{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 333,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003003003003003003,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 2.0251,
      "step": 1
    },
    {
      "epoch": 0.006006006006006006,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 2.8155,
      "step": 2
    },
    {
      "epoch": 0.009009009009009009,
      "grad_norm": 8.254266738891602,
      "learning_rate": 0.0001999955498150411,
      "loss": 2.3407,
      "step": 3
    },
    {
      "epoch": 0.012012012012012012,
      "grad_norm": 2.888874053955078,
      "learning_rate": 0.00019998219965624734,
      "loss": 1.982,
      "step": 4
    },
    {
      "epoch": 0.015015015015015015,
      "grad_norm": 2.099008083343506,
      "learning_rate": 0.0001999599507118322,
      "loss": 1.3602,
      "step": 5
    },
    {
      "epoch": 0.018018018018018018,
      "grad_norm": 4.129324913024902,
      "learning_rate": 0.000199928804962034,
      "loss": 2.4564,
      "step": 6
    },
    {
      "epoch": 0.021021021021021023,
      "grad_norm": 3.6175684928894043,
      "learning_rate": 0.0001998887651789398,
      "loss": 1.9079,
      "step": 7
    },
    {
      "epoch": 0.024024024024024024,
      "grad_norm": 3.246344804763794,
      "learning_rate": 0.00019983983492623833,
      "loss": 1.6866,
      "step": 8
    },
    {
      "epoch": 0.02702702702702703,
      "grad_norm": 3.2417070865631104,
      "learning_rate": 0.00019978201855890308,
      "loss": 1.4891,
      "step": 9
    },
    {
      "epoch": 0.03003003003003003,
      "grad_norm": 5.3369832038879395,
      "learning_rate": 0.00019971532122280464,
      "loss": 2.0856,
      "step": 10
    },
    {
      "epoch": 0.03303303303303303,
      "grad_norm": 3.8723933696746826,
      "learning_rate": 0.00019963974885425266,
      "loss": 1.9191,
      "step": 11
    },
    {
      "epoch": 0.036036036036036036,
      "grad_norm": 5.872828006744385,
      "learning_rate": 0.00019955530817946748,
      "loss": 1.9715,
      "step": 12
    },
    {
      "epoch": 0.03903903903903904,
      "grad_norm": 5.758902549743652,
      "learning_rate": 0.0001994620067139815,
      "loss": 1.9539,
      "step": 13
    },
    {
      "epoch": 0.042042042042042045,
      "grad_norm": 4.494828224182129,
      "learning_rate": 0.0001993598527619703,
      "loss": 1.8494,
      "step": 14
    },
    {
      "epoch": 0.04504504504504504,
      "grad_norm": 4.702944755554199,
      "learning_rate": 0.0001992488554155135,
      "loss": 1.7613,
      "step": 15
    },
    {
      "epoch": 0.04804804804804805,
      "grad_norm": 4.821094512939453,
      "learning_rate": 0.00019912902455378556,
      "loss": 1.5019,
      "step": 16
    },
    {
      "epoch": 0.05105105105105105,
      "grad_norm": 4.842085838317871,
      "learning_rate": 0.00019900037084217637,
      "loss": 1.014,
      "step": 17
    },
    {
      "epoch": 0.05405405405405406,
      "grad_norm": 4.73835563659668,
      "learning_rate": 0.00019886290573134228,
      "loss": 1.7198,
      "step": 18
    },
    {
      "epoch": 0.057057057057057055,
      "grad_norm": 5.116694927215576,
      "learning_rate": 0.00019871664145618657,
      "loss": 1.029,
      "step": 19
    },
    {
      "epoch": 0.06006006006006006,
      "grad_norm": 3.1407368183135986,
      "learning_rate": 0.00019856159103477086,
      "loss": 1.0887,
      "step": 20
    },
    {
      "epoch": 0.06306306306306306,
      "grad_norm": 4.0600666999816895,
      "learning_rate": 0.00019839776826715614,
      "loss": 1.7268,
      "step": 21
    },
    {
      "epoch": 0.06606606606606606,
      "grad_norm": 5.035831928253174,
      "learning_rate": 0.0001982251877341748,
      "loss": 1.2828,
      "step": 22
    },
    {
      "epoch": 0.06906906906906907,
      "grad_norm": 6.41340446472168,
      "learning_rate": 0.0001980438647961327,
      "loss": 1.6047,
      "step": 23
    },
    {
      "epoch": 0.07207207207207207,
      "grad_norm": 4.085684776306152,
      "learning_rate": 0.00019785381559144196,
      "loss": 1.477,
      "step": 24
    },
    {
      "epoch": 0.07507507507507508,
      "grad_norm": 3.9870212078094482,
      "learning_rate": 0.00019765505703518496,
      "loss": 0.8285,
      "step": 25
    },
    {
      "epoch": 0.07807807807807808,
      "grad_norm": 4.476605415344238,
      "learning_rate": 0.00019744760681760832,
      "loss": 1.3635,
      "step": 26
    },
    {
      "epoch": 0.08108108108108109,
      "grad_norm": 4.659677982330322,
      "learning_rate": 0.00019723148340254892,
      "loss": 1.7153,
      "step": 27
    },
    {
      "epoch": 0.08408408408408409,
      "grad_norm": 4.323594570159912,
      "learning_rate": 0.00019700670602579008,
      "loss": 1.5809,
      "step": 28
    },
    {
      "epoch": 0.08708708708708708,
      "grad_norm": 3.4452884197235107,
      "learning_rate": 0.0001967732946933499,
      "loss": 1.4132,
      "step": 29
    },
    {
      "epoch": 0.09009009009009009,
      "grad_norm": 5.972443103790283,
      "learning_rate": 0.00019653127017970034,
      "loss": 1.6207,
      "step": 30
    },
    {
      "epoch": 0.09309309309309309,
      "grad_norm": 2.909363269805908,
      "learning_rate": 0.00019628065402591845,
      "loss": 1.2312,
      "step": 31
    },
    {
      "epoch": 0.0960960960960961,
      "grad_norm": 3.1354382038116455,
      "learning_rate": 0.00019602146853776894,
      "loss": 1.2398,
      "step": 32
    },
    {
      "epoch": 0.0990990990990991,
      "grad_norm": 4.161502361297607,
      "learning_rate": 0.00019575373678371909,
      "loss": 1.5237,
      "step": 33
    },
    {
      "epoch": 0.1021021021021021,
      "grad_norm": 3.4831933975219727,
      "learning_rate": 0.00019547748259288536,
      "loss": 1.3345,
      "step": 34
    },
    {
      "epoch": 0.10510510510510511,
      "grad_norm": 3.050612688064575,
      "learning_rate": 0.00019519273055291266,
      "loss": 1.233,
      "step": 35
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": 3.520677089691162,
      "learning_rate": 0.0001948995060077859,
      "loss": 1.3311,
      "step": 36
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 3.586829423904419,
      "learning_rate": 0.00019459783505557424,
      "loss": 1.212,
      "step": 37
    },
    {
      "epoch": 0.11411411411411411,
      "grad_norm": 2.9168314933776855,
      "learning_rate": 0.00019428774454610843,
      "loss": 1.084,
      "step": 38
    },
    {
      "epoch": 0.11711711711711711,
      "grad_norm": 3.1117663383483887,
      "learning_rate": 0.00019396926207859084,
      "loss": 0.978,
      "step": 39
    },
    {
      "epoch": 0.12012012012012012,
      "grad_norm": 3.9365386962890625,
      "learning_rate": 0.00019364241599913924,
      "loss": 0.91,
      "step": 40
    },
    {
      "epoch": 0.12312312312312312,
      "grad_norm": 5.414772987365723,
      "learning_rate": 0.00019330723539826375,
      "loss": 1.5547,
      "step": 41
    },
    {
      "epoch": 0.12612612612612611,
      "grad_norm": 3.866046905517578,
      "learning_rate": 0.00019296375010827773,
      "loss": 1.3311,
      "step": 42
    },
    {
      "epoch": 0.12912912912912913,
      "grad_norm": 4.769541263580322,
      "learning_rate": 0.0001926119907006426,
      "loss": 0.8167,
      "step": 43
    },
    {
      "epoch": 0.13213213213213212,
      "grad_norm": 3.6581079959869385,
      "learning_rate": 0.0001922519884832469,
      "loss": 1.2906,
      "step": 44
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 4.367158889770508,
      "learning_rate": 0.00019188377549761963,
      "loss": 1.2016,
      "step": 45
    },
    {
      "epoch": 0.13813813813813813,
      "grad_norm": 3.591726541519165,
      "learning_rate": 0.0001915073845160786,
      "loss": 1.4798,
      "step": 46
    },
    {
      "epoch": 0.14114114114114115,
      "grad_norm": 4.844123840332031,
      "learning_rate": 0.0001911228490388136,
      "loss": 1.4799,
      "step": 47
    },
    {
      "epoch": 0.14414414414414414,
      "grad_norm": 5.353418350219727,
      "learning_rate": 0.00019073020329090444,
      "loss": 1.2234,
      "step": 48
    },
    {
      "epoch": 0.14714714714714713,
      "grad_norm": 3.3358774185180664,
      "learning_rate": 0.00019032948221927524,
      "loss": 1.0556,
      "step": 49
    },
    {
      "epoch": 0.15015015015015015,
      "grad_norm": 3.674219846725464,
      "learning_rate": 0.00018992072148958368,
      "loss": 1.1757,
      "step": 50
    },
    {
      "epoch": 0.15315315315315314,
      "grad_norm": 4.523245334625244,
      "learning_rate": 0.00018950395748304678,
      "loss": 1.2357,
      "step": 51
    },
    {
      "epoch": 0.15615615615615616,
      "grad_norm": 4.535871982574463,
      "learning_rate": 0.00018907922729320285,
      "loss": 1.5018,
      "step": 52
    },
    {
      "epoch": 0.15915915915915915,
      "grad_norm": 3.2581071853637695,
      "learning_rate": 0.00018864656872260985,
      "loss": 1.1452,
      "step": 53
    },
    {
      "epoch": 0.16216216216216217,
      "grad_norm": 3.132718324661255,
      "learning_rate": 0.00018820602027948114,
      "loss": 1.1584,
      "step": 54
    },
    {
      "epoch": 0.16516516516516516,
      "grad_norm": 4.070220470428467,
      "learning_rate": 0.00018775762117425777,
      "loss": 1.1046,
      "step": 55
    },
    {
      "epoch": 0.16816816816816818,
      "grad_norm": 3.8557350635528564,
      "learning_rate": 0.00018730141131611882,
      "loss": 0.9695,
      "step": 56
    },
    {
      "epoch": 0.17117117117117117,
      "grad_norm": 3.3533196449279785,
      "learning_rate": 0.00018683743130942928,
      "loss": 1.1877,
      "step": 57
    },
    {
      "epoch": 0.17417417417417416,
      "grad_norm": 3.0984268188476562,
      "learning_rate": 0.00018636572245012606,
      "loss": 1.3991,
      "step": 58
    },
    {
      "epoch": 0.17717717717717718,
      "grad_norm": 10.649101257324219,
      "learning_rate": 0.00018588632672204264,
      "loss": 1.1049,
      "step": 59
    },
    {
      "epoch": 0.18018018018018017,
      "grad_norm": 4.183538436889648,
      "learning_rate": 0.0001853992867931721,
      "loss": 1.4726,
      "step": 60
    },
    {
      "epoch": 0.1831831831831832,
      "grad_norm": 3.4067232608795166,
      "learning_rate": 0.0001849046460118698,
      "loss": 1.3283,
      "step": 61
    },
    {
      "epoch": 0.18618618618618618,
      "grad_norm": 3.2232909202575684,
      "learning_rate": 0.00018440244840299506,
      "loss": 1.0828,
      "step": 62
    },
    {
      "epoch": 0.1891891891891892,
      "grad_norm": 3.587733030319214,
      "learning_rate": 0.00018389273866399275,
      "loss": 1.4606,
      "step": 63
    },
    {
      "epoch": 0.1921921921921922,
      "grad_norm": 3.715364456176758,
      "learning_rate": 0.00018337556216091517,
      "loss": 1.3308,
      "step": 64
    },
    {
      "epoch": 0.19519519519519518,
      "grad_norm": 3.0346460342407227,
      "learning_rate": 0.00018285096492438424,
      "loss": 1.1785,
      "step": 65
    },
    {
      "epoch": 0.1981981981981982,
      "grad_norm": 2.9115614891052246,
      "learning_rate": 0.00018231899364549455,
      "loss": 0.8434,
      "step": 66
    },
    {
      "epoch": 0.2012012012012012,
      "grad_norm": 3.1807260513305664,
      "learning_rate": 0.0001817796956716578,
      "loss": 1.0018,
      "step": 67
    },
    {
      "epoch": 0.2042042042042042,
      "grad_norm": 3.0817840099334717,
      "learning_rate": 0.0001812331190023886,
      "loss": 1.0185,
      "step": 68
    },
    {
      "epoch": 0.2072072072072072,
      "grad_norm": 3.2719409465789795,
      "learning_rate": 0.00018067931228503246,
      "loss": 1.4434,
      "step": 69
    },
    {
      "epoch": 0.21021021021021022,
      "grad_norm": 4.187236309051514,
      "learning_rate": 0.00018011832481043576,
      "loss": 1.0969,
      "step": 70
    },
    {
      "epoch": 0.2132132132132132,
      "grad_norm": 3.2186405658721924,
      "learning_rate": 0.000179550206508559,
      "loss": 1.2105,
      "step": 71
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": 3.406670570373535,
      "learning_rate": 0.0001789750079440326,
      "loss": 1.3271,
      "step": 72
    },
    {
      "epoch": 0.21921921921921922,
      "grad_norm": 3.0242960453033447,
      "learning_rate": 0.00017839278031165658,
      "loss": 1.1269,
      "step": 73
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 4.0513691902160645,
      "learning_rate": 0.00017780357543184397,
      "loss": 1.1778,
      "step": 74
    },
    {
      "epoch": 0.22522522522522523,
      "grad_norm": 4.116867542266846,
      "learning_rate": 0.00017720744574600863,
      "loss": 1.2357,
      "step": 75
    },
    {
      "epoch": 0.22822822822822822,
      "grad_norm": 3.957306146621704,
      "learning_rate": 0.0001766044443118978,
      "loss": 1.4235,
      "step": 76
    },
    {
      "epoch": 0.23123123123123124,
      "grad_norm": 7.28619384765625,
      "learning_rate": 0.00017599462479886974,
      "loss": 1.102,
      "step": 77
    },
    {
      "epoch": 0.23423423423423423,
      "grad_norm": 4.001276969909668,
      "learning_rate": 0.00017537804148311695,
      "loss": 1.1948,
      "step": 78
    },
    {
      "epoch": 0.23723723723723725,
      "grad_norm": 2.7599635124206543,
      "learning_rate": 0.00017475474924283536,
      "loss": 1.0386,
      "step": 79
    },
    {
      "epoch": 0.24024024024024024,
      "grad_norm": 3.36354923248291,
      "learning_rate": 0.00017412480355334005,
      "loss": 1.6077,
      "step": 80
    },
    {
      "epoch": 0.24324324324324326,
      "grad_norm": NaN,
      "learning_rate": 0.00017412480355334005,
      "loss": 1.4291,
      "step": 81
    },
    {
      "epoch": 0.24624624624624625,
      "grad_norm": 4.241931915283203,
      "learning_rate": 0.0001734882604821276,
      "loss": 1.37,
      "step": 82
    },
    {
      "epoch": 0.24924924924924924,
      "grad_norm": 3.40556001663208,
      "learning_rate": 0.0001728451766838861,
      "loss": 1.4526,
      "step": 83
    },
    {
      "epoch": 0.25225225225225223,
      "grad_norm": 3.1627070903778076,
      "learning_rate": 0.00017219560939545246,
      "loss": 1.1918,
      "step": 84
    },
    {
      "epoch": 0.2552552552552553,
      "grad_norm": 2.915019989013672,
      "learning_rate": 0.0001715396164307182,
      "loss": 1.1523,
      "step": 85
    },
    {
      "epoch": 0.25825825825825827,
      "grad_norm": 3.027531862258911,
      "learning_rate": 0.00017087725617548385,
      "loss": 1.097,
      "step": 86
    },
    {
      "epoch": 0.26126126126126126,
      "grad_norm": 3.198509931564331,
      "learning_rate": 0.00017020858758226229,
      "loss": 1.1172,
      "step": 87
    },
    {
      "epoch": 0.26426426426426425,
      "grad_norm": 2.9282870292663574,
      "learning_rate": 0.00016953367016503182,
      "loss": 0.9913,
      "step": 88
    },
    {
      "epoch": 0.2672672672672673,
      "grad_norm": 2.8152143955230713,
      "learning_rate": 0.00016885256399393924,
      "loss": 0.9582,
      "step": 89
    },
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 5.513664245605469,
      "learning_rate": 0.00016816532968995328,
      "loss": 1.5983,
      "step": 90
    },
    {
      "epoch": 0.2732732732732733,
      "grad_norm": 3.0489561557769775,
      "learning_rate": 0.00016747202841946928,
      "loss": 1.3503,
      "step": 91
    },
    {
      "epoch": 0.27627627627627627,
      "grad_norm": 3.1149275302886963,
      "learning_rate": 0.00016677272188886483,
      "loss": 1.0439,
      "step": 92
    },
    {
      "epoch": 0.27927927927927926,
      "grad_norm": 5.150669097900391,
      "learning_rate": 0.00016606747233900815,
      "loss": 1.5164,
      "step": 93
    },
    {
      "epoch": 0.2822822822822823,
      "grad_norm": 3.6513853073120117,
      "learning_rate": 0.00016535634253971794,
      "loss": 0.8632,
      "step": 94
    },
    {
      "epoch": 0.2852852852852853,
      "grad_norm": 2.818716287612915,
      "learning_rate": 0.00016463939578417692,
      "loss": 0.9685,
      "step": 95
    },
    {
      "epoch": 0.2882882882882883,
      "grad_norm": 4.800100803375244,
      "learning_rate": 0.0001639166958832985,
      "loss": 1.6414,
      "step": 96
    },
    {
      "epoch": 0.2912912912912913,
      "grad_norm": 5.5120649337768555,
      "learning_rate": 0.00016318830716004722,
      "loss": 2.0318,
      "step": 97
    },
    {
      "epoch": 0.29429429429429427,
      "grad_norm": 3.650167226791382,
      "learning_rate": 0.0001624542944437139,
      "loss": 1.3504,
      "step": 98
    },
    {
      "epoch": 0.2972972972972973,
      "grad_norm": 3.262024402618408,
      "learning_rate": 0.00016171472306414554,
      "loss": 0.9678,
      "step": 99
    },
    {
      "epoch": 0.3003003003003003,
      "grad_norm": 3.3580527305603027,
      "learning_rate": 0.0001609696588459307,
      "loss": 1.2071,
      "step": 100
    },
    {
      "epoch": 0.3033033033033033,
      "grad_norm": 2.174422025680542,
      "learning_rate": 0.00016021916810254097,
      "loss": 0.8678,
      "step": 101
    },
    {
      "epoch": 0.3063063063063063,
      "grad_norm": 3.338526487350464,
      "learning_rate": 0.00015946331763042867,
      "loss": 1.1964,
      "step": 102
    },
    {
      "epoch": 0.30930930930930933,
      "grad_norm": 2.4254307746887207,
      "learning_rate": 0.00015870217470308188,
      "loss": 1.1689,
      "step": 103
    },
    {
      "epoch": 0.3123123123123123,
      "grad_norm": 3.5244359970092773,
      "learning_rate": 0.0001579358070650367,
      "loss": 1.5078,
      "step": 104
    },
    {
      "epoch": 0.3153153153153153,
      "grad_norm": 3.7619662284851074,
      "learning_rate": 0.00015716428292584787,
      "loss": 1.2496,
      "step": 105
    },
    {
      "epoch": 0.3183183183183183,
      "grad_norm": 4.3766303062438965,
      "learning_rate": 0.0001563876709540178,
      "loss": 1.673,
      "step": 106
    },
    {
      "epoch": 0.3213213213213213,
      "grad_norm": 1.925053596496582,
      "learning_rate": 0.00015560604027088477,
      "loss": 0.7445,
      "step": 107
    },
    {
      "epoch": 0.32432432432432434,
      "grad_norm": 2.5130960941314697,
      "learning_rate": 0.00015481946044447099,
      "loss": 0.8784,
      "step": 108
    },
    {
      "epoch": 0.32732732732732733,
      "grad_norm": 3.086637020111084,
      "learning_rate": 0.00015402800148329071,
      "loss": 1.1608,
      "step": 109
    },
    {
      "epoch": 0.3303303303303303,
      "grad_norm": 2.877929925918579,
      "learning_rate": 0.0001532317338301192,
      "loss": 0.9467,
      "step": 110
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 2.76326847076416,
      "learning_rate": 0.00015243072835572318,
      "loss": 1.0425,
      "step": 111
    },
    {
      "epoch": 0.33633633633633636,
      "grad_norm": 3.9744467735290527,
      "learning_rate": 0.00015162505635255287,
      "loss": 1.3432,
      "step": 112
    },
    {
      "epoch": 0.33933933933933935,
      "grad_norm": 5.023432731628418,
      "learning_rate": 0.00015081478952839693,
      "loss": 1.6413,
      "step": 113
    },
    {
      "epoch": 0.34234234234234234,
      "grad_norm": 3.5280025005340576,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.0987,
      "step": 114
    },
    {
      "epoch": 0.34534534534534533,
      "grad_norm": 2.802316665649414,
      "learning_rate": 0.0001491807602866442,
      "loss": 0.7508,
      "step": 115
    },
    {
      "epoch": 0.3483483483483483,
      "grad_norm": 3.0784826278686523,
      "learning_rate": 0.00014835714330369446,
      "loss": 1.199,
      "step": 116
    },
    {
      "epoch": 0.35135135135135137,
      "grad_norm": 4.75717306137085,
      "learning_rate": 0.000147529222356109,
      "loss": 1.3701,
      "step": 117
    },
    {
      "epoch": 0.35435435435435436,
      "grad_norm": 2.9851152896881104,
      "learning_rate": 0.00014669707113191483,
      "loss": 1.037,
      "step": 118
    },
    {
      "epoch": 0.35735735735735735,
      "grad_norm": 4.035271644592285,
      "learning_rate": 0.00014586076369564908,
      "loss": 1.0533,
      "step": 119
    },
    {
      "epoch": 0.36036036036036034,
      "grad_norm": 9.006219863891602,
      "learning_rate": 0.00014502037448176734,
      "loss": 1.0655,
      "step": 120
    },
    {
      "epoch": 0.3633633633633634,
      "grad_norm": 3.5663275718688965,
      "learning_rate": 0.00014417597828801832,
      "loss": 1.568,
      "step": 121
    },
    {
      "epoch": 0.3663663663663664,
      "grad_norm": 2.996906280517578,
      "learning_rate": 0.00014332765026878687,
      "loss": 1.0472,
      "step": 122
    },
    {
      "epoch": 0.36936936936936937,
      "grad_norm": 2.879059076309204,
      "learning_rate": 0.0001424754659284048,
      "loss": 1.214,
      "step": 123
    },
    {
      "epoch": 0.37237237237237236,
      "grad_norm": 3.065863847732544,
      "learning_rate": 0.00014161950111443077,
      "loss": 0.8353,
      "step": 124
    },
    {
      "epoch": 0.37537537537537535,
      "grad_norm": 4.549298286437988,
      "learning_rate": 0.00014075983201089964,
      "loss": 0.9154,
      "step": 125
    },
    {
      "epoch": 0.3783783783783784,
      "grad_norm": 4.853454113006592,
      "learning_rate": 0.00013989653513154165,
      "loss": 1.5181,
      "step": 126
    },
    {
      "epoch": 0.3813813813813814,
      "grad_norm": 2.2490577697753906,
      "learning_rate": 0.00013902968731297255,
      "loss": 0.9221,
      "step": 127
    },
    {
      "epoch": 0.3843843843843844,
      "grad_norm": 4.746774673461914,
      "learning_rate": 0.00013815936570785487,
      "loss": 0.7953,
      "step": 128
    },
    {
      "epoch": 0.38738738738738737,
      "grad_norm": 3.5353190898895264,
      "learning_rate": 0.00013728564777803088,
      "loss": 0.9101,
      "step": 129
    },
    {
      "epoch": 0.39039039039039036,
      "grad_norm": 3.052245855331421,
      "learning_rate": 0.0001364086112876284,
      "loss": 1.3159,
      "step": 130
    },
    {
      "epoch": 0.3933933933933934,
      "grad_norm": 4.477910041809082,
      "learning_rate": 0.00013552833429613938,
      "loss": 1.2709,
      "step": 131
    },
    {
      "epoch": 0.3963963963963964,
      "grad_norm": 7.228553295135498,
      "learning_rate": 0.00013464489515147238,
      "loss": 1.4622,
      "step": 132
    },
    {
      "epoch": 0.3993993993993994,
      "grad_norm": 2.7557127475738525,
      "learning_rate": 0.00013375837248297926,
      "loss": 1.4031,
      "step": 133
    },
    {
      "epoch": 0.4024024024024024,
      "grad_norm": 5.027473449707031,
      "learning_rate": 0.0001328688451944569,
      "loss": 1.2564,
      "step": 134
    },
    {
      "epoch": 0.40540540540540543,
      "grad_norm": 2.9252965450286865,
      "learning_rate": 0.00013197639245712454,
      "loss": 1.0321,
      "step": 135
    },
    {
      "epoch": 0.4084084084084084,
      "grad_norm": 2.841583728790283,
      "learning_rate": 0.00013108109370257712,
      "loss": 0.9534,
      "step": 136
    },
    {
      "epoch": 0.4114114114114114,
      "grad_norm": 4.3325114250183105,
      "learning_rate": 0.0001301830286157157,
      "loss": 1.4278,
      "step": 137
    },
    {
      "epoch": 0.4144144144144144,
      "grad_norm": 3.721039056777954,
      "learning_rate": 0.00012928227712765504,
      "loss": 1.4167,
      "step": 138
    },
    {
      "epoch": 0.4174174174174174,
      "grad_norm": 4.287530422210693,
      "learning_rate": 0.00012837891940860972,
      "loss": 1.4874,
      "step": 139
    },
    {
      "epoch": 0.42042042042042044,
      "grad_norm": 3.366671085357666,
      "learning_rate": 0.0001274730358607583,
      "loss": 1.0406,
      "step": 140
    },
    {
      "epoch": 0.42342342342342343,
      "grad_norm": 4.121444225311279,
      "learning_rate": 0.00012656470711108764,
      "loss": 1.6264,
      "step": 141
    },
    {
      "epoch": 0.4264264264264264,
      "grad_norm": 3.2435896396636963,
      "learning_rate": 0.00012565401400421651,
      "loss": 1.1203,
      "step": 142
    },
    {
      "epoch": 0.4294294294294294,
      "grad_norm": 2.8955342769622803,
      "learning_rate": 0.00012474103759520027,
      "loss": 1.2582,
      "step": 143
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 4.04188346862793,
      "learning_rate": 0.0001238258591423165,
      "loss": 1.0391,
      "step": 144
    },
    {
      "epoch": 0.43543543543543545,
      "grad_norm": 4.958117961883545,
      "learning_rate": 0.000122908560099833,
      "loss": 1.4298,
      "step": 145
    },
    {
      "epoch": 0.43843843843843844,
      "grad_norm": 1.997272253036499,
      "learning_rate": 0.00012198922211075778,
      "loss": 0.9793,
      "step": 146
    },
    {
      "epoch": 0.44144144144144143,
      "grad_norm": 2.4838814735412598,
      "learning_rate": 0.00012106792699957263,
      "loss": 1.0245,
      "step": 147
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 3.6618947982788086,
      "learning_rate": 0.00012014475676495052,
      "loss": 1.2034,
      "step": 148
    },
    {
      "epoch": 0.44744744744744747,
      "grad_norm": 2.2039713859558105,
      "learning_rate": 0.0001192197935724573,
      "loss": 0.9593,
      "step": 149
    },
    {
      "epoch": 0.45045045045045046,
      "grad_norm": 3.798941135406494,
      "learning_rate": 0.00011829311974723867,
      "loss": 1.6691,
      "step": 150
    },
    {
      "epoch": 0.45345345345345345,
      "grad_norm": 1.9355311393737793,
      "learning_rate": 0.00011736481776669306,
      "loss": 0.6611,
      "step": 151
    },
    {
      "epoch": 0.45645645645645644,
      "grad_norm": 2.3967108726501465,
      "learning_rate": 0.00011643497025313061,
      "loss": 1.0664,
      "step": 152
    },
    {
      "epoch": 0.4594594594594595,
      "grad_norm": 4.215780735015869,
      "learning_rate": 0.00011550365996641979,
      "loss": 0.9672,
      "step": 153
    },
    {
      "epoch": 0.4624624624624625,
      "grad_norm": 3.002946615219116,
      "learning_rate": 0.00011457096979662114,
      "loss": 1.6195,
      "step": 154
    },
    {
      "epoch": 0.46546546546546547,
      "grad_norm": 2.1367151737213135,
      "learning_rate": 0.00011363698275661001,
      "loss": 0.7318,
      "step": 155
    },
    {
      "epoch": 0.46846846846846846,
      "grad_norm": 2.3746261596679688,
      "learning_rate": 0.00011270178197468789,
      "loss": 0.7527,
      "step": 156
    },
    {
      "epoch": 0.47147147147147145,
      "grad_norm": 4.308503150939941,
      "learning_rate": 0.00011176545068718385,
      "loss": 1.6989,
      "step": 157
    },
    {
      "epoch": 0.4744744744744745,
      "grad_norm": 2.32792067527771,
      "learning_rate": 0.0001108280722310462,
      "loss": 1.262,
      "step": 158
    },
    {
      "epoch": 0.4774774774774775,
      "grad_norm": 4.225987911224365,
      "learning_rate": 0.00010988973003642499,
      "loss": 1.4396,
      "step": 159
    },
    {
      "epoch": 0.4804804804804805,
      "grad_norm": 3.8827497959136963,
      "learning_rate": 0.00010895050761924668,
      "loss": 1.5353,
      "step": 160
    },
    {
      "epoch": 0.48348348348348347,
      "grad_norm": 3.854318380355835,
      "learning_rate": 0.00010801048857378071,
      "loss": 1.4654,
      "step": 161
    },
    {
      "epoch": 0.4864864864864865,
      "grad_norm": 2.3658535480499268,
      "learning_rate": 0.00010706975656519946,
      "loss": 1.0751,
      "step": 162
    },
    {
      "epoch": 0.4894894894894895,
      "grad_norm": 6.701672554016113,
      "learning_rate": 0.00010612839532213164,
      "loss": 1.6829,
      "step": 163
    },
    {
      "epoch": 0.4924924924924925,
      "grad_norm": 3.207954168319702,
      "learning_rate": 0.00010518648862921012,
      "loss": 1.4072,
      "step": 164
    },
    {
      "epoch": 0.4954954954954955,
      "grad_norm": 2.800644636154175,
      "learning_rate": 0.00010424412031961484,
      "loss": 1.0728,
      "step": 165
    },
    {
      "epoch": 0.4984984984984985,
      "grad_norm": 4.086751461029053,
      "learning_rate": 0.00010330137426761135,
      "loss": 1.1628,
      "step": 166
    },
    {
      "epoch": 0.5015015015015015,
      "grad_norm": 2.659355640411377,
      "learning_rate": 0.00010235833438108571,
      "loss": 1.1724,
      "step": 167
    },
    {
      "epoch": 0.5045045045045045,
      "grad_norm": 3.152151107788086,
      "learning_rate": 0.00010141508459407623,
      "loss": 1.2078,
      "step": 168
    },
    {
      "epoch": 0.5075075075075075,
      "grad_norm": 3.8074827194213867,
      "learning_rate": 0.00010047170885930324,
      "loss": 1.1832,
      "step": 169
    },
    {
      "epoch": 0.5105105105105106,
      "grad_norm": 3.1562180519104004,
      "learning_rate": 9.95282911406968e-05,
      "loss": 1.1005,
      "step": 170
    },
    {
      "epoch": 0.5135135135135135,
      "grad_norm": 2.793989419937134,
      "learning_rate": 9.858491540592382e-05,
      "loss": 1.0381,
      "step": 171
    },
    {
      "epoch": 0.5165165165165165,
      "grad_norm": 3.589442491531372,
      "learning_rate": 9.764166561891432e-05,
      "loss": 0.9335,
      "step": 172
    },
    {
      "epoch": 0.5195195195195195,
      "grad_norm": 4.19896125793457,
      "learning_rate": 9.669862573238863e-05,
      "loss": 1.1411,
      "step": 173
    },
    {
      "epoch": 0.5225225225225225,
      "grad_norm": 3.931088924407959,
      "learning_rate": 9.57558796803852e-05,
      "loss": 1.0498,
      "step": 174
    },
    {
      "epoch": 0.5255255255255256,
      "grad_norm": 2.746661424636841,
      "learning_rate": 9.48135113707899e-05,
      "loss": 1.0747,
      "step": 175
    },
    {
      "epoch": 0.5285285285285285,
      "grad_norm": 2.2940986156463623,
      "learning_rate": 9.38716046778684e-05,
      "loss": 1.0899,
      "step": 176
    },
    {
      "epoch": 0.5315315315315315,
      "grad_norm": 2.696507692337036,
      "learning_rate": 9.293024343480055e-05,
      "loss": 0.7636,
      "step": 177
    },
    {
      "epoch": 0.5345345345345346,
      "grad_norm": 2.972304344177246,
      "learning_rate": 9.198951142621929e-05,
      "loss": 1.349,
      "step": 178
    },
    {
      "epoch": 0.5375375375375375,
      "grad_norm": 2.4269001483917236,
      "learning_rate": 9.104949238075336e-05,
      "loss": 1.1242,
      "step": 179
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 3.105961799621582,
      "learning_rate": 9.011026996357503e-05,
      "loss": 1.0303,
      "step": 180
    },
    {
      "epoch": 0.5435435435435435,
      "grad_norm": 2.861002206802368,
      "learning_rate": 8.917192776895382e-05,
      "loss": 1.2752,
      "step": 181
    },
    {
      "epoch": 0.5465465465465466,
      "grad_norm": 3.16262149810791,
      "learning_rate": 8.823454931281616e-05,
      "loss": 0.9932,
      "step": 182
    },
    {
      "epoch": 0.5495495495495496,
      "grad_norm": 2.2218563556671143,
      "learning_rate": 8.729821802531212e-05,
      "loss": 0.9025,
      "step": 183
    },
    {
      "epoch": 0.5525525525525525,
      "grad_norm": 3.3385350704193115,
      "learning_rate": 8.636301724339004e-05,
      "loss": 1.1192,
      "step": 184
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 1.895119071006775,
      "learning_rate": 8.542903020337887e-05,
      "loss": 0.7014,
      "step": 185
    },
    {
      "epoch": 0.5585585585585585,
      "grad_norm": 2.023733377456665,
      "learning_rate": 8.449634003358022e-05,
      "loss": 0.8134,
      "step": 186
    },
    {
      "epoch": 0.5615615615615616,
      "grad_norm": 3.346677303314209,
      "learning_rate": 8.356502974686941e-05,
      "loss": 0.8806,
      "step": 187
    },
    {
      "epoch": 0.5645645645645646,
      "grad_norm": 2.9996836185455322,
      "learning_rate": 8.263518223330697e-05,
      "loss": 1.3907,
      "step": 188
    },
    {
      "epoch": 0.5675675675675675,
      "grad_norm": 4.624329090118408,
      "learning_rate": 8.170688025276134e-05,
      "loss": 1.2675,
      "step": 189
    },
    {
      "epoch": 0.5705705705705706,
      "grad_norm": 4.569002628326416,
      "learning_rate": 8.078020642754274e-05,
      "loss": 1.176,
      "step": 190
    },
    {
      "epoch": 0.5735735735735735,
      "grad_norm": 4.073513031005859,
      "learning_rate": 7.985524323504948e-05,
      "loss": 1.058,
      "step": 191
    },
    {
      "epoch": 0.5765765765765766,
      "grad_norm": 3.1799652576446533,
      "learning_rate": 7.89320730004274e-05,
      "loss": 1.1819,
      "step": 192
    },
    {
      "epoch": 0.5795795795795796,
      "grad_norm": 3.175107002258301,
      "learning_rate": 7.801077788924224e-05,
      "loss": 1.1484,
      "step": 193
    },
    {
      "epoch": 0.5825825825825826,
      "grad_norm": 7.873251914978027,
      "learning_rate": 7.709143990016702e-05,
      "loss": 1.172,
      "step": 194
    },
    {
      "epoch": 0.5855855855855856,
      "grad_norm": 2.4473395347595215,
      "learning_rate": 7.617414085768351e-05,
      "loss": 1.0935,
      "step": 195
    },
    {
      "epoch": 0.5885885885885885,
      "grad_norm": 2.298689842224121,
      "learning_rate": 7.525896240479976e-05,
      "loss": 1.1773,
      "step": 196
    },
    {
      "epoch": 0.5915915915915916,
      "grad_norm": 3.7667293548583984,
      "learning_rate": 7.434598599578351e-05,
      "loss": 1.0643,
      "step": 197
    },
    {
      "epoch": 0.5945945945945946,
      "grad_norm": 2.9455878734588623,
      "learning_rate": 7.343529288891239e-05,
      "loss": 1.227,
      "step": 198
    },
    {
      "epoch": 0.5975975975975976,
      "grad_norm": 7.777294158935547,
      "learning_rate": 7.252696413924174e-05,
      "loss": 1.2713,
      "step": 199
    },
    {
      "epoch": 0.6006006006006006,
      "grad_norm": 2.827641248703003,
      "learning_rate": 7.162108059139032e-05,
      "loss": 1.2447,
      "step": 200
    },
    {
      "epoch": 0.6036036036036037,
      "grad_norm": 2.9091506004333496,
      "learning_rate": 7.071772287234497e-05,
      "loss": 1.0227,
      "step": 201
    },
    {
      "epoch": 0.6066066066066066,
      "grad_norm": 2.9833085536956787,
      "learning_rate": 6.981697138428434e-05,
      "loss": 0.9794,
      "step": 202
    },
    {
      "epoch": 0.6096096096096096,
      "grad_norm": 3.3673200607299805,
      "learning_rate": 6.891890629742288e-05,
      "loss": 0.9187,
      "step": 203
    },
    {
      "epoch": 0.6126126126126126,
      "grad_norm": 2.38704252243042,
      "learning_rate": 6.802360754287547e-05,
      "loss": 1.0263,
      "step": 204
    },
    {
      "epoch": 0.6156156156156156,
      "grad_norm": 4.426513195037842,
      "learning_rate": 6.713115480554313e-05,
      "loss": 1.1677,
      "step": 205
    },
    {
      "epoch": 0.6186186186186187,
      "grad_norm": 3.6128177642822266,
      "learning_rate": 6.624162751702076e-05,
      "loss": 1.3946,
      "step": 206
    },
    {
      "epoch": 0.6216216216216216,
      "grad_norm": 3.2020866870880127,
      "learning_rate": 6.535510484852767e-05,
      "loss": 1.5255,
      "step": 207
    },
    {
      "epoch": 0.6246246246246246,
      "grad_norm": 2.582364082336426,
      "learning_rate": 6.447166570386063e-05,
      "loss": 1.1196,
      "step": 208
    },
    {
      "epoch": 0.6276276276276276,
      "grad_norm": 3.6883230209350586,
      "learning_rate": 6.35913887123716e-05,
      "loss": 1.2505,
      "step": 209
    },
    {
      "epoch": 0.6306306306306306,
      "grad_norm": 2.0863749980926514,
      "learning_rate": 6.271435222196916e-05,
      "loss": 0.5439,
      "step": 210
    },
    {
      "epoch": 0.6336336336336337,
      "grad_norm": 1.9187757968902588,
      "learning_rate": 6.184063429214515e-05,
      "loss": 0.6077,
      "step": 211
    },
    {
      "epoch": 0.6366366366366366,
      "grad_norm": 2.5035970211029053,
      "learning_rate": 6.097031268702746e-05,
      "loss": 1.0272,
      "step": 212
    },
    {
      "epoch": 0.6396396396396397,
      "grad_norm": 2.1252877712249756,
      "learning_rate": 6.010346486845837e-05,
      "loss": 0.877,
      "step": 213
    },
    {
      "epoch": 0.6426426426426426,
      "grad_norm": 2.2181661128997803,
      "learning_rate": 5.924016798910037e-05,
      "loss": 0.7115,
      "step": 214
    },
    {
      "epoch": 0.6456456456456456,
      "grad_norm": 2.6346538066864014,
      "learning_rate": 5.838049888556925e-05,
      "loss": 1.2154,
      "step": 215
    },
    {
      "epoch": 0.6486486486486487,
      "grad_norm": 3.103731870651245,
      "learning_rate": 5.752453407159522e-05,
      "loss": 1.021,
      "step": 216
    },
    {
      "epoch": 0.6516516516516516,
      "grad_norm": 3.415545701980591,
      "learning_rate": 5.667234973121317e-05,
      "loss": 1.5522,
      "step": 217
    },
    {
      "epoch": 0.6546546546546547,
      "grad_norm": 3.22251558303833,
      "learning_rate": 5.5824021711981686e-05,
      "loss": 0.9561,
      "step": 218
    },
    {
      "epoch": 0.6576576576576577,
      "grad_norm": 2.920732259750366,
      "learning_rate": 5.497962551823266e-05,
      "loss": 1.0558,
      "step": 219
    },
    {
      "epoch": 0.6606606606606606,
      "grad_norm": 4.05772590637207,
      "learning_rate": 5.4139236304350935e-05,
      "loss": 1.0468,
      "step": 220
    },
    {
      "epoch": 0.6636636636636637,
      "grad_norm": 2.826936960220337,
      "learning_rate": 5.33029288680852e-05,
      "loss": 1.1075,
      "step": 221
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 4.209110260009766,
      "learning_rate": 5.247077764389099e-05,
      "loss": 1.1172,
      "step": 222
    },
    {
      "epoch": 0.6696696696696697,
      "grad_norm": 3.3651530742645264,
      "learning_rate": 5.1642856696305575e-05,
      "loss": 1.0825,
      "step": 223
    },
    {
      "epoch": 0.6726726726726727,
      "grad_norm": 2.487950086593628,
      "learning_rate": 5.081923971335582e-05,
      "loss": 0.7995,
      "step": 224
    },
    {
      "epoch": 0.6756756756756757,
      "grad_norm": 3.0736727714538574,
      "learning_rate": 5.000000000000002e-05,
      "loss": 1.0645,
      "step": 225
    },
    {
      "epoch": 0.6786786786786787,
      "grad_norm": 4.154182434082031,
      "learning_rate": 4.918521047160308e-05,
      "loss": 1.784,
      "step": 226
    },
    {
      "epoch": 0.6816816816816816,
      "grad_norm": 2.6880645751953125,
      "learning_rate": 4.837494364744711e-05,
      "loss": 0.806,
      "step": 227
    },
    {
      "epoch": 0.6846846846846847,
      "grad_norm": 8.7504301071167,
      "learning_rate": 4.756927164427685e-05,
      "loss": 1.2716,
      "step": 228
    },
    {
      "epoch": 0.6876876876876877,
      "grad_norm": 3.641247510910034,
      "learning_rate": 4.6768266169880804e-05,
      "loss": 1.0403,
      "step": 229
    },
    {
      "epoch": 0.6906906906906907,
      "grad_norm": 2.9611194133758545,
      "learning_rate": 4.597199851670932e-05,
      "loss": 1.2985,
      "step": 230
    },
    {
      "epoch": 0.6936936936936937,
      "grad_norm": 2.1863701343536377,
      "learning_rate": 4.518053955552903e-05,
      "loss": 0.9741,
      "step": 231
    },
    {
      "epoch": 0.6966966966966966,
      "grad_norm": 2.5241053104400635,
      "learning_rate": 4.4393959729115244e-05,
      "loss": 1.0619,
      "step": 232
    },
    {
      "epoch": 0.6996996996996997,
      "grad_norm": 2.0366642475128174,
      "learning_rate": 4.3612329045982236e-05,
      "loss": 1.0319,
      "step": 233
    },
    {
      "epoch": 0.7027027027027027,
      "grad_norm": 3.1480021476745605,
      "learning_rate": 4.283571707415214e-05,
      "loss": 1.2822,
      "step": 234
    },
    {
      "epoch": 0.7057057057057057,
      "grad_norm": 3.6605899333953857,
      "learning_rate": 4.206419293496333e-05,
      "loss": 1.0404,
      "step": 235
    },
    {
      "epoch": 0.7087087087087087,
      "grad_norm": 2.7231175899505615,
      "learning_rate": 4.129782529691815e-05,
      "loss": 1.0927,
      "step": 236
    },
    {
      "epoch": 0.7117117117117117,
      "grad_norm": 2.513577938079834,
      "learning_rate": 4.053668236957134e-05,
      "loss": 1.2299,
      "step": 237
    },
    {
      "epoch": 0.7147147147147147,
      "grad_norm": 1.9379348754882812,
      "learning_rate": 3.978083189745907e-05,
      "loss": 0.7212,
      "step": 238
    },
    {
      "epoch": 0.7177177177177178,
      "grad_norm": 2.7951018810272217,
      "learning_rate": 3.903034115406931e-05,
      "loss": 1.0704,
      "step": 239
    },
    {
      "epoch": 0.7207207207207207,
      "grad_norm": 2.4771158695220947,
      "learning_rate": 3.828527693585451e-05,
      "loss": 1.0166,
      "step": 240
    },
    {
      "epoch": 0.7237237237237237,
      "grad_norm": 3.3941121101379395,
      "learning_rate": 3.7545705556286126e-05,
      "loss": 1.5398,
      "step": 241
    },
    {
      "epoch": 0.7267267267267268,
      "grad_norm": 2.322334051132202,
      "learning_rate": 3.681169283995279e-05,
      "loss": 1.2624,
      "step": 242
    },
    {
      "epoch": 0.7297297297297297,
      "grad_norm": 2.8599162101745605,
      "learning_rate": 3.6083304116701535e-05,
      "loss": 1.1381,
      "step": 243
    },
    {
      "epoch": 0.7327327327327328,
      "grad_norm": 4.170224666595459,
      "learning_rate": 3.536060421582309e-05,
      "loss": 1.4004,
      "step": 244
    },
    {
      "epoch": 0.7357357357357357,
      "grad_norm": 3.191027879714966,
      "learning_rate": 3.464365746028208e-05,
      "loss": 1.1464,
      "step": 245
    },
    {
      "epoch": 0.7387387387387387,
      "grad_norm": 2.834343671798706,
      "learning_rate": 3.393252766099187e-05,
      "loss": 1.142,
      "step": 246
    },
    {
      "epoch": 0.7417417417417418,
      "grad_norm": 3.2168824672698975,
      "learning_rate": 3.322727811113516e-05,
      "loss": 1.2666,
      "step": 247
    },
    {
      "epoch": 0.7447447447447447,
      "grad_norm": 2.456047296524048,
      "learning_rate": 3.252797158053077e-05,
      "loss": 1.2571,
      "step": 248
    },
    {
      "epoch": 0.7477477477477478,
      "grad_norm": 2.9790220260620117,
      "learning_rate": 3.1834670310046734e-05,
      "loss": 1.2003,
      "step": 249
    },
    {
      "epoch": 0.7507507507507507,
      "grad_norm": 3.3574981689453125,
      "learning_rate": 3.114743600606078e-05,
      "loss": 1.3745,
      "step": 250
    },
    {
      "epoch": 0.7537537537537538,
      "grad_norm": 2.140984296798706,
      "learning_rate": 3.0466329834968233e-05,
      "loss": 0.8346,
      "step": 251
    },
    {
      "epoch": 0.7567567567567568,
      "grad_norm": 3.07039475440979,
      "learning_rate": 2.979141241773775e-05,
      "loss": 1.2459,
      "step": 252
    },
    {
      "epoch": 0.7597597597597597,
      "grad_norm": 2.29309344291687,
      "learning_rate": 2.9122743824516195e-05,
      "loss": 1.0559,
      "step": 253
    },
    {
      "epoch": 0.7627627627627628,
      "grad_norm": 2.319108247756958,
      "learning_rate": 2.8460383569281824e-05,
      "loss": 0.8545,
      "step": 254
    },
    {
      "epoch": 0.7657657657657657,
      "grad_norm": 3.5860605239868164,
      "learning_rate": 2.7804390604547557e-05,
      "loss": 0.9624,
      "step": 255
    },
    {
      "epoch": 0.7687687687687688,
      "grad_norm": 2.4737586975097656,
      "learning_rate": 2.7154823316113932e-05,
      "loss": 1.1101,
      "step": 256
    },
    {
      "epoch": 0.7717717717717718,
      "grad_norm": 2.6330103874206543,
      "learning_rate": 2.6511739517872426e-05,
      "loss": 1.1027,
      "step": 257
    },
    {
      "epoch": 0.7747747747747747,
      "grad_norm": 2.807921886444092,
      "learning_rate": 2.587519644666001e-05,
      "loss": 0.8148,
      "step": 258
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 4.0378546714782715,
      "learning_rate": 2.5245250757164663e-05,
      "loss": 1.3036,
      "step": 259
    },
    {
      "epoch": 0.7807807807807807,
      "grad_norm": 2.8638672828674316,
      "learning_rate": 2.462195851688306e-05,
      "loss": 0.8851,
      "step": 260
    },
    {
      "epoch": 0.7837837837837838,
      "grad_norm": 2.558032512664795,
      "learning_rate": 2.4005375201130274e-05,
      "loss": 1.1158,
      "step": 261
    },
    {
      "epoch": 0.7867867867867868,
      "grad_norm": 1.8975292444229126,
      "learning_rate": 2.339555568810221e-05,
      "loss": 0.8933,
      "step": 262
    },
    {
      "epoch": 0.7897897897897898,
      "grad_norm": 2.8043062686920166,
      "learning_rate": 2.2792554253991415e-05,
      "loss": 0.9539,
      "step": 263
    },
    {
      "epoch": 0.7927927927927928,
      "grad_norm": 3.37785267829895,
      "learning_rate": 2.2196424568156073e-05,
      "loss": 1.3296,
      "step": 264
    },
    {
      "epoch": 0.7957957957957958,
      "grad_norm": 2.7959485054016113,
      "learning_rate": 2.160721968834344e-05,
      "loss": 1.1462,
      "step": 265
    },
    {
      "epoch": 0.7987987987987988,
      "grad_norm": 7.449779510498047,
      "learning_rate": 2.102499205596743e-05,
      "loss": 1.0893,
      "step": 266
    },
    {
      "epoch": 0.8018018018018018,
      "grad_norm": 6.506124019622803,
      "learning_rate": 2.0449793491441028e-05,
      "loss": 1.1367,
      "step": 267
    },
    {
      "epoch": 0.8048048048048048,
      "grad_norm": 2.821166515350342,
      "learning_rate": 1.9881675189564254e-05,
      "loss": 1.6805,
      "step": 268
    },
    {
      "epoch": 0.8078078078078078,
      "grad_norm": 2.951826333999634,
      "learning_rate": 1.93206877149676e-05,
      "loss": 0.8443,
      "step": 269
    },
    {
      "epoch": 0.8108108108108109,
      "grad_norm": 3.3361992835998535,
      "learning_rate": 1.8766880997611424e-05,
      "loss": 1.2579,
      "step": 270
    },
    {
      "epoch": 0.8138138138138138,
      "grad_norm": 1.7760874032974243,
      "learning_rate": 1.8220304328342252e-05,
      "loss": 0.6704,
      "step": 271
    },
    {
      "epoch": 0.8168168168168168,
      "grad_norm": 3.165902614593506,
      "learning_rate": 1.7681006354505493e-05,
      "loss": 1.0814,
      "step": 272
    },
    {
      "epoch": 0.8198198198198198,
      "grad_norm": 2.863865613937378,
      "learning_rate": 1.7149035075615794e-05,
      "loss": 1.0898,
      "step": 273
    },
    {
      "epoch": 0.8228228228228228,
      "grad_norm": 2.5821480751037598,
      "learning_rate": 1.6624437839084862e-05,
      "loss": 0.8588,
      "step": 274
    },
    {
      "epoch": 0.8258258258258259,
      "grad_norm": 3.5799527168273926,
      "learning_rate": 1.6107261336007285e-05,
      "loss": 1.2082,
      "step": 275
    },
    {
      "epoch": 0.8288288288288288,
      "grad_norm": 1.9022583961486816,
      "learning_rate": 1.5597551597004966e-05,
      "loss": 0.8508,
      "step": 276
    },
    {
      "epoch": 0.8318318318318318,
      "grad_norm": 3.3668415546417236,
      "learning_rate": 1.5095353988130235e-05,
      "loss": 1.4462,
      "step": 277
    },
    {
      "epoch": 0.8348348348348348,
      "grad_norm": 3.1614718437194824,
      "learning_rate": 1.4600713206827932e-05,
      "loss": 0.7332,
      "step": 278
    },
    {
      "epoch": 0.8378378378378378,
      "grad_norm": 3.1946263313293457,
      "learning_rate": 1.4113673277957395e-05,
      "loss": 1.2424,
      "step": 279
    },
    {
      "epoch": 0.8408408408408409,
      "grad_norm": 3.346984386444092,
      "learning_rate": 1.3634277549873953e-05,
      "loss": 1.1425,
      "step": 280
    },
    {
      "epoch": 0.8438438438438438,
      "grad_norm": 2.6733968257904053,
      "learning_rate": 1.3162568690570743e-05,
      "loss": 1.0175,
      "step": 281
    },
    {
      "epoch": 0.8468468468468469,
      "grad_norm": 3.606302499771118,
      "learning_rate": 1.2698588683881186e-05,
      "loss": 1.1272,
      "step": 282
    },
    {
      "epoch": 0.8498498498498499,
      "grad_norm": 3.11902117729187,
      "learning_rate": 1.224237882574224e-05,
      "loss": 0.8483,
      "step": 283
    },
    {
      "epoch": 0.8528528528528528,
      "grad_norm": 2.8845720291137695,
      "learning_rate": 1.1793979720518866e-05,
      "loss": 0.9861,
      "step": 284
    },
    {
      "epoch": 0.8558558558558559,
      "grad_norm": 3.02492094039917,
      "learning_rate": 1.1353431277390126e-05,
      "loss": 1.2887,
      "step": 285
    },
    {
      "epoch": 0.8588588588588588,
      "grad_norm": 3.848069906234741,
      "learning_rate": 1.0920772706797167e-05,
      "loss": 1.0295,
      "step": 286
    },
    {
      "epoch": 0.8618618618618619,
      "grad_norm": 2.647904396057129,
      "learning_rate": 1.0496042516953209e-05,
      "loss": 0.9551,
      "step": 287
    },
    {
      "epoch": 0.8648648648648649,
      "grad_norm": 2.807253360748291,
      "learning_rate": 1.0079278510416313e-05,
      "loss": 0.7592,
      "step": 288
    },
    {
      "epoch": 0.8678678678678678,
      "grad_norm": 3.8293511867523193,
      "learning_rate": 9.670517780724775e-06,
      "loss": 1.0225,
      "step": 289
    },
    {
      "epoch": 0.8708708708708709,
      "grad_norm": 2.4294826984405518,
      "learning_rate": 9.269796709095558e-06,
      "loss": 1.4176,
      "step": 290
    },
    {
      "epoch": 0.8738738738738738,
      "grad_norm": 4.781210899353027,
      "learning_rate": 8.87715096118642e-06,
      "loss": 0.8798,
      "step": 291
    },
    {
      "epoch": 0.8768768768768769,
      "grad_norm": 2.406425714492798,
      "learning_rate": 8.492615483921395e-06,
      "loss": 0.8694,
      "step": 292
    },
    {
      "epoch": 0.8798798798798799,
      "grad_norm": 1.9549373388290405,
      "learning_rate": 8.116224502380387e-06,
      "loss": 1.1899,
      "step": 293
    },
    {
      "epoch": 0.8828828828828829,
      "grad_norm": 3.0934197902679443,
      "learning_rate": 7.74801151675314e-06,
      "loss": 0.9323,
      "step": 294
    },
    {
      "epoch": 0.8858858858858859,
      "grad_norm": 4.107941150665283,
      "learning_rate": 7.3880092993574125e-06,
      "loss": 1.3923,
      "step": 295
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 2.7095839977264404,
      "learning_rate": 7.03624989172228e-06,
      "loss": 0.8522,
      "step": 296
    },
    {
      "epoch": 0.8918918918918919,
      "grad_norm": 1.8515009880065918,
      "learning_rate": 6.692764601736268e-06,
      "loss": 0.6926,
      "step": 297
    },
    {
      "epoch": 0.8948948948948949,
      "grad_norm": 3.2831356525421143,
      "learning_rate": 6.357584000860761e-06,
      "loss": 0.9239,
      "step": 298
    },
    {
      "epoch": 0.8978978978978979,
      "grad_norm": 2.5845866203308105,
      "learning_rate": 6.030737921409169e-06,
      "loss": 0.8028,
      "step": 299
    },
    {
      "epoch": 0.9009009009009009,
      "grad_norm": 2.855114221572876,
      "learning_rate": 5.71225545389158e-06,
      "loss": 1.1832,
      "step": 300
    },
    {
      "epoch": 0.9039039039039038,
      "grad_norm": 3.3236331939697266,
      "learning_rate": 5.402164944425758e-06,
      "loss": 1.1724,
      "step": 301
    },
    {
      "epoch": 0.9069069069069069,
      "grad_norm": 6.83448600769043,
      "learning_rate": 5.100493992214128e-06,
      "loss": 1.3314,
      "step": 302
    },
    {
      "epoch": 0.9099099099099099,
      "grad_norm": 2.863325834274292,
      "learning_rate": 4.807269447087348e-06,
      "loss": 1.0996,
      "step": 303
    },
    {
      "epoch": 0.9129129129129129,
      "grad_norm": 3.2937326431274414,
      "learning_rate": 4.5225174071146455e-06,
      "loss": 1.1262,
      "step": 304
    },
    {
      "epoch": 0.9159159159159159,
      "grad_norm": 4.532299995422363,
      "learning_rate": 4.24626321628091e-06,
      "loss": 0.8499,
      "step": 305
    },
    {
      "epoch": 0.918918918918919,
      "grad_norm": 3.1992688179016113,
      "learning_rate": 3.9785314622310495e-06,
      "loss": 1.3525,
      "step": 306
    },
    {
      "epoch": 0.9219219219219219,
      "grad_norm": 2.4705193042755127,
      "learning_rate": 3.7193459740815674e-06,
      "loss": 1.0908,
      "step": 307
    },
    {
      "epoch": 0.924924924924925,
      "grad_norm": 2.904529333114624,
      "learning_rate": 3.4687298202996655e-06,
      "loss": 0.9582,
      "step": 308
    },
    {
      "epoch": 0.9279279279279279,
      "grad_norm": 2.3138301372528076,
      "learning_rate": 3.226705306650113e-06,
      "loss": 1.2733,
      "step": 309
    },
    {
      "epoch": 0.9309309309309309,
      "grad_norm": 2.09416127204895,
      "learning_rate": 2.9932939742099208e-06,
      "loss": 0.7504,
      "step": 310
    },
    {
      "epoch": 0.933933933933934,
      "grad_norm": 3.167368173599243,
      "learning_rate": 2.7685165974510986e-06,
      "loss": 1.2412,
      "step": 311
    },
    {
      "epoch": 0.9369369369369369,
      "grad_norm": 3.094839572906494,
      "learning_rate": 2.552393182391677e-06,
      "loss": 0.9607,
      "step": 312
    },
    {
      "epoch": 0.93993993993994,
      "grad_norm": 2.5439722537994385,
      "learning_rate": 2.3449429648150665e-06,
      "loss": 1.1211,
      "step": 313
    },
    {
      "epoch": 0.9429429429429429,
      "grad_norm": 3.0354812145233154,
      "learning_rate": 2.1461844085580385e-06,
      "loss": 1.1613,
      "step": 314
    },
    {
      "epoch": 0.9459459459459459,
      "grad_norm": 2.3744139671325684,
      "learning_rate": 1.9561352038673263e-06,
      "loss": 0.9695,
      "step": 315
    },
    {
      "epoch": 0.948948948948949,
      "grad_norm": 4.216712474822998,
      "learning_rate": 1.7748122658251876e-06,
      "loss": 0.7317,
      "step": 316
    },
    {
      "epoch": 0.9519519519519519,
      "grad_norm": 2.2783091068267822,
      "learning_rate": 1.6022317328438506e-06,
      "loss": 1.0139,
      "step": 317
    },
    {
      "epoch": 0.954954954954955,
      "grad_norm": 3.2791147232055664,
      "learning_rate": 1.4384089652291543e-06,
      "loss": 1.1532,
      "step": 318
    },
    {
      "epoch": 0.9579579579579579,
      "grad_norm": 2.5588083267211914,
      "learning_rate": 1.2833585438134287e-06,
      "loss": 0.9971,
      "step": 319
    },
    {
      "epoch": 0.960960960960961,
      "grad_norm": 2.4663734436035156,
      "learning_rate": 1.1370942686577347e-06,
      "loss": 1.1583,
      "step": 320
    },
    {
      "epoch": 0.963963963963964,
      "grad_norm": 3.0910394191741943,
      "learning_rate": 9.996291578236228e-07,
      "loss": 1.3676,
      "step": 321
    },
    {
      "epoch": 0.9669669669669669,
      "grad_norm": 2.7286369800567627,
      "learning_rate": 8.709754462144615e-07,
      "loss": 1.1954,
      "step": 322
    },
    {
      "epoch": 0.96996996996997,
      "grad_norm": 2.4788362979888916,
      "learning_rate": 7.511445844864962e-07,
      "loss": 0.6394,
      "step": 323
    },
    {
      "epoch": 0.972972972972973,
      "grad_norm": 2.686504364013672,
      "learning_rate": 6.401472380297091e-07,
      "loss": 1.2232,
      "step": 324
    },
    {
      "epoch": 0.975975975975976,
      "grad_norm": 2.3043410778045654,
      "learning_rate": 5.379932860185122e-07,
      "loss": 0.8467,
      "step": 325
    },
    {
      "epoch": 0.978978978978979,
      "grad_norm": 2.39601993560791,
      "learning_rate": 4.44691820532539e-07,
      "loss": 1.031,
      "step": 326
    },
    {
      "epoch": 0.9819819819819819,
      "grad_norm": 3.4683892726898193,
      "learning_rate": 3.6025114574734785e-07,
      "loss": 1.2397,
      "step": 327
    },
    {
      "epoch": 0.984984984984985,
      "grad_norm": 3.130098819732666,
      "learning_rate": 2.846787771953574e-07,
      "loss": 1.0141,
      "step": 328
    },
    {
      "epoch": 0.987987987987988,
      "grad_norm": 3.894436836242676,
      "learning_rate": 2.179814410969261e-07,
      "loss": 1.4286,
      "step": 329
    },
    {
      "epoch": 0.990990990990991,
      "grad_norm": 3.297236919403076,
      "learning_rate": 1.6016507376169777e-07,
      "loss": 1.2933,
      "step": 330
    },
    {
      "epoch": 0.993993993993994,
      "grad_norm": 4.986927509307861,
      "learning_rate": 1.1123482106021322e-07,
      "loss": 1.6548,
      "step": 331
    },
    {
      "epoch": 0.996996996996997,
      "grad_norm": 3.8665215969085693,
      "learning_rate": 7.119503796599868e-08,
      "loss": 0.8686,
      "step": 332
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.562675952911377,
      "learning_rate": 4.0049288167842705e-08,
      "loss": 0.8482,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.0635182857513428,
      "eval_runtime": 6.3055,
      "eval_samples_per_second": 11.26,
      "eval_steps_per_second": 11.26,
      "step": 333
    }
  ],
  "logging_steps": 1,
  "max_steps": 333,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.159048946325914e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}