": 5.7142674764127e-05,
      "loss": 0.0426,
      "step": 401
    },
    {
      "epoch": 6.290322580645161,
      "grad_norm": 0.382231205701828,
      "learning_rate": 5.667792534718639e-05,
      "loss": 0.0387,
      "step": 402
    },
    {
      "epoch": 6.306451612903226,
      "grad_norm": 0.3789753019809723,
      "learning_rate": 5.6214325005208355e-05,
      "loss": 0.0411,
      "step": 403
    },
    {
      "epoch": 6.32258064516129,
      "grad_norm": 0.36216092109680176,
      "learning_rate": 5.5751886034731115e-05,
      "loss": 0.0411,
      "step": 404
    },
    {
      "epoch": 6.338709677419355,
      "grad_norm": 0.44374072551727295,
      "learning_rate": 5.5290620701488594e-05,
      "loss": 0.0408,
      "step": 405
    },
    {
      "epoch": 6.354838709677419,
      "grad_norm": 0.46136826276779175,
      "learning_rate": 5.483054124008528e-05,
      "loss": 0.045,
      "step": 406
    },
    {
      "epoch": 6.370967741935484,
      "grad_norm": 0.3711608052253723,
      "learning_rate": 5.437165985367145e-05,
      "loss": 0.0369,
      "step": 407
    },
    {
      "epoch": 6.387096774193548,
      "grad_norm": 0.41239285469055176,
      "learning_rate": 5.391398871361972e-05,
      "loss": 0.0379,
      "step": 408
    },
    {
      "epoch": 6.403225806451613,
      "grad_norm": 0.5803573727607727,
      "learning_rate": 5.3457539959202086e-05,
      "loss": 0.0515,
      "step": 409
    },
    {
      "epoch": 6.419354838709677,
      "grad_norm": 0.4359411597251892,
      "learning_rate": 5.300232569726804e-05,
      "loss": 0.0427,
      "step": 410
    },
    {
      "epoch": 6.435483870967742,
      "grad_norm": 0.4077586233615875,
      "learning_rate": 5.2548358001923204e-05,
      "loss": 0.0399,
      "step": 411
    },
    {
      "epoch": 6.451612903225806,
      "grad_norm": 0.3488485813140869,
      "learning_rate": 5.2095648914209525e-05,
      "loss": 0.0396,
      "step": 412
    },
    {
      "epoch": 6.467741935483871,
      "grad_norm": 0.39937523007392883,
      "learning_rate": 5.1644210441785467e-05,
      "loss": 0.039,
      "step": 413
    },
    {
      "epoch": 6.483870967741936,
      "grad_norm": 0.43873974680900574,
      "learning_rate": 5.119405455860772e-05,
      "loss": 0.0366,
      "step": 414
    },
    {
      "epoch": 6.5,
      "grad_norm": 0.356111079454422,
      "learning_rate": 5.074519320461357e-05,
      "loss": 0.0372,
      "step": 415
    },
    {
      "epoch": 6.516129032258064,
      "grad_norm": 0.42101165652275085,
      "learning_rate": 5.029763828540419e-05,
      "loss": 0.0411,
      "step": 416
    },
    {
      "epoch": 6.516129032258064,
      "eval_loss": 2.2114336490631104,
      "eval_runtime": 358.1731,
      "eval_samples_per_second": 2.959,
      "eval_steps_per_second": 0.494,
      "step": 416
    },
    {
      "epoch": 6.532258064516129,
      "grad_norm": 0.3797813653945923,
      "learning_rate": 4.9851401671928934e-05,
      "loss": 0.0431,
      "step": 417
    },
    {
      "epoch": 6.548387096774194,
      "grad_norm": 0.48072004318237305,
      "learning_rate": 4.940649520017035e-05,
      "loss": 0.0359,
      "step": 418
    },
    {
      "epoch": 6.564516129032258,
      "grad_norm": 0.38997748494148254,
      "learning_rate": 4.896293067083032e-05,
      "loss": 0.0386,
      "step": 419
    },
    {
      "epoch": 6.580645161290323,
      "grad_norm": 0.35900595784187317,
      "learning_rate": 4.852071984901696e-05,
      "loss": 0.0412,
      "step": 420
    },
    {
      "epoch": 6.596774193548387,
      "grad_norm": 0.3810931444168091,
      "learning_rate": 4.807987446393275e-05,
      "loss": 0.0356,
      "step": 421
    },
    {
      "epoch": 6.612903225806452,
      "grad_norm": 0.6008711457252502,
      "learning_rate": 4.7640406208563224e-05,
      "loss": 0.0433,
      "step": 422
    },
    {
      "epoch": 6.629032258064516,
      "grad_norm": 0.5079227685928345,
      "learning_rate": 4.720232673936706e-05,
      "loss": 0.0369,
      "step": 423
    },
    {
      "epoch": 6.645161290322581,
      "grad_norm": 0.3621387183666229,
      "learning_rate": 4.676564767596663e-05,
      "loss": 0.0373,
      "step": 424
    },
    {
      "epoch": 6.661290322580645,
      "grad_norm": 0.418442964553833,
      "learning_rate": 4.633038060083996e-05,
      "loss": 0.0445,
      "step": 425
    },
    {
      "epoch": 6.67741935483871,
      "grad_norm": 0.37667208909988403,
      "learning_rate": 4.5896537059013536e-05,
      "loss": 0.0368,
      "step": 426
    },
    {
      "epoch": 6.693548387096774,
      "grad_norm": 0.3964817523956299,
      "learning_rate": 4.546412855775595e-05,
      "loss": 0.0395,
      "step": 427
    },
    {
      "epoch": 6.709677419354839,
      "grad_norm": 0.3593597710132599,
      "learning_rate": 4.503316656627294e-05,
      "loss": 0.038,
      "step": 428
    },
    {
      "epoch": 6.725806451612903,
      "grad_norm": 0.6818132400512695,
      "learning_rate": 4.460366251540281e-05,
      "loss": 0.0504,
      "step": 429
    },
    {
      "epoch": 6.741935483870968,
      "grad_norm": 0.41429397463798523,
      "learning_rate": 4.417562779731355e-05,
      "loss": 0.0405,
      "step": 430
    },
    {
      "epoch": 6.758064516129032,
      "grad_norm": 0.5057131052017212,
      "learning_rate": 4.374907376520054e-05,
      "loss": 0.0395,
      "step": 431
    },
    {
      "epoch": 6.774193548387097,
      "grad_norm": 0.5655283331871033,
      "learning_rate": 4.3324011732985433e-05,
      "loss": 0.0446,
      "step": 432
    },
    {
      "epoch": 6.774193548387097,
      "eval_loss": 2.2080209255218506,
      "eval_runtime": 357.0367,
      "eval_samples_per_second": 2.969,
      "eval_steps_per_second": 0.496,
      "step": 432
    },
    {
      "epoch": 6.790322580645161,
      "grad_norm": 0.5865839719772339,
      "learning_rate": 4.2900452975016037e-05,
      "loss": 0.0479,
      "step": 433
    },
    {
      "epoch": 6.806451612903226,
      "grad_norm": 0.43115484714508057,
      "learning_rate": 4.247840872576739e-05,
      "loss": 0.0429,
      "step": 434
    }
  ],
  "logging_steps": 1,
  "max_steps": 620,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 62,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.1927216431929754e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}