{
  "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": 8.949604988098145,
      "learning_rate": 0.0001999955498150411,
      "loss": 2.3407,
      "step": 3
    },
    {
      "epoch": 0.012012012012012012,
      "grad_norm": 3.158568859100342,
      "learning_rate": 0.00019998219965624734,
      "loss": 1.9823,
      "step": 4
    },
    {
      "epoch": 0.015015015015015015,
      "grad_norm": 2.2516987323760986,
      "learning_rate": 0.0001999599507118322,
      "loss": 1.3624,
      "step": 5
    },
    {
      "epoch": 0.018018018018018018,
      "grad_norm": 4.390817642211914,
      "learning_rate": 0.000199928804962034,
      "loss": 2.4517,
      "step": 6
    },
    {
      "epoch": 0.021021021021021023,
      "grad_norm": 3.761112689971924,
      "learning_rate": 0.0001998887651789398,
      "loss": 1.9101,
      "step": 7
    },
    {
      "epoch": 0.024024024024024024,
      "grad_norm": 3.4166648387908936,
      "learning_rate": 0.00019983983492623833,
      "loss": 1.6885,
      "step": 8
    },
    {
      "epoch": 0.02702702702702703,
      "grad_norm": 3.3827452659606934,
      "learning_rate": 0.00019978201855890308,
      "loss": 1.4844,
      "step": 9
    },
    {
      "epoch": 0.03003003003003003,
      "grad_norm": 5.928102016448975,
      "learning_rate": 0.00019971532122280464,
      "loss": 2.0922,
      "step": 10
    },
    {
      "epoch": 0.03303303303303303,
      "grad_norm": 3.9921727180480957,
      "learning_rate": 0.00019963974885425266,
      "loss": 1.9214,
      "step": 11
    },
    {
      "epoch": 0.036036036036036036,
      "grad_norm": 6.364567279815674,
      "learning_rate": 0.00019955530817946748,
      "loss": 1.9784,
      "step": 12
    },
    {
      "epoch": 0.03903903903903904,
      "grad_norm": 6.44351053237915,
      "learning_rate": 0.0001994620067139815,
      "loss": 1.9525,
      "step": 13
    },
    {
      "epoch": 0.042042042042042045,
      "grad_norm": 4.626143455505371,
      "learning_rate": 0.0001993598527619703,
      "loss": 1.8573,
      "step": 14
    },
    {
      "epoch": 0.04504504504504504,
      "grad_norm": 5.128786087036133,
      "learning_rate": 0.0001992488554155135,
      "loss": 1.7945,
      "step": 15
    },
    {
      "epoch": 0.04804804804804805,
      "grad_norm": 4.881668567657471,
      "learning_rate": 0.00019912902455378556,
      "loss": 1.5265,
      "step": 16
    },
    {
      "epoch": 0.05105105105105105,
      "grad_norm": 5.330976486206055,
      "learning_rate": 0.00019900037084217637,
      "loss": 1.0192,
      "step": 17
    },
    {
      "epoch": 0.05405405405405406,
      "grad_norm": 4.7276458740234375,
      "learning_rate": 0.00019886290573134228,
      "loss": 1.7171,
      "step": 18
    },
    {
      "epoch": 0.057057057057057055,
      "grad_norm": 4.941858768463135,
      "learning_rate": 0.00019871664145618657,
      "loss": 1.0095,
      "step": 19
    },
    {
      "epoch": 0.06006006006006006,
      "grad_norm": 3.3863754272460938,
      "learning_rate": 0.00019856159103477086,
      "loss": 1.0899,
      "step": 20
    },
    {
      "epoch": 0.06306306306306306,
      "grad_norm": 4.0780029296875,
      "learning_rate": 0.00019839776826715614,
      "loss": 1.7246,
      "step": 21
    },
    {
      "epoch": 0.06606606606606606,
      "grad_norm": 4.969494342803955,
      "learning_rate": 0.0001982251877341748,
      "loss": 1.2525,
      "step": 22
    },
    {
      "epoch": 0.06906906906906907,
      "grad_norm": 9.143044471740723,
      "learning_rate": 0.0001980438647961327,
      "loss": 1.642,
      "step": 23
    },
    {
      "epoch": 0.07207207207207207,
      "grad_norm": 4.1555070877075195,
      "learning_rate": 0.00019785381559144196,
      "loss": 1.4793,
      "step": 24
    },
    {
      "epoch": 0.07507507507507508,
      "grad_norm": 4.046628952026367,
      "learning_rate": 0.00019765505703518496,
      "loss": 0.85,
      "step": 25
    },
    {
      "epoch": 0.07807807807807808,
      "grad_norm": 4.636494159698486,
      "learning_rate": 0.00019744760681760832,
      "loss": 1.3454,
      "step": 26
    },
    {
      "epoch": 0.08108108108108109,
      "grad_norm": 4.610245704650879,
      "learning_rate": 0.00019723148340254892,
      "loss": 1.7203,
      "step": 27
    },
    {
      "epoch": 0.08408408408408409,
      "grad_norm": 4.697399139404297,
      "learning_rate": 0.00019700670602579008,
      "loss": 1.5735,
      "step": 28
    },
    {
      "epoch": 0.08708708708708708,
      "grad_norm": 3.4270856380462646,
      "learning_rate": 0.0001967732946933499,
      "loss": 1.4224,
      "step": 29
    },
    {
      "epoch": 0.09009009009009009,
      "grad_norm": 6.80886697769165,
      "learning_rate": 0.00019653127017970034,
      "loss": 1.5906,
      "step": 30
    },
    {
      "epoch": 0.09309309309309309,
      "grad_norm": 2.8819735050201416,
      "learning_rate": 0.00019628065402591845,
      "loss": 1.2217,
      "step": 31
    },
    {
      "epoch": 0.0960960960960961,
      "grad_norm": 3.6171391010284424,
      "learning_rate": 0.00019602146853776894,
      "loss": 1.2468,
      "step": 32
    },
    {
      "epoch": 0.0990990990990991,
      "grad_norm": 4.199411869049072,
      "learning_rate": 0.00019575373678371909,
      "loss": 1.563,
      "step": 33
    },
    {
      "epoch": 0.1021021021021021,
      "grad_norm": 3.5157337188720703,
      "learning_rate": 0.00019547748259288536,
      "loss": 1.3674,
      "step": 34
    },
    {
      "epoch": 0.10510510510510511,
      "grad_norm": 3.1449432373046875,
      "learning_rate": 0.00019519273055291266,
      "loss": 1.2334,
      "step": 35
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": 3.480318546295166,
      "learning_rate": 0.0001948995060077859,
      "loss": 1.3391,
      "step": 36
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 3.561872720718384,
      "learning_rate": 0.00019459783505557424,
      "loss": 1.2206,
      "step": 37
    },
    {
      "epoch": 0.11411411411411411,
      "grad_norm": 2.9358267784118652,
      "learning_rate": 0.00019428774454610843,
      "loss": 1.0831,
      "step": 38
    },
    {
      "epoch": 0.11711711711711711,
      "grad_norm": 3.375826358795166,
      "learning_rate": 0.00019396926207859084,
      "loss": 0.991,
      "step": 39
    },
    {
      "epoch": 0.12012012012012012,
      "grad_norm": 4.3282246589660645,
      "learning_rate": 0.00019364241599913924,
      "loss": 0.9534,
      "step": 40
    },
    {
      "epoch": 0.12312312312312312,
      "grad_norm": 5.404246807098389,
      "learning_rate": 0.00019330723539826375,
      "loss": 1.5467,
      "step": 41
    },
    {
      "epoch": 0.12612612612612611,
      "grad_norm": 4.246641159057617,
      "learning_rate": 0.00019296375010827773,
      "loss": 1.3542,
      "step": 42
    },
    {
      "epoch": 0.12912912912912913,
      "grad_norm": 4.657464027404785,
      "learning_rate": 0.0001926119907006426,
      "loss": 0.8422,
      "step": 43
    },
    {
      "epoch": 0.13213213213213212,
      "grad_norm": 3.8296756744384766,
      "learning_rate": 0.0001922519884832469,
      "loss": 1.3043,
      "step": 44
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 4.33470344543457,
      "learning_rate": 0.00019188377549761963,
      "loss": 1.2141,
      "step": 45
    },
    {
      "epoch": 0.13813813813813813,
      "grad_norm": 3.89436674118042,
      "learning_rate": 0.0001915073845160786,
      "loss": 1.4874,
      "step": 46
    },
    {
      "epoch": 0.14114114114114115,
      "grad_norm": 4.670392990112305,
      "learning_rate": 0.0001911228490388136,
      "loss": 1.475,
      "step": 47
    },
    {
      "epoch": 0.14414414414414414,
      "grad_norm": 3.8425967693328857,
      "learning_rate": 0.00019073020329090444,
      "loss": 1.2083,
      "step": 48
    },
    {
      "epoch": 0.14714714714714713,
      "grad_norm": 3.335406541824341,
      "learning_rate": 0.00019032948221927524,
      "loss": 1.0553,
      "step": 49
    },
    {
      "epoch": 0.15015015015015015,
      "grad_norm": 3.949777364730835,
      "learning_rate": 0.00018992072148958368,
      "loss": 1.1888,
      "step": 50
    },
    {
      "epoch": 0.15315315315315314,
      "grad_norm": 5.711514949798584,
      "learning_rate": 0.00018950395748304678,
      "loss": 1.2669,
      "step": 51
    },
    {
      "epoch": 0.15615615615615616,
      "grad_norm": 3.32204008102417,
      "learning_rate": 0.00018907922729320285,
      "loss": 1.5032,
      "step": 52
    },
    {
      "epoch": 0.15915915915915915,
      "grad_norm": 3.5603139400482178,
      "learning_rate": 0.00018864656872260985,
      "loss": 1.1452,
      "step": 53
    },
    {
      "epoch": 0.16216216216216217,
      "grad_norm": 2.997321128845215,
      "learning_rate": 0.00018820602027948114,
      "loss": 1.1479,
      "step": 54
    },
    {
      "epoch": 0.16516516516516516,
      "grad_norm": 3.761380672454834,
      "learning_rate": 0.00018775762117425777,
      "loss": 1.1018,
      "step": 55
    },
    {
      "epoch": 0.16816816816816818,
      "grad_norm": 3.998138904571533,
      "learning_rate": 0.00018730141131611882,
      "loss": 0.9831,
      "step": 56
    },
    {
      "epoch": 0.17117117117117117,
      "grad_norm": 3.5861902236938477,
      "learning_rate": 0.00018683743130942928,
      "loss": 1.181,
      "step": 57
    },
    {
      "epoch": 0.17417417417417416,
      "grad_norm": 3.1308274269104004,
      "learning_rate": 0.00018636572245012606,
      "loss": 1.3986,
      "step": 58
    },
    {
      "epoch": 0.17717717717717718,
      "grad_norm": 10.603771209716797,
      "learning_rate": 0.00018588632672204264,
      "loss": 1.1666,
      "step": 59
    },
    {
      "epoch": 0.18018018018018017,
      "grad_norm": 4.469778537750244,
      "learning_rate": 0.0001853992867931721,
      "loss": 1.4776,
      "step": 60
    },
    {
      "epoch": 0.1831831831831832,
      "grad_norm": 3.3826351165771484,
      "learning_rate": 0.0001849046460118698,
      "loss": 1.3352,
      "step": 61
    },
    {
      "epoch": 0.18618618618618618,
      "grad_norm": 3.4881980419158936,
      "learning_rate": 0.00018440244840299506,
      "loss": 1.1307,
      "step": 62
    },
    {
      "epoch": 0.1891891891891892,
      "grad_norm": 3.8292853832244873,
      "learning_rate": 0.00018389273866399275,
      "loss": 1.4379,
      "step": 63
    },
    {
      "epoch": 0.1921921921921922,
      "grad_norm": 3.452981472015381,
      "learning_rate": 0.00018337556216091517,
      "loss": 1.3291,
      "step": 64
    },
    {
      "epoch": 0.19519519519519518,
      "grad_norm": 3.15205717086792,
      "learning_rate": 0.00018285096492438424,
      "loss": 1.1697,
      "step": 65
    },
    {
      "epoch": 0.1981981981981982,
      "grad_norm": 2.998598098754883,
      "learning_rate": 0.00018231899364549455,
      "loss": 0.8398,
      "step": 66
    },
    {
      "epoch": 0.2012012012012012,
      "grad_norm": 3.3119194507598877,
      "learning_rate": 0.0001817796956716578,
      "loss": 0.9666,
      "step": 67
    },
    {
      "epoch": 0.2042042042042042,
      "grad_norm": 3.2154204845428467,
      "learning_rate": 0.0001812331190023886,
      "loss": 1.0111,
      "step": 68
    },
    {
      "epoch": 0.2072072072072072,
      "grad_norm": 3.498479127883911,
      "learning_rate": 0.00018067931228503246,
      "loss": 1.4255,
      "step": 69
    },
    {
      "epoch": 0.21021021021021022,
      "grad_norm": 3.3297171592712402,
      "learning_rate": 0.00018011832481043576,
      "loss": 1.0459,
      "step": 70
    },
    {
      "epoch": 0.2132132132132132,
      "grad_norm": 3.0861032009124756,
      "learning_rate": 0.000179550206508559,
      "loss": 1.1825,
      "step": 71
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": 3.7197835445404053,
      "learning_rate": 0.0001789750079440326,
      "loss": 1.3545,
      "step": 72
    },
    {
      "epoch": 0.21921921921921922,
      "grad_norm": 2.9662370681762695,
      "learning_rate": 0.00017839278031165658,
      "loss": 1.1287,
      "step": 73
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 3.009904623031616,
      "learning_rate": 0.00017780357543184397,
      "loss": 1.1675,
      "step": 74
    },
    {
      "epoch": 0.22522522522522523,
      "grad_norm": 3.819753885269165,
      "learning_rate": 0.00017720744574600863,
      "loss": 1.2138,
      "step": 75
    },
    {
      "epoch": 0.22822822822822822,
      "grad_norm": 3.731964111328125,
      "learning_rate": 0.0001766044443118978,
      "loss": 1.4024,
      "step": 76
    },
    {
      "epoch": 0.23123123123123124,
      "grad_norm": 7.4664082527160645,
      "learning_rate": 0.00017599462479886974,
      "loss": 1.1637,
      "step": 77
    },
    {
      "epoch": 0.23423423423423423,
      "grad_norm": 3.3976633548736572,
      "learning_rate": 0.00017537804148311695,
      "loss": 1.2395,
      "step": 78
    },
    {
      "epoch": 0.23723723723723725,
      "grad_norm": 2.8055222034454346,
      "learning_rate": 0.00017475474924283536,
      "loss": 1.0323,
      "step": 79
    },
    {
      "epoch": 0.24024024024024024,
      "grad_norm": 5.117397308349609,
      "learning_rate": 0.00017412480355334005,
      "loss": 1.6292,
      "step": 80
    },
    {
      "epoch": 0.24324324324324326,
      "grad_norm": 6.144725799560547,
      "learning_rate": 0.0001734882604821276,
      "loss": 1.5008,
      "step": 81
    },
    {
      "epoch": 0.24624624624624625,
      "grad_norm": 3.7815804481506348,
      "learning_rate": 0.0001728451766838861,
      "loss": 1.3559,
      "step": 82
    },
    {
      "epoch": 0.24924924924924924,
      "grad_norm": 3.6141855716705322,
      "learning_rate": 0.00017219560939545246,
      "loss": 1.505,
      "step": 83
    },
    {
      "epoch": 0.25225225225225223,
      "grad_norm": 2.9968454837799072,
      "learning_rate": 0.0001715396164307182,
      "loss": 1.1781,
      "step": 84
    },
    {
      "epoch": 0.2552552552552553,
      "grad_norm": 2.8306217193603516,
      "learning_rate": 0.00017087725617548385,
      "loss": 1.1847,
      "step": 85
    },
    {
      "epoch": 0.25825825825825827,
      "grad_norm": 2.852055788040161,
      "learning_rate": 0.00017020858758226229,
      "loss": 1.0893,
      "step": 86
    },
    {
      "epoch": 0.26126126126126126,
      "grad_norm": 3.723259687423706,
      "learning_rate": 0.00016953367016503182,
      "loss": 1.2045,
      "step": 87
    },
    {
      "epoch": 0.26426426426426425,
      "grad_norm": 2.880476236343384,
      "learning_rate": 0.00016885256399393924,
      "loss": 0.9824,
      "step": 88
    },
    {
      "epoch": 0.2672672672672673,
      "grad_norm": 2.7408432960510254,
      "learning_rate": 0.00016816532968995328,
      "loss": 0.9685,
      "step": 89
    },
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 6.530210494995117,
      "learning_rate": 0.00016747202841946928,
      "loss": 1.5825,
      "step": 90
    },
    {
      "epoch": 0.2732732732732733,
      "grad_norm": 3.415400266647339,
      "learning_rate": 0.00016677272188886483,
      "loss": 1.4,
      "step": 91
    },
    {
      "epoch": 0.27627627627627627,
      "grad_norm": 3.045269250869751,
      "learning_rate": 0.00016606747233900815,
      "loss": 1.0537,
      "step": 92
    },
    {
      "epoch": 0.27927927927927926,
      "grad_norm": 4.4474992752075195,
      "learning_rate": 0.00016535634253971794,
      "loss": 1.4919,
      "step": 93
    },
    {
      "epoch": 0.2822822822822823,
      "grad_norm": 3.2899246215820312,
      "learning_rate": 0.00016463939578417692,
      "loss": 0.9117,
      "step": 94
    },
    {
      "epoch": 0.2852852852852853,
      "grad_norm": 3.275552749633789,
      "learning_rate": 0.0001639166958832985,
      "loss": 0.9903,
      "step": 95
    },
    {
      "epoch": 0.2882882882882883,
      "grad_norm": 4.8841118812561035,
      "learning_rate": 0.00016318830716004722,
      "loss": 1.615,
      "step": 96
    },
    {
      "epoch": 0.2912912912912913,
      "grad_norm": 4.650697231292725,
      "learning_rate": 0.0001624542944437139,
      "loss": 2.0446,
      "step": 97
    },
    {
      "epoch": 0.29429429429429427,
      "grad_norm": 3.8506672382354736,
      "learning_rate": 0.00016171472306414554,
      "loss": 1.3541,
      "step": 98
    },
    {
      "epoch": 0.2972972972972973,
      "grad_norm": 3.125844955444336,
      "learning_rate": 0.0001609696588459307,
      "loss": 0.9896,
      "step": 99
    },
    {
      "epoch": 0.3003003003003003,
      "grad_norm": 3.528669595718384,
      "learning_rate": 0.00016021916810254097,
      "loss": 1.2391,
      "step": 100
    },
    {
      "epoch": 0.3033033033033033,
      "grad_norm": 2.1554737091064453,
      "learning_rate": 0.00015946331763042867,
      "loss": 0.8665,
      "step": 101
    },
    {
      "epoch": 0.3063063063063063,
      "grad_norm": 3.8150954246520996,
      "learning_rate": 0.00015870217470308188,
      "loss": 1.2792,
      "step": 102
    },
    {
      "epoch": 0.30930930930930933,
      "grad_norm": 2.630399465560913,
      "learning_rate": 0.0001579358070650367,
      "loss": 1.177,
      "step": 103
    },
    {
      "epoch": 0.3123123123123123,
      "grad_norm": 3.1974780559539795,
      "learning_rate": 0.00015716428292584787,
      "loss": 1.5204,
      "step": 104
    },
    {
      "epoch": 0.3153153153153153,
      "grad_norm": 3.4595398902893066,
      "learning_rate": 0.0001563876709540178,
      "loss": 1.261,
      "step": 105
    },
    {
      "epoch": 0.3183183183183183,
      "grad_norm": 4.504167556762695,
      "learning_rate": 0.00015560604027088477,
      "loss": 1.7519,
      "step": 106
    },
    {
      "epoch": 0.3213213213213213,
      "grad_norm": 2.0379419326782227,
      "learning_rate": 0.00015481946044447099,
      "loss": 0.7486,
      "step": 107
    },
    {
      "epoch": 0.32432432432432434,
      "grad_norm": 2.478163957595825,
      "learning_rate": 0.00015402800148329071,
      "loss": 0.8723,
      "step": 108
    },
    {
      "epoch": 0.32732732732732733,
      "grad_norm": 2.9465012550354004,
      "learning_rate": 0.0001532317338301192,
      "loss": 1.1437,
      "step": 109
    },
    {
      "epoch": 0.3303303303303303,
      "grad_norm": 3.080664873123169,
      "learning_rate": 0.00015243072835572318,
      "loss": 0.968,
      "step": 110
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 2.778723955154419,
      "learning_rate": 0.00015162505635255287,
      "loss": 1.0228,
      "step": 111
    },
    {
      "epoch": 0.33633633633633636,
      "grad_norm": 3.867264986038208,
      "learning_rate": 0.00015081478952839693,
      "loss": 1.3582,
      "step": 112
    },
    {
      "epoch": 0.33933933933933935,
      "grad_norm": 4.303924560546875,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.6162,
      "step": 113
    },
    {
      "epoch": 0.34234234234234234,
      "grad_norm": 3.681415319442749,
      "learning_rate": 0.0001491807602866442,
      "loss": 1.075,
      "step": 114
    },
    {
      "epoch": 0.34534534534534533,
      "grad_norm": 3.065018892288208,
      "learning_rate": 0.00014835714330369446,
      "loss": 0.7634,
      "step": 115
    },
    {
      "epoch": 0.3483483483483483,
      "grad_norm": 3.532973051071167,
      "learning_rate": 0.000147529222356109,
      "loss": 1.2287,
      "step": 116
    },
    {
      "epoch": 0.35135135135135137,
      "grad_norm": 4.905853748321533,
      "learning_rate": 0.00014669707113191483,
      "loss": 1.3884,
      "step": 117
    },
    {
      "epoch": 0.35435435435435436,
      "grad_norm": 2.8591182231903076,
      "learning_rate": 0.00014586076369564908,
      "loss": 1.0066,
      "step": 118
    },
    {
      "epoch": 0.35735735735735735,
      "grad_norm": 5.718966007232666,
      "learning_rate": 0.00014502037448176734,
      "loss": 1.0447,
      "step": 119
    },
    {
      "epoch": 0.36036036036036034,
      "grad_norm": 3.5775551795959473,
      "learning_rate": 0.00014417597828801832,
      "loss": 1.0552,
      "step": 120
    },
    {
      "epoch": 0.3633633633633634,
      "grad_norm": 3.6629276275634766,
      "learning_rate": 0.00014332765026878687,
      "loss": 1.5753,
      "step": 121
    },
    {
      "epoch": 0.3663663663663664,
      "grad_norm": 3.239745616912842,
      "learning_rate": 0.0001424754659284048,
      "loss": 1.0734,
      "step": 122
    },
    {
      "epoch": 0.36936936936936937,
      "grad_norm": 3.027463674545288,
      "learning_rate": 0.00014161950111443077,
      "loss": 1.2182,
      "step": 123
    },
    {
      "epoch": 0.37237237237237236,
      "grad_norm": 2.7655885219573975,
      "learning_rate": 0.00014075983201089964,
      "loss": 0.8409,
      "step": 124
    },
    {
      "epoch": 0.37537537537537535,
      "grad_norm": 2.6868016719818115,
      "learning_rate": 0.00013989653513154165,
      "loss": 0.9132,
      "step": 125
    },
    {
      "epoch": 0.3783783783783784,
      "grad_norm": 4.335800647735596,
      "learning_rate": 0.00013902968731297255,
      "loss": 1.448,
      "step": 126
    },
    {
      "epoch": 0.3813813813813814,
      "grad_norm": 2.2871532440185547,
      "learning_rate": 0.00013815936570785487,
      "loss": 0.889,
      "step": 127
    },
    {
      "epoch": 0.3843843843843844,
      "grad_norm": 4.444313049316406,
      "learning_rate": 0.00013728564777803088,
      "loss": 0.8284,
      "step": 128
    },
    {
      "epoch": 0.38738738738738737,
      "grad_norm": 3.820131778717041,
      "learning_rate": 0.0001364086112876284,
      "loss": 0.8969,
      "step": 129
    },
    {
      "epoch": 0.39039039039039036,
      "grad_norm": 4.358783721923828,
      "learning_rate": 0.00013552833429613938,
      "loss": 1.3421,
      "step": 130
    },
    {
      "epoch": 0.3933933933933934,
      "grad_norm": 5.490592002868652,
      "learning_rate": 0.00013464489515147238,
      "loss": 1.3454,
      "step": 131
    },
    {
      "epoch": 0.3963963963963964,
      "grad_norm": 5.831946849822998,
      "learning_rate": 0.00013375837248297926,
      "loss": 1.3816,
      "step": 132
    },
    {
      "epoch": 0.3993993993993994,
      "grad_norm": 2.685199022293091,
      "learning_rate": 0.0001328688451944569,
      "loss": 1.4342,
      "step": 133
    },
    {
      "epoch": 0.4024024024024024,
      "grad_norm": 3.5410306453704834,
      "learning_rate": 0.00013197639245712454,
      "loss": 1.2398,
      "step": 134
    },
    {
      "epoch": 0.40540540540540543,
      "grad_norm": 4.072748184204102,
      "learning_rate": 0.00013108109370257712,
      "loss": 1.0573,
      "step": 135
    },
    {
      "epoch": 0.4084084084084084,
      "grad_norm": 2.7305827140808105,
      "learning_rate": 0.0001301830286157157,
      "loss": 0.9445,
      "step": 136
    },
    {
      "epoch": 0.4114114114114114,
      "grad_norm": 3.4876914024353027,
      "learning_rate": 0.00012928227712765504,
      "loss": 1.424,
      "step": 137
    },
    {
      "epoch": 0.4144144144144144,
      "grad_norm": 3.93389630317688,
      "learning_rate": 0.00012837891940860972,
      "loss": 1.3908,
      "step": 138
    },
    {
      "epoch": 0.4174174174174174,
      "grad_norm": 4.051177501678467,
      "learning_rate": 0.0001274730358607583,
      "loss": 1.487,
      "step": 139
    },
    {
      "epoch": 0.42042042042042044,
      "grad_norm": 3.429589033126831,
      "learning_rate": 0.00012656470711108764,
      "loss": 1.0791,
      "step": 140
    },
    {
      "epoch": 0.42342342342342343,
      "grad_norm": 4.349189281463623,
      "learning_rate": 0.00012565401400421651,
      "loss": 1.5873,
      "step": 141
    },
    {
      "epoch": 0.4264264264264264,
      "grad_norm": 3.6553049087524414,
      "learning_rate": 0.00012474103759520027,
      "loss": 1.1005,
      "step": 142
    },
    {
      "epoch": 0.4294294294294294,
      "grad_norm": 2.88079571723938,
      "learning_rate": 0.0001238258591423165,
      "loss": 1.2325,
      "step": 143
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 3.8122270107269287,
      "learning_rate": 0.000122908560099833,
      "loss": 1.0523,
      "step": 144
    },
    {
      "epoch": 0.43543543543543545,
      "grad_norm": 3.8025801181793213,
      "learning_rate": 0.00012198922211075778,
      "loss": 1.3929,
      "step": 145
    },
    {
      "epoch": 0.43843843843843844,
      "grad_norm": 2.05446195602417,
      "learning_rate": 0.00012106792699957263,
      "loss": 0.9597,
      "step": 146
    },
    {
      "epoch": 0.44144144144144143,
      "grad_norm": 2.6509203910827637,
      "learning_rate": 0.00012014475676495052,
      "loss": 1.0216,
      "step": 147
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 3.2547495365142822,
      "learning_rate": 0.0001192197935724573,
      "loss": 1.1975,
      "step": 148
    },
    {
      "epoch": 0.44744744744744747,
      "grad_norm": 2.5003983974456787,
      "learning_rate": 0.00011829311974723867,
      "loss": 0.9849,
      "step": 149
    },
    {
      "epoch": 0.45045045045045046,
      "grad_norm": 4.184463024139404,
      "learning_rate": 0.00011736481776669306,
      "loss": 1.6907,
      "step": 150
    },
    {
      "epoch": 0.45345345345345345,
      "grad_norm": 1.7590183019638062,
      "learning_rate": 0.00011643497025313061,
      "loss": 0.6678,
      "step": 151
    },
    {
      "epoch": 0.45645645645645644,
      "grad_norm": 2.4469213485717773,
      "learning_rate": 0.00011550365996641979,
      "loss": 1.084,
      "step": 152
    },
    {
      "epoch": 0.4594594594594595,
      "grad_norm": 4.256711959838867,
      "learning_rate": 0.00011457096979662114,
      "loss": 0.999,
      "step": 153
    },
    {
      "epoch": 0.4624624624624625,
      "grad_norm": 3.6662344932556152,
      "learning_rate": 0.00011363698275661001,
      "loss": 1.6327,
      "step": 154
    },
    {
      "epoch": 0.46546546546546547,
      "grad_norm": 2.139150619506836,
      "learning_rate": 0.00011270178197468789,
      "loss": 0.7365,
      "step": 155
    },
    {
      "epoch": 0.46846846846846846,
      "grad_norm": 2.397113561630249,
      "learning_rate": 0.00011176545068718385,
      "loss": 0.7469,
      "step": 156
    },
    {
      "epoch": 0.47147147147147145,
      "grad_norm": 4.046786785125732,
      "learning_rate": 0.0001108280722310462,
      "loss": 1.7294,
      "step": 157
    },
    {
      "epoch": 0.4744744744744745,
      "grad_norm": 3.422342538833618,
      "learning_rate": 0.00010988973003642499,
      "loss": 1.3217,
      "step": 158
    },
    {
      "epoch": 0.4774774774774775,
      "grad_norm": 4.208369255065918,
      "learning_rate": 0.00010895050761924668,
      "loss": 1.4273,
      "step": 159
    },
    {
      "epoch": 0.4804804804804805,
      "grad_norm": 4.233487129211426,
      "learning_rate": 0.00010801048857378071,
      "loss": 1.5523,
      "step": 160
    },
    {
      "epoch": 0.48348348348348347,
      "grad_norm": 3.681049346923828,
      "learning_rate": 0.00010706975656519946,
      "loss": 1.4675,
      "step": 161
    },
    {
      "epoch": 0.4864864864864865,
      "grad_norm": 2.444506883621216,
      "learning_rate": 0.00010612839532213164,
      "loss": 1.0676,
      "step": 162
    },
    {
      "epoch": 0.4894894894894895,
      "grad_norm": 5.741203784942627,
      "learning_rate": 0.00010518648862921012,
      "loss": 1.6099,
      "step": 163
    },
    {
      "epoch": 0.4924924924924925,
      "grad_norm": 3.325943946838379,
      "learning_rate": 0.00010424412031961484,
      "loss": 1.4014,
      "step": 164
    },
    {
      "epoch": 0.4954954954954955,
      "grad_norm": 3.2008140087127686,
      "learning_rate": 0.00010330137426761135,
      "loss": 1.0755,
      "step": 165
    },
    {
      "epoch": 0.4984984984984985,
      "grad_norm": 4.403491020202637,
      "learning_rate": 0.00010235833438108571,
      "loss": 1.1924,
      "step": 166
    },
    {
      "epoch": 0.5015015015015015,
      "grad_norm": 2.671586513519287,
      "learning_rate": 0.00010141508459407623,
      "loss": 1.2323,
      "step": 167
    },
    {
      "epoch": 0.5045045045045045,
      "grad_norm": 3.2359049320220947,
      "learning_rate": 0.00010047170885930324,
      "loss": 1.2092,
      "step": 168
    },
    {
      "epoch": 0.5075075075075075,
      "grad_norm": 4.325455188751221,
      "learning_rate": 9.95282911406968e-05,
      "loss": 1.1624,
      "step": 169
    },
    {
      "epoch": 0.5105105105105106,
      "grad_norm": 3.6989574432373047,
      "learning_rate": 9.858491540592382e-05,
      "loss": 1.0925,
      "step": 170
    },
    {
      "epoch": 0.5135135135135135,
      "grad_norm": 3.4216420650482178,
      "learning_rate": 9.764166561891432e-05,
      "loss": 1.0068,
      "step": 171
    },
    {
      "epoch": 0.5165165165165165,
      "grad_norm": 3.371088743209839,
      "learning_rate": 9.669862573238863e-05,
      "loss": 0.9391,
      "step": 172
    },
    {
      "epoch": 0.5195195195195195,
      "grad_norm": 3.9000446796417236,
      "learning_rate": 9.57558796803852e-05,
      "loss": 1.1322,
      "step": 173
    },
    {
      "epoch": 0.5225225225225225,
      "grad_norm": 4.006927967071533,
      "learning_rate": 9.48135113707899e-05,
      "loss": 1.0941,
      "step": 174
    },
    {
      "epoch": 0.5255255255255256,
      "grad_norm": 2.8356428146362305,
      "learning_rate": 9.38716046778684e-05,
      "loss": 1.0821,
      "step": 175
    },
    {
      "epoch": 0.5285285285285285,
      "grad_norm": 2.2834103107452393,
      "learning_rate": 9.293024343480055e-05,
      "loss": 1.0736,
      "step": 176
    },
    {
      "epoch": 0.5315315315315315,
      "grad_norm": 2.1150338649749756,
      "learning_rate": 9.198951142621929e-05,
      "loss": 0.7405,
      "step": 177
    },
    {
      "epoch": 0.5345345345345346,
      "grad_norm": 4.170374393463135,
      "learning_rate": 9.104949238075336e-05,
      "loss": 1.3548,
      "step": 178
    },
    {
      "epoch": 0.5375375375375375,
      "grad_norm": 2.320065975189209,
      "learning_rate": 9.011026996357503e-05,
      "loss": 1.1287,
      "step": 179
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 3.3114922046661377,
      "learning_rate": 8.917192776895382e-05,
      "loss": 1.0874,
      "step": 180
    },
    {
      "epoch": 0.5435435435435435,
      "grad_norm": 2.822983980178833,
      "learning_rate": 8.823454931281616e-05,
      "loss": 1.2849,
      "step": 181
    },
    {
      "epoch": 0.5465465465465466,
      "grad_norm": 5.101154804229736,
      "learning_rate": 8.729821802531212e-05,
      "loss": 1.0091,
      "step": 182
    },
    {
      "epoch": 0.5495495495495496,
      "grad_norm": 2.1716604232788086,
      "learning_rate": 8.636301724339004e-05,
      "loss": 0.9004,
      "step": 183
    },
    {
      "epoch": 0.5525525525525525,
      "grad_norm": 3.0461654663085938,
      "learning_rate": 8.542903020337887e-05,
      "loss": 1.1352,
      "step": 184
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 1.9528117179870605,
      "learning_rate": 8.449634003358022e-05,
      "loss": 0.7149,
      "step": 185
    },
    {
      "epoch": 0.5585585585585585,
      "grad_norm": 2.121596097946167,
      "learning_rate": 8.356502974686941e-05,
      "loss": 0.8156,
      "step": 186
    },
    {
      "epoch": 0.5615615615615616,
      "grad_norm": 3.440051317214966,
      "learning_rate": 8.263518223330697e-05,
      "loss": 0.8836,
      "step": 187
    },
    {
      "epoch": 0.5645645645645646,
      "grad_norm": 3.4065990447998047,
      "learning_rate": 8.170688025276134e-05,
      "loss": 1.3883,
      "step": 188
    },
    {
      "epoch": 0.5675675675675675,
      "grad_norm": 4.436142444610596,
      "learning_rate": 8.078020642754274e-05,
      "loss": 1.247,
      "step": 189
    },
    {
      "epoch": 0.5705705705705706,
      "grad_norm": 4.292184829711914,
      "learning_rate": 7.985524323504948e-05,
      "loss": 1.1434,
      "step": 190
    },
    {
      "epoch": 0.5735735735735735,
      "grad_norm": 3.944159984588623,
      "learning_rate": 7.89320730004274e-05,
      "loss": 1.0251,
      "step": 191
    },
    {
      "epoch": 0.5765765765765766,
      "grad_norm": 3.428690195083618,
      "learning_rate": 7.801077788924224e-05,
      "loss": 1.2212,
      "step": 192
    },
    {
      "epoch": 0.5795795795795796,
      "grad_norm": 2.958847761154175,
      "learning_rate": 7.709143990016702e-05,
      "loss": 1.1812,
      "step": 193
    },
    {
      "epoch": 0.5825825825825826,
      "grad_norm": 4.4013214111328125,
      "learning_rate": 7.617414085768351e-05,
      "loss": 1.1677,
      "step": 194
    },
    {
      "epoch": 0.5855855855855856,
      "grad_norm": 2.435934543609619,
      "learning_rate": 7.525896240479976e-05,
      "loss": 1.0538,
      "step": 195
    },
    {
      "epoch": 0.5885885885885885,
      "grad_norm": 2.3836328983306885,
      "learning_rate": 7.434598599578351e-05,
      "loss": 1.1743,
      "step": 196
    },
    {
      "epoch": 0.5915915915915916,
      "grad_norm": 3.5238161087036133,
      "learning_rate": 7.343529288891239e-05,
      "loss": 1.112,
      "step": 197
    },
    {
      "epoch": 0.5945945945945946,
      "grad_norm": 3.281916379928589,
      "learning_rate": 7.252696413924174e-05,
      "loss": 1.2468,
      "step": 198
    },
    {
      "epoch": 0.5975975975975976,
      "grad_norm": 9.559804916381836,
      "learning_rate": 7.162108059139032e-05,
      "loss": 1.3009,
      "step": 199
    },
    {
      "epoch": 0.6006006006006006,
      "grad_norm": 2.9067914485931396,
      "learning_rate": 7.071772287234497e-05,
      "loss": 1.2777,
      "step": 200
    },
    {
      "epoch": 0.6036036036036037,
      "grad_norm": 3.17146897315979,
      "learning_rate": 6.981697138428434e-05,
      "loss": 1.0077,
      "step": 201
    },
    {
      "epoch": 0.6066066066066066,
      "grad_norm": 2.9536023139953613,
      "learning_rate": 6.891890629742288e-05,
      "loss": 0.9833,
      "step": 202
    },
    {
      "epoch": 0.6096096096096096,
      "grad_norm": 3.4014861583709717,
      "learning_rate": 6.802360754287547e-05,
      "loss": 0.9078,
      "step": 203
    },
    {
      "epoch": 0.6126126126126126,
      "grad_norm": 2.692471981048584,
      "learning_rate": 6.713115480554313e-05,
      "loss": 1.0275,
      "step": 204
    },
    {
      "epoch": 0.6156156156156156,
      "grad_norm": 4.035511016845703,
      "learning_rate": 6.624162751702076e-05,
      "loss": 1.1448,
      "step": 205
    },
    {
      "epoch": 0.6186186186186187,
      "grad_norm": 3.6545097827911377,
      "learning_rate": 6.535510484852767e-05,
      "loss": 1.3975,
      "step": 206
    },
    {
      "epoch": 0.6216216216216216,
      "grad_norm": 3.810364007949829,
      "learning_rate": 6.447166570386063e-05,
      "loss": 1.543,
      "step": 207
    },
    {
      "epoch": 0.6246246246246246,
      "grad_norm": 2.650916337966919,
      "learning_rate": 6.35913887123716e-05,
      "loss": 1.1199,
      "step": 208
    },
    {
      "epoch": 0.6276276276276276,
      "grad_norm": 4.023564338684082,
      "learning_rate": 6.271435222196916e-05,
      "loss": 1.256,
      "step": 209
    },
    {
      "epoch": 0.6306306306306306,
      "grad_norm": 2.7010152339935303,
      "learning_rate": 6.184063429214515e-05,
      "loss": 0.5501,
      "step": 210
    },
    {
      "epoch": 0.6336336336336337,
      "grad_norm": 1.9381567239761353,
      "learning_rate": 6.097031268702746e-05,
      "loss": 0.6213,
      "step": 211
    },
    {
      "epoch": 0.6366366366366366,
      "grad_norm": 2.4009511470794678,
      "learning_rate": 6.010346486845837e-05,
      "loss": 1.0056,
      "step": 212
    },
    {
      "epoch": 0.6396396396396397,
      "grad_norm": 2.6076042652130127,
      "learning_rate": 5.924016798910037e-05,
      "loss": 0.9052,
      "step": 213
    },
    {
      "epoch": 0.6426426426426426,
      "grad_norm": 2.4669220447540283,
      "learning_rate": 5.838049888556925e-05,
      "loss": 0.7062,
      "step": 214
    },
    {
      "epoch": 0.6456456456456456,
      "grad_norm": 2.6070826053619385,
      "learning_rate": 5.752453407159522e-05,
      "loss": 1.2074,
      "step": 215
    },
    {
      "epoch": 0.6486486486486487,
      "grad_norm": 3.0781683921813965,
      "learning_rate": 5.667234973121317e-05,
      "loss": 1.027,
      "step": 216
    },
    {
      "epoch": 0.6516516516516516,
      "grad_norm": 3.333461284637451,
      "learning_rate": 5.5824021711981686e-05,
      "loss": 1.5397,
      "step": 217
    },
    {
      "epoch": 0.6546546546546547,
      "grad_norm": 3.359348773956299,
      "learning_rate": 5.497962551823266e-05,
      "loss": 0.9678,
      "step": 218
    },
    {
      "epoch": 0.6576576576576577,
      "grad_norm": 3.1527299880981445,
      "learning_rate": 5.4139236304350935e-05,
      "loss": 1.0678,
      "step": 219
    },
    {
      "epoch": 0.6606606606606606,
      "grad_norm": 3.3422963619232178,
      "learning_rate": 5.33029288680852e-05,
      "loss": 1.0821,
      "step": 220
    },
    {
      "epoch": 0.6636636636636637,
      "grad_norm": 2.5791242122650146,
      "learning_rate": 5.247077764389099e-05,
      "loss": 1.0926,
      "step": 221
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 4.386955738067627,
      "learning_rate": 5.1642856696305575e-05,
      "loss": 1.1258,
      "step": 222
    },
    {
      "epoch": 0.6696696696696697,
      "grad_norm": 2.5412847995758057,
      "learning_rate": 5.081923971335582e-05,
      "loss": 1.0448,
      "step": 223
    },
    {
      "epoch": 0.6726726726726727,
      "grad_norm": 2.4744250774383545,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.8041,
      "step": 224
    },
    {
      "epoch": 0.6756756756756757,
      "grad_norm": 3.471261978149414,
      "learning_rate": 4.918521047160308e-05,
      "loss": 1.077,
      "step": 225
    },
    {
      "epoch": 0.6786786786786787,
      "grad_norm": 4.173779487609863,
      "learning_rate": 4.837494364744711e-05,
      "loss": 1.798,
      "step": 226
    },
    {
      "epoch": 0.6816816816816816,
      "grad_norm": 3.305908203125,
      "learning_rate": 4.756927164427685e-05,
      "loss": 0.7939,
      "step": 227
    },
    {
      "epoch": 0.6846846846846847,
      "grad_norm": 3.1384143829345703,
      "learning_rate": 4.6768266169880804e-05,
      "loss": 1.2368,
      "step": 228
    },
    {
      "epoch": 0.6876876876876877,
      "grad_norm": 3.3017380237579346,
      "learning_rate": 4.597199851670932e-05,
      "loss": 1.0357,
      "step": 229
    },
    {
      "epoch": 0.6906906906906907,
      "grad_norm": 3.067096710205078,
      "learning_rate": 4.518053955552903e-05,
      "loss": 1.2825,
      "step": 230
    },
    {
      "epoch": 0.6936936936936937,
      "grad_norm": 2.126237392425537,
      "learning_rate": 4.4393959729115244e-05,
      "loss": 0.9703,
      "step": 231
    },
    {
      "epoch": 0.6966966966966966,
      "grad_norm": 2.740218162536621,
      "learning_rate": 4.3612329045982236e-05,
      "loss": 1.0771,
      "step": 232
    },
    {
      "epoch": 0.6996996996996997,
      "grad_norm": 2.1864259243011475,
      "learning_rate": 4.283571707415214e-05,
      "loss": 1.0516,
      "step": 233
    },
    {
      "epoch": 0.7027027027027027,
      "grad_norm": 3.2261359691619873,
      "learning_rate": 4.206419293496333e-05,
      "loss": 1.317,
      "step": 234
    },
    {
      "epoch": 0.7057057057057057,
      "grad_norm": 3.8331665992736816,
      "learning_rate": 4.129782529691815e-05,
      "loss": 1.0472,
      "step": 235
    },
    {
      "epoch": 0.7087087087087087,
      "grad_norm": 2.4469823837280273,
      "learning_rate": 4.053668236957134e-05,
      "loss": 1.0914,
      "step": 236
    },
    {
      "epoch": 0.7117117117117117,
      "grad_norm": 2.4445111751556396,
      "learning_rate": 3.978083189745907e-05,
      "loss": 1.2176,
      "step": 237
    },
    {
      "epoch": 0.7147147147147147,
      "grad_norm": 1.970625400543213,
      "learning_rate": 3.903034115406931e-05,
      "loss": 0.7056,
      "step": 238
    },
    {
      "epoch": 0.7177177177177178,
      "grad_norm": 2.919154644012451,
      "learning_rate": 3.828527693585451e-05,
      "loss": 1.0735,
      "step": 239
    },
    {
      "epoch": 0.7207207207207207,
      "grad_norm": 3.0129635334014893,
      "learning_rate": 3.7545705556286126e-05,
      "loss": 1.0387,
      "step": 240
    },
    {
      "epoch": 0.7237237237237237,
      "grad_norm": 3.2934532165527344,
      "learning_rate": 3.681169283995279e-05,
      "loss": 1.5478,
      "step": 241
    },
    {
      "epoch": 0.7267267267267268,
      "grad_norm": 2.250554084777832,
      "learning_rate": 3.6083304116701535e-05,
      "loss": 1.2424,
      "step": 242
    },
    {
      "epoch": 0.7297297297297297,
      "grad_norm": 2.934713125228882,
      "learning_rate": 3.536060421582309e-05,
      "loss": 1.1404,
      "step": 243
    },
    {
      "epoch": 0.7327327327327328,
      "grad_norm": 3.759920358657837,
      "learning_rate": 3.464365746028208e-05,
      "loss": 1.4122,
      "step": 244
    },
    {
      "epoch": 0.7357357357357357,
      "grad_norm": 3.219802141189575,
      "learning_rate": 3.393252766099187e-05,
      "loss": 1.1218,
      "step": 245
    },
    {
      "epoch": 0.7387387387387387,
      "grad_norm": 2.7375502586364746,
      "learning_rate": 3.322727811113516e-05,
      "loss": 1.1416,
      "step": 246
    },
    {
      "epoch": 0.7417417417417418,
      "grad_norm": 3.227217674255371,
      "learning_rate": 3.252797158053077e-05,
      "loss": 1.3001,
      "step": 247
    },
    {
      "epoch": 0.7447447447447447,
      "grad_norm": 2.4813485145568848,
      "learning_rate": 3.1834670310046734e-05,
      "loss": 1.251,
      "step": 248
    },
    {
      "epoch": 0.7477477477477478,
      "grad_norm": 3.096740245819092,
      "learning_rate": 3.114743600606078e-05,
      "loss": 1.2156,
      "step": 249
    },
    {
      "epoch": 0.7507507507507507,
      "grad_norm": 3.479696750640869,
      "learning_rate": 3.0466329834968233e-05,
      "loss": 1.3375,
      "step": 250
    },
    {
      "epoch": 0.7537537537537538,
      "grad_norm": 2.182914972305298,
      "learning_rate": 2.979141241773775e-05,
      "loss": 0.8452,
      "step": 251
    },
    {
      "epoch": 0.7567567567567568,
      "grad_norm": 3.065699338912964,
      "learning_rate": 2.9122743824516195e-05,
      "loss": 1.2515,
      "step": 252
    },
    {
      "epoch": 0.7597597597597597,
      "grad_norm": 2.5178773403167725,
      "learning_rate": 2.8460383569281824e-05,
      "loss": 1.066,
      "step": 253
    },
    {
      "epoch": 0.7627627627627628,
      "grad_norm": 2.5615763664245605,
      "learning_rate": 2.7804390604547557e-05,
      "loss": 0.8671,
      "step": 254
    },
    {
      "epoch": 0.7657657657657657,
      "grad_norm": 3.6489756107330322,
      "learning_rate": 2.7154823316113932e-05,
      "loss": 0.9719,
      "step": 255
    },
    {
      "epoch": 0.7687687687687688,
      "grad_norm": 2.6565563678741455,
      "learning_rate": 2.6511739517872426e-05,
      "loss": 1.1096,
      "step": 256
    },
    {
      "epoch": 0.7717717717717718,
      "grad_norm": 2.854301691055298,
      "learning_rate": 2.587519644666001e-05,
      "loss": 1.1078,
      "step": 257
    },
    {
      "epoch": 0.7747747747747747,
      "grad_norm": 3.2702455520629883,
      "learning_rate": 2.5245250757164663e-05,
      "loss": 0.8153,
      "step": 258
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 4.333303928375244,
      "learning_rate": 2.462195851688306e-05,
      "loss": 1.3388,
      "step": 259
    },
    {
      "epoch": 0.7807807807807807,
      "grad_norm": 3.0669684410095215,
      "learning_rate": 2.4005375201130274e-05,
      "loss": 0.8611,
      "step": 260
    },
    {
      "epoch": 0.7837837837837838,
      "grad_norm": 2.525719404220581,
      "learning_rate": 2.339555568810221e-05,
      "loss": 1.1003,
      "step": 261
    },
    {
      "epoch": 0.7867867867867868,
      "grad_norm": 2.2282748222351074,
      "learning_rate": 2.2792554253991415e-05,
      "loss": 0.9158,
      "step": 262
    },
    {
      "epoch": 0.7897897897897898,
      "grad_norm": 2.8235883712768555,
      "learning_rate": 2.2196424568156073e-05,
      "loss": 0.9614,
      "step": 263
    },
    {
      "epoch": 0.7927927927927928,
      "grad_norm": 3.252837896347046,
      "learning_rate": 2.160721968834344e-05,
      "loss": 1.3249,
      "step": 264
    },
    {
      "epoch": 0.7957957957957958,
      "grad_norm": 2.533545732498169,
      "learning_rate": 2.102499205596743e-05,
      "loss": 1.1374,
      "step": 265
    },
    {
      "epoch": 0.7987987987987988,
      "grad_norm": 6.542397975921631,
      "learning_rate": 2.0449793491441028e-05,
      "loss": 1.1266,
      "step": 266
    },
    {
      "epoch": 0.8018018018018018,
      "grad_norm": 4.502058982849121,
      "learning_rate": 1.9881675189564254e-05,
      "loss": 1.0552,
      "step": 267
    },
    {
      "epoch": 0.8048048048048048,
      "grad_norm": 2.8032190799713135,
      "learning_rate": 1.93206877149676e-05,
      "loss": 1.6937,
      "step": 268
    },
    {
      "epoch": 0.8078078078078078,
      "grad_norm": 2.657517194747925,
      "learning_rate": 1.8766880997611424e-05,
      "loss": 0.8906,
      "step": 269
    },
    {
      "epoch": 0.8108108108108109,
      "grad_norm": 2.660195827484131,
      "learning_rate": 1.8220304328342252e-05,
      "loss": 1.2647,
      "step": 270
    },
    {
      "epoch": 0.8138138138138138,
      "grad_norm": 1.883196473121643,
      "learning_rate": 1.7681006354505493e-05,
      "loss": 0.6738,
      "step": 271
    },
    {
      "epoch": 0.8168168168168168,
      "grad_norm": 3.13309645652771,
      "learning_rate": 1.7149035075615794e-05,
      "loss": 1.066,
      "step": 272
    },
    {
      "epoch": 0.8198198198198198,
      "grad_norm": 2.7584190368652344,
      "learning_rate": 1.6624437839084862e-05,
      "loss": 1.0969,
      "step": 273
    },
    {
      "epoch": 0.8228228228228228,
      "grad_norm": 2.3647868633270264,
      "learning_rate": 1.6107261336007285e-05,
      "loss": 0.8421,
      "step": 274
    },
    {
      "epoch": 0.8258258258258259,
      "grad_norm": 3.7344658374786377,
      "learning_rate": 1.5597551597004966e-05,
      "loss": 1.2212,
      "step": 275
    },
    {
      "epoch": 0.8288288288288288,
      "grad_norm": 1.9428234100341797,
      "learning_rate": 1.5095353988130235e-05,
      "loss": 0.8606,
      "step": 276
    },
    {
      "epoch": 0.8318318318318318,
      "grad_norm": 4.204195499420166,
      "learning_rate": 1.4600713206827932e-05,
      "loss": 1.4646,
      "step": 277
    },
    {
      "epoch": 0.8348348348348348,
      "grad_norm": 3.156510353088379,
      "learning_rate": 1.4113673277957395e-05,
      "loss": 0.7277,
      "step": 278
    },
    {
      "epoch": 0.8378378378378378,
      "grad_norm": 2.952470064163208,
      "learning_rate": 1.3634277549873953e-05,
      "loss": 1.2394,
      "step": 279
    },
    {
      "epoch": 0.8408408408408409,
      "grad_norm": 3.20043683052063,
      "learning_rate": 1.3162568690570743e-05,
      "loss": 1.1353,
      "step": 280
    },
    {
      "epoch": 0.8438438438438438,
      "grad_norm": 2.7060203552246094,
      "learning_rate": 1.2698588683881186e-05,
      "loss": 1.03,
      "step": 281
    },
    {
      "epoch": 0.8468468468468469,
      "grad_norm": 3.0565147399902344,
      "learning_rate": 1.224237882574224e-05,
      "loss": 1.0829,
      "step": 282
    },
    {
      "epoch": 0.8498498498498499,
      "grad_norm": 3.7081923484802246,
      "learning_rate": 1.1793979720518866e-05,
      "loss": 0.861,
      "step": 283
    },
    {
      "epoch": 0.8528528528528528,
      "grad_norm": 2.978846311569214,
      "learning_rate": 1.1353431277390126e-05,
      "loss": 0.9791,
      "step": 284
    },
    {
      "epoch": 0.8558558558558559,
      "grad_norm": 3.253490447998047,
      "learning_rate": 1.0920772706797167e-05,
      "loss": 1.2799,
      "step": 285
    },
    {
      "epoch": 0.8588588588588588,
      "grad_norm": 3.5447134971618652,
      "learning_rate": 1.0496042516953209e-05,
      "loss": 0.9983,
      "step": 286
    },
    {
      "epoch": 0.8618618618618619,
      "grad_norm": 3.0113589763641357,
      "learning_rate": 1.0079278510416313e-05,
      "loss": 0.9575,
      "step": 287
    },
    {
      "epoch": 0.8648648648648649,
      "grad_norm": 2.7044694423675537,
      "learning_rate": 9.670517780724775e-06,
      "loss": 0.7598,
      "step": 288
    },
    {
      "epoch": 0.8678678678678678,
      "grad_norm": 3.9310684204101562,
      "learning_rate": 9.269796709095558e-06,
      "loss": 1.0002,
      "step": 289
    },
    {
      "epoch": 0.8708708708708709,
      "grad_norm": 2.882972478866577,
      "learning_rate": 8.87715096118642e-06,
      "loss": 1.4311,
      "step": 290
    },
    {
      "epoch": 0.8738738738738738,
      "grad_norm": 4.454821586608887,
      "learning_rate": 8.492615483921395e-06,
      "loss": 0.8625,
      "step": 291
    },
    {
      "epoch": 0.8768768768768769,
      "grad_norm": 2.4712319374084473,
      "learning_rate": 8.116224502380387e-06,
      "loss": 0.868,
      "step": 292
    },
    {
      "epoch": 0.8798798798798799,
      "grad_norm": 2.3259506225585938,
      "learning_rate": 7.74801151675314e-06,
      "loss": 1.21,
      "step": 293
    },
    {
      "epoch": 0.8828828828828829,
      "grad_norm": 2.29254412651062,
      "learning_rate": 7.3880092993574125e-06,
      "loss": 0.9161,
      "step": 294
    },
    {
      "epoch": 0.8858858858858859,
      "grad_norm": 3.6006367206573486,
      "learning_rate": 7.03624989172228e-06,
      "loss": 1.3222,
      "step": 295
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 2.694861888885498,
      "learning_rate": 6.692764601736268e-06,
      "loss": 0.8479,
      "step": 296
    },
    {
      "epoch": 0.8918918918918919,
      "grad_norm": 1.8544005155563354,
      "learning_rate": 6.357584000860761e-06,
      "loss": 0.7101,
      "step": 297
    },
    {
      "epoch": 0.8948948948948949,
      "grad_norm": 3.2788209915161133,
      "learning_rate": 6.030737921409169e-06,
      "loss": 0.9239,
      "step": 298
    },
    {
      "epoch": 0.8978978978978979,
      "grad_norm": 2.618945598602295,
      "learning_rate": 5.71225545389158e-06,
      "loss": 0.827,
      "step": 299
    },
    {
      "epoch": 0.9009009009009009,
      "grad_norm": 2.999677896499634,
      "learning_rate": 5.402164944425758e-06,
      "loss": 1.1641,
      "step": 300
    },
    {
      "epoch": 0.9039039039039038,
      "grad_norm": 2.9957101345062256,
      "learning_rate": 5.100493992214128e-06,
      "loss": 1.1766,
      "step": 301
    },
    {
      "epoch": 0.9069069069069069,
      "grad_norm": 7.010153293609619,
      "learning_rate": 4.807269447087348e-06,
      "loss": 1.3179,
      "step": 302
    },
    {
      "epoch": 0.9099099099099099,
      "grad_norm": 2.962459087371826,
      "learning_rate": 4.5225174071146455e-06,
      "loss": 1.1249,
      "step": 303
    },
    {
      "epoch": 0.9129129129129129,
      "grad_norm": 3.1985106468200684,
      "learning_rate": 4.24626321628091e-06,
      "loss": 1.0897,
      "step": 304
    },
    {
      "epoch": 0.9159159159159159,
      "grad_norm": 3.808082103729248,
      "learning_rate": 3.9785314622310495e-06,
      "loss": 0.8197,
      "step": 305
    },
    {
      "epoch": 0.918918918918919,
      "grad_norm": 3.2726027965545654,
      "learning_rate": 3.7193459740815674e-06,
      "loss": 1.3593,
      "step": 306
    },
    {
      "epoch": 0.9219219219219219,
      "grad_norm": 2.5150132179260254,
      "learning_rate": 3.4687298202996655e-06,
      "loss": 1.1216,
      "step": 307
    },
    {
      "epoch": 0.924924924924925,
      "grad_norm": 2.964665174484253,
      "learning_rate": 3.226705306650113e-06,
      "loss": 0.9923,
      "step": 308
    },
    {
      "epoch": 0.9279279279279279,
      "grad_norm": 2.368405342102051,
      "learning_rate": 2.9932939742099208e-06,
      "loss": 1.2781,
      "step": 309
    },
    {
      "epoch": 0.9309309309309309,
      "grad_norm": 2.1340932846069336,
      "learning_rate": 2.7685165974510986e-06,
      "loss": 0.771,
      "step": 310
    },
    {
      "epoch": 0.933933933933934,
      "grad_norm": 3.647322654724121,
      "learning_rate": 2.552393182391677e-06,
      "loss": 1.2626,
      "step": 311
    },
    {
      "epoch": 0.9369369369369369,
      "grad_norm": 3.0686633586883545,
      "learning_rate": 2.3449429648150665e-06,
      "loss": 0.9542,
      "step": 312
    },
    {
      "epoch": 0.93993993993994,
      "grad_norm": 2.4045958518981934,
      "learning_rate": 2.1461844085580385e-06,
      "loss": 1.1157,
      "step": 313
    },
    {
      "epoch": 0.9429429429429429,
      "grad_norm": 3.171212673187256,
      "learning_rate": 1.9561352038673263e-06,
      "loss": 1.154,
      "step": 314
    },
    {
      "epoch": 0.9459459459459459,
      "grad_norm": 2.600048065185547,
      "learning_rate": 1.7748122658251876e-06,
      "loss": 0.985,
      "step": 315
    },
    {
      "epoch": 0.948948948948949,
      "grad_norm": 3.850813388824463,
      "learning_rate": 1.6022317328438506e-06,
      "loss": 0.7198,
      "step": 316
    },
    {
      "epoch": 0.9519519519519519,
      "grad_norm": 2.7421891689300537,
      "learning_rate": 1.4384089652291543e-06,
      "loss": 1.0198,
      "step": 317
    },
    {
      "epoch": 0.954954954954955,
      "grad_norm": 3.2563424110412598,
      "learning_rate": 1.2833585438134287e-06,
      "loss": 1.1602,
      "step": 318
    },
    {
      "epoch": 0.9579579579579579,
      "grad_norm": 2.593169689178467,
      "learning_rate": 1.1370942686577347e-06,
      "loss": 1.0172,
      "step": 319
    },
    {
      "epoch": 0.960960960960961,
      "grad_norm": 2.467902421951294,
      "learning_rate": 9.996291578236228e-07,
      "loss": 1.158,
      "step": 320
    },
    {
      "epoch": 0.963963963963964,
      "grad_norm": 3.1894989013671875,
      "learning_rate": 8.709754462144615e-07,
      "loss": 1.366,
      "step": 321
    },
    {
      "epoch": 0.9669669669669669,
      "grad_norm": 2.78214955329895,
      "learning_rate": 7.511445844864962e-07,
      "loss": 1.19,
      "step": 322
    },
    {
      "epoch": 0.96996996996997,
      "grad_norm": 2.4907963275909424,
      "learning_rate": 6.401472380297091e-07,
      "loss": 0.645,
      "step": 323
    },
    {
      "epoch": 0.972972972972973,
      "grad_norm": 2.79376482963562,
      "learning_rate": 5.379932860185122e-07,
      "loss": 1.2244,
      "step": 324
    },
    {
      "epoch": 0.975975975975976,
      "grad_norm": 2.3573567867279053,
      "learning_rate": 4.44691820532539e-07,
      "loss": 0.8455,
      "step": 325
    },
    {
      "epoch": 0.978978978978979,
      "grad_norm": 2.453552484512329,
      "learning_rate": 3.6025114574734785e-07,
      "loss": 1.0234,
      "step": 326
    },
    {
      "epoch": 0.9819819819819819,
      "grad_norm": 3.1703238487243652,
      "learning_rate": 2.846787771953574e-07,
      "loss": 1.2226,
      "step": 327
    },
    {
      "epoch": 0.984984984984985,
      "grad_norm": 3.3608462810516357,
      "learning_rate": 2.179814410969261e-07,
      "loss": 1.0183,
      "step": 328
    },
    {
      "epoch": 0.987987987987988,
      "grad_norm": 4.895633220672607,
      "learning_rate": 1.6016507376169777e-07,
      "loss": 1.4253,
      "step": 329
    },
    {
      "epoch": 0.990990990990991,
      "grad_norm": 3.5701801776885986,
      "learning_rate": 1.1123482106021322e-07,
      "loss": 1.3085,
      "step": 330
    },
    {
      "epoch": 0.993993993993994,
      "grad_norm": 5.8992815017700195,
      "learning_rate": 7.119503796599868e-08,
      "loss": 1.6318,
      "step": 331
    },
    {
      "epoch": 0.996996996996997,
      "grad_norm": 2.636950969696045,
      "learning_rate": 4.0049288167842705e-08,
      "loss": 0.8327,
      "step": 332
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.5497934818267822,
      "learning_rate": 1.7800343752683023e-08,
      "loss": 0.8514,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.0642523765563965,
      "eval_runtime": 7.6037,
      "eval_samples_per_second": 9.338,
      "eval_steps_per_second": 9.338,
      "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
}