{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.11090163025396474,
  "eval_steps": 375,
  "global_step": 375,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002957376806772393,
      "grad_norm": 5.918768405914307,
      "learning_rate": 2e-05,
      "loss": 1.3931,
      "step": 1
    },
    {
      "epoch": 0.0005914753613544786,
      "grad_norm": 6.164484024047852,
      "learning_rate": 4e-05,
      "loss": 1.5398,
      "step": 2
    },
    {
      "epoch": 0.0008872130420317178,
      "grad_norm": 5.500333309173584,
      "learning_rate": 6e-05,
      "loss": 1.4837,
      "step": 3
    },
    {
      "epoch": 0.0011829507227089572,
      "grad_norm": 6.977994441986084,
      "learning_rate": 8e-05,
      "loss": 1.5093,
      "step": 4
    },
    {
      "epoch": 0.0014786884033861965,
      "grad_norm": 10.189373016357422,
      "learning_rate": 0.0001,
      "loss": 1.3296,
      "step": 5
    },
    {
      "epoch": 0.0017744260840634356,
      "grad_norm": 8.993965148925781,
      "learning_rate": 0.00012,
      "loss": 0.9724,
      "step": 6
    },
    {
      "epoch": 0.002070163764740675,
      "grad_norm": 2.4879002571105957,
      "learning_rate": 0.00014,
      "loss": 0.6618,
      "step": 7
    },
    {
      "epoch": 0.0023659014454179145,
      "grad_norm": 3.1456634998321533,
      "learning_rate": 0.00016,
      "loss": 0.5917,
      "step": 8
    },
    {
      "epoch": 0.0026616391260951538,
      "grad_norm": 2.20988392829895,
      "learning_rate": 0.00018,
      "loss": 0.5093,
      "step": 9
    },
    {
      "epoch": 0.002957376806772393,
      "grad_norm": 1.189419150352478,
      "learning_rate": 0.0002,
      "loss": 0.5016,
      "step": 10
    },
    {
      "epoch": 0.003253114487449632,
      "grad_norm": 0.7363479733467102,
      "learning_rate": 0.00019999977772170748,
      "loss": 0.4919,
      "step": 11
    },
    {
      "epoch": 0.0035488521681268713,
      "grad_norm": 0.8657339215278625,
      "learning_rate": 0.00019999911088781805,
      "loss": 0.5377,
      "step": 12
    },
    {
      "epoch": 0.0038445898488041106,
      "grad_norm": 0.5705428123474121,
      "learning_rate": 0.0001999979995012962,
      "loss": 0.5056,
      "step": 13
    },
    {
      "epoch": 0.00414032752948135,
      "grad_norm": 0.6129299402236938,
      "learning_rate": 0.00019999644356708261,
      "loss": 0.4554,
      "step": 14
    },
    {
      "epoch": 0.00443606521015859,
      "grad_norm": 0.4173682928085327,
      "learning_rate": 0.00019999444309209432,
      "loss": 0.3437,
      "step": 15
    },
    {
      "epoch": 0.004731802890835829,
      "grad_norm": 0.39718082547187805,
      "learning_rate": 0.0001999919980852246,
      "loss": 0.5607,
      "step": 16
    },
    {
      "epoch": 0.005027540571513068,
      "grad_norm": 0.2396816462278366,
      "learning_rate": 0.00019998910855734288,
      "loss": 0.4337,
      "step": 17
    },
    {
      "epoch": 0.0053232782521903076,
      "grad_norm": 0.36948394775390625,
      "learning_rate": 0.0001999857745212947,
      "loss": 0.4386,
      "step": 18
    },
    {
      "epoch": 0.005619015932867547,
      "grad_norm": 0.4336908161640167,
      "learning_rate": 0.00019998199599190178,
      "loss": 0.4447,
      "step": 19
    },
    {
      "epoch": 0.005914753613544786,
      "grad_norm": 0.3717949390411377,
      "learning_rate": 0.0001999777729859618,
      "loss": 0.3468,
      "step": 20
    },
    {
      "epoch": 0.0062104912942220255,
      "grad_norm": 0.2210528403520584,
      "learning_rate": 0.00019997310552224846,
      "loss": 0.3254,
      "step": 21
    },
    {
      "epoch": 0.006506228974899264,
      "grad_norm": 0.373976469039917,
      "learning_rate": 0.00019996799362151122,
      "loss": 0.3819,
      "step": 22
    },
    {
      "epoch": 0.006801966655576503,
      "grad_norm": 0.4056873917579651,
      "learning_rate": 0.00019996243730647538,
      "loss": 0.395,
      "step": 23
    },
    {
      "epoch": 0.0070977043362537426,
      "grad_norm": 0.2301822304725647,
      "learning_rate": 0.00019995643660184191,
      "loss": 0.4185,
      "step": 24
    },
    {
      "epoch": 0.007393442016930982,
      "grad_norm": 0.22644546627998352,
      "learning_rate": 0.00019994999153428737,
      "loss": 0.3096,
      "step": 25
    },
    {
      "epoch": 0.007689179697608221,
      "grad_norm": 0.3260557949542999,
      "learning_rate": 0.00019994310213246368,
      "loss": 0.3562,
      "step": 26
    },
    {
      "epoch": 0.007984917378285461,
      "grad_norm": 0.2493218034505844,
      "learning_rate": 0.00019993576842699816,
      "loss": 0.4506,
      "step": 27
    },
    {
      "epoch": 0.0082806550589627,
      "grad_norm": 0.21800749003887177,
      "learning_rate": 0.0001999279904504933,
      "loss": 0.3406,
      "step": 28
    },
    {
      "epoch": 0.00857639273963994,
      "grad_norm": 0.2646995186805725,
      "learning_rate": 0.00019991976823752653,
      "loss": 0.3676,
      "step": 29
    },
    {
      "epoch": 0.00887213042031718,
      "grad_norm": 0.2616923749446869,
      "learning_rate": 0.00019991110182465032,
      "loss": 0.3685,
      "step": 30
    },
    {
      "epoch": 0.009167868100994419,
      "grad_norm": 0.2577691078186035,
      "learning_rate": 0.00019990199125039174,
      "loss": 0.3006,
      "step": 31
    },
    {
      "epoch": 0.009463605781671658,
      "grad_norm": 0.26562878489494324,
      "learning_rate": 0.00019989243655525247,
      "loss": 0.3532,
      "step": 32
    },
    {
      "epoch": 0.009759343462348897,
      "grad_norm": 0.26207393407821655,
      "learning_rate": 0.00019988243778170853,
      "loss": 0.3386,
      "step": 33
    },
    {
      "epoch": 0.010055081143026137,
      "grad_norm": 0.2501125931739807,
      "learning_rate": 0.0001998719949742101,
      "loss": 0.2988,
      "step": 34
    },
    {
      "epoch": 0.010350818823703376,
      "grad_norm": 0.3094285726547241,
      "learning_rate": 0.0001998611081791814,
      "loss": 0.3979,
      "step": 35
    },
    {
      "epoch": 0.010646556504380615,
      "grad_norm": 0.2816741466522217,
      "learning_rate": 0.00019984977744502038,
      "loss": 0.3338,
      "step": 36
    },
    {
      "epoch": 0.010942294185057854,
      "grad_norm": 0.33405667543411255,
      "learning_rate": 0.00019983800282209857,
      "loss": 0.4424,
      "step": 37
    },
    {
      "epoch": 0.011238031865735094,
      "grad_norm": 0.26445043087005615,
      "learning_rate": 0.00019982578436276082,
      "loss": 0.3255,
      "step": 38
    },
    {
      "epoch": 0.011533769546412333,
      "grad_norm": 0.2719035744667053,
      "learning_rate": 0.00019981312212132512,
      "loss": 0.3665,
      "step": 39
    },
    {
      "epoch": 0.011829507227089572,
      "grad_norm": 0.41192904114723206,
      "learning_rate": 0.00019980001615408228,
      "loss": 0.3978,
      "step": 40
    },
    {
      "epoch": 0.012125244907766812,
      "grad_norm": 0.30053630471229553,
      "learning_rate": 0.00019978646651929572,
      "loss": 0.3416,
      "step": 41
    },
    {
      "epoch": 0.012420982588444051,
      "grad_norm": 0.32080647349357605,
      "learning_rate": 0.00019977247327720128,
      "loss": 0.3517,
      "step": 42
    },
    {
      "epoch": 0.012716720269121289,
      "grad_norm": 0.3234342038631439,
      "learning_rate": 0.0001997580364900068,
      "loss": 0.2878,
      "step": 43
    },
    {
      "epoch": 0.013012457949798528,
      "grad_norm": 0.33844128251075745,
      "learning_rate": 0.000199743156221892,
      "loss": 0.2822,
      "step": 44
    },
    {
      "epoch": 0.013308195630475767,
      "grad_norm": 0.36423033475875854,
      "learning_rate": 0.00019972783253900808,
      "loss": 0.3715,
      "step": 45
    },
    {
      "epoch": 0.013603933311153006,
      "grad_norm": 0.34381452202796936,
      "learning_rate": 0.00019971206550947748,
      "loss": 0.3983,
      "step": 46
    },
    {
      "epoch": 0.013899670991830246,
      "grad_norm": 0.3789922595024109,
      "learning_rate": 0.00019969585520339354,
      "loss": 0.2693,
      "step": 47
    },
    {
      "epoch": 0.014195408672507485,
      "grad_norm": 0.4301562011241913,
      "learning_rate": 0.0001996792016928203,
      "loss": 0.3752,
      "step": 48
    },
    {
      "epoch": 0.014491146353184724,
      "grad_norm": 0.4085782766342163,
      "learning_rate": 0.00019966210505179197,
      "loss": 0.3779,
      "step": 49
    },
    {
      "epoch": 0.014786884033861964,
      "grad_norm": 0.7027013897895813,
      "learning_rate": 0.00019964456535631286,
      "loss": 0.4713,
      "step": 50
    },
    {
      "epoch": 0.015082621714539203,
      "grad_norm": 0.12943406403064728,
      "learning_rate": 0.0001996265826843568,
      "loss": 0.1727,
      "step": 51
    },
    {
      "epoch": 0.015378359395216442,
      "grad_norm": 0.20666781067848206,
      "learning_rate": 0.00019960815711586696,
      "loss": 0.2999,
      "step": 52
    },
    {
      "epoch": 0.01567409707589368,
      "grad_norm": 0.18581970036029816,
      "learning_rate": 0.00019958928873275539,
      "loss": 0.3003,
      "step": 53
    },
    {
      "epoch": 0.015969834756570923,
      "grad_norm": 0.1757449209690094,
      "learning_rate": 0.00019956997761890277,
      "loss": 0.2614,
      "step": 54
    },
    {
      "epoch": 0.01626557243724816,
      "grad_norm": 0.1774774044752121,
      "learning_rate": 0.00019955022386015792,
      "loss": 0.3129,
      "step": 55
    },
    {
      "epoch": 0.0165613101179254,
      "grad_norm": 0.17331115901470184,
      "learning_rate": 0.00019953002754433743,
      "loss": 0.3113,
      "step": 56
    },
    {
      "epoch": 0.01685704779860264,
      "grad_norm": 0.18873649835586548,
      "learning_rate": 0.00019950938876122542,
      "loss": 0.2683,
      "step": 57
    },
    {
      "epoch": 0.01715278547927988,
      "grad_norm": 0.15520928800106049,
      "learning_rate": 0.00019948830760257291,
      "loss": 0.2173,
      "step": 58
    },
    {
      "epoch": 0.017448523159957118,
      "grad_norm": 0.14979037642478943,
      "learning_rate": 0.0001994667841620976,
      "loss": 0.23,
      "step": 59
    },
    {
      "epoch": 0.01774426084063436,
      "grad_norm": 0.15720731019973755,
      "learning_rate": 0.00019944481853548335,
      "loss": 0.2606,
      "step": 60
    },
    {
      "epoch": 0.018039998521311596,
      "grad_norm": 0.18836985528469086,
      "learning_rate": 0.00019942241082037982,
      "loss": 0.34,
      "step": 61
    },
    {
      "epoch": 0.018335736201988837,
      "grad_norm": 0.17339695990085602,
      "learning_rate": 0.00019939956111640197,
      "loss": 0.2927,
      "step": 62
    },
    {
      "epoch": 0.018631473882666075,
      "grad_norm": 0.16999205946922302,
      "learning_rate": 0.00019937626952512964,
      "loss": 0.2591,
      "step": 63
    },
    {
      "epoch": 0.018927211563343316,
      "grad_norm": 0.1601104885339737,
      "learning_rate": 0.0001993525361501072,
      "loss": 0.2929,
      "step": 64
    },
    {
      "epoch": 0.019222949244020553,
      "grad_norm": 0.17350880801677704,
      "learning_rate": 0.00019932836109684286,
      "loss": 0.2854,
      "step": 65
    },
    {
      "epoch": 0.019518686924697794,
      "grad_norm": 0.18091264367103577,
      "learning_rate": 0.00019930374447280845,
      "loss": 0.2839,
      "step": 66
    },
    {
      "epoch": 0.019814424605375032,
      "grad_norm": 0.1761292666196823,
      "learning_rate": 0.00019927868638743875,
      "loss": 0.2545,
      "step": 67
    },
    {
      "epoch": 0.020110162286052273,
      "grad_norm": 0.18896149098873138,
      "learning_rate": 0.0001992531869521312,
      "loss": 0.2782,
      "step": 68
    },
    {
      "epoch": 0.02040589996672951,
      "grad_norm": 0.1839849352836609,
      "learning_rate": 0.00019922724628024515,
      "loss": 0.2596,
      "step": 69
    },
    {
      "epoch": 0.02070163764740675,
      "grad_norm": 0.18426676094532013,
      "learning_rate": 0.0001992008644871016,
      "loss": 0.2921,
      "step": 70
    },
    {
      "epoch": 0.02099737532808399,
      "grad_norm": 0.23805294930934906,
      "learning_rate": 0.00019917404168998256,
      "loss": 0.3308,
      "step": 71
    },
    {
      "epoch": 0.02129311300876123,
      "grad_norm": 0.18368969857692719,
      "learning_rate": 0.0001991467780081305,
      "loss": 0.3328,
      "step": 72
    },
    {
      "epoch": 0.021588850689438468,
      "grad_norm": 0.20601886510849,
      "learning_rate": 0.00019911907356274795,
      "loss": 0.3049,
      "step": 73
    },
    {
      "epoch": 0.02188458837011571,
      "grad_norm": 0.21643660962581635,
      "learning_rate": 0.00019909092847699683,
      "loss": 0.3097,
      "step": 74
    },
    {
      "epoch": 0.022180326050792946,
      "grad_norm": 0.1990053504705429,
      "learning_rate": 0.00019906234287599798,
      "loss": 0.3245,
      "step": 75
    },
    {
      "epoch": 0.022476063731470187,
      "grad_norm": 0.18081244826316833,
      "learning_rate": 0.00019903331688683057,
      "loss": 0.2234,
      "step": 76
    },
    {
      "epoch": 0.022771801412147425,
      "grad_norm": 0.19501319527626038,
      "learning_rate": 0.00019900385063853154,
      "loss": 0.2852,
      "step": 77
    },
    {
      "epoch": 0.023067539092824666,
      "grad_norm": 0.19676417112350464,
      "learning_rate": 0.00019897394426209505,
      "loss": 0.1825,
      "step": 78
    },
    {
      "epoch": 0.023363276773501904,
      "grad_norm": 0.22049355506896973,
      "learning_rate": 0.00019894359789047187,
      "loss": 0.2708,
      "step": 79
    },
    {
      "epoch": 0.023659014454179145,
      "grad_norm": 0.24137771129608154,
      "learning_rate": 0.00019891281165856873,
      "loss": 0.317,
      "step": 80
    },
    {
      "epoch": 0.023954752134856382,
      "grad_norm": 0.2464693933725357,
      "learning_rate": 0.00019888158570324795,
      "loss": 0.281,
      "step": 81
    },
    {
      "epoch": 0.024250489815533623,
      "grad_norm": 0.2559899091720581,
      "learning_rate": 0.0001988499201633265,
      "loss": 0.2977,
      "step": 82
    },
    {
      "epoch": 0.02454622749621086,
      "grad_norm": 0.23781578242778778,
      "learning_rate": 0.00019881781517957562,
      "loss": 0.2156,
      "step": 83
    },
    {
      "epoch": 0.024841965176888102,
      "grad_norm": 0.25769996643066406,
      "learning_rate": 0.0001987852708947202,
      "loss": 0.2588,
      "step": 84
    },
    {
      "epoch": 0.02513770285756534,
      "grad_norm": 0.24173754453659058,
      "learning_rate": 0.00019875228745343794,
      "loss": 0.2689,
      "step": 85
    },
    {
      "epoch": 0.025433440538242577,
      "grad_norm": 0.23814626038074493,
      "learning_rate": 0.0001987188650023589,
      "loss": 0.2404,
      "step": 86
    },
    {
      "epoch": 0.025729178218919818,
      "grad_norm": 0.2124136984348297,
      "learning_rate": 0.0001986850036900648,
      "loss": 0.2472,
      "step": 87
    },
    {
      "epoch": 0.026024915899597056,
      "grad_norm": 0.24799956381320953,
      "learning_rate": 0.00019865070366708836,
      "loss": 0.2429,
      "step": 88
    },
    {
      "epoch": 0.026320653580274297,
      "grad_norm": 0.2826499938964844,
      "learning_rate": 0.00019861596508591255,
      "loss": 0.2906,
      "step": 89
    },
    {
      "epoch": 0.026616391260951534,
      "grad_norm": 0.25857439637184143,
      "learning_rate": 0.00019858078810097002,
      "loss": 0.2139,
      "step": 90
    },
    {
      "epoch": 0.026912128941628775,
      "grad_norm": 0.25622865557670593,
      "learning_rate": 0.00019854517286864245,
      "loss": 0.266,
      "step": 91
    },
    {
      "epoch": 0.027207866622306013,
      "grad_norm": 0.2770698368549347,
      "learning_rate": 0.0001985091195472596,
      "loss": 0.254,
      "step": 92
    },
    {
      "epoch": 0.027503604302983254,
      "grad_norm": 0.31867358088493347,
      "learning_rate": 0.0001984726282970989,
      "loss": 0.2851,
      "step": 93
    },
    {
      "epoch": 0.02779934198366049,
      "grad_norm": 0.35994890332221985,
      "learning_rate": 0.0001984356992803847,
      "loss": 0.321,
      "step": 94
    },
    {
      "epoch": 0.028095079664337733,
      "grad_norm": 0.337107390165329,
      "learning_rate": 0.00019839833266128724,
      "loss": 0.2248,
      "step": 95
    },
    {
      "epoch": 0.02839081734501497,
      "grad_norm": 0.34881696105003357,
      "learning_rate": 0.00019836052860592237,
      "loss": 0.2786,
      "step": 96
    },
    {
      "epoch": 0.02868655502569221,
      "grad_norm": 0.3969687521457672,
      "learning_rate": 0.0001983222872823505,
      "loss": 0.3405,
      "step": 97
    },
    {
      "epoch": 0.02898229270636945,
      "grad_norm": 0.38202965259552,
      "learning_rate": 0.00019828360886057594,
      "loss": 0.275,
      "step": 98
    },
    {
      "epoch": 0.02927803038704669,
      "grad_norm": 0.4236074686050415,
      "learning_rate": 0.00019824449351254616,
      "loss": 0.2973,
      "step": 99
    },
    {
      "epoch": 0.029573768067723927,
      "grad_norm": 0.6627792716026306,
      "learning_rate": 0.00019820494141215104,
      "loss": 0.3571,
      "step": 100
    },
    {
      "epoch": 0.02986950574840117,
      "grad_norm": 0.14578954875469208,
      "learning_rate": 0.000198164952735222,
      "loss": 0.1857,
      "step": 101
    },
    {
      "epoch": 0.030165243429078406,
      "grad_norm": 0.1730443388223648,
      "learning_rate": 0.00019812452765953135,
      "loss": 0.2189,
      "step": 102
    },
    {
      "epoch": 0.030460981109755647,
      "grad_norm": 0.20889230072498322,
      "learning_rate": 0.00019808366636479147,
      "loss": 0.264,
      "step": 103
    },
    {
      "epoch": 0.030756718790432885,
      "grad_norm": 0.19660377502441406,
      "learning_rate": 0.00019804236903265388,
      "loss": 0.3058,
      "step": 104
    },
    {
      "epoch": 0.031052456471110126,
      "grad_norm": 0.16153180599212646,
      "learning_rate": 0.00019800063584670863,
      "loss": 0.2465,
      "step": 105
    },
    {
      "epoch": 0.03134819415178736,
      "grad_norm": 0.17819426953792572,
      "learning_rate": 0.00019795846699248332,
      "loss": 0.2406,
      "step": 106
    },
    {
      "epoch": 0.031643931832464604,
      "grad_norm": 0.16484011709690094,
      "learning_rate": 0.00019791586265744237,
      "loss": 0.211,
      "step": 107
    },
    {
      "epoch": 0.031939669513141845,
      "grad_norm": 0.19172953069210052,
      "learning_rate": 0.00019787282303098617,
      "loss": 0.2686,
      "step": 108
    },
    {
      "epoch": 0.03223540719381908,
      "grad_norm": 0.17775307595729828,
      "learning_rate": 0.0001978293483044502,
      "loss": 0.2464,
      "step": 109
    },
    {
      "epoch": 0.03253114487449632,
      "grad_norm": 0.17548003792762756,
      "learning_rate": 0.00019778543867110426,
      "loss": 0.2489,
      "step": 110
    },
    {
      "epoch": 0.03282688255517356,
      "grad_norm": 0.17837557196617126,
      "learning_rate": 0.00019774109432615147,
      "loss": 0.2305,
      "step": 111
    },
    {
      "epoch": 0.0331226202358508,
      "grad_norm": 0.21005579829216003,
      "learning_rate": 0.00019769631546672756,
      "loss": 0.3109,
      "step": 112
    },
    {
      "epoch": 0.03341835791652804,
      "grad_norm": 0.1606261134147644,
      "learning_rate": 0.00019765110229189988,
      "loss": 0.2297,
      "step": 113
    },
    {
      "epoch": 0.03371409559720528,
      "grad_norm": 0.16127589344978333,
      "learning_rate": 0.00019760545500266657,
      "loss": 0.2121,
      "step": 114
    },
    {
      "epoch": 0.03400983327788252,
      "grad_norm": 0.18138477206230164,
      "learning_rate": 0.00019755937380195568,
      "loss": 0.2556,
      "step": 115
    },
    {
      "epoch": 0.03430557095855976,
      "grad_norm": 0.19160465896129608,
      "learning_rate": 0.00019751285889462423,
      "loss": 0.2534,
      "step": 116
    },
    {
      "epoch": 0.034601308639236994,
      "grad_norm": 0.19009210169315338,
      "learning_rate": 0.0001974659104874573,
      "loss": 0.2289,
      "step": 117
    },
    {
      "epoch": 0.034897046319914235,
      "grad_norm": 0.1938568651676178,
      "learning_rate": 0.0001974185287891671,
      "loss": 0.2483,
      "step": 118
    },
    {
      "epoch": 0.035192784000591476,
      "grad_norm": 0.19120760262012482,
      "learning_rate": 0.0001973707140103921,
      "loss": 0.2522,
      "step": 119
    },
    {
      "epoch": 0.03548852168126872,
      "grad_norm": 0.20597144961357117,
      "learning_rate": 0.00019732246636369605,
      "loss": 0.2776,
      "step": 120
    },
    {
      "epoch": 0.03578425936194595,
      "grad_norm": 0.19169169664382935,
      "learning_rate": 0.00019727378606356703,
      "loss": 0.2821,
      "step": 121
    },
    {
      "epoch": 0.03607999704262319,
      "grad_norm": 0.24905505776405334,
      "learning_rate": 0.00019722467332641656,
      "loss": 0.3392,
      "step": 122
    },
    {
      "epoch": 0.03637573472330043,
      "grad_norm": 0.21315141022205353,
      "learning_rate": 0.00019717512837057855,
      "loss": 0.2514,
      "step": 123
    },
    {
      "epoch": 0.036671472403977674,
      "grad_norm": 0.20183053612709045,
      "learning_rate": 0.0001971251514163083,
      "loss": 0.2522,
      "step": 124
    },
    {
      "epoch": 0.03696721008465491,
      "grad_norm": 0.21825973689556122,
      "learning_rate": 0.0001970747426857817,
      "loss": 0.2249,
      "step": 125
    },
    {
      "epoch": 0.03726294776533215,
      "grad_norm": 0.19961951673030853,
      "learning_rate": 0.00019702390240309404,
      "loss": 0.2081,
      "step": 126
    },
    {
      "epoch": 0.03755868544600939,
      "grad_norm": 0.24127651751041412,
      "learning_rate": 0.0001969726307942592,
      "loss": 0.2543,
      "step": 127
    },
    {
      "epoch": 0.03785442312668663,
      "grad_norm": 0.18847639858722687,
      "learning_rate": 0.00019692092808720846,
      "loss": 0.1804,
      "step": 128
    },
    {
      "epoch": 0.038150160807363866,
      "grad_norm": 0.2245255559682846,
      "learning_rate": 0.0001968687945117896,
      "loss": 0.2615,
      "step": 129
    },
    {
      "epoch": 0.03844589848804111,
      "grad_norm": 0.2330857813358307,
      "learning_rate": 0.00019681623029976588,
      "loss": 0.24,
      "step": 130
    },
    {
      "epoch": 0.03874163616871835,
      "grad_norm": 0.2308180183172226,
      "learning_rate": 0.00019676323568481498,
      "loss": 0.2735,
      "step": 131
    },
    {
      "epoch": 0.03903737384939559,
      "grad_norm": 0.23675177991390228,
      "learning_rate": 0.00019670981090252792,
      "loss": 0.273,
      "step": 132
    },
    {
      "epoch": 0.03933311153007282,
      "grad_norm": 0.2156166285276413,
      "learning_rate": 0.00019665595619040808,
      "loss": 0.2038,
      "step": 133
    },
    {
      "epoch": 0.039628849210750064,
      "grad_norm": 0.22249513864517212,
      "learning_rate": 0.0001966016717878702,
      "loss": 0.2396,
      "step": 134
    },
    {
      "epoch": 0.039924586891427305,
      "grad_norm": 0.25741225481033325,
      "learning_rate": 0.00019654695793623907,
      "loss": 0.2921,
      "step": 135
    },
    {
      "epoch": 0.040220324572104546,
      "grad_norm": 0.25070619583129883,
      "learning_rate": 0.0001964918148787488,
      "loss": 0.2107,
      "step": 136
    },
    {
      "epoch": 0.04051606225278178,
      "grad_norm": 0.2761012017726898,
      "learning_rate": 0.00019643624286054144,
      "loss": 0.2443,
      "step": 137
    },
    {
      "epoch": 0.04081179993345902,
      "grad_norm": 0.22816140949726105,
      "learning_rate": 0.00019638024212866606,
      "loss": 0.1939,
      "step": 138
    },
    {
      "epoch": 0.04110753761413626,
      "grad_norm": 0.2465653121471405,
      "learning_rate": 0.0001963238129320776,
      "loss": 0.2535,
      "step": 139
    },
    {
      "epoch": 0.0414032752948135,
      "grad_norm": 0.38914790749549866,
      "learning_rate": 0.00019626695552163578,
      "loss": 0.3959,
      "step": 140
    },
    {
      "epoch": 0.04169901297549074,
      "grad_norm": 0.2719482481479645,
      "learning_rate": 0.00019620967015010395,
      "loss": 0.273,
      "step": 141
    },
    {
      "epoch": 0.04199475065616798,
      "grad_norm": 0.26919126510620117,
      "learning_rate": 0.00019615195707214803,
      "loss": 0.2197,
      "step": 142
    },
    {
      "epoch": 0.04229048833684522,
      "grad_norm": 0.2746446132659912,
      "learning_rate": 0.0001960938165443353,
      "loss": 0.251,
      "step": 143
    },
    {
      "epoch": 0.04258622601752246,
      "grad_norm": 0.31786006689071655,
      "learning_rate": 0.00019603524882513327,
      "loss": 0.2585,
      "step": 144
    },
    {
      "epoch": 0.042881963698199695,
      "grad_norm": 0.3586949110031128,
      "learning_rate": 0.0001959762541749086,
      "loss": 0.2868,
      "step": 145
    },
    {
      "epoch": 0.043177701378876936,
      "grad_norm": 0.3204839527606964,
      "learning_rate": 0.00019591683285592593,
      "loss": 0.2449,
      "step": 146
    },
    {
      "epoch": 0.04347343905955418,
      "grad_norm": 0.3199440836906433,
      "learning_rate": 0.00019585698513234663,
      "loss": 0.238,
      "step": 147
    },
    {
      "epoch": 0.04376917674023142,
      "grad_norm": 0.460660457611084,
      "learning_rate": 0.0001957967112702277,
      "loss": 0.2707,
      "step": 148
    },
    {
      "epoch": 0.04406491442090865,
      "grad_norm": 0.3981362581253052,
      "learning_rate": 0.00019573601153752052,
      "loss": 0.2259,
      "step": 149
    },
    {
      "epoch": 0.04436065210158589,
      "grad_norm": 0.5862023234367371,
      "learning_rate": 0.00019567488620406983,
      "loss": 0.3031,
      "step": 150
    },
    {
      "epoch": 0.044656389782263134,
      "grad_norm": 0.14805294573307037,
      "learning_rate": 0.00019561333554161224,
      "loss": 0.1515,
      "step": 151
    },
    {
      "epoch": 0.044952127462940375,
      "grad_norm": 0.2211844027042389,
      "learning_rate": 0.0001955513598237753,
      "loss": 0.2199,
      "step": 152
    },
    {
      "epoch": 0.04524786514361761,
      "grad_norm": 0.20431561768054962,
      "learning_rate": 0.00019548895932607621,
      "loss": 0.2077,
      "step": 153
    },
    {
      "epoch": 0.04554360282429485,
      "grad_norm": 0.1585177332162857,
      "learning_rate": 0.00019542613432592038,
      "loss": 0.1702,
      "step": 154
    },
    {
      "epoch": 0.04583934050497209,
      "grad_norm": 0.21959953010082245,
      "learning_rate": 0.00019536288510260056,
      "loss": 0.3018,
      "step": 155
    },
    {
      "epoch": 0.04613507818564933,
      "grad_norm": 0.18285472691059113,
      "learning_rate": 0.00019529921193729534,
      "loss": 0.2621,
      "step": 156
    },
    {
      "epoch": 0.046430815866326566,
      "grad_norm": 0.19817829132080078,
      "learning_rate": 0.00019523511511306793,
      "loss": 0.2542,
      "step": 157
    },
    {
      "epoch": 0.04672655354700381,
      "grad_norm": 0.2109287828207016,
      "learning_rate": 0.000195170594914865,
      "loss": 0.2398,
      "step": 158
    },
    {
      "epoch": 0.04702229122768105,
      "grad_norm": 0.20559227466583252,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.2302,
      "step": 159
    },
    {
      "epoch": 0.04731802890835829,
      "grad_norm": 0.2374628186225891,
      "learning_rate": 0.00019504028554572864,
      "loss": 0.2729,
      "step": 160
    },
    {
      "epoch": 0.047613766589035524,
      "grad_norm": 0.17768986523151398,
      "learning_rate": 0.00019497449695409408,
      "loss": 0.2692,
      "step": 161
    },
    {
      "epoch": 0.047909504269712765,
      "grad_norm": 0.1690852791070938,
      "learning_rate": 0.00019490828614707916,
      "loss": 0.2147,
      "step": 162
    },
    {
      "epoch": 0.048205241950390006,
      "grad_norm": 0.20444796979427338,
      "learning_rate": 0.00019484165341902845,
      "loss": 0.2317,
      "step": 163
    },
    {
      "epoch": 0.04850097963106725,
      "grad_norm": 0.2058713436126709,
      "learning_rate": 0.00019477459906616206,
      "loss": 0.1968,
      "step": 164
    },
    {
      "epoch": 0.04879671731174448,
      "grad_norm": 0.20283836126327515,
      "learning_rate": 0.00019470712338657458,
      "loss": 0.2275,
      "step": 165
    },
    {
      "epoch": 0.04909245499242172,
      "grad_norm": 0.18474236130714417,
      "learning_rate": 0.0001946392266802336,
      "loss": 0.2602,
      "step": 166
    },
    {
      "epoch": 0.04938819267309896,
      "grad_norm": 0.17107436060905457,
      "learning_rate": 0.0001945709092489783,
      "loss": 0.2182,
      "step": 167
    },
    {
      "epoch": 0.049683930353776204,
      "grad_norm": 0.18627148866653442,
      "learning_rate": 0.00019450217139651844,
      "loss": 0.1782,
      "step": 168
    },
    {
      "epoch": 0.04997966803445344,
      "grad_norm": 0.19079387187957764,
      "learning_rate": 0.0001944330134284326,
      "loss": 0.2239,
      "step": 169
    },
    {
      "epoch": 0.05027540571513068,
      "grad_norm": 0.22388561069965363,
      "learning_rate": 0.00019436343565216711,
      "loss": 0.2257,
      "step": 170
    },
    {
      "epoch": 0.05057114339580792,
      "grad_norm": 0.20720115303993225,
      "learning_rate": 0.00019429343837703455,
      "loss": 0.2546,
      "step": 171
    },
    {
      "epoch": 0.050866881076485154,
      "grad_norm": 0.19800806045532227,
      "learning_rate": 0.0001942230219142124,
      "loss": 0.1958,
      "step": 172
    },
    {
      "epoch": 0.051162618757162395,
      "grad_norm": 0.22758133709430695,
      "learning_rate": 0.0001941521865767417,
      "loss": 0.2499,
      "step": 173
    },
    {
      "epoch": 0.051458356437839636,
      "grad_norm": 0.20841172337532043,
      "learning_rate": 0.0001940809326795256,
      "loss": 0.2369,
      "step": 174
    },
    {
      "epoch": 0.05175409411851688,
      "grad_norm": 0.20555779337882996,
      "learning_rate": 0.000194009260539328,
      "loss": 0.2435,
      "step": 175
    },
    {
      "epoch": 0.05204983179919411,
      "grad_norm": 0.2264283448457718,
      "learning_rate": 0.0001939371704747721,
      "loss": 0.2603,
      "step": 176
    },
    {
      "epoch": 0.05234556947987135,
      "grad_norm": 0.22826440632343292,
      "learning_rate": 0.00019386466280633906,
      "loss": 0.2574,
      "step": 177
    },
    {
      "epoch": 0.052641307160548594,
      "grad_norm": 0.2327851504087448,
      "learning_rate": 0.00019379173785636646,
      "loss": 0.2125,
      "step": 178
    },
    {
      "epoch": 0.052937044841225835,
      "grad_norm": 0.25769078731536865,
      "learning_rate": 0.000193718395949047,
      "loss": 0.2594,
      "step": 179
    },
    {
      "epoch": 0.05323278252190307,
      "grad_norm": 0.24143129587173462,
      "learning_rate": 0.00019364463741042694,
      "loss": 0.2285,
      "step": 180
    },
    {
      "epoch": 0.05352852020258031,
      "grad_norm": 0.21483063697814941,
      "learning_rate": 0.00019357046256840473,
      "loss": 0.1883,
      "step": 181
    },
    {
      "epoch": 0.05382425788325755,
      "grad_norm": 0.2387738972902298,
      "learning_rate": 0.00019349587175272948,
      "loss": 0.2697,
      "step": 182
    },
    {
      "epoch": 0.05411999556393479,
      "grad_norm": 0.2653301954269409,
      "learning_rate": 0.0001934208652949996,
      "loss": 0.2403,
      "step": 183
    },
    {
      "epoch": 0.054415733244612026,
      "grad_norm": 0.28791022300720215,
      "learning_rate": 0.00019334544352866127,
      "loss": 0.268,
      "step": 184
    },
    {
      "epoch": 0.05471147092528927,
      "grad_norm": 0.2307739108800888,
      "learning_rate": 0.00019326960678900688,
      "loss": 0.2088,
      "step": 185
    },
    {
      "epoch": 0.05500720860596651,
      "grad_norm": 0.2275734543800354,
      "learning_rate": 0.00019319335541317361,
      "loss": 0.1935,
      "step": 186
    },
    {
      "epoch": 0.05530294628664375,
      "grad_norm": 0.23581242561340332,
      "learning_rate": 0.00019311668974014208,
      "loss": 0.2037,
      "step": 187
    },
    {
      "epoch": 0.05559868396732098,
      "grad_norm": 0.25955161452293396,
      "learning_rate": 0.00019303961011073447,
      "loss": 0.2216,
      "step": 188
    },
    {
      "epoch": 0.055894421647998224,
      "grad_norm": 0.262517511844635,
      "learning_rate": 0.00019296211686761346,
      "loss": 0.2143,
      "step": 189
    },
    {
      "epoch": 0.056190159328675465,
      "grad_norm": 0.3077569305896759,
      "learning_rate": 0.00019288421035528028,
      "loss": 0.2356,
      "step": 190
    },
    {
      "epoch": 0.056485897009352706,
      "grad_norm": 0.26791897416114807,
      "learning_rate": 0.00019280589092007352,
      "loss": 0.1884,
      "step": 191
    },
    {
      "epoch": 0.05678163469002994,
      "grad_norm": 0.27822402119636536,
      "learning_rate": 0.00019272715891016735,
      "loss": 0.2118,
      "step": 192
    },
    {
      "epoch": 0.05707737237070718,
      "grad_norm": 0.2592899203300476,
      "learning_rate": 0.00019264801467557007,
      "loss": 0.1402,
      "step": 193
    },
    {
      "epoch": 0.05737311005138442,
      "grad_norm": 0.37037453055381775,
      "learning_rate": 0.00019256845856812266,
      "loss": 0.3472,
      "step": 194
    },
    {
      "epoch": 0.057668847732061664,
      "grad_norm": 0.30506840348243713,
      "learning_rate": 0.000192488490941497,
      "loss": 0.1907,
      "step": 195
    },
    {
      "epoch": 0.0579645854127389,
      "grad_norm": 0.3820033669471741,
      "learning_rate": 0.00019240811215119448,
      "loss": 0.2557,
      "step": 196
    },
    {
      "epoch": 0.05826032309341614,
      "grad_norm": 0.40331634879112244,
      "learning_rate": 0.00019232732255454422,
      "loss": 0.2579,
      "step": 197
    },
    {
      "epoch": 0.05855606077409338,
      "grad_norm": 0.4118432104587555,
      "learning_rate": 0.00019224612251070175,
      "loss": 0.2316,
      "step": 198
    },
    {
      "epoch": 0.05885179845477062,
      "grad_norm": 0.4977587163448334,
      "learning_rate": 0.0001921645123806472,
      "loss": 0.2964,
      "step": 199
    },
    {
      "epoch": 0.059147536135447855,
      "grad_norm": 0.5816993713378906,
      "learning_rate": 0.0001920824925271838,
      "loss": 0.2308,
      "step": 200
    },
    {
      "epoch": 0.059443273816125096,
      "grad_norm": 0.1586022526025772,
      "learning_rate": 0.0001920000633149362,
      "loss": 0.1695,
      "step": 201
    },
    {
      "epoch": 0.05973901149680234,
      "grad_norm": 0.17268988490104675,
      "learning_rate": 0.00019191722511034884,
      "loss": 0.1737,
      "step": 202
    },
    {
      "epoch": 0.06003474917747958,
      "grad_norm": 0.17306619882583618,
      "learning_rate": 0.00019183397828168448,
      "loss": 0.1928,
      "step": 203
    },
    {
      "epoch": 0.06033048685815681,
      "grad_norm": 0.18508224189281464,
      "learning_rate": 0.00019175032319902234,
      "loss": 0.2293,
      "step": 204
    },
    {
      "epoch": 0.06062622453883405,
      "grad_norm": 0.15483330190181732,
      "learning_rate": 0.00019166626023425662,
      "loss": 0.1827,
      "step": 205
    },
    {
      "epoch": 0.060921962219511294,
      "grad_norm": 0.190659299492836,
      "learning_rate": 0.00019158178976109476,
      "loss": 0.2827,
      "step": 206
    },
    {
      "epoch": 0.061217699900188535,
      "grad_norm": 0.16438104212284088,
      "learning_rate": 0.0001914969121550558,
      "loss": 0.2186,
      "step": 207
    },
    {
      "epoch": 0.06151343758086577,
      "grad_norm": 0.17598582804203033,
      "learning_rate": 0.00019141162779346874,
      "loss": 0.1971,
      "step": 208
    },
    {
      "epoch": 0.06180917526154301,
      "grad_norm": 0.18765893578529358,
      "learning_rate": 0.00019132593705547082,
      "loss": 0.1996,
      "step": 209
    },
    {
      "epoch": 0.06210491294222025,
      "grad_norm": 0.21454760432243347,
      "learning_rate": 0.00019123984032200586,
      "loss": 0.2427,
      "step": 210
    },
    {
      "epoch": 0.06240065062289749,
      "grad_norm": 0.21339420974254608,
      "learning_rate": 0.00019115333797582254,
      "loss": 0.2539,
      "step": 211
    },
    {
      "epoch": 0.06269638830357473,
      "grad_norm": 0.18333065509796143,
      "learning_rate": 0.00019106643040147278,
      "loss": 0.2447,
      "step": 212
    },
    {
      "epoch": 0.06299212598425197,
      "grad_norm": 0.19549886882305145,
      "learning_rate": 0.00019097911798530987,
      "loss": 0.2451,
      "step": 213
    },
    {
      "epoch": 0.06328786366492921,
      "grad_norm": 0.19182579219341278,
      "learning_rate": 0.00019089140111548696,
      "loss": 0.2058,
      "step": 214
    },
    {
      "epoch": 0.06358360134560645,
      "grad_norm": 0.19501961767673492,
      "learning_rate": 0.00019080328018195513,
      "loss": 0.2365,
      "step": 215
    },
    {
      "epoch": 0.06387933902628369,
      "grad_norm": 0.19913062453269958,
      "learning_rate": 0.0001907147555764618,
      "loss": 0.2204,
      "step": 216
    },
    {
      "epoch": 0.06417507670696093,
      "grad_norm": 0.1938629001379013,
      "learning_rate": 0.00019062582769254895,
      "loss": 0.2554,
      "step": 217
    },
    {
      "epoch": 0.06447081438763816,
      "grad_norm": 0.20500774681568146,
      "learning_rate": 0.00019053649692555135,
      "loss": 0.2719,
      "step": 218
    },
    {
      "epoch": 0.0647665520683154,
      "grad_norm": 0.19601133465766907,
      "learning_rate": 0.00019044676367259476,
      "loss": 0.2176,
      "step": 219
    },
    {
      "epoch": 0.06506228974899264,
      "grad_norm": 0.21002735197544098,
      "learning_rate": 0.00019035662833259432,
      "loss": 0.2987,
      "step": 220
    },
    {
      "epoch": 0.06535802742966988,
      "grad_norm": 0.19716577231884003,
      "learning_rate": 0.00019026609130625257,
      "loss": 0.2103,
      "step": 221
    },
    {
      "epoch": 0.06565376511034712,
      "grad_norm": 0.20321358740329742,
      "learning_rate": 0.00019017515299605788,
      "loss": 0.2373,
      "step": 222
    },
    {
      "epoch": 0.06594950279102436,
      "grad_norm": 0.21129213273525238,
      "learning_rate": 0.00019008381380628247,
      "loss": 0.2284,
      "step": 223
    },
    {
      "epoch": 0.0662452404717016,
      "grad_norm": 0.20547550916671753,
      "learning_rate": 0.00018999207414298067,
      "loss": 0.2162,
      "step": 224
    },
    {
      "epoch": 0.06654097815237885,
      "grad_norm": 0.19809496402740479,
      "learning_rate": 0.00018989993441398726,
      "loss": 0.2176,
      "step": 225
    },
    {
      "epoch": 0.06683671583305607,
      "grad_norm": 0.23077711462974548,
      "learning_rate": 0.00018980739502891546,
      "loss": 0.2389,
      "step": 226
    },
    {
      "epoch": 0.06713245351373331,
      "grad_norm": 0.24560177326202393,
      "learning_rate": 0.0001897144563991552,
      "loss": 0.2347,
      "step": 227
    },
    {
      "epoch": 0.06742819119441056,
      "grad_norm": 0.24137191474437714,
      "learning_rate": 0.00018962111893787128,
      "loss": 0.2191,
      "step": 228
    },
    {
      "epoch": 0.0677239288750878,
      "grad_norm": 0.23104238510131836,
      "learning_rate": 0.00018952738306000151,
      "loss": 0.2207,
      "step": 229
    },
    {
      "epoch": 0.06801966655576504,
      "grad_norm": 0.22218018770217896,
      "learning_rate": 0.00018943324918225494,
      "loss": 0.21,
      "step": 230
    },
    {
      "epoch": 0.06831540423644228,
      "grad_norm": 0.21070846915245056,
      "learning_rate": 0.0001893387177231099,
      "loss": 0.165,
      "step": 231
    },
    {
      "epoch": 0.06861114191711952,
      "grad_norm": 0.2444663941860199,
      "learning_rate": 0.0001892437891028122,
      "loss": 0.2336,
      "step": 232
    },
    {
      "epoch": 0.06890687959779676,
      "grad_norm": 0.2369096875190735,
      "learning_rate": 0.0001891484637433733,
      "loss": 0.2232,
      "step": 233
    },
    {
      "epoch": 0.06920261727847399,
      "grad_norm": 0.2586706280708313,
      "learning_rate": 0.00018905274206856837,
      "loss": 0.2468,
      "step": 234
    },
    {
      "epoch": 0.06949835495915123,
      "grad_norm": 0.30194905400276184,
      "learning_rate": 0.00018895662450393438,
      "loss": 0.254,
      "step": 235
    },
    {
      "epoch": 0.06979409263982847,
      "grad_norm": 0.2761548161506653,
      "learning_rate": 0.00018886011147676833,
      "loss": 0.2953,
      "step": 236
    },
    {
      "epoch": 0.07008983032050571,
      "grad_norm": 0.23956750333309174,
      "learning_rate": 0.00018876320341612522,
      "loss": 0.2249,
      "step": 237
    },
    {
      "epoch": 0.07038556800118295,
      "grad_norm": 0.2570217549800873,
      "learning_rate": 0.00018866590075281624,
      "loss": 0.2153,
      "step": 238
    },
    {
      "epoch": 0.0706813056818602,
      "grad_norm": 0.2857867181301117,
      "learning_rate": 0.00018856820391940674,
      "loss": 0.3025,
      "step": 239
    },
    {
      "epoch": 0.07097704336253743,
      "grad_norm": 0.25232836604118347,
      "learning_rate": 0.00018847011335021449,
      "loss": 0.201,
      "step": 240
    },
    {
      "epoch": 0.07127278104321468,
      "grad_norm": 0.28288912773132324,
      "learning_rate": 0.00018837162948130752,
      "loss": 0.2385,
      "step": 241
    },
    {
      "epoch": 0.0715685187238919,
      "grad_norm": 0.3228309154510498,
      "learning_rate": 0.00018827275275050233,
      "loss": 0.2761,
      "step": 242
    },
    {
      "epoch": 0.07186425640456914,
      "grad_norm": 0.2894141972064972,
      "learning_rate": 0.00018817348359736203,
      "loss": 0.2615,
      "step": 243
    },
    {
      "epoch": 0.07215999408524638,
      "grad_norm": 0.3046562373638153,
      "learning_rate": 0.00018807382246319412,
      "loss": 0.237,
      "step": 244
    },
    {
      "epoch": 0.07245573176592363,
      "grad_norm": 0.3270159661769867,
      "learning_rate": 0.00018797376979104872,
      "loss": 0.209,
      "step": 245
    },
    {
      "epoch": 0.07275146944660087,
      "grad_norm": 0.2986398935317993,
      "learning_rate": 0.00018787332602571662,
      "loss": 0.2032,
      "step": 246
    },
    {
      "epoch": 0.07304720712727811,
      "grad_norm": 0.3203541040420532,
      "learning_rate": 0.00018777249161372713,
      "loss": 0.2154,
      "step": 247
    },
    {
      "epoch": 0.07334294480795535,
      "grad_norm": 0.3694257438182831,
      "learning_rate": 0.00018767126700334634,
      "loss": 0.1959,
      "step": 248
    },
    {
      "epoch": 0.07363868248863259,
      "grad_norm": 0.6173413991928101,
      "learning_rate": 0.0001875696526445749,
      "loss": 0.1682,
      "step": 249
    },
    {
      "epoch": 0.07393442016930982,
      "grad_norm": 0.5118496417999268,
      "learning_rate": 0.0001874676489891461,
      "loss": 0.276,
      "step": 250
    },
    {
      "epoch": 0.07423015784998706,
      "grad_norm": 0.15977254509925842,
      "learning_rate": 0.00018736525649052394,
      "loss": 0.2124,
      "step": 251
    },
    {
      "epoch": 0.0745258955306643,
      "grad_norm": 0.15199963748455048,
      "learning_rate": 0.00018726247560390099,
      "loss": 0.1718,
      "step": 252
    },
    {
      "epoch": 0.07482163321134154,
      "grad_norm": 0.16801315546035767,
      "learning_rate": 0.00018715930678619644,
      "loss": 0.1961,
      "step": 253
    },
    {
      "epoch": 0.07511737089201878,
      "grad_norm": 0.17173269391059875,
      "learning_rate": 0.00018705575049605413,
      "loss": 0.2053,
      "step": 254
    },
    {
      "epoch": 0.07541310857269602,
      "grad_norm": 0.19244447350502014,
      "learning_rate": 0.00018695180719384029,
      "loss": 0.2841,
      "step": 255
    },
    {
      "epoch": 0.07570884625337326,
      "grad_norm": 0.1731448471546173,
      "learning_rate": 0.00018684747734164177,
      "loss": 0.2246,
      "step": 256
    },
    {
      "epoch": 0.07600458393405049,
      "grad_norm": 0.1740599274635315,
      "learning_rate": 0.00018674276140326376,
      "loss": 0.229,
      "step": 257
    },
    {
      "epoch": 0.07630032161472773,
      "grad_norm": 0.15664459764957428,
      "learning_rate": 0.00018663765984422786,
      "loss": 0.2015,
      "step": 258
    },
    {
      "epoch": 0.07659605929540497,
      "grad_norm": 0.18093277513980865,
      "learning_rate": 0.00018653217313177004,
      "loss": 0.2371,
      "step": 259
    },
    {
      "epoch": 0.07689179697608221,
      "grad_norm": 0.15789927542209625,
      "learning_rate": 0.00018642630173483832,
      "loss": 0.19,
      "step": 260
    },
    {
      "epoch": 0.07718753465675945,
      "grad_norm": 0.1597701758146286,
      "learning_rate": 0.00018632004612409103,
      "loss": 0.2096,
      "step": 261
    },
    {
      "epoch": 0.0774832723374367,
      "grad_norm": 0.17183595895767212,
      "learning_rate": 0.00018621340677189453,
      "loss": 0.2333,
      "step": 262
    },
    {
      "epoch": 0.07777901001811394,
      "grad_norm": 0.17315109074115753,
      "learning_rate": 0.00018610638415232097,
      "loss": 0.2215,
      "step": 263
    },
    {
      "epoch": 0.07807474769879118,
      "grad_norm": 0.17420059442520142,
      "learning_rate": 0.00018599897874114652,
      "loss": 0.2216,
      "step": 264
    },
    {
      "epoch": 0.0783704853794684,
      "grad_norm": 0.19842545688152313,
      "learning_rate": 0.00018589119101584898,
      "loss": 0.212,
      "step": 265
    },
    {
      "epoch": 0.07866622306014565,
      "grad_norm": 0.18231399357318878,
      "learning_rate": 0.00018578302145560584,
      "loss": 0.2284,
      "step": 266
    },
    {
      "epoch": 0.07896196074082289,
      "grad_norm": 0.1868034154176712,
      "learning_rate": 0.00018567447054129195,
      "loss": 0.2458,
      "step": 267
    },
    {
      "epoch": 0.07925769842150013,
      "grad_norm": 0.19086702167987823,
      "learning_rate": 0.00018556553875547754,
      "loss": 0.2335,
      "step": 268
    },
    {
      "epoch": 0.07955343610217737,
      "grad_norm": 0.2202424705028534,
      "learning_rate": 0.00018545622658242607,
      "loss": 0.282,
      "step": 269
    },
    {
      "epoch": 0.07984917378285461,
      "grad_norm": 0.20102711021900177,
      "learning_rate": 0.00018534653450809197,
      "loss": 0.2376,
      "step": 270
    },
    {
      "epoch": 0.08014491146353185,
      "grad_norm": 0.2291051596403122,
      "learning_rate": 0.00018523646302011867,
      "loss": 0.2448,
      "step": 271
    },
    {
      "epoch": 0.08044064914420909,
      "grad_norm": 0.20590786635875702,
      "learning_rate": 0.00018512601260783606,
      "loss": 0.2235,
      "step": 272
    },
    {
      "epoch": 0.08073638682488632,
      "grad_norm": 0.18361449241638184,
      "learning_rate": 0.00018501518376225887,
      "loss": 0.1882,
      "step": 273
    },
    {
      "epoch": 0.08103212450556356,
      "grad_norm": 0.20607051253318787,
      "learning_rate": 0.00018490397697608395,
      "loss": 0.216,
      "step": 274
    },
    {
      "epoch": 0.0813278621862408,
      "grad_norm": 0.20951667428016663,
      "learning_rate": 0.0001847923927436884,
      "loss": 0.2283,
      "step": 275
    },
    {
      "epoch": 0.08162359986691804,
      "grad_norm": 0.23473979532718658,
      "learning_rate": 0.00018468043156112728,
      "loss": 0.2582,
      "step": 276
    },
    {
      "epoch": 0.08191933754759528,
      "grad_norm": 0.1933351308107376,
      "learning_rate": 0.0001845680939261314,
      "loss": 0.1938,
      "step": 277
    },
    {
      "epoch": 0.08221507522827252,
      "grad_norm": 0.23549608886241913,
      "learning_rate": 0.00018445538033810515,
      "loss": 0.2166,
      "step": 278
    },
    {
      "epoch": 0.08251081290894977,
      "grad_norm": 0.2569220960140228,
      "learning_rate": 0.00018434229129812418,
      "loss": 0.2697,
      "step": 279
    },
    {
      "epoch": 0.082806550589627,
      "grad_norm": 0.22212399542331696,
      "learning_rate": 0.0001842288273089332,
      "loss": 0.26,
      "step": 280
    },
    {
      "epoch": 0.08310228827030423,
      "grad_norm": 0.21168506145477295,
      "learning_rate": 0.00018411498887494396,
      "loss": 0.2008,
      "step": 281
    },
    {
      "epoch": 0.08339802595098147,
      "grad_norm": 0.23749881982803345,
      "learning_rate": 0.00018400077650223263,
      "loss": 0.2163,
      "step": 282
    },
    {
      "epoch": 0.08369376363165872,
      "grad_norm": 0.23951789736747742,
      "learning_rate": 0.0001838861906985379,
      "loss": 0.2235,
      "step": 283
    },
    {
      "epoch": 0.08398950131233596,
      "grad_norm": 0.23467004299163818,
      "learning_rate": 0.00018377123197325842,
      "loss": 0.2119,
      "step": 284
    },
    {
      "epoch": 0.0842852389930132,
      "grad_norm": 0.25748157501220703,
      "learning_rate": 0.00018365590083745085,
      "loss": 0.2498,
      "step": 285
    },
    {
      "epoch": 0.08458097667369044,
      "grad_norm": 0.2640005946159363,
      "learning_rate": 0.00018354019780382735,
      "loss": 0.2297,
      "step": 286
    },
    {
      "epoch": 0.08487671435436768,
      "grad_norm": 0.22059418261051178,
      "learning_rate": 0.0001834241233867533,
      "loss": 0.1856,
      "step": 287
    },
    {
      "epoch": 0.08517245203504492,
      "grad_norm": 0.2318236380815506,
      "learning_rate": 0.00018330767810224524,
      "loss": 0.186,
      "step": 288
    },
    {
      "epoch": 0.08546818971572215,
      "grad_norm": 0.22884918749332428,
      "learning_rate": 0.0001831908624679683,
      "loss": 0.2019,
      "step": 289
    },
    {
      "epoch": 0.08576392739639939,
      "grad_norm": 0.26514625549316406,
      "learning_rate": 0.0001830736770032341,
      "loss": 0.2338,
      "step": 290
    },
    {
      "epoch": 0.08605966507707663,
      "grad_norm": 0.2545234262943268,
      "learning_rate": 0.0001829561222289984,
      "loss": 0.2051,
      "step": 291
    },
    {
      "epoch": 0.08635540275775387,
      "grad_norm": 0.31720927357673645,
      "learning_rate": 0.00018283819866785853,
      "loss": 0.2127,
      "step": 292
    },
    {
      "epoch": 0.08665114043843111,
      "grad_norm": 0.24507926404476166,
      "learning_rate": 0.0001827199068440516,
      "loss": 0.1481,
      "step": 293
    },
    {
      "epoch": 0.08694687811910835,
      "grad_norm": 0.2604232728481293,
      "learning_rate": 0.00018260124728345162,
      "loss": 0.1804,
      "step": 294
    },
    {
      "epoch": 0.0872426157997856,
      "grad_norm": 0.2785932123661041,
      "learning_rate": 0.00018248222051356754,
      "loss": 0.2188,
      "step": 295
    },
    {
      "epoch": 0.08753835348046284,
      "grad_norm": 0.3473379611968994,
      "learning_rate": 0.00018236282706354063,
      "loss": 0.2223,
      "step": 296
    },
    {
      "epoch": 0.08783409116114006,
      "grad_norm": 0.35401713848114014,
      "learning_rate": 0.00018224306746414238,
      "loss": 0.2602,
      "step": 297
    },
    {
      "epoch": 0.0881298288418173,
      "grad_norm": 0.4033154249191284,
      "learning_rate": 0.00018212294224777197,
      "loss": 0.2324,
      "step": 298
    },
    {
      "epoch": 0.08842556652249454,
      "grad_norm": 0.5243091583251953,
      "learning_rate": 0.00018200245194845399,
      "loss": 0.3447,
      "step": 299
    },
    {
      "epoch": 0.08872130420317179,
      "grad_norm": 0.5621427297592163,
      "learning_rate": 0.00018188159710183594,
      "loss": 0.2627,
      "step": 300
    },
    {
      "epoch": 0.08901704188384903,
      "grad_norm": 0.1358180195093155,
      "learning_rate": 0.000181760378245186,
      "loss": 0.1579,
      "step": 301
    },
    {
      "epoch": 0.08931277956452627,
      "grad_norm": 0.16979822516441345,
      "learning_rate": 0.00018163879591739067,
      "loss": 0.2157,
      "step": 302
    },
    {
      "epoch": 0.08960851724520351,
      "grad_norm": 0.18489453196525574,
      "learning_rate": 0.0001815168506589521,
      "loss": 0.2149,
      "step": 303
    },
    {
      "epoch": 0.08990425492588075,
      "grad_norm": 0.19990918040275574,
      "learning_rate": 0.000181394543011986,
      "loss": 0.254,
      "step": 304
    },
    {
      "epoch": 0.09019999260655798,
      "grad_norm": 0.17698073387145996,
      "learning_rate": 0.00018127187352021907,
      "loss": 0.2131,
      "step": 305
    },
    {
      "epoch": 0.09049573028723522,
      "grad_norm": 0.1820111721754074,
      "learning_rate": 0.0001811488427289866,
      "loss": 0.2372,
      "step": 306
    },
    {
      "epoch": 0.09079146796791246,
      "grad_norm": 0.1698734015226364,
      "learning_rate": 0.00018102545118523007,
      "loss": 0.2199,
      "step": 307
    },
    {
      "epoch": 0.0910872056485897,
      "grad_norm": 0.17691490054130554,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.2474,
      "step": 308
    },
    {
      "epoch": 0.09138294332926694,
      "grad_norm": 0.1919829100370407,
      "learning_rate": 0.00018077758803592718,
      "loss": 0.2447,
      "step": 309
    },
    {
      "epoch": 0.09167868100994418,
      "grad_norm": 0.4307519495487213,
      "learning_rate": 0.00018065311753227273,
      "loss": 0.2342,
      "step": 310
    },
    {
      "epoch": 0.09197441869062142,
      "grad_norm": 0.18838980793952942,
      "learning_rate": 0.0001805282884798732,
      "loss": 0.1829,
      "step": 311
    },
    {
      "epoch": 0.09227015637129866,
      "grad_norm": 0.1960785984992981,
      "learning_rate": 0.00018040310143366446,
      "loss": 0.2279,
      "step": 312
    },
    {
      "epoch": 0.09256589405197589,
      "grad_norm": 0.1780913770198822,
      "learning_rate": 0.00018027755695017368,
      "loss": 0.222,
      "step": 313
    },
    {
      "epoch": 0.09286163173265313,
      "grad_norm": 0.1910991370677948,
      "learning_rate": 0.00018015165558751717,
      "loss": 0.2378,
      "step": 314
    },
    {
      "epoch": 0.09315736941333037,
      "grad_norm": 0.17035876214504242,
      "learning_rate": 0.00018002539790539773,
      "loss": 0.1834,
      "step": 315
    },
    {
      "epoch": 0.09345310709400761,
      "grad_norm": 0.18461062014102936,
      "learning_rate": 0.00017989878446510215,
      "loss": 0.2255,
      "step": 316
    },
    {
      "epoch": 0.09374884477468486,
      "grad_norm": 0.18789273500442505,
      "learning_rate": 0.00017977181582949888,
      "loss": 0.2236,
      "step": 317
    },
    {
      "epoch": 0.0940445824553621,
      "grad_norm": 0.18466150760650635,
      "learning_rate": 0.0001796444925630353,
      "loss": 0.1987,
      "step": 318
    },
    {
      "epoch": 0.09434032013603934,
      "grad_norm": 0.2048148661851883,
      "learning_rate": 0.00017951681523173542,
      "loss": 0.2059,
      "step": 319
    },
    {
      "epoch": 0.09463605781671658,
      "grad_norm": 0.2097977101802826,
      "learning_rate": 0.0001793887844031972,
      "loss": 0.231,
      "step": 320
    },
    {
      "epoch": 0.0949317954973938,
      "grad_norm": 0.20636926591396332,
      "learning_rate": 0.00017926040064659014,
      "loss": 0.2326,
      "step": 321
    },
    {
      "epoch": 0.09522753317807105,
      "grad_norm": 0.2094830870628357,
      "learning_rate": 0.0001791316645326526,
      "loss": 0.2059,
      "step": 322
    },
    {
      "epoch": 0.09552327085874829,
      "grad_norm": 0.22407394647598267,
      "learning_rate": 0.00017900257663368963,
      "loss": 0.226,
      "step": 323
    },
    {
      "epoch": 0.09581900853942553,
      "grad_norm": 0.19603627920150757,
      "learning_rate": 0.0001788731375235698,
      "loss": 0.2188,
      "step": 324
    },
    {
      "epoch": 0.09611474622010277,
      "grad_norm": 0.23884060978889465,
      "learning_rate": 0.00017874334777772327,
      "loss": 0.2372,
      "step": 325
    },
    {
      "epoch": 0.09641048390078001,
      "grad_norm": 0.22886501252651215,
      "learning_rate": 0.00017861320797313892,
      "loss": 0.2336,
      "step": 326
    },
    {
      "epoch": 0.09670622158145725,
      "grad_norm": 0.22485503554344177,
      "learning_rate": 0.0001784827186883618,
      "loss": 0.2339,
      "step": 327
    },
    {
      "epoch": 0.0970019592621345,
      "grad_norm": 0.21763861179351807,
      "learning_rate": 0.00017835188050349064,
      "loss": 0.2002,
      "step": 328
    },
    {
      "epoch": 0.09729769694281172,
      "grad_norm": 0.2242451012134552,
      "learning_rate": 0.00017822069400017516,
      "loss": 0.2347,
      "step": 329
    },
    {
      "epoch": 0.09759343462348896,
      "grad_norm": 0.24562625586986542,
      "learning_rate": 0.00017808915976161362,
      "loss": 0.2339,
      "step": 330
    },
    {
      "epoch": 0.0978891723041662,
      "grad_norm": 0.2314700335264206,
      "learning_rate": 0.00017795727837255015,
      "loss": 0.2708,
      "step": 331
    },
    {
      "epoch": 0.09818490998484344,
      "grad_norm": 0.26339125633239746,
      "learning_rate": 0.00017782505041927216,
      "loss": 0.2557,
      "step": 332
    },
    {
      "epoch": 0.09848064766552068,
      "grad_norm": 0.22803835570812225,
      "learning_rate": 0.00017769247648960774,
      "loss": 0.196,
      "step": 333
    },
    {
      "epoch": 0.09877638534619793,
      "grad_norm": 0.22814923524856567,
      "learning_rate": 0.00017755955717292296,
      "loss": 0.1687,
      "step": 334
    },
    {
      "epoch": 0.09907212302687517,
      "grad_norm": 0.25240692496299744,
      "learning_rate": 0.00017742629306011944,
      "loss": 0.2064,
      "step": 335
    },
    {
      "epoch": 0.09936786070755241,
      "grad_norm": 0.23173846304416656,
      "learning_rate": 0.00017729268474363154,
      "loss": 0.1797,
      "step": 336
    },
    {
      "epoch": 0.09966359838822964,
      "grad_norm": 0.2367689609527588,
      "learning_rate": 0.0001771587328174239,
      "loss": 0.1796,
      "step": 337
    },
    {
      "epoch": 0.09995933606890688,
      "grad_norm": 0.2612314522266388,
      "learning_rate": 0.0001770244378769885,
      "loss": 0.2132,
      "step": 338
    },
    {
      "epoch": 0.10025507374958412,
      "grad_norm": 0.2403004765510559,
      "learning_rate": 0.0001768898005193425,
      "loss": 0.1919,
      "step": 339
    },
    {
      "epoch": 0.10055081143026136,
      "grad_norm": 0.26991987228393555,
      "learning_rate": 0.000176754821343025,
      "loss": 0.2262,
      "step": 340
    },
    {
      "epoch": 0.1008465491109386,
      "grad_norm": 0.28544318675994873,
      "learning_rate": 0.0001766195009480949,
      "loss": 0.2229,
      "step": 341
    },
    {
      "epoch": 0.10114228679161584,
      "grad_norm": 0.2717716693878174,
      "learning_rate": 0.0001764838399361279,
      "loss": 0.2146,
      "step": 342
    },
    {
      "epoch": 0.10143802447229308,
      "grad_norm": 0.2891225218772888,
      "learning_rate": 0.00017634783891021393,
      "loss": 0.2462,
      "step": 343
    },
    {
      "epoch": 0.10173376215297031,
      "grad_norm": 0.3248477578163147,
      "learning_rate": 0.00017621149847495458,
      "loss": 0.2475,
      "step": 344
    },
    {
      "epoch": 0.10202949983364755,
      "grad_norm": 0.3657064735889435,
      "learning_rate": 0.00017607481923646016,
      "loss": 0.28,
      "step": 345
    },
    {
      "epoch": 0.10232523751432479,
      "grad_norm": 0.3362722396850586,
      "learning_rate": 0.0001759378018023473,
      "loss": 0.2462,
      "step": 346
    },
    {
      "epoch": 0.10262097519500203,
      "grad_norm": 0.3996289074420929,
      "learning_rate": 0.00017580044678173592,
      "loss": 0.2258,
      "step": 347
    },
    {
      "epoch": 0.10291671287567927,
      "grad_norm": 0.36670979857444763,
      "learning_rate": 0.00017566275478524693,
      "loss": 0.2466,
      "step": 348
    },
    {
      "epoch": 0.10321245055635651,
      "grad_norm": 0.48458173871040344,
      "learning_rate": 0.0001755247264249991,
      "loss": 0.3022,
      "step": 349
    },
    {
      "epoch": 0.10350818823703375,
      "grad_norm": 0.49845030903816223,
      "learning_rate": 0.0001753863623146066,
      "loss": 0.2424,
      "step": 350
    },
    {
      "epoch": 0.103803925917711,
      "grad_norm": 0.11847740411758423,
      "learning_rate": 0.00017524766306917618,
      "loss": 0.1449,
      "step": 351
    },
    {
      "epoch": 0.10409966359838822,
      "grad_norm": 0.14606598019599915,
      "learning_rate": 0.0001751086293053045,
      "loss": 0.1713,
      "step": 352
    },
    {
      "epoch": 0.10439540127906546,
      "grad_norm": 0.1666148602962494,
      "learning_rate": 0.0001749692616410753,
      "loss": 0.2063,
      "step": 353
    },
    {
      "epoch": 0.1046911389597427,
      "grad_norm": 0.1671825349330902,
      "learning_rate": 0.00017482956069605668,
      "loss": 0.2283,
      "step": 354
    },
    {
      "epoch": 0.10498687664041995,
      "grad_norm": 0.17825308442115784,
      "learning_rate": 0.00017468952709129846,
      "loss": 0.2379,
      "step": 355
    },
    {
      "epoch": 0.10528261432109719,
      "grad_norm": 0.1678950935602188,
      "learning_rate": 0.00017454916144932922,
      "loss": 0.2227,
      "step": 356
    },
    {
      "epoch": 0.10557835200177443,
      "grad_norm": 0.16522592306137085,
      "learning_rate": 0.0001744084643941536,
      "loss": 0.2099,
      "step": 357
    },
    {
      "epoch": 0.10587408968245167,
      "grad_norm": 0.17215241491794586,
      "learning_rate": 0.00017426743655124974,
      "loss": 0.2612,
      "step": 358
    },
    {
      "epoch": 0.10616982736312891,
      "grad_norm": 0.17087267339229584,
      "learning_rate": 0.0001741260785475661,
      "loss": 0.2301,
      "step": 359
    },
    {
      "epoch": 0.10646556504380614,
      "grad_norm": 0.1661638766527176,
      "learning_rate": 0.00017398439101151905,
      "loss": 0.2174,
      "step": 360
    },
    {
      "epoch": 0.10676130272448338,
      "grad_norm": 0.17075875401496887,
      "learning_rate": 0.00017384237457298987,
      "loss": 0.1701,
      "step": 361
    },
    {
      "epoch": 0.10705704040516062,
      "grad_norm": 0.1797911673784256,
      "learning_rate": 0.00017370002986332193,
      "loss": 0.2192,
      "step": 362
    },
    {
      "epoch": 0.10735277808583786,
      "grad_norm": 0.17848677933216095,
      "learning_rate": 0.00017355735751531807,
      "loss": 0.2193,
      "step": 363
    },
    {
      "epoch": 0.1076485157665151,
      "grad_norm": 0.17944815754890442,
      "learning_rate": 0.00017341435816323756,
      "loss": 0.2008,
      "step": 364
    },
    {
      "epoch": 0.10794425344719234,
      "grad_norm": 0.17322401702404022,
      "learning_rate": 0.00017327103244279348,
      "loss": 0.2084,
      "step": 365
    },
    {
      "epoch": 0.10823999112786958,
      "grad_norm": 0.19021335244178772,
      "learning_rate": 0.00017312738099114973,
      "loss": 0.2398,
      "step": 366
    },
    {
      "epoch": 0.10853572880854682,
      "grad_norm": 0.18541230261325836,
      "learning_rate": 0.00017298340444691835,
      "loss": 0.2618,
      "step": 367
    },
    {
      "epoch": 0.10883146648922405,
      "grad_norm": 0.18366391956806183,
      "learning_rate": 0.00017283910345015647,
      "loss": 0.2356,
      "step": 368
    },
    {
      "epoch": 0.10912720416990129,
      "grad_norm": 0.1941191852092743,
      "learning_rate": 0.0001726944786423637,
      "loss": 0.2228,
      "step": 369
    },
    {
      "epoch": 0.10942294185057853,
      "grad_norm": 0.16953422129154205,
      "learning_rate": 0.00017254953066647913,
      "loss": 0.1555,
      "step": 370
    },
    {
      "epoch": 0.10971867953125577,
      "grad_norm": 0.20326456427574158,
      "learning_rate": 0.00017240426016687863,
      "loss": 0.2514,
      "step": 371
    },
    {
      "epoch": 0.11001441721193302,
      "grad_norm": 0.1932348906993866,
      "learning_rate": 0.00017225866778937165,
      "loss": 0.2068,
      "step": 372
    },
    {
      "epoch": 0.11031015489261026,
      "grad_norm": 0.21190403401851654,
      "learning_rate": 0.00017211275418119876,
      "loss": 0.2196,
      "step": 373
    },
    {
      "epoch": 0.1106058925732875,
      "grad_norm": 0.20619221031665802,
      "learning_rate": 0.0001719665199910285,
      "loss": 0.2368,
      "step": 374
    },
    {
      "epoch": 0.11090163025396474,
      "grad_norm": 0.1878051608800888,
      "learning_rate": 0.00017181996586895454,
      "loss": 0.1801,
      "step": 375
    },
    {
      "epoch": 0.11090163025396474,
      "eval_loss": 0.21186766028404236,
      "eval_runtime": 323.3922,
      "eval_samples_per_second": 17.61,
      "eval_steps_per_second": 8.807,
      "step": 375
    }
  ],
  "logging_steps": 1,
  "max_steps": 1500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 375,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.959891216264069e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}