GuilhermeNaturaUmana's picture
Upload folder using huggingface_hub
dbb0b52 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.3334453781512605,
"eval_steps": 500,
"global_step": 496,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0006722689075630252,
"grad_norm": 0.0835651233792305,
"learning_rate": 1.0000000000000002e-06,
"loss": 1.0786,
"step": 1
},
{
"epoch": 0.0013445378151260505,
"grad_norm": 0.08339695632457733,
"learning_rate": 2.0000000000000003e-06,
"loss": 1.0642,
"step": 2
},
{
"epoch": 0.0020168067226890756,
"grad_norm": 0.08287601917982101,
"learning_rate": 3e-06,
"loss": 0.9508,
"step": 3
},
{
"epoch": 0.002689075630252101,
"grad_norm": 0.09812851250171661,
"learning_rate": 4.000000000000001e-06,
"loss": 0.9892,
"step": 4
},
{
"epoch": 0.0033613445378151263,
"grad_norm": 0.10798798501491547,
"learning_rate": 5e-06,
"loss": 0.9393,
"step": 5
},
{
"epoch": 0.004033613445378151,
"grad_norm": 0.11012189835309982,
"learning_rate": 6e-06,
"loss": 1.0222,
"step": 6
},
{
"epoch": 0.004705882352941176,
"grad_norm": 0.0818193256855011,
"learning_rate": 7e-06,
"loss": 0.9702,
"step": 7
},
{
"epoch": 0.005378151260504202,
"grad_norm": 0.08617620915174484,
"learning_rate": 8.000000000000001e-06,
"loss": 1.1444,
"step": 8
},
{
"epoch": 0.006050420168067227,
"grad_norm": 0.07566545158624649,
"learning_rate": 9e-06,
"loss": 0.9204,
"step": 9
},
{
"epoch": 0.0067226890756302525,
"grad_norm": 0.07344148308038712,
"learning_rate": 1e-05,
"loss": 0.8932,
"step": 10
},
{
"epoch": 0.007394957983193277,
"grad_norm": 0.1588195115327835,
"learning_rate": 9.999988689583452e-06,
"loss": 1.0167,
"step": 11
},
{
"epoch": 0.008067226890756302,
"grad_norm": 0.105576291680336,
"learning_rate": 9.999954758384983e-06,
"loss": 1.0244,
"step": 12
},
{
"epoch": 0.008739495798319327,
"grad_norm": 0.10251228511333466,
"learning_rate": 9.999898206558095e-06,
"loss": 1.0446,
"step": 13
},
{
"epoch": 0.009411764705882352,
"grad_norm": 0.11292218416929245,
"learning_rate": 9.999819034358644e-06,
"loss": 1.0304,
"step": 14
},
{
"epoch": 0.010084033613445379,
"grad_norm": 0.12369322031736374,
"learning_rate": 9.999717242144817e-06,
"loss": 1.049,
"step": 15
},
{
"epoch": 0.010756302521008404,
"grad_norm": 0.16626787185668945,
"learning_rate": 9.99959283037714e-06,
"loss": 1.0647,
"step": 16
},
{
"epoch": 0.011428571428571429,
"grad_norm": 0.800682008266449,
"learning_rate": 9.99944579961847e-06,
"loss": 0.9812,
"step": 17
},
{
"epoch": 0.012100840336134453,
"grad_norm": 0.09268046170473099,
"learning_rate": 9.999276150534001e-06,
"loss": 0.9062,
"step": 18
},
{
"epoch": 0.012773109243697478,
"grad_norm": 0.0998532846570015,
"learning_rate": 9.999083883891251e-06,
"loss": 1.0247,
"step": 19
},
{
"epoch": 0.013445378151260505,
"grad_norm": 0.17539170384407043,
"learning_rate": 9.99886900056007e-06,
"loss": 1.0814,
"step": 20
},
{
"epoch": 0.01411764705882353,
"grad_norm": 0.150508314371109,
"learning_rate": 9.998631501512624e-06,
"loss": 0.9967,
"step": 21
},
{
"epoch": 0.014789915966386555,
"grad_norm": 0.10628243535757065,
"learning_rate": 9.998371387823398e-06,
"loss": 0.9941,
"step": 22
},
{
"epoch": 0.01546218487394958,
"grad_norm": 0.13679274916648865,
"learning_rate": 9.998088660669189e-06,
"loss": 0.983,
"step": 23
},
{
"epoch": 0.016134453781512605,
"grad_norm": 0.10756199061870575,
"learning_rate": 9.997783321329104e-06,
"loss": 1.002,
"step": 24
},
{
"epoch": 0.01680672268907563,
"grad_norm": 0.1575344055891037,
"learning_rate": 9.997455371184546e-06,
"loss": 1.0167,
"step": 25
},
{
"epoch": 0.017478991596638654,
"grad_norm": 0.16291604936122894,
"learning_rate": 9.997104811719221e-06,
"loss": 1.0141,
"step": 26
},
{
"epoch": 0.01815126050420168,
"grad_norm": 0.21997588872909546,
"learning_rate": 9.996731644519111e-06,
"loss": 0.8077,
"step": 27
},
{
"epoch": 0.018823529411764704,
"grad_norm": 0.1384553760290146,
"learning_rate": 9.996335871272494e-06,
"loss": 1.0216,
"step": 28
},
{
"epoch": 0.019495798319327733,
"grad_norm": 0.1880977898836136,
"learning_rate": 9.995917493769912e-06,
"loss": 1.0098,
"step": 29
},
{
"epoch": 0.020168067226890758,
"grad_norm": 0.14351259171962738,
"learning_rate": 9.995476513904171e-06,
"loss": 1.0134,
"step": 30
},
{
"epoch": 0.020840336134453782,
"grad_norm": 0.1357450932264328,
"learning_rate": 9.995012933670341e-06,
"loss": 0.9587,
"step": 31
},
{
"epoch": 0.021512605042016807,
"grad_norm": 0.15096725523471832,
"learning_rate": 9.994526755165736e-06,
"loss": 0.8823,
"step": 32
},
{
"epoch": 0.022184873949579832,
"grad_norm": 0.2435840666294098,
"learning_rate": 9.994017980589907e-06,
"loss": 0.9802,
"step": 33
},
{
"epoch": 0.022857142857142857,
"grad_norm": 0.12320239096879959,
"learning_rate": 9.993486612244634e-06,
"loss": 1.0142,
"step": 34
},
{
"epoch": 0.023529411764705882,
"grad_norm": 0.11510821431875229,
"learning_rate": 9.99293265253392e-06,
"loss": 0.8819,
"step": 35
},
{
"epoch": 0.024201680672268907,
"grad_norm": 0.13881511986255646,
"learning_rate": 9.992356103963967e-06,
"loss": 1.0291,
"step": 36
},
{
"epoch": 0.024873949579831932,
"grad_norm": 0.12611961364746094,
"learning_rate": 9.99175696914318e-06,
"loss": 0.8883,
"step": 37
},
{
"epoch": 0.025546218487394957,
"grad_norm": 0.1128062754869461,
"learning_rate": 9.991135250782143e-06,
"loss": 0.9399,
"step": 38
},
{
"epoch": 0.02621848739495798,
"grad_norm": 0.17889104783535004,
"learning_rate": 9.990490951693612e-06,
"loss": 0.8848,
"step": 39
},
{
"epoch": 0.02689075630252101,
"grad_norm": 0.10607869923114777,
"learning_rate": 9.989824074792507e-06,
"loss": 0.9864,
"step": 40
},
{
"epoch": 0.027563025210084035,
"grad_norm": 0.11618159711360931,
"learning_rate": 9.989134623095888e-06,
"loss": 0.9561,
"step": 41
},
{
"epoch": 0.02823529411764706,
"grad_norm": 0.13454240560531616,
"learning_rate": 9.98842259972295e-06,
"loss": 0.949,
"step": 42
},
{
"epoch": 0.028907563025210085,
"grad_norm": 0.11738969385623932,
"learning_rate": 9.987688007895002e-06,
"loss": 0.9184,
"step": 43
},
{
"epoch": 0.02957983193277311,
"grad_norm": 0.11672742664813995,
"learning_rate": 9.986930850935465e-06,
"loss": 0.945,
"step": 44
},
{
"epoch": 0.030252100840336135,
"grad_norm": 0.10767639428377151,
"learning_rate": 9.986151132269843e-06,
"loss": 1.0525,
"step": 45
},
{
"epoch": 0.03092436974789916,
"grad_norm": 0.11100558191537857,
"learning_rate": 9.98534885542571e-06,
"loss": 0.8767,
"step": 46
},
{
"epoch": 0.03159663865546219,
"grad_norm": 0.12392528355121613,
"learning_rate": 9.9845240240327e-06,
"loss": 0.9066,
"step": 47
},
{
"epoch": 0.03226890756302521,
"grad_norm": 0.12757766246795654,
"learning_rate": 9.98367664182249e-06,
"loss": 0.8557,
"step": 48
},
{
"epoch": 0.03294117647058824,
"grad_norm": 0.09705185890197754,
"learning_rate": 9.982806712628776e-06,
"loss": 0.8187,
"step": 49
},
{
"epoch": 0.03361344537815126,
"grad_norm": 0.11287973076105118,
"learning_rate": 9.981914240387264e-06,
"loss": 0.8826,
"step": 50
},
{
"epoch": 0.03428571428571429,
"grad_norm": 0.10316391289234161,
"learning_rate": 9.98099922913565e-06,
"loss": 0.8536,
"step": 51
},
{
"epoch": 0.03495798319327731,
"grad_norm": 0.09859252721071243,
"learning_rate": 9.980061683013594e-06,
"loss": 0.7973,
"step": 52
},
{
"epoch": 0.03563025210084034,
"grad_norm": 0.10780596733093262,
"learning_rate": 9.979101606262709e-06,
"loss": 0.8864,
"step": 53
},
{
"epoch": 0.03630252100840336,
"grad_norm": 0.13508446514606476,
"learning_rate": 9.978119003226546e-06,
"loss": 0.9185,
"step": 54
},
{
"epoch": 0.03697478991596639,
"grad_norm": 0.12588554620742798,
"learning_rate": 9.977113878350561e-06,
"loss": 0.8077,
"step": 55
},
{
"epoch": 0.03764705882352941,
"grad_norm": 0.09272392839193344,
"learning_rate": 9.976086236182113e-06,
"loss": 0.9335,
"step": 56
},
{
"epoch": 0.03831932773109244,
"grad_norm": 0.0940898135304451,
"learning_rate": 9.975036081370417e-06,
"loss": 0.8295,
"step": 57
},
{
"epoch": 0.038991596638655465,
"grad_norm": 0.36463847756385803,
"learning_rate": 9.973963418666556e-06,
"loss": 0.9301,
"step": 58
},
{
"epoch": 0.03966386554621849,
"grad_norm": 0.10689139366149902,
"learning_rate": 9.972868252923433e-06,
"loss": 0.8314,
"step": 59
},
{
"epoch": 0.040336134453781515,
"grad_norm": 0.10545141249895096,
"learning_rate": 9.97175058909576e-06,
"loss": 0.836,
"step": 60
},
{
"epoch": 0.041008403361344536,
"grad_norm": 0.09649187326431274,
"learning_rate": 9.970610432240033e-06,
"loss": 0.798,
"step": 61
},
{
"epoch": 0.041680672268907565,
"grad_norm": 0.11074765026569366,
"learning_rate": 9.969447787514512e-06,
"loss": 0.9432,
"step": 62
},
{
"epoch": 0.042352941176470586,
"grad_norm": 0.14206334948539734,
"learning_rate": 9.968262660179197e-06,
"loss": 1.03,
"step": 63
},
{
"epoch": 0.043025210084033615,
"grad_norm": 0.2147335410118103,
"learning_rate": 9.9670550555958e-06,
"loss": 0.8486,
"step": 64
},
{
"epoch": 0.043697478991596636,
"grad_norm": 0.11276064813137054,
"learning_rate": 9.965824979227727e-06,
"loss": 0.8415,
"step": 65
},
{
"epoch": 0.044369747899159664,
"grad_norm": 0.1048726737499237,
"learning_rate": 9.964572436640046e-06,
"loss": 0.8171,
"step": 66
},
{
"epoch": 0.045042016806722686,
"grad_norm": 0.09552193433046341,
"learning_rate": 9.96329743349947e-06,
"loss": 0.818,
"step": 67
},
{
"epoch": 0.045714285714285714,
"grad_norm": 0.11481764167547226,
"learning_rate": 9.961999975574327e-06,
"loss": 0.8802,
"step": 68
},
{
"epoch": 0.04638655462184874,
"grad_norm": 0.12009887397289276,
"learning_rate": 9.960680068734528e-06,
"loss": 0.8471,
"step": 69
},
{
"epoch": 0.047058823529411764,
"grad_norm": 0.11171095073223114,
"learning_rate": 9.959337718951558e-06,
"loss": 0.7807,
"step": 70
},
{
"epoch": 0.04773109243697479,
"grad_norm": 0.19787555932998657,
"learning_rate": 9.957972932298425e-06,
"loss": 0.7859,
"step": 71
},
{
"epoch": 0.048403361344537814,
"grad_norm": 0.14838945865631104,
"learning_rate": 9.956585714949656e-06,
"loss": 0.84,
"step": 72
},
{
"epoch": 0.04907563025210084,
"grad_norm": 0.1107582226395607,
"learning_rate": 9.95517607318125e-06,
"loss": 0.8462,
"step": 73
},
{
"epoch": 0.049747899159663864,
"grad_norm": 0.10351675003767014,
"learning_rate": 9.953744013370664e-06,
"loss": 0.8877,
"step": 74
},
{
"epoch": 0.05042016806722689,
"grad_norm": 0.10547688603401184,
"learning_rate": 9.952289541996772e-06,
"loss": 0.9026,
"step": 75
},
{
"epoch": 0.051092436974789913,
"grad_norm": 0.1045449823141098,
"learning_rate": 9.950812665639846e-06,
"loss": 0.7632,
"step": 76
},
{
"epoch": 0.05176470588235294,
"grad_norm": 0.10957052558660507,
"learning_rate": 9.949313390981523e-06,
"loss": 0.6904,
"step": 77
},
{
"epoch": 0.05243697478991596,
"grad_norm": 0.11886177957057953,
"learning_rate": 9.94779172480477e-06,
"loss": 0.8598,
"step": 78
},
{
"epoch": 0.05310924369747899,
"grad_norm": 0.11801187694072723,
"learning_rate": 9.946247673993859e-06,
"loss": 0.7523,
"step": 79
},
{
"epoch": 0.05378151260504202,
"grad_norm": 0.11699094623327255,
"learning_rate": 9.944681245534329e-06,
"loss": 0.7911,
"step": 80
},
{
"epoch": 0.05445378151260504,
"grad_norm": 0.12566529214382172,
"learning_rate": 9.943092446512969e-06,
"loss": 0.7427,
"step": 81
},
{
"epoch": 0.05512605042016807,
"grad_norm": 0.12246568500995636,
"learning_rate": 9.941481284117767e-06,
"loss": 0.6664,
"step": 82
},
{
"epoch": 0.05579831932773109,
"grad_norm": 0.13946433365345,
"learning_rate": 9.939847765637892e-06,
"loss": 0.7136,
"step": 83
},
{
"epoch": 0.05647058823529412,
"grad_norm": 0.1847638487815857,
"learning_rate": 9.938191898463652e-06,
"loss": 0.7466,
"step": 84
},
{
"epoch": 0.05714285714285714,
"grad_norm": 0.15350033342838287,
"learning_rate": 9.936513690086466e-06,
"loss": 0.8925,
"step": 85
},
{
"epoch": 0.05781512605042017,
"grad_norm": 0.12483131885528564,
"learning_rate": 9.934813148098833e-06,
"loss": 0.7337,
"step": 86
},
{
"epoch": 0.05848739495798319,
"grad_norm": 0.22703243792057037,
"learning_rate": 9.93309028019428e-06,
"loss": 0.7534,
"step": 87
},
{
"epoch": 0.05915966386554622,
"grad_norm": 0.1408054232597351,
"learning_rate": 9.931345094167355e-06,
"loss": 0.7855,
"step": 88
},
{
"epoch": 0.05983193277310924,
"grad_norm": 0.10884613543748856,
"learning_rate": 9.929577597913569e-06,
"loss": 0.873,
"step": 89
},
{
"epoch": 0.06050420168067227,
"grad_norm": 0.12801045179367065,
"learning_rate": 9.927787799429366e-06,
"loss": 0.731,
"step": 90
},
{
"epoch": 0.0611764705882353,
"grad_norm": 0.11761047691106796,
"learning_rate": 9.925975706812099e-06,
"loss": 0.8504,
"step": 91
},
{
"epoch": 0.06184873949579832,
"grad_norm": 0.11633070558309555,
"learning_rate": 9.924141328259973e-06,
"loss": 0.771,
"step": 92
},
{
"epoch": 0.06252100840336135,
"grad_norm": 0.1195223405957222,
"learning_rate": 9.922284672072022e-06,
"loss": 0.8507,
"step": 93
},
{
"epoch": 0.06319327731092438,
"grad_norm": 0.11958979815244675,
"learning_rate": 9.920405746648067e-06,
"loss": 0.8864,
"step": 94
},
{
"epoch": 0.06386554621848739,
"grad_norm": 0.4856259822845459,
"learning_rate": 9.918504560488683e-06,
"loss": 0.8751,
"step": 95
},
{
"epoch": 0.06453781512605042,
"grad_norm": 0.14082475006580353,
"learning_rate": 9.91658112219515e-06,
"loss": 0.749,
"step": 96
},
{
"epoch": 0.06521008403361345,
"grad_norm": 0.13045863807201385,
"learning_rate": 9.914635440469427e-06,
"loss": 0.7975,
"step": 97
},
{
"epoch": 0.06588235294117648,
"grad_norm": 0.14883267879486084,
"learning_rate": 9.912667524114097e-06,
"loss": 0.8199,
"step": 98
},
{
"epoch": 0.06655462184873949,
"grad_norm": 0.128151535987854,
"learning_rate": 9.910677382032346e-06,
"loss": 0.7441,
"step": 99
},
{
"epoch": 0.06722689075630252,
"grad_norm": 0.13587278127670288,
"learning_rate": 9.908665023227906e-06,
"loss": 0.8143,
"step": 100
},
{
"epoch": 0.06789915966386555,
"grad_norm": 0.18061594665050507,
"learning_rate": 9.906630456805024e-06,
"loss": 0.9194,
"step": 101
},
{
"epoch": 0.06857142857142857,
"grad_norm": 0.14718933403491974,
"learning_rate": 9.904573691968417e-06,
"loss": 0.8189,
"step": 102
},
{
"epoch": 0.0692436974789916,
"grad_norm": 0.11956693977117538,
"learning_rate": 9.902494738023233e-06,
"loss": 0.7266,
"step": 103
},
{
"epoch": 0.06991596638655462,
"grad_norm": 0.14369268715381622,
"learning_rate": 9.900393604375006e-06,
"loss": 0.8043,
"step": 104
},
{
"epoch": 0.07058823529411765,
"grad_norm": 0.12656539678573608,
"learning_rate": 9.898270300529615e-06,
"loss": 0.8553,
"step": 105
},
{
"epoch": 0.07126050420168067,
"grad_norm": 0.1397569477558136,
"learning_rate": 9.89612483609324e-06,
"loss": 0.8091,
"step": 106
},
{
"epoch": 0.0719327731092437,
"grad_norm": 0.1262049674987793,
"learning_rate": 9.893957220772319e-06,
"loss": 0.8208,
"step": 107
},
{
"epoch": 0.07260504201680672,
"grad_norm": 2.6684651374816895,
"learning_rate": 9.891767464373503e-06,
"loss": 0.9089,
"step": 108
},
{
"epoch": 0.07327731092436975,
"grad_norm": 0.3158283233642578,
"learning_rate": 9.889555576803617e-06,
"loss": 0.8193,
"step": 109
},
{
"epoch": 0.07394957983193277,
"grad_norm": 0.1529214233160019,
"learning_rate": 9.887321568069612e-06,
"loss": 0.7586,
"step": 110
},
{
"epoch": 0.0746218487394958,
"grad_norm": 0.13424837589263916,
"learning_rate": 9.88506544827851e-06,
"loss": 0.7868,
"step": 111
},
{
"epoch": 0.07529411764705882,
"grad_norm": 0.1253993809223175,
"learning_rate": 9.882787227637376e-06,
"loss": 0.7582,
"step": 112
},
{
"epoch": 0.07596638655462185,
"grad_norm": 0.1568586230278015,
"learning_rate": 9.88048691645326e-06,
"loss": 0.7763,
"step": 113
},
{
"epoch": 0.07663865546218487,
"grad_norm": 0.16978754103183746,
"learning_rate": 9.87816452513315e-06,
"loss": 0.796,
"step": 114
},
{
"epoch": 0.0773109243697479,
"grad_norm": 0.1352425515651703,
"learning_rate": 9.875820064183936e-06,
"loss": 0.7634,
"step": 115
},
{
"epoch": 0.07798319327731093,
"grad_norm": 0.1855115294456482,
"learning_rate": 9.873453544212347e-06,
"loss": 0.6697,
"step": 116
},
{
"epoch": 0.07865546218487394,
"grad_norm": 0.1740746945142746,
"learning_rate": 9.871064975924913e-06,
"loss": 0.7209,
"step": 117
},
{
"epoch": 0.07932773109243697,
"grad_norm": 0.2007463425397873,
"learning_rate": 9.868654370127918e-06,
"loss": 0.7044,
"step": 118
},
{
"epoch": 0.08,
"grad_norm": 0.12837733328342438,
"learning_rate": 9.866221737727341e-06,
"loss": 0.7969,
"step": 119
},
{
"epoch": 0.08067226890756303,
"grad_norm": 0.17075017094612122,
"learning_rate": 9.86376708972882e-06,
"loss": 0.6553,
"step": 120
},
{
"epoch": 0.08134453781512604,
"grad_norm": 0.1436099112033844,
"learning_rate": 9.861290437237585e-06,
"loss": 0.7498,
"step": 121
},
{
"epoch": 0.08201680672268907,
"grad_norm": 0.12680667638778687,
"learning_rate": 9.858791791458431e-06,
"loss": 0.6969,
"step": 122
},
{
"epoch": 0.0826890756302521,
"grad_norm": 0.21285346150398254,
"learning_rate": 9.856271163695646e-06,
"loss": 0.8366,
"step": 123
},
{
"epoch": 0.08336134453781513,
"grad_norm": 0.1799962818622589,
"learning_rate": 9.85372856535297e-06,
"loss": 0.6776,
"step": 124
},
{
"epoch": 0.08403361344537816,
"grad_norm": 0.1583629548549652,
"learning_rate": 9.851164007933539e-06,
"loss": 0.8507,
"step": 125
},
{
"epoch": 0.08470588235294117,
"grad_norm": 0.15405218303203583,
"learning_rate": 9.848577503039843e-06,
"loss": 0.7331,
"step": 126
},
{
"epoch": 0.0853781512605042,
"grad_norm": 0.18484558165073395,
"learning_rate": 9.845969062373655e-06,
"loss": 0.7908,
"step": 127
},
{
"epoch": 0.08605042016806723,
"grad_norm": 0.1605813205242157,
"learning_rate": 9.843338697736e-06,
"loss": 0.8332,
"step": 128
},
{
"epoch": 0.08672268907563026,
"grad_norm": 0.14769910275936127,
"learning_rate": 9.840686421027085e-06,
"loss": 0.7287,
"step": 129
},
{
"epoch": 0.08739495798319327,
"grad_norm": 0.16447949409484863,
"learning_rate": 9.83801224424625e-06,
"loss": 0.7388,
"step": 130
},
{
"epoch": 0.0880672268907563,
"grad_norm": 0.15745119750499725,
"learning_rate": 9.835316179491919e-06,
"loss": 0.729,
"step": 131
},
{
"epoch": 0.08873949579831933,
"grad_norm": 0.18337000906467438,
"learning_rate": 9.832598238961534e-06,
"loss": 0.7714,
"step": 132
},
{
"epoch": 0.08941176470588236,
"grad_norm": 0.14670008420944214,
"learning_rate": 9.829858434951516e-06,
"loss": 0.7787,
"step": 133
},
{
"epoch": 0.09008403361344537,
"grad_norm": 0.15470527112483978,
"learning_rate": 9.82709677985719e-06,
"loss": 0.8125,
"step": 134
},
{
"epoch": 0.0907563025210084,
"grad_norm": 0.15246663987636566,
"learning_rate": 9.824313286172748e-06,
"loss": 0.7938,
"step": 135
},
{
"epoch": 0.09142857142857143,
"grad_norm": 0.15700078010559082,
"learning_rate": 9.821507966491178e-06,
"loss": 0.6438,
"step": 136
},
{
"epoch": 0.09210084033613446,
"grad_norm": 0.15387018024921417,
"learning_rate": 9.81868083350421e-06,
"loss": 0.6915,
"step": 137
},
{
"epoch": 0.09277310924369749,
"grad_norm": 0.17690274119377136,
"learning_rate": 9.81583190000227e-06,
"loss": 0.6618,
"step": 138
},
{
"epoch": 0.0934453781512605,
"grad_norm": 0.1894235461950302,
"learning_rate": 9.812961178874404e-06,
"loss": 0.7949,
"step": 139
},
{
"epoch": 0.09411764705882353,
"grad_norm": 0.27365830540657043,
"learning_rate": 9.810068683108233e-06,
"loss": 0.6956,
"step": 140
},
{
"epoch": 0.09478991596638656,
"grad_norm": 0.1983897089958191,
"learning_rate": 9.807154425789894e-06,
"loss": 0.6946,
"step": 141
},
{
"epoch": 0.09546218487394958,
"grad_norm": 0.16158057749271393,
"learning_rate": 9.804218420103969e-06,
"loss": 0.6912,
"step": 142
},
{
"epoch": 0.0961344537815126,
"grad_norm": 0.1842929571866989,
"learning_rate": 9.801260679333435e-06,
"loss": 0.6841,
"step": 143
},
{
"epoch": 0.09680672268907563,
"grad_norm": 0.18475371599197388,
"learning_rate": 9.798281216859608e-06,
"loss": 0.8085,
"step": 144
},
{
"epoch": 0.09747899159663866,
"grad_norm": 0.16353516280651093,
"learning_rate": 9.795280046162072e-06,
"loss": 0.7655,
"step": 145
},
{
"epoch": 0.09815126050420168,
"grad_norm": 0.15461254119873047,
"learning_rate": 9.792257180818622e-06,
"loss": 0.7782,
"step": 146
},
{
"epoch": 0.0988235294117647,
"grad_norm": 0.1649758517742157,
"learning_rate": 9.789212634505205e-06,
"loss": 0.728,
"step": 147
},
{
"epoch": 0.09949579831932773,
"grad_norm": 0.1581656038761139,
"learning_rate": 9.786146420995856e-06,
"loss": 0.832,
"step": 148
},
{
"epoch": 0.10016806722689076,
"grad_norm": 0.15653114020824432,
"learning_rate": 9.783058554162637e-06,
"loss": 0.7491,
"step": 149
},
{
"epoch": 0.10084033613445378,
"grad_norm": 0.18371178209781647,
"learning_rate": 9.779949047975568e-06,
"loss": 0.7454,
"step": 150
},
{
"epoch": 0.10151260504201681,
"grad_norm": 0.1631736010313034,
"learning_rate": 9.776817916502577e-06,
"loss": 0.7361,
"step": 151
},
{
"epoch": 0.10218487394957983,
"grad_norm": 0.16311539709568024,
"learning_rate": 9.773665173909424e-06,
"loss": 0.6452,
"step": 152
},
{
"epoch": 0.10285714285714286,
"grad_norm": 0.19410477578639984,
"learning_rate": 9.770490834459641e-06,
"loss": 0.8368,
"step": 153
},
{
"epoch": 0.10352941176470588,
"grad_norm": 0.19130192697048187,
"learning_rate": 9.767294912514468e-06,
"loss": 0.6695,
"step": 154
},
{
"epoch": 0.10420168067226891,
"grad_norm": 0.15637724101543427,
"learning_rate": 9.76407742253279e-06,
"loss": 0.6275,
"step": 155
},
{
"epoch": 0.10487394957983193,
"grad_norm": 0.16742682456970215,
"learning_rate": 9.760838379071065e-06,
"loss": 0.7172,
"step": 156
},
{
"epoch": 0.10554621848739495,
"grad_norm": 0.47532567381858826,
"learning_rate": 9.757577796783268e-06,
"loss": 0.8479,
"step": 157
},
{
"epoch": 0.10621848739495798,
"grad_norm": 0.14579716324806213,
"learning_rate": 9.754295690420815e-06,
"loss": 0.6863,
"step": 158
},
{
"epoch": 0.10689075630252101,
"grad_norm": 0.1644534468650818,
"learning_rate": 9.750992074832503e-06,
"loss": 0.7262,
"step": 159
},
{
"epoch": 0.10756302521008404,
"grad_norm": 0.1633559912443161,
"learning_rate": 9.74766696496444e-06,
"loss": 0.5784,
"step": 160
},
{
"epoch": 0.10823529411764705,
"grad_norm": 0.17903897166252136,
"learning_rate": 9.744320375859975e-06,
"loss": 0.7111,
"step": 161
},
{
"epoch": 0.10890756302521008,
"grad_norm": 0.1747799664735794,
"learning_rate": 9.740952322659636e-06,
"loss": 0.6858,
"step": 162
},
{
"epoch": 0.10957983193277311,
"grad_norm": 0.15818876028060913,
"learning_rate": 9.737562820601058e-06,
"loss": 0.7589,
"step": 163
},
{
"epoch": 0.11025210084033614,
"grad_norm": 0.16842347383499146,
"learning_rate": 9.73415188501891e-06,
"loss": 0.6315,
"step": 164
},
{
"epoch": 0.11092436974789915,
"grad_norm": 0.17130237817764282,
"learning_rate": 9.730719531344837e-06,
"loss": 0.7264,
"step": 165
},
{
"epoch": 0.11159663865546218,
"grad_norm": 0.21110771596431732,
"learning_rate": 9.727265775107375e-06,
"loss": 0.8001,
"step": 166
},
{
"epoch": 0.11226890756302521,
"grad_norm": 0.2074054777622223,
"learning_rate": 9.723790631931892e-06,
"loss": 0.7568,
"step": 167
},
{
"epoch": 0.11294117647058824,
"grad_norm": 0.17436759173870087,
"learning_rate": 9.72029411754052e-06,
"loss": 0.7216,
"step": 168
},
{
"epoch": 0.11361344537815125,
"grad_norm": 0.15503355860710144,
"learning_rate": 9.71677624775207e-06,
"loss": 0.5998,
"step": 169
},
{
"epoch": 0.11428571428571428,
"grad_norm": 0.2187543511390686,
"learning_rate": 9.71323703848197e-06,
"loss": 0.8118,
"step": 170
},
{
"epoch": 0.11495798319327731,
"grad_norm": 0.17232966423034668,
"learning_rate": 9.709676505742194e-06,
"loss": 0.7798,
"step": 171
},
{
"epoch": 0.11563025210084034,
"grad_norm": 0.16726981103420258,
"learning_rate": 9.706094665641184e-06,
"loss": 0.7202,
"step": 172
},
{
"epoch": 0.11630252100840337,
"grad_norm": 0.1730181723833084,
"learning_rate": 9.70249153438378e-06,
"loss": 0.724,
"step": 173
},
{
"epoch": 0.11697478991596638,
"grad_norm": 0.2613270580768585,
"learning_rate": 9.698867128271152e-06,
"loss": 0.639,
"step": 174
},
{
"epoch": 0.11764705882352941,
"grad_norm": 0.17092633247375488,
"learning_rate": 9.695221463700715e-06,
"loss": 0.7663,
"step": 175
},
{
"epoch": 0.11831932773109244,
"grad_norm": 5.159976959228516,
"learning_rate": 9.691554557166063e-06,
"loss": 0.6931,
"step": 176
},
{
"epoch": 0.11899159663865547,
"grad_norm": 0.16329586505889893,
"learning_rate": 9.687866425256894e-06,
"loss": 0.6889,
"step": 177
},
{
"epoch": 0.11966386554621848,
"grad_norm": 0.1860726773738861,
"learning_rate": 9.684157084658929e-06,
"loss": 0.6816,
"step": 178
},
{
"epoch": 0.12033613445378151,
"grad_norm": 0.16123488545417786,
"learning_rate": 9.680426552153843e-06,
"loss": 0.6856,
"step": 179
},
{
"epoch": 0.12100840336134454,
"grad_norm": 0.180853471159935,
"learning_rate": 9.676674844619187e-06,
"loss": 0.693,
"step": 180
},
{
"epoch": 0.12168067226890757,
"grad_norm": 0.20253466069698334,
"learning_rate": 9.67290197902831e-06,
"loss": 0.8013,
"step": 181
},
{
"epoch": 0.1223529411764706,
"grad_norm": 0.17012205719947815,
"learning_rate": 9.66910797245029e-06,
"loss": 0.7746,
"step": 182
},
{
"epoch": 0.12302521008403361,
"grad_norm": 0.24241431057453156,
"learning_rate": 9.665292842049836e-06,
"loss": 0.7619,
"step": 183
},
{
"epoch": 0.12369747899159664,
"grad_norm": 0.3148103654384613,
"learning_rate": 9.66145660508724e-06,
"loss": 0.738,
"step": 184
},
{
"epoch": 0.12436974789915967,
"grad_norm": 0.20171897113323212,
"learning_rate": 9.657599278918278e-06,
"loss": 0.7616,
"step": 185
},
{
"epoch": 0.1250420168067227,
"grad_norm": 0.17481227219104767,
"learning_rate": 9.65372088099413e-06,
"loss": 0.7468,
"step": 186
},
{
"epoch": 0.12571428571428572,
"grad_norm": 0.20101875066757202,
"learning_rate": 9.649821428861319e-06,
"loss": 0.7537,
"step": 187
},
{
"epoch": 0.12638655462184875,
"grad_norm": 0.20836427807807922,
"learning_rate": 9.645900940161616e-06,
"loss": 0.7499,
"step": 188
},
{
"epoch": 0.12705882352941175,
"grad_norm": 0.22894078493118286,
"learning_rate": 9.641959432631966e-06,
"loss": 0.7718,
"step": 189
},
{
"epoch": 0.12773109243697478,
"grad_norm": 0.17879128456115723,
"learning_rate": 9.637996924104403e-06,
"loss": 0.6813,
"step": 190
},
{
"epoch": 0.1284033613445378,
"grad_norm": 0.1844119280576706,
"learning_rate": 9.634013432505977e-06,
"loss": 0.8137,
"step": 191
},
{
"epoch": 0.12907563025210084,
"grad_norm": 0.16975240409374237,
"learning_rate": 9.630008975858667e-06,
"loss": 0.7139,
"step": 192
},
{
"epoch": 0.12974789915966387,
"grad_norm": 0.17935213446617126,
"learning_rate": 9.625983572279304e-06,
"loss": 0.6553,
"step": 193
},
{
"epoch": 0.1304201680672269,
"grad_norm": 0.19229981303215027,
"learning_rate": 9.621937239979484e-06,
"loss": 0.6752,
"step": 194
},
{
"epoch": 0.13109243697478992,
"grad_norm": 0.20354849100112915,
"learning_rate": 9.617869997265486e-06,
"loss": 0.6714,
"step": 195
},
{
"epoch": 0.13176470588235295,
"grad_norm": 0.21125207841396332,
"learning_rate": 9.613781862538196e-06,
"loss": 0.6478,
"step": 196
},
{
"epoch": 0.13243697478991598,
"grad_norm": 0.1878240555524826,
"learning_rate": 9.609672854293018e-06,
"loss": 0.6485,
"step": 197
},
{
"epoch": 0.13310924369747898,
"grad_norm": 0.1830340474843979,
"learning_rate": 9.605542991119787e-06,
"loss": 0.8007,
"step": 198
},
{
"epoch": 0.133781512605042,
"grad_norm": 0.1766654998064041,
"learning_rate": 9.601392291702693e-06,
"loss": 0.6918,
"step": 199
},
{
"epoch": 0.13445378151260504,
"grad_norm": 0.2146570086479187,
"learning_rate": 9.597220774820193e-06,
"loss": 0.7351,
"step": 200
},
{
"epoch": 0.13512605042016806,
"grad_norm": 0.3166307210922241,
"learning_rate": 9.593028459344923e-06,
"loss": 0.7551,
"step": 201
},
{
"epoch": 0.1357983193277311,
"grad_norm": 0.20315152406692505,
"learning_rate": 9.588815364243618e-06,
"loss": 0.7196,
"step": 202
},
{
"epoch": 0.13647058823529412,
"grad_norm": 0.19757510721683502,
"learning_rate": 9.58458150857702e-06,
"loss": 0.7198,
"step": 203
},
{
"epoch": 0.13714285714285715,
"grad_norm": 0.1865769773721695,
"learning_rate": 9.5803269114998e-06,
"loss": 0.6766,
"step": 204
},
{
"epoch": 0.13781512605042018,
"grad_norm": 0.21868400275707245,
"learning_rate": 9.576051592260464e-06,
"loss": 0.7456,
"step": 205
},
{
"epoch": 0.1384873949579832,
"grad_norm": 0.23371611535549164,
"learning_rate": 9.571755570201266e-06,
"loss": 0.7324,
"step": 206
},
{
"epoch": 0.1391596638655462,
"grad_norm": 0.1825055480003357,
"learning_rate": 9.567438864758128e-06,
"loss": 0.7392,
"step": 207
},
{
"epoch": 0.13983193277310924,
"grad_norm": 0.20412546396255493,
"learning_rate": 9.563101495460543e-06,
"loss": 0.6748,
"step": 208
},
{
"epoch": 0.14050420168067226,
"grad_norm": 0.18851631879806519,
"learning_rate": 9.558743481931494e-06,
"loss": 0.7368,
"step": 209
},
{
"epoch": 0.1411764705882353,
"grad_norm": 0.19340087473392487,
"learning_rate": 9.554364843887361e-06,
"loss": 0.7966,
"step": 210
},
{
"epoch": 0.14184873949579832,
"grad_norm": 0.21277926862239838,
"learning_rate": 9.549965601137827e-06,
"loss": 0.7708,
"step": 211
},
{
"epoch": 0.14252100840336135,
"grad_norm": 0.19546258449554443,
"learning_rate": 9.545545773585806e-06,
"loss": 0.8285,
"step": 212
},
{
"epoch": 0.14319327731092438,
"grad_norm": 2.4378411769866943,
"learning_rate": 9.54110538122733e-06,
"loss": 0.6936,
"step": 213
},
{
"epoch": 0.1438655462184874,
"grad_norm": 0.17651917040348053,
"learning_rate": 9.536644444151475e-06,
"loss": 0.6601,
"step": 214
},
{
"epoch": 0.14453781512605043,
"grad_norm": 0.19953793287277222,
"learning_rate": 9.532162982540264e-06,
"loss": 0.6732,
"step": 215
},
{
"epoch": 0.14521008403361343,
"grad_norm": 0.18227693438529968,
"learning_rate": 9.527661016668577e-06,
"loss": 0.7152,
"step": 216
},
{
"epoch": 0.14588235294117646,
"grad_norm": 0.2055724710226059,
"learning_rate": 9.523138566904053e-06,
"loss": 0.651,
"step": 217
},
{
"epoch": 0.1465546218487395,
"grad_norm": 0.1922536939382553,
"learning_rate": 9.518595653707015e-06,
"loss": 0.694,
"step": 218
},
{
"epoch": 0.14722689075630252,
"grad_norm": 0.1832892894744873,
"learning_rate": 9.514032297630354e-06,
"loss": 0.7108,
"step": 219
},
{
"epoch": 0.14789915966386555,
"grad_norm": 0.20151115953922272,
"learning_rate": 9.509448519319455e-06,
"loss": 0.7187,
"step": 220
},
{
"epoch": 0.14857142857142858,
"grad_norm": 0.1979878842830658,
"learning_rate": 9.504844339512096e-06,
"loss": 0.7189,
"step": 221
},
{
"epoch": 0.1492436974789916,
"grad_norm": 0.20959986746311188,
"learning_rate": 9.500219779038353e-06,
"loss": 0.7598,
"step": 222
},
{
"epoch": 0.14991596638655463,
"grad_norm": 0.26220154762268066,
"learning_rate": 9.495574858820507e-06,
"loss": 0.6579,
"step": 223
},
{
"epoch": 0.15058823529411763,
"grad_norm": 0.20292134582996368,
"learning_rate": 9.49090959987295e-06,
"loss": 0.6989,
"step": 224
},
{
"epoch": 0.15126050420168066,
"grad_norm": 0.18850331008434296,
"learning_rate": 9.486224023302095e-06,
"loss": 0.6869,
"step": 225
},
{
"epoch": 0.1519327731092437,
"grad_norm": 0.2740769386291504,
"learning_rate": 9.481518150306267e-06,
"loss": 0.7336,
"step": 226
},
{
"epoch": 0.15260504201680672,
"grad_norm": 0.2561083734035492,
"learning_rate": 9.476792002175621e-06,
"loss": 0.7116,
"step": 227
},
{
"epoch": 0.15327731092436975,
"grad_norm": 0.19910801947116852,
"learning_rate": 9.47204560029204e-06,
"loss": 0.6767,
"step": 228
},
{
"epoch": 0.15394957983193278,
"grad_norm": 0.1883971393108368,
"learning_rate": 9.467278966129034e-06,
"loss": 0.7448,
"step": 229
},
{
"epoch": 0.1546218487394958,
"grad_norm": 0.20471471548080444,
"learning_rate": 9.462492121251653e-06,
"loss": 0.6735,
"step": 230
},
{
"epoch": 0.15529411764705883,
"grad_norm": 0.2020663022994995,
"learning_rate": 9.45768508731638e-06,
"loss": 0.7307,
"step": 231
},
{
"epoch": 0.15596638655462186,
"grad_norm": 0.1929408609867096,
"learning_rate": 9.452857886071037e-06,
"loss": 0.7016,
"step": 232
},
{
"epoch": 0.15663865546218486,
"grad_norm": 0.29967066645622253,
"learning_rate": 9.448010539354684e-06,
"loss": 0.7133,
"step": 233
},
{
"epoch": 0.1573109243697479,
"grad_norm": 0.18856149911880493,
"learning_rate": 9.443143069097531e-06,
"loss": 0.6637,
"step": 234
},
{
"epoch": 0.15798319327731092,
"grad_norm": 0.18955619633197784,
"learning_rate": 9.43825549732082e-06,
"loss": 0.7367,
"step": 235
},
{
"epoch": 0.15865546218487395,
"grad_norm": 1.0548439025878906,
"learning_rate": 9.433347846136743e-06,
"loss": 0.7294,
"step": 236
},
{
"epoch": 0.15932773109243697,
"grad_norm": 0.19085678458213806,
"learning_rate": 9.428420137748329e-06,
"loss": 0.7797,
"step": 237
},
{
"epoch": 0.16,
"grad_norm": 0.2003992199897766,
"learning_rate": 9.423472394449354e-06,
"loss": 0.7579,
"step": 238
},
{
"epoch": 0.16067226890756303,
"grad_norm": 0.4015868902206421,
"learning_rate": 9.418504638624233e-06,
"loss": 0.6845,
"step": 239
},
{
"epoch": 0.16134453781512606,
"grad_norm": 0.1845397651195526,
"learning_rate": 9.413516892747918e-06,
"loss": 0.7254,
"step": 240
},
{
"epoch": 0.1620168067226891,
"grad_norm": 0.2877404987812042,
"learning_rate": 9.408509179385806e-06,
"loss": 0.5533,
"step": 241
},
{
"epoch": 0.1626890756302521,
"grad_norm": 1.1842849254608154,
"learning_rate": 9.403481521193625e-06,
"loss": 0.7173,
"step": 242
},
{
"epoch": 0.16336134453781512,
"grad_norm": 0.19836628437042236,
"learning_rate": 9.398433940917337e-06,
"loss": 0.6032,
"step": 243
},
{
"epoch": 0.16403361344537815,
"grad_norm": 0.18493618071079254,
"learning_rate": 9.39336646139304e-06,
"loss": 0.691,
"step": 244
},
{
"epoch": 0.16470588235294117,
"grad_norm": 0.21216131746768951,
"learning_rate": 9.388279105546852e-06,
"loss": 0.7955,
"step": 245
},
{
"epoch": 0.1653781512605042,
"grad_norm": 0.19313201308250427,
"learning_rate": 9.38317189639482e-06,
"loss": 0.6655,
"step": 246
},
{
"epoch": 0.16605042016806723,
"grad_norm": 0.20905853807926178,
"learning_rate": 9.37804485704281e-06,
"loss": 0.7399,
"step": 247
},
{
"epoch": 0.16672268907563026,
"grad_norm": 0.19061219692230225,
"learning_rate": 9.3728980106864e-06,
"loss": 0.6734,
"step": 248
},
{
"epoch": 0.1673949579831933,
"grad_norm": 0.31909891963005066,
"learning_rate": 9.367731380610784e-06,
"loss": 0.8297,
"step": 249
},
{
"epoch": 0.16806722689075632,
"grad_norm": 0.18734252452850342,
"learning_rate": 9.362544990190654e-06,
"loss": 0.6964,
"step": 250
},
{
"epoch": 0.16873949579831932,
"grad_norm": 0.2664547562599182,
"learning_rate": 9.357338862890107e-06,
"loss": 0.6729,
"step": 251
},
{
"epoch": 0.16941176470588235,
"grad_norm": 0.23206093907356262,
"learning_rate": 9.352113022262525e-06,
"loss": 0.7237,
"step": 252
},
{
"epoch": 0.17008403361344537,
"grad_norm": 0.19709858298301697,
"learning_rate": 9.34686749195049e-06,
"loss": 0.7221,
"step": 253
},
{
"epoch": 0.1707563025210084,
"grad_norm": 0.2132461667060852,
"learning_rate": 9.341602295685649e-06,
"loss": 0.7707,
"step": 254
},
{
"epoch": 0.17142857142857143,
"grad_norm": 0.20399631559848785,
"learning_rate": 9.33631745728863e-06,
"loss": 0.6073,
"step": 255
},
{
"epoch": 0.17210084033613446,
"grad_norm": 0.21512362360954285,
"learning_rate": 9.33101300066892e-06,
"loss": 0.7637,
"step": 256
},
{
"epoch": 0.1727731092436975,
"grad_norm": 0.38459283113479614,
"learning_rate": 9.325688949824768e-06,
"loss": 0.7271,
"step": 257
},
{
"epoch": 0.17344537815126052,
"grad_norm": 0.6972576975822449,
"learning_rate": 9.320345328843063e-06,
"loss": 0.7559,
"step": 258
},
{
"epoch": 0.17411764705882352,
"grad_norm": 0.20466119050979614,
"learning_rate": 9.31498216189924e-06,
"loss": 0.6713,
"step": 259
},
{
"epoch": 0.17478991596638654,
"grad_norm": 0.3543570637702942,
"learning_rate": 9.309599473257157e-06,
"loss": 0.7256,
"step": 260
},
{
"epoch": 0.17546218487394957,
"grad_norm": 0.19050233066082,
"learning_rate": 9.304197287269e-06,
"loss": 0.7107,
"step": 261
},
{
"epoch": 0.1761344537815126,
"grad_norm": 0.19116462767124176,
"learning_rate": 9.29877562837515e-06,
"loss": 0.6839,
"step": 262
},
{
"epoch": 0.17680672268907563,
"grad_norm": 0.22071011364459991,
"learning_rate": 9.293334521104103e-06,
"loss": 0.7256,
"step": 263
},
{
"epoch": 0.17747899159663866,
"grad_norm": 0.21820850670337677,
"learning_rate": 9.287873990072328e-06,
"loss": 0.6952,
"step": 264
},
{
"epoch": 0.1781512605042017,
"grad_norm": 0.19550518691539764,
"learning_rate": 9.282394059984186e-06,
"loss": 0.697,
"step": 265
},
{
"epoch": 0.17882352941176471,
"grad_norm": 0.18131797015666962,
"learning_rate": 9.276894755631785e-06,
"loss": 0.6845,
"step": 266
},
{
"epoch": 0.17949579831932774,
"grad_norm": 0.2566013038158417,
"learning_rate": 9.271376101894897e-06,
"loss": 0.694,
"step": 267
},
{
"epoch": 0.18016806722689074,
"grad_norm": 0.20400108397006989,
"learning_rate": 9.265838123740833e-06,
"loss": 0.6565,
"step": 268
},
{
"epoch": 0.18084033613445377,
"grad_norm": 0.22308161854743958,
"learning_rate": 9.260280846224328e-06,
"loss": 0.6994,
"step": 269
},
{
"epoch": 0.1815126050420168,
"grad_norm": 0.19968609511852264,
"learning_rate": 9.25470429448743e-06,
"loss": 0.7693,
"step": 270
},
{
"epoch": 0.18218487394957983,
"grad_norm": 0.19011756777763367,
"learning_rate": 9.24910849375939e-06,
"loss": 0.6951,
"step": 271
},
{
"epoch": 0.18285714285714286,
"grad_norm": 0.2302047312259674,
"learning_rate": 9.243493469356543e-06,
"loss": 0.765,
"step": 272
},
{
"epoch": 0.18352941176470589,
"grad_norm": 0.19871503114700317,
"learning_rate": 9.237859246682194e-06,
"loss": 0.5769,
"step": 273
},
{
"epoch": 0.1842016806722689,
"grad_norm": 0.20518113672733307,
"learning_rate": 9.232205851226504e-06,
"loss": 0.6779,
"step": 274
},
{
"epoch": 0.18487394957983194,
"grad_norm": 0.2253684103488922,
"learning_rate": 9.226533308566379e-06,
"loss": 0.8146,
"step": 275
},
{
"epoch": 0.18554621848739497,
"grad_norm": 0.21118251979351044,
"learning_rate": 9.220841644365343e-06,
"loss": 0.6319,
"step": 276
},
{
"epoch": 0.18621848739495797,
"grad_norm": 0.229267880320549,
"learning_rate": 9.215130884373437e-06,
"loss": 0.5965,
"step": 277
},
{
"epoch": 0.186890756302521,
"grad_norm": 0.21749767661094666,
"learning_rate": 9.20940105442709e-06,
"loss": 0.6744,
"step": 278
},
{
"epoch": 0.18756302521008403,
"grad_norm": 0.21476207673549652,
"learning_rate": 9.203652180449006e-06,
"loss": 0.7267,
"step": 279
},
{
"epoch": 0.18823529411764706,
"grad_norm": 0.21310514211654663,
"learning_rate": 9.19788428844805e-06,
"loss": 0.6398,
"step": 280
},
{
"epoch": 0.18890756302521008,
"grad_norm": 0.20523132383823395,
"learning_rate": 9.192097404519125e-06,
"loss": 0.71,
"step": 281
},
{
"epoch": 0.1895798319327731,
"grad_norm": 0.21132954955101013,
"learning_rate": 9.186291554843058e-06,
"loss": 0.7067,
"step": 282
},
{
"epoch": 0.19025210084033614,
"grad_norm": 0.3063057065010071,
"learning_rate": 9.180466765686485e-06,
"loss": 0.7032,
"step": 283
},
{
"epoch": 0.19092436974789917,
"grad_norm": 0.22190402448177338,
"learning_rate": 9.174623063401715e-06,
"loss": 0.6836,
"step": 284
},
{
"epoch": 0.1915966386554622,
"grad_norm": 0.19611823558807373,
"learning_rate": 9.168760474426637e-06,
"loss": 0.6805,
"step": 285
},
{
"epoch": 0.1922689075630252,
"grad_norm": 0.19553613662719727,
"learning_rate": 9.162879025284576e-06,
"loss": 0.6299,
"step": 286
},
{
"epoch": 0.19294117647058823,
"grad_norm": 0.20817598700523376,
"learning_rate": 9.156978742584193e-06,
"loss": 0.7777,
"step": 287
},
{
"epoch": 0.19361344537815126,
"grad_norm": 0.2142859697341919,
"learning_rate": 9.151059653019345e-06,
"loss": 0.6493,
"step": 288
},
{
"epoch": 0.19428571428571428,
"grad_norm": 0.21361011266708374,
"learning_rate": 9.145121783368983e-06,
"loss": 0.5819,
"step": 289
},
{
"epoch": 0.1949579831932773,
"grad_norm": 0.19033358991146088,
"learning_rate": 9.139165160497017e-06,
"loss": 0.5813,
"step": 290
},
{
"epoch": 0.19563025210084034,
"grad_norm": 0.20409995317459106,
"learning_rate": 9.133189811352198e-06,
"loss": 0.6008,
"step": 291
},
{
"epoch": 0.19630252100840337,
"grad_norm": 0.20880399644374847,
"learning_rate": 9.127195762968008e-06,
"loss": 0.7718,
"step": 292
},
{
"epoch": 0.1969747899159664,
"grad_norm": 0.33951178193092346,
"learning_rate": 9.121183042462517e-06,
"loss": 0.7092,
"step": 293
},
{
"epoch": 0.1976470588235294,
"grad_norm": 0.2210870087146759,
"learning_rate": 9.115151677038274e-06,
"loss": 0.786,
"step": 294
},
{
"epoch": 0.19831932773109243,
"grad_norm": 0.22350308299064636,
"learning_rate": 9.109101693982183e-06,
"loss": 0.7115,
"step": 295
},
{
"epoch": 0.19899159663865545,
"grad_norm": 0.23932407796382904,
"learning_rate": 9.103033120665372e-06,
"loss": 0.6476,
"step": 296
},
{
"epoch": 0.19966386554621848,
"grad_norm": 0.2179158478975296,
"learning_rate": 9.096945984543082e-06,
"loss": 0.653,
"step": 297
},
{
"epoch": 0.2003361344537815,
"grad_norm": 0.20750783383846283,
"learning_rate": 9.090840313154527e-06,
"loss": 0.6717,
"step": 298
},
{
"epoch": 0.20100840336134454,
"grad_norm": 0.2178952544927597,
"learning_rate": 9.084716134122785e-06,
"loss": 0.636,
"step": 299
},
{
"epoch": 0.20168067226890757,
"grad_norm": 0.19057603180408478,
"learning_rate": 9.078573475154663e-06,
"loss": 0.6087,
"step": 300
},
{
"epoch": 0.2023529411764706,
"grad_norm": 0.3372030258178711,
"learning_rate": 9.072412364040569e-06,
"loss": 0.794,
"step": 301
},
{
"epoch": 0.20302521008403362,
"grad_norm": 0.2145543247461319,
"learning_rate": 9.066232828654398e-06,
"loss": 0.649,
"step": 302
},
{
"epoch": 0.20369747899159663,
"grad_norm": 0.22783125936985016,
"learning_rate": 9.0600348969534e-06,
"loss": 0.6988,
"step": 303
},
{
"epoch": 0.20436974789915965,
"grad_norm": 0.35722485184669495,
"learning_rate": 9.053818596978051e-06,
"loss": 0.5973,
"step": 304
},
{
"epoch": 0.20504201680672268,
"grad_norm": 0.256307989358902,
"learning_rate": 9.047583956851924e-06,
"loss": 0.733,
"step": 305
},
{
"epoch": 0.2057142857142857,
"grad_norm": 0.3715127110481262,
"learning_rate": 9.041331004781571e-06,
"loss": 0.7164,
"step": 306
},
{
"epoch": 0.20638655462184874,
"grad_norm": 0.21380753815174103,
"learning_rate": 9.035059769056392e-06,
"loss": 0.6332,
"step": 307
},
{
"epoch": 0.20705882352941177,
"grad_norm": 0.22382056713104248,
"learning_rate": 9.0287702780485e-06,
"loss": 0.5795,
"step": 308
},
{
"epoch": 0.2077310924369748,
"grad_norm": 0.2213864028453827,
"learning_rate": 9.0224625602126e-06,
"loss": 0.6573,
"step": 309
},
{
"epoch": 0.20840336134453782,
"grad_norm": 0.2228260636329651,
"learning_rate": 9.01613664408586e-06,
"loss": 0.8475,
"step": 310
},
{
"epoch": 0.20907563025210085,
"grad_norm": 0.25468334555625916,
"learning_rate": 9.009792558287777e-06,
"loss": 0.819,
"step": 311
},
{
"epoch": 0.20974789915966385,
"grad_norm": 0.20580936968326569,
"learning_rate": 9.003430331520054e-06,
"loss": 0.7051,
"step": 312
},
{
"epoch": 0.21042016806722688,
"grad_norm": 0.22535796463489532,
"learning_rate": 8.997049992566463e-06,
"loss": 0.6888,
"step": 313
},
{
"epoch": 0.2110924369747899,
"grad_norm": 0.1907246857881546,
"learning_rate": 8.990651570292719e-06,
"loss": 0.5605,
"step": 314
},
{
"epoch": 0.21176470588235294,
"grad_norm": 0.203364759683609,
"learning_rate": 8.984235093646355e-06,
"loss": 0.6962,
"step": 315
},
{
"epoch": 0.21243697478991597,
"grad_norm": 0.2653529942035675,
"learning_rate": 8.977800591656578e-06,
"loss": 0.6416,
"step": 316
},
{
"epoch": 0.213109243697479,
"grad_norm": 0.19569313526153564,
"learning_rate": 8.971348093434147e-06,
"loss": 0.5888,
"step": 317
},
{
"epoch": 0.21378151260504202,
"grad_norm": 0.20980022847652435,
"learning_rate": 8.96487762817124e-06,
"loss": 0.7006,
"step": 318
},
{
"epoch": 0.21445378151260505,
"grad_norm": 0.20609882473945618,
"learning_rate": 8.958389225141319e-06,
"loss": 0.5779,
"step": 319
},
{
"epoch": 0.21512605042016808,
"grad_norm": 0.2215481400489807,
"learning_rate": 8.951882913699001e-06,
"loss": 0.7546,
"step": 320
},
{
"epoch": 0.21579831932773108,
"grad_norm": 0.23511946201324463,
"learning_rate": 8.945358723279922e-06,
"loss": 0.7205,
"step": 321
},
{
"epoch": 0.2164705882352941,
"grad_norm": 0.41210508346557617,
"learning_rate": 8.938816683400609e-06,
"loss": 0.755,
"step": 322
},
{
"epoch": 0.21714285714285714,
"grad_norm": 0.29828765988349915,
"learning_rate": 8.932256823658337e-06,
"loss": 0.681,
"step": 323
},
{
"epoch": 0.21781512605042017,
"grad_norm": 0.2204638570547104,
"learning_rate": 8.925679173731005e-06,
"loss": 0.6376,
"step": 324
},
{
"epoch": 0.2184873949579832,
"grad_norm": 0.27005571126937866,
"learning_rate": 8.919083763377001e-06,
"loss": 0.7109,
"step": 325
},
{
"epoch": 0.21915966386554622,
"grad_norm": 0.24745038151741028,
"learning_rate": 8.912470622435056e-06,
"loss": 0.6251,
"step": 326
},
{
"epoch": 0.21983193277310925,
"grad_norm": 0.20610134303569794,
"learning_rate": 8.905839780824124e-06,
"loss": 0.687,
"step": 327
},
{
"epoch": 0.22050420168067228,
"grad_norm": 0.22061991691589355,
"learning_rate": 8.899191268543237e-06,
"loss": 0.6248,
"step": 328
},
{
"epoch": 0.2211764705882353,
"grad_norm": 0.22769795358181,
"learning_rate": 8.892525115671372e-06,
"loss": 0.7537,
"step": 329
},
{
"epoch": 0.2218487394957983,
"grad_norm": 0.2176414579153061,
"learning_rate": 8.885841352367315e-06,
"loss": 0.6707,
"step": 330
},
{
"epoch": 0.22252100840336134,
"grad_norm": 0.23448556661605835,
"learning_rate": 8.879140008869525e-06,
"loss": 0.6581,
"step": 331
},
{
"epoch": 0.22319327731092437,
"grad_norm": 0.47701385617256165,
"learning_rate": 8.872421115495996e-06,
"loss": 0.6326,
"step": 332
},
{
"epoch": 0.2238655462184874,
"grad_norm": 0.2669718265533447,
"learning_rate": 8.865684702644121e-06,
"loss": 0.6678,
"step": 333
},
{
"epoch": 0.22453781512605042,
"grad_norm": 0.2369898110628128,
"learning_rate": 8.858930800790557e-06,
"loss": 0.6582,
"step": 334
},
{
"epoch": 0.22521008403361345,
"grad_norm": 0.2101169228553772,
"learning_rate": 8.852159440491077e-06,
"loss": 0.7423,
"step": 335
},
{
"epoch": 0.22588235294117648,
"grad_norm": 0.21075445413589478,
"learning_rate": 8.845370652380447e-06,
"loss": 0.6468,
"step": 336
},
{
"epoch": 0.2265546218487395,
"grad_norm": 0.2244008332490921,
"learning_rate": 8.838564467172274e-06,
"loss": 0.6697,
"step": 337
},
{
"epoch": 0.2272268907563025,
"grad_norm": 0.21729138493537903,
"learning_rate": 8.831740915658872e-06,
"loss": 0.682,
"step": 338
},
{
"epoch": 0.22789915966386554,
"grad_norm": 0.21469177305698395,
"learning_rate": 8.824900028711128e-06,
"loss": 0.6144,
"step": 339
},
{
"epoch": 0.22857142857142856,
"grad_norm": 0.19239458441734314,
"learning_rate": 8.818041837278355e-06,
"loss": 0.6099,
"step": 340
},
{
"epoch": 0.2292436974789916,
"grad_norm": 0.24779051542282104,
"learning_rate": 8.811166372388149e-06,
"loss": 0.6901,
"step": 341
},
{
"epoch": 0.22991596638655462,
"grad_norm": 0.21615615487098694,
"learning_rate": 8.804273665146263e-06,
"loss": 0.6693,
"step": 342
},
{
"epoch": 0.23058823529411765,
"grad_norm": 0.27268433570861816,
"learning_rate": 8.797363746736452e-06,
"loss": 0.8542,
"step": 343
},
{
"epoch": 0.23126050420168068,
"grad_norm": 0.2103165239095688,
"learning_rate": 8.790436648420338e-06,
"loss": 0.6726,
"step": 344
},
{
"epoch": 0.2319327731092437,
"grad_norm": 0.2211274951696396,
"learning_rate": 8.783492401537268e-06,
"loss": 0.7011,
"step": 345
},
{
"epoch": 0.23260504201680673,
"grad_norm": 0.22610008716583252,
"learning_rate": 8.77653103750417e-06,
"loss": 0.5894,
"step": 346
},
{
"epoch": 0.23327731092436974,
"grad_norm": 0.21889732778072357,
"learning_rate": 8.769552587815417e-06,
"loss": 0.6557,
"step": 347
},
{
"epoch": 0.23394957983193276,
"grad_norm": 0.22735275328159332,
"learning_rate": 8.76255708404268e-06,
"loss": 0.6196,
"step": 348
},
{
"epoch": 0.2346218487394958,
"grad_norm": 0.24510014057159424,
"learning_rate": 8.755544557834779e-06,
"loss": 0.6766,
"step": 349
},
{
"epoch": 0.23529411764705882,
"grad_norm": 0.20867806673049927,
"learning_rate": 8.748515040917555e-06,
"loss": 0.694,
"step": 350
},
{
"epoch": 0.23596638655462185,
"grad_norm": 0.23174314200878143,
"learning_rate": 8.741468565093713e-06,
"loss": 0.6212,
"step": 351
},
{
"epoch": 0.23663865546218488,
"grad_norm": 0.2600148022174835,
"learning_rate": 8.73440516224268e-06,
"loss": 0.5647,
"step": 352
},
{
"epoch": 0.2373109243697479,
"grad_norm": 0.21916405856609344,
"learning_rate": 8.727324864320472e-06,
"loss": 0.7096,
"step": 353
},
{
"epoch": 0.23798319327731093,
"grad_norm": 0.25194647908210754,
"learning_rate": 8.720227703359536e-06,
"loss": 0.7456,
"step": 354
},
{
"epoch": 0.23865546218487396,
"grad_norm": 0.2153853476047516,
"learning_rate": 8.713113711468607e-06,
"loss": 0.6285,
"step": 355
},
{
"epoch": 0.23932773109243696,
"grad_norm": 0.2569597065448761,
"learning_rate": 8.705982920832573e-06,
"loss": 0.6491,
"step": 356
},
{
"epoch": 0.24,
"grad_norm": 0.2086285650730133,
"learning_rate": 8.698835363712318e-06,
"loss": 0.662,
"step": 357
},
{
"epoch": 0.24067226890756302,
"grad_norm": 0.23374126851558685,
"learning_rate": 8.691671072444582e-06,
"loss": 0.729,
"step": 358
},
{
"epoch": 0.24134453781512605,
"grad_norm": 0.2192952185869217,
"learning_rate": 8.684490079441813e-06,
"loss": 0.6381,
"step": 359
},
{
"epoch": 0.24201680672268908,
"grad_norm": 0.2088990956544876,
"learning_rate": 8.677292417192018e-06,
"loss": 0.6033,
"step": 360
},
{
"epoch": 0.2426890756302521,
"grad_norm": 0.21980631351470947,
"learning_rate": 8.67007811825862e-06,
"loss": 0.6557,
"step": 361
},
{
"epoch": 0.24336134453781513,
"grad_norm": 0.21364949643611908,
"learning_rate": 8.66284721528031e-06,
"loss": 0.5617,
"step": 362
},
{
"epoch": 0.24403361344537816,
"grad_norm": 0.21444816887378693,
"learning_rate": 8.6555997409709e-06,
"loss": 0.7188,
"step": 363
},
{
"epoch": 0.2447058823529412,
"grad_norm": 0.3139742910861969,
"learning_rate": 8.648335728119168e-06,
"loss": 0.6365,
"step": 364
},
{
"epoch": 0.2453781512605042,
"grad_norm": 0.3673727810382843,
"learning_rate": 8.64105520958872e-06,
"loss": 0.6725,
"step": 365
},
{
"epoch": 0.24605042016806722,
"grad_norm": 0.22386662662029266,
"learning_rate": 8.633758218317836e-06,
"loss": 0.6167,
"step": 366
},
{
"epoch": 0.24672268907563025,
"grad_norm": 0.2022496610879898,
"learning_rate": 8.62644478731932e-06,
"loss": 0.6761,
"step": 367
},
{
"epoch": 0.24739495798319328,
"grad_norm": 0.35748136043548584,
"learning_rate": 8.619114949680349e-06,
"loss": 0.6699,
"step": 368
},
{
"epoch": 0.2480672268907563,
"grad_norm": 0.23497340083122253,
"learning_rate": 8.611768738562333e-06,
"loss": 0.7103,
"step": 369
},
{
"epoch": 0.24873949579831933,
"grad_norm": 0.23439949750900269,
"learning_rate": 8.604406187200758e-06,
"loss": 0.7444,
"step": 370
},
{
"epoch": 0.24941176470588236,
"grad_norm": 0.19876611232757568,
"learning_rate": 8.597027328905026e-06,
"loss": 0.5419,
"step": 371
},
{
"epoch": 0.2500840336134454,
"grad_norm": 0.2008461058139801,
"learning_rate": 8.589632197058326e-06,
"loss": 0.5705,
"step": 372
},
{
"epoch": 0.2507563025210084,
"grad_norm": 0.279691606760025,
"learning_rate": 8.582220825117466e-06,
"loss": 0.6726,
"step": 373
},
{
"epoch": 0.25142857142857145,
"grad_norm": 0.21170209348201752,
"learning_rate": 8.574793246612727e-06,
"loss": 0.599,
"step": 374
},
{
"epoch": 0.25210084033613445,
"grad_norm": 0.23143023252487183,
"learning_rate": 8.567349495147711e-06,
"loss": 0.673,
"step": 375
},
{
"epoch": 0.2527731092436975,
"grad_norm": 0.3455113172531128,
"learning_rate": 8.559889604399195e-06,
"loss": 0.7567,
"step": 376
},
{
"epoch": 0.2534453781512605,
"grad_norm": 0.23424625396728516,
"learning_rate": 8.552413608116959e-06,
"loss": 0.6846,
"step": 377
},
{
"epoch": 0.2541176470588235,
"grad_norm": 0.25633034110069275,
"learning_rate": 8.544921540123663e-06,
"loss": 0.6866,
"step": 378
},
{
"epoch": 0.25478991596638656,
"grad_norm": 0.2438989281654358,
"learning_rate": 8.537413434314668e-06,
"loss": 0.5694,
"step": 379
},
{
"epoch": 0.25546218487394956,
"grad_norm": 0.2545592784881592,
"learning_rate": 8.529889324657894e-06,
"loss": 0.7359,
"step": 380
},
{
"epoch": 0.2561344537815126,
"grad_norm": 0.33247342705726624,
"learning_rate": 8.52234924519367e-06,
"loss": 0.6206,
"step": 381
},
{
"epoch": 0.2568067226890756,
"grad_norm": 0.31537359952926636,
"learning_rate": 8.51479323003457e-06,
"loss": 0.6515,
"step": 382
},
{
"epoch": 0.2574789915966387,
"grad_norm": 0.2566099464893341,
"learning_rate": 8.507221313365266e-06,
"loss": 0.7823,
"step": 383
},
{
"epoch": 0.2581512605042017,
"grad_norm": 0.21989482641220093,
"learning_rate": 8.499633529442373e-06,
"loss": 0.6416,
"step": 384
},
{
"epoch": 0.25882352941176473,
"grad_norm": 0.23314514756202698,
"learning_rate": 8.492029912594284e-06,
"loss": 0.7286,
"step": 385
},
{
"epoch": 0.25949579831932773,
"grad_norm": 0.2304847538471222,
"learning_rate": 8.484410497221036e-06,
"loss": 0.7232,
"step": 386
},
{
"epoch": 0.26016806722689073,
"grad_norm": 0.3086731731891632,
"learning_rate": 8.476775317794126e-06,
"loss": 0.797,
"step": 387
},
{
"epoch": 0.2608403361344538,
"grad_norm": 0.24391745030879974,
"learning_rate": 8.469124408856384e-06,
"loss": 0.6864,
"step": 388
},
{
"epoch": 0.2615126050420168,
"grad_norm": 0.2130875438451767,
"learning_rate": 8.461457805021793e-06,
"loss": 0.7461,
"step": 389
},
{
"epoch": 0.26218487394957984,
"grad_norm": 0.2305675446987152,
"learning_rate": 8.45377554097535e-06,
"loss": 0.7015,
"step": 390
},
{
"epoch": 0.26285714285714284,
"grad_norm": 0.24206651747226715,
"learning_rate": 8.446077651472892e-06,
"loss": 0.6689,
"step": 391
},
{
"epoch": 0.2635294117647059,
"grad_norm": 0.2249177098274231,
"learning_rate": 8.438364171340957e-06,
"loss": 0.6084,
"step": 392
},
{
"epoch": 0.2642016806722689,
"grad_norm": 0.23055896162986755,
"learning_rate": 8.430635135476616e-06,
"loss": 0.6501,
"step": 393
},
{
"epoch": 0.26487394957983196,
"grad_norm": 0.30286553502082825,
"learning_rate": 8.422890578847313e-06,
"loss": 0.6421,
"step": 394
},
{
"epoch": 0.26554621848739496,
"grad_norm": 0.20739050209522247,
"learning_rate": 8.415130536490712e-06,
"loss": 0.6456,
"step": 395
},
{
"epoch": 0.26621848739495796,
"grad_norm": 0.23757591843605042,
"learning_rate": 8.407355043514538e-06,
"loss": 0.7336,
"step": 396
},
{
"epoch": 0.266890756302521,
"grad_norm": 0.2152106910943985,
"learning_rate": 8.399564135096417e-06,
"loss": 0.6866,
"step": 397
},
{
"epoch": 0.267563025210084,
"grad_norm": 0.22571507096290588,
"learning_rate": 8.39175784648372e-06,
"loss": 0.6797,
"step": 398
},
{
"epoch": 0.26823529411764707,
"grad_norm": 0.2353668212890625,
"learning_rate": 8.383936212993392e-06,
"loss": 0.624,
"step": 399
},
{
"epoch": 0.2689075630252101,
"grad_norm": 0.2632080018520355,
"learning_rate": 8.376099270011808e-06,
"loss": 0.7362,
"step": 400
},
{
"epoch": 0.26957983193277313,
"grad_norm": 0.26158758997917175,
"learning_rate": 8.368247052994605e-06,
"loss": 0.5969,
"step": 401
},
{
"epoch": 0.27025210084033613,
"grad_norm": 0.239485502243042,
"learning_rate": 8.360379597466519e-06,
"loss": 0.631,
"step": 402
},
{
"epoch": 0.2709243697478992,
"grad_norm": 0.2522924840450287,
"learning_rate": 8.352496939021233e-06,
"loss": 0.7101,
"step": 403
},
{
"epoch": 0.2715966386554622,
"grad_norm": 0.22495077550411224,
"learning_rate": 8.344599113321203e-06,
"loss": 0.5785,
"step": 404
},
{
"epoch": 0.2722689075630252,
"grad_norm": 0.25629207491874695,
"learning_rate": 8.336686156097512e-06,
"loss": 0.757,
"step": 405
},
{
"epoch": 0.27294117647058824,
"grad_norm": 0.40765833854675293,
"learning_rate": 8.328758103149696e-06,
"loss": 0.7224,
"step": 406
},
{
"epoch": 0.27361344537815124,
"grad_norm": 0.2634163200855255,
"learning_rate": 8.320814990345587e-06,
"loss": 0.7794,
"step": 407
},
{
"epoch": 0.2742857142857143,
"grad_norm": 0.24929873645305634,
"learning_rate": 8.312856853621152e-06,
"loss": 0.7422,
"step": 408
},
{
"epoch": 0.2749579831932773,
"grad_norm": 0.2845971882343292,
"learning_rate": 8.304883728980325e-06,
"loss": 0.7359,
"step": 409
},
{
"epoch": 0.27563025210084036,
"grad_norm": 0.24346016347408295,
"learning_rate": 8.296895652494851e-06,
"loss": 0.6485,
"step": 410
},
{
"epoch": 0.27630252100840336,
"grad_norm": 0.23367783427238464,
"learning_rate": 8.288892660304122e-06,
"loss": 0.5814,
"step": 411
},
{
"epoch": 0.2769747899159664,
"grad_norm": 0.34782543778419495,
"learning_rate": 8.280874788615004e-06,
"loss": 0.5857,
"step": 412
},
{
"epoch": 0.2776470588235294,
"grad_norm": 0.27658021450042725,
"learning_rate": 8.272842073701688e-06,
"loss": 0.679,
"step": 413
},
{
"epoch": 0.2783193277310924,
"grad_norm": 0.2381054013967514,
"learning_rate": 8.264794551905512e-06,
"loss": 0.5859,
"step": 414
},
{
"epoch": 0.27899159663865547,
"grad_norm": 0.2386159598827362,
"learning_rate": 8.256732259634807e-06,
"loss": 0.7333,
"step": 415
},
{
"epoch": 0.27966386554621847,
"grad_norm": 0.23790478706359863,
"learning_rate": 8.248655233364724e-06,
"loss": 0.6381,
"step": 416
},
{
"epoch": 0.2803361344537815,
"grad_norm": 0.2430446296930313,
"learning_rate": 8.24056350963708e-06,
"loss": 0.6681,
"step": 417
},
{
"epoch": 0.2810084033613445,
"grad_norm": 0.2563830614089966,
"learning_rate": 8.232457125060178e-06,
"loss": 0.7506,
"step": 418
},
{
"epoch": 0.2816806722689076,
"grad_norm": 0.236500084400177,
"learning_rate": 8.224336116308654e-06,
"loss": 0.6722,
"step": 419
},
{
"epoch": 0.2823529411764706,
"grad_norm": 0.24401167035102844,
"learning_rate": 8.216200520123305e-06,
"loss": 0.7555,
"step": 420
},
{
"epoch": 0.28302521008403364,
"grad_norm": 0.24071764945983887,
"learning_rate": 8.20805037331092e-06,
"loss": 0.6701,
"step": 421
},
{
"epoch": 0.28369747899159664,
"grad_norm": 0.2599017322063446,
"learning_rate": 8.199885712744128e-06,
"loss": 0.7838,
"step": 422
},
{
"epoch": 0.28436974789915964,
"grad_norm": 0.23312319815158844,
"learning_rate": 8.191706575361208e-06,
"loss": 0.6454,
"step": 423
},
{
"epoch": 0.2850420168067227,
"grad_norm": 0.3320861756801605,
"learning_rate": 8.183512998165941e-06,
"loss": 0.5617,
"step": 424
},
{
"epoch": 0.2857142857142857,
"grad_norm": 0.29827767610549927,
"learning_rate": 8.175305018227439e-06,
"loss": 0.6889,
"step": 425
},
{
"epoch": 0.28638655462184875,
"grad_norm": 0.2738671898841858,
"learning_rate": 8.167082672679968e-06,
"loss": 0.7371,
"step": 426
},
{
"epoch": 0.28705882352941176,
"grad_norm": 0.24301859736442566,
"learning_rate": 8.15884599872279e-06,
"loss": 0.6621,
"step": 427
},
{
"epoch": 0.2877310924369748,
"grad_norm": 0.2335437387228012,
"learning_rate": 8.150595033619989e-06,
"loss": 0.6062,
"step": 428
},
{
"epoch": 0.2884033613445378,
"grad_norm": 0.24218881130218506,
"learning_rate": 8.142329814700306e-06,
"loss": 0.7732,
"step": 429
},
{
"epoch": 0.28907563025210087,
"grad_norm": 0.23290084302425385,
"learning_rate": 8.13405037935697e-06,
"loss": 0.671,
"step": 430
},
{
"epoch": 0.28974789915966387,
"grad_norm": 0.24484236538410187,
"learning_rate": 8.125756765047528e-06,
"loss": 0.7383,
"step": 431
},
{
"epoch": 0.29042016806722687,
"grad_norm": 0.2516631782054901,
"learning_rate": 8.117449009293668e-06,
"loss": 0.6141,
"step": 432
},
{
"epoch": 0.2910924369747899,
"grad_norm": 0.5268867015838623,
"learning_rate": 8.109127149681065e-06,
"loss": 0.626,
"step": 433
},
{
"epoch": 0.2917647058823529,
"grad_norm": 0.46247419714927673,
"learning_rate": 8.100791223859198e-06,
"loss": 0.6713,
"step": 434
},
{
"epoch": 0.292436974789916,
"grad_norm": 0.33584773540496826,
"learning_rate": 8.092441269541182e-06,
"loss": 0.7156,
"step": 435
},
{
"epoch": 0.293109243697479,
"grad_norm": 0.29816320538520813,
"learning_rate": 8.084077324503602e-06,
"loss": 0.6754,
"step": 436
},
{
"epoch": 0.29378151260504204,
"grad_norm": 0.253115713596344,
"learning_rate": 8.075699426586345e-06,
"loss": 0.6449,
"step": 437
},
{
"epoch": 0.29445378151260504,
"grad_norm": 0.24944230914115906,
"learning_rate": 8.067307613692408e-06,
"loss": 0.5776,
"step": 438
},
{
"epoch": 0.29512605042016804,
"grad_norm": 0.25170648097991943,
"learning_rate": 8.058901923787757e-06,
"loss": 0.5794,
"step": 439
},
{
"epoch": 0.2957983193277311,
"grad_norm": 0.3000252842903137,
"learning_rate": 8.050482394901132e-06,
"loss": 0.7025,
"step": 440
},
{
"epoch": 0.2964705882352941,
"grad_norm": 0.25940564274787903,
"learning_rate": 8.042049065123882e-06,
"loss": 0.6512,
"step": 441
},
{
"epoch": 0.29714285714285715,
"grad_norm": 0.25988590717315674,
"learning_rate": 8.0336019726098e-06,
"loss": 0.6544,
"step": 442
},
{
"epoch": 0.29781512605042015,
"grad_norm": 0.3429681956768036,
"learning_rate": 8.025141155574939e-06,
"loss": 0.7266,
"step": 443
},
{
"epoch": 0.2984873949579832,
"grad_norm": 0.3786052167415619,
"learning_rate": 8.016666652297443e-06,
"loss": 0.7693,
"step": 444
},
{
"epoch": 0.2991596638655462,
"grad_norm": 0.24071510136127472,
"learning_rate": 8.008178501117376e-06,
"loss": 0.692,
"step": 445
},
{
"epoch": 0.29983193277310927,
"grad_norm": 0.22229009866714478,
"learning_rate": 7.999676740436553e-06,
"loss": 0.6618,
"step": 446
},
{
"epoch": 0.30050420168067227,
"grad_norm": 0.2864013910293579,
"learning_rate": 7.991161408718353e-06,
"loss": 0.7082,
"step": 447
},
{
"epoch": 0.30117647058823527,
"grad_norm": 0.22621232271194458,
"learning_rate": 7.982632544487555e-06,
"loss": 0.5874,
"step": 448
},
{
"epoch": 0.3018487394957983,
"grad_norm": 0.24563252925872803,
"learning_rate": 7.974090186330165e-06,
"loss": 0.7186,
"step": 449
},
{
"epoch": 0.3025210084033613,
"grad_norm": 0.30611452460289,
"learning_rate": 7.96553437289323e-06,
"loss": 0.6962,
"step": 450
},
{
"epoch": 0.3031932773109244,
"grad_norm": 0.23493875563144684,
"learning_rate": 7.956965142884678e-06,
"loss": 0.6031,
"step": 451
},
{
"epoch": 0.3038655462184874,
"grad_norm": 0.26626601815223694,
"learning_rate": 7.948382535073134e-06,
"loss": 0.6433,
"step": 452
},
{
"epoch": 0.30453781512605044,
"grad_norm": 0.2446458488702774,
"learning_rate": 7.939786588287743e-06,
"loss": 0.8106,
"step": 453
},
{
"epoch": 0.30521008403361344,
"grad_norm": 0.2521326243877411,
"learning_rate": 7.931177341418003e-06,
"loss": 0.6874,
"step": 454
},
{
"epoch": 0.3058823529411765,
"grad_norm": 0.23391471803188324,
"learning_rate": 7.922554833413581e-06,
"loss": 0.6423,
"step": 455
},
{
"epoch": 0.3065546218487395,
"grad_norm": 0.24418647587299347,
"learning_rate": 7.91391910328414e-06,
"loss": 0.6531,
"step": 456
},
{
"epoch": 0.3072268907563025,
"grad_norm": 0.2206183671951294,
"learning_rate": 7.90527019009916e-06,
"loss": 0.7098,
"step": 457
},
{
"epoch": 0.30789915966386555,
"grad_norm": 0.23588207364082336,
"learning_rate": 7.89660813298777e-06,
"loss": 0.6648,
"step": 458
},
{
"epoch": 0.30857142857142855,
"grad_norm": 0.35487234592437744,
"learning_rate": 7.887932971138555e-06,
"loss": 0.7094,
"step": 459
},
{
"epoch": 0.3092436974789916,
"grad_norm": 0.26851218938827515,
"learning_rate": 7.879244743799393e-06,
"loss": 0.7412,
"step": 460
},
{
"epoch": 0.3099159663865546,
"grad_norm": 0.2544209063053131,
"learning_rate": 7.870543490277274e-06,
"loss": 0.6263,
"step": 461
},
{
"epoch": 0.31058823529411766,
"grad_norm": 0.21729524433612823,
"learning_rate": 7.861829249938119e-06,
"loss": 0.6552,
"step": 462
},
{
"epoch": 0.31126050420168067,
"grad_norm": 0.3726813495159149,
"learning_rate": 7.853102062206601e-06,
"loss": 0.6353,
"step": 463
},
{
"epoch": 0.3119327731092437,
"grad_norm": 0.225904643535614,
"learning_rate": 7.844361966565973e-06,
"loss": 0.6529,
"step": 464
},
{
"epoch": 0.3126050420168067,
"grad_norm": 0.432298481464386,
"learning_rate": 7.835609002557883e-06,
"loss": 0.6485,
"step": 465
},
{
"epoch": 0.3132773109243697,
"grad_norm": 0.45495152473449707,
"learning_rate": 7.8268432097822e-06,
"loss": 0.6468,
"step": 466
},
{
"epoch": 0.3139495798319328,
"grad_norm": 0.23771986365318298,
"learning_rate": 7.81806462789683e-06,
"loss": 0.6454,
"step": 467
},
{
"epoch": 0.3146218487394958,
"grad_norm": 0.2486136257648468,
"learning_rate": 7.80927329661754e-06,
"loss": 0.6243,
"step": 468
},
{
"epoch": 0.31529411764705884,
"grad_norm": 0.29532894492149353,
"learning_rate": 7.80046925571778e-06,
"loss": 0.7355,
"step": 469
},
{
"epoch": 0.31596638655462184,
"grad_norm": 0.29661232233047485,
"learning_rate": 7.791652545028494e-06,
"loss": 0.5596,
"step": 470
},
{
"epoch": 0.3166386554621849,
"grad_norm": 0.2840026021003723,
"learning_rate": 7.782823204437952e-06,
"loss": 0.7123,
"step": 471
},
{
"epoch": 0.3173109243697479,
"grad_norm": 0.24036720395088196,
"learning_rate": 7.773981273891563e-06,
"loss": 0.6763,
"step": 472
},
{
"epoch": 0.31798319327731095,
"grad_norm": 0.3194415271282196,
"learning_rate": 7.765126793391691e-06,
"loss": 0.7346,
"step": 473
},
{
"epoch": 0.31865546218487395,
"grad_norm": 0.24713455140590668,
"learning_rate": 7.756259802997483e-06,
"loss": 0.6414,
"step": 474
},
{
"epoch": 0.31932773109243695,
"grad_norm": 0.2846837043762207,
"learning_rate": 7.747380342824683e-06,
"loss": 0.5973,
"step": 475
},
{
"epoch": 0.32,
"grad_norm": 0.25316038727760315,
"learning_rate": 7.738488453045446e-06,
"loss": 0.6392,
"step": 476
},
{
"epoch": 0.320672268907563,
"grad_norm": 0.23145373165607452,
"learning_rate": 7.729584173888162e-06,
"loss": 0.6528,
"step": 477
},
{
"epoch": 0.32134453781512606,
"grad_norm": 0.2564818561077118,
"learning_rate": 7.720667545637278e-06,
"loss": 0.7126,
"step": 478
},
{
"epoch": 0.32201680672268906,
"grad_norm": 0.2856581509113312,
"learning_rate": 7.7117386086331e-06,
"loss": 0.6829,
"step": 479
},
{
"epoch": 0.3226890756302521,
"grad_norm": 0.25063401460647583,
"learning_rate": 7.70279740327163e-06,
"loss": 0.6701,
"step": 480
},
{
"epoch": 0.3233613445378151,
"grad_norm": 0.24919474124908447,
"learning_rate": 7.693843970004369e-06,
"loss": 0.6791,
"step": 481
},
{
"epoch": 0.3240336134453782,
"grad_norm": 0.2518171966075897,
"learning_rate": 7.684878349338144e-06,
"loss": 0.6549,
"step": 482
},
{
"epoch": 0.3247058823529412,
"grad_norm": 0.22823643684387207,
"learning_rate": 7.675900581834914e-06,
"loss": 0.6602,
"step": 483
},
{
"epoch": 0.3253781512605042,
"grad_norm": 0.22611699998378754,
"learning_rate": 7.666910708111597e-06,
"loss": 0.6114,
"step": 484
},
{
"epoch": 0.32605042016806723,
"grad_norm": 0.21574345231056213,
"learning_rate": 7.657908768839879e-06,
"loss": 0.5915,
"step": 485
},
{
"epoch": 0.32672268907563023,
"grad_norm": 0.26198115944862366,
"learning_rate": 7.648894804746031e-06,
"loss": 0.6995,
"step": 486
},
{
"epoch": 0.3273949579831933,
"grad_norm": 0.2797788381576538,
"learning_rate": 7.63986885661073e-06,
"loss": 0.7056,
"step": 487
},
{
"epoch": 0.3280672268907563,
"grad_norm": 0.26868724822998047,
"learning_rate": 7.630830965268872e-06,
"loss": 0.6964,
"step": 488
},
{
"epoch": 0.32873949579831935,
"grad_norm": 0.2783353626728058,
"learning_rate": 7.621781171609379e-06,
"loss": 0.8026,
"step": 489
},
{
"epoch": 0.32941176470588235,
"grad_norm": 0.25210657715797424,
"learning_rate": 7.612719516575027e-06,
"loss": 0.7001,
"step": 490
},
{
"epoch": 0.3300840336134454,
"grad_norm": 0.25456830859184265,
"learning_rate": 7.603646041162253e-06,
"loss": 0.7183,
"step": 491
},
{
"epoch": 0.3307563025210084,
"grad_norm": 0.2586143910884857,
"learning_rate": 7.594560786420974e-06,
"loss": 0.6673,
"step": 492
},
{
"epoch": 0.3314285714285714,
"grad_norm": 0.23656786978244781,
"learning_rate": 7.585463793454393e-06,
"loss": 0.6919,
"step": 493
},
{
"epoch": 0.33210084033613446,
"grad_norm": 0.2484300434589386,
"learning_rate": 7.576355103418822e-06,
"loss": 0.6797,
"step": 494
},
{
"epoch": 0.33277310924369746,
"grad_norm": 0.2324364334344864,
"learning_rate": 7.567234757523495e-06,
"loss": 0.5792,
"step": 495
},
{
"epoch": 0.3334453781512605,
"grad_norm": 0.2646612226963043,
"learning_rate": 7.558102797030376e-06,
"loss": 0.6596,
"step": 496
}
],
"logging_steps": 1,
"max_steps": 1487,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 248,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 3.1838970659809e+19,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}