souging's picture
Training in progress, epoch 0, checkpoint
0232c15 verified
Raw
History Blame Contribute Delete
86.9 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.8463817181548878,
"eval_steps": 500,
"global_step": 500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0016927634363097758,
"grad_norm": 0.21856777369976044,
"learning_rate": 2.02e-06,
"loss": 2.0481,
"step": 1
},
{
"epoch": 0.0033855268726195515,
"grad_norm": 0.23913073539733887,
"learning_rate": 4.04e-06,
"loss": 2.0244,
"step": 2
},
{
"epoch": 0.0050782903089293275,
"grad_norm": 0.2251112014055252,
"learning_rate": 6.06e-06,
"loss": 2.0831,
"step": 3
},
{
"epoch": 0.006771053745239103,
"grad_norm": 0.22981800138950348,
"learning_rate": 8.08e-06,
"loss": 2.0097,
"step": 4
},
{
"epoch": 0.008463817181548879,
"grad_norm": 0.24785353243350983,
"learning_rate": 1.0100000000000002e-05,
"loss": 2.1596,
"step": 5
},
{
"epoch": 0.010156580617858655,
"grad_norm": 0.2091209888458252,
"learning_rate": 1.212e-05,
"loss": 2.0497,
"step": 6
},
{
"epoch": 0.01184934405416843,
"grad_norm": 0.2210516482591629,
"learning_rate": 1.4140000000000002e-05,
"loss": 2.0596,
"step": 7
},
{
"epoch": 0.013542107490478206,
"grad_norm": 0.21174772083759308,
"learning_rate": 1.616e-05,
"loss": 2.017,
"step": 8
},
{
"epoch": 0.01523487092678798,
"grad_norm": 0.22919593751430511,
"learning_rate": 1.818e-05,
"loss": 2.0424,
"step": 9
},
{
"epoch": 0.016927634363097757,
"grad_norm": 0.21787938475608826,
"learning_rate": 2.0200000000000003e-05,
"loss": 2.0222,
"step": 10
},
{
"epoch": 0.018620397799407534,
"grad_norm": 0.2346174418926239,
"learning_rate": 2.222e-05,
"loss": 2.1,
"step": 11
},
{
"epoch": 0.02031316123571731,
"grad_norm": 0.21451573073863983,
"learning_rate": 2.424e-05,
"loss": 2.027,
"step": 12
},
{
"epoch": 0.022005924672027083,
"grad_norm": 0.19577345252037048,
"learning_rate": 2.6260000000000003e-05,
"loss": 2.0718,
"step": 13
},
{
"epoch": 0.02369868810833686,
"grad_norm": 0.20922431349754333,
"learning_rate": 2.8280000000000004e-05,
"loss": 2.1276,
"step": 14
},
{
"epoch": 0.025391451544646636,
"grad_norm": 0.16791805624961853,
"learning_rate": 3.0299999999999998e-05,
"loss": 2.0778,
"step": 15
},
{
"epoch": 0.027084214980956412,
"grad_norm": 0.21578575670719147,
"learning_rate": 3.232e-05,
"loss": 2.0501,
"step": 16
},
{
"epoch": 0.02877697841726619,
"grad_norm": 0.20047278702259064,
"learning_rate": 3.434e-05,
"loss": 2.0688,
"step": 17
},
{
"epoch": 0.03046974185357596,
"grad_norm": 0.1888180375099182,
"learning_rate": 3.636e-05,
"loss": 2.004,
"step": 18
},
{
"epoch": 0.03216250528988574,
"grad_norm": 0.2372732013463974,
"learning_rate": 3.838e-05,
"loss": 2.0889,
"step": 19
},
{
"epoch": 0.033855268726195514,
"grad_norm": 0.22184057533740997,
"learning_rate": 4.0400000000000006e-05,
"loss": 1.8746,
"step": 20
},
{
"epoch": 0.03554803216250529,
"grad_norm": 0.2352249026298523,
"learning_rate": 4.242e-05,
"loss": 2.0653,
"step": 21
},
{
"epoch": 0.03724079559881507,
"grad_norm": 0.19941262900829315,
"learning_rate": 4.444e-05,
"loss": 2.0372,
"step": 22
},
{
"epoch": 0.03893355903512484,
"grad_norm": 0.19495126605033875,
"learning_rate": 4.6460000000000006e-05,
"loss": 1.9998,
"step": 23
},
{
"epoch": 0.04062632247143462,
"grad_norm": 0.1923140585422516,
"learning_rate": 4.848e-05,
"loss": 1.9869,
"step": 24
},
{
"epoch": 0.04231908590774439,
"grad_norm": 0.18755634129047394,
"learning_rate": 5.05e-05,
"loss": 1.9735,
"step": 25
},
{
"epoch": 0.044011849344054166,
"grad_norm": 0.17831045389175415,
"learning_rate": 5.2520000000000005e-05,
"loss": 1.9195,
"step": 26
},
{
"epoch": 0.045704612780363946,
"grad_norm": 0.18653540313243866,
"learning_rate": 5.454e-05,
"loss": 1.9599,
"step": 27
},
{
"epoch": 0.04739737621667372,
"grad_norm": 0.18552574515342712,
"learning_rate": 5.656000000000001e-05,
"loss": 2.0633,
"step": 28
},
{
"epoch": 0.0490901396529835,
"grad_norm": 0.18219119310379028,
"learning_rate": 5.858e-05,
"loss": 1.9686,
"step": 29
},
{
"epoch": 0.05078290308929327,
"grad_norm": 0.1793995052576065,
"learning_rate": 6.0599999999999996e-05,
"loss": 2.0293,
"step": 30
},
{
"epoch": 0.052475666525603044,
"grad_norm": 0.1970832496881485,
"learning_rate": 6.262000000000001e-05,
"loss": 1.8754,
"step": 31
},
{
"epoch": 0.054168429961912824,
"grad_norm": 0.18978503346443176,
"learning_rate": 6.464e-05,
"loss": 2.0828,
"step": 32
},
{
"epoch": 0.0558611933982226,
"grad_norm": 0.18691568076610565,
"learning_rate": 6.666e-05,
"loss": 1.9331,
"step": 33
},
{
"epoch": 0.05755395683453238,
"grad_norm": 0.20160901546478271,
"learning_rate": 6.868e-05,
"loss": 2.007,
"step": 34
},
{
"epoch": 0.05924672027084215,
"grad_norm": 0.180143803358078,
"learning_rate": 7.07e-05,
"loss": 1.9634,
"step": 35
},
{
"epoch": 0.06093948370715192,
"grad_norm": 0.18108704686164856,
"learning_rate": 7.272e-05,
"loss": 2.1212,
"step": 36
},
{
"epoch": 0.0626322471434617,
"grad_norm": 0.17915402352809906,
"learning_rate": 7.474e-05,
"loss": 2.0112,
"step": 37
},
{
"epoch": 0.06432501057977148,
"grad_norm": 0.19328810274600983,
"learning_rate": 7.676e-05,
"loss": 1.9586,
"step": 38
},
{
"epoch": 0.06601777401608125,
"grad_norm": 0.18603388965129852,
"learning_rate": 7.878e-05,
"loss": 2.0371,
"step": 39
},
{
"epoch": 0.06771053745239103,
"grad_norm": 0.1937795877456665,
"learning_rate": 8.080000000000001e-05,
"loss": 2.0589,
"step": 40
},
{
"epoch": 0.06940330088870081,
"grad_norm": 0.16889318823814392,
"learning_rate": 8.282e-05,
"loss": 1.9922,
"step": 41
},
{
"epoch": 0.07109606432501057,
"grad_norm": 0.19249765574932098,
"learning_rate": 8.484e-05,
"loss": 2.0219,
"step": 42
},
{
"epoch": 0.07278882776132035,
"grad_norm": 0.1795249879360199,
"learning_rate": 8.686e-05,
"loss": 2.0005,
"step": 43
},
{
"epoch": 0.07448159119763013,
"grad_norm": 0.21890012919902802,
"learning_rate": 8.888e-05,
"loss": 2.0732,
"step": 44
},
{
"epoch": 0.0761743546339399,
"grad_norm": 0.2015288770198822,
"learning_rate": 9.09e-05,
"loss": 1.9067,
"step": 45
},
{
"epoch": 0.07786711807024968,
"grad_norm": 0.19771352410316467,
"learning_rate": 9.292000000000001e-05,
"loss": 1.9698,
"step": 46
},
{
"epoch": 0.07955988150655946,
"grad_norm": 0.22185812890529633,
"learning_rate": 9.494e-05,
"loss": 2.1254,
"step": 47
},
{
"epoch": 0.08125264494286924,
"grad_norm": 0.19680249691009521,
"learning_rate": 9.696e-05,
"loss": 2.0022,
"step": 48
},
{
"epoch": 0.082945408379179,
"grad_norm": 0.21367794275283813,
"learning_rate": 9.898e-05,
"loss": 1.8728,
"step": 49
},
{
"epoch": 0.08463817181548879,
"grad_norm": 0.2153550088405609,
"learning_rate": 0.000101,
"loss": 2.0168,
"step": 50
},
{
"epoch": 0.08633093525179857,
"grad_norm": 0.20331734418869019,
"learning_rate": 0.00010302,
"loss": 2.0049,
"step": 51
},
{
"epoch": 0.08802369868810833,
"grad_norm": 0.19431838393211365,
"learning_rate": 0.00010504000000000001,
"loss": 1.8976,
"step": 52
},
{
"epoch": 0.08971646212441811,
"grad_norm": 0.19682154059410095,
"learning_rate": 0.00010706000000000001,
"loss": 1.898,
"step": 53
},
{
"epoch": 0.09140922556072789,
"grad_norm": 0.20410743355751038,
"learning_rate": 0.00010908,
"loss": 1.9067,
"step": 54
},
{
"epoch": 0.09310198899703766,
"grad_norm": 0.21040071547031403,
"learning_rate": 0.00011110000000000002,
"loss": 2.0007,
"step": 55
},
{
"epoch": 0.09479475243334744,
"grad_norm": 0.2420426458120346,
"learning_rate": 0.00011312000000000001,
"loss": 1.9398,
"step": 56
},
{
"epoch": 0.09648751586965722,
"grad_norm": 0.24033543467521667,
"learning_rate": 0.00011514,
"loss": 2.001,
"step": 57
},
{
"epoch": 0.098180279305967,
"grad_norm": 0.23176445066928864,
"learning_rate": 0.00011716,
"loss": 2.081,
"step": 58
},
{
"epoch": 0.09987304274227676,
"grad_norm": 0.21144893765449524,
"learning_rate": 0.00011918,
"loss": 1.8212,
"step": 59
},
{
"epoch": 0.10156580617858654,
"grad_norm": 0.23067671060562134,
"learning_rate": 0.00012119999999999999,
"loss": 1.9066,
"step": 60
},
{
"epoch": 0.10325856961489632,
"grad_norm": 0.26889732480049133,
"learning_rate": 0.00012322,
"loss": 1.8263,
"step": 61
},
{
"epoch": 0.10495133305120609,
"grad_norm": 0.21251942217350006,
"learning_rate": 0.00012524000000000001,
"loss": 1.9031,
"step": 62
},
{
"epoch": 0.10664409648751587,
"grad_norm": 0.21674378216266632,
"learning_rate": 0.00012726,
"loss": 1.8843,
"step": 63
},
{
"epoch": 0.10833685992382565,
"grad_norm": 0.2463655322790146,
"learning_rate": 0.00012928,
"loss": 1.9816,
"step": 64
},
{
"epoch": 0.11002962336013541,
"grad_norm": 0.2431013435125351,
"learning_rate": 0.00013130000000000002,
"loss": 1.9958,
"step": 65
},
{
"epoch": 0.1117223867964452,
"grad_norm": 0.21589888632297516,
"learning_rate": 0.00013332,
"loss": 1.9283,
"step": 66
},
{
"epoch": 0.11341515023275497,
"grad_norm": 0.2475602626800537,
"learning_rate": 0.00013534000000000002,
"loss": 1.8687,
"step": 67
},
{
"epoch": 0.11510791366906475,
"grad_norm": 0.22713498771190643,
"learning_rate": 0.00013736,
"loss": 1.8763,
"step": 68
},
{
"epoch": 0.11680067710537452,
"grad_norm": 0.21402622759342194,
"learning_rate": 0.00013937999999999998,
"loss": 1.9201,
"step": 69
},
{
"epoch": 0.1184934405416843,
"grad_norm": 0.24653713405132294,
"learning_rate": 0.0001414,
"loss": 1.9369,
"step": 70
},
{
"epoch": 0.12018620397799408,
"grad_norm": 0.23254817724227905,
"learning_rate": 0.00014342,
"loss": 1.9923,
"step": 71
},
{
"epoch": 0.12187896741430385,
"grad_norm": 0.22863097488880157,
"learning_rate": 0.00014544,
"loss": 1.9701,
"step": 72
},
{
"epoch": 0.12357173085061363,
"grad_norm": 0.2209753394126892,
"learning_rate": 0.00014746,
"loss": 1.8904,
"step": 73
},
{
"epoch": 0.1252644942869234,
"grad_norm": 0.2530592381954193,
"learning_rate": 0.00014948,
"loss": 1.9259,
"step": 74
},
{
"epoch": 0.12695725772323319,
"grad_norm": 0.23368902504444122,
"learning_rate": 0.0001515,
"loss": 1.9462,
"step": 75
},
{
"epoch": 0.12865002115954297,
"grad_norm": 0.24833092093467712,
"learning_rate": 0.00015352,
"loss": 1.9063,
"step": 76
},
{
"epoch": 0.13034278459585272,
"grad_norm": 0.23310640454292297,
"learning_rate": 0.00015554000000000002,
"loss": 1.9147,
"step": 77
},
{
"epoch": 0.1320355480321625,
"grad_norm": 0.2354939877986908,
"learning_rate": 0.00015756,
"loss": 2.0259,
"step": 78
},
{
"epoch": 0.13372831146847228,
"grad_norm": 0.24625660479068756,
"learning_rate": 0.00015958000000000001,
"loss": 1.9424,
"step": 79
},
{
"epoch": 0.13542107490478206,
"grad_norm": 0.26915672421455383,
"learning_rate": 0.00016160000000000002,
"loss": 1.9616,
"step": 80
},
{
"epoch": 0.13711383834109184,
"grad_norm": 0.20115861296653748,
"learning_rate": 0.00016362,
"loss": 1.8272,
"step": 81
},
{
"epoch": 0.13880660177740162,
"grad_norm": 0.21742068231105804,
"learning_rate": 0.00016564,
"loss": 1.9483,
"step": 82
},
{
"epoch": 0.1404993652137114,
"grad_norm": 0.21801471710205078,
"learning_rate": 0.00016766,
"loss": 1.9739,
"step": 83
},
{
"epoch": 0.14219212865002115,
"grad_norm": 0.23018628358840942,
"learning_rate": 0.00016968,
"loss": 1.9386,
"step": 84
},
{
"epoch": 0.14388489208633093,
"grad_norm": 0.24194473028182983,
"learning_rate": 0.0001717,
"loss": 1.8877,
"step": 85
},
{
"epoch": 0.1455776555226407,
"grad_norm": 0.2352004051208496,
"learning_rate": 0.00017372,
"loss": 1.9368,
"step": 86
},
{
"epoch": 0.1472704189589505,
"grad_norm": 0.20487657189369202,
"learning_rate": 0.00017574,
"loss": 1.8582,
"step": 87
},
{
"epoch": 0.14896318239526027,
"grad_norm": 0.24406185746192932,
"learning_rate": 0.00017776,
"loss": 1.9033,
"step": 88
},
{
"epoch": 0.15065594583157005,
"grad_norm": 0.235113725066185,
"learning_rate": 0.00017978000000000002,
"loss": 1.9519,
"step": 89
},
{
"epoch": 0.1523487092678798,
"grad_norm": 0.22690711915493011,
"learning_rate": 0.0001818,
"loss": 1.8798,
"step": 90
},
{
"epoch": 0.15404147270418958,
"grad_norm": 0.2338939756155014,
"learning_rate": 0.00018382,
"loss": 1.938,
"step": 91
},
{
"epoch": 0.15573423614049936,
"grad_norm": 0.2826458811759949,
"learning_rate": 0.00018584000000000002,
"loss": 1.8859,
"step": 92
},
{
"epoch": 0.15742699957680914,
"grad_norm": 0.23302127420902252,
"learning_rate": 0.00018786,
"loss": 1.9253,
"step": 93
},
{
"epoch": 0.15911976301311892,
"grad_norm": 0.22500993311405182,
"learning_rate": 0.00018988,
"loss": 1.8338,
"step": 94
},
{
"epoch": 0.1608125264494287,
"grad_norm": 0.2076253741979599,
"learning_rate": 0.0001919,
"loss": 1.7979,
"step": 95
},
{
"epoch": 0.16250528988573848,
"grad_norm": 0.23616939783096313,
"learning_rate": 0.00019392,
"loss": 1.9603,
"step": 96
},
{
"epoch": 0.16419805332204823,
"grad_norm": 0.20899280905723572,
"learning_rate": 0.00019594,
"loss": 1.8669,
"step": 97
},
{
"epoch": 0.165890816758358,
"grad_norm": 0.23518052697181702,
"learning_rate": 0.00019796,
"loss": 1.9586,
"step": 98
},
{
"epoch": 0.1675835801946678,
"grad_norm": 0.2177092283964157,
"learning_rate": 0.00019998,
"loss": 1.8993,
"step": 99
},
{
"epoch": 0.16927634363097757,
"grad_norm": 0.22413797676563263,
"learning_rate": 0.000202,
"loss": 1.9742,
"step": 100
},
{
"epoch": 0.17096910706728735,
"grad_norm": 0.21205808222293854,
"learning_rate": 0.00020199688492212377,
"loss": 1.8326,
"step": 101
},
{
"epoch": 0.17266187050359713,
"grad_norm": 0.20058460533618927,
"learning_rate": 0.00020198753988064772,
"loss": 1.9229,
"step": 102
},
{
"epoch": 0.1743546339399069,
"grad_norm": 0.21106334030628204,
"learning_rate": 0.00020197196545201806,
"loss": 1.8479,
"step": 103
},
{
"epoch": 0.17604739737621666,
"grad_norm": 0.20998717844486237,
"learning_rate": 0.0002019501625969389,
"loss": 1.9287,
"step": 104
},
{
"epoch": 0.17774016081252644,
"grad_norm": 0.20730508863925934,
"learning_rate": 0.00020192213266031304,
"loss": 1.9189,
"step": 105
},
{
"epoch": 0.17943292424883622,
"grad_norm": 0.20150446891784668,
"learning_rate": 0.00020188787737115897,
"loss": 1.9076,
"step": 106
},
{
"epoch": 0.181125687685146,
"grad_norm": 0.20014949142932892,
"learning_rate": 0.00020184739884250436,
"loss": 1.8554,
"step": 107
},
{
"epoch": 0.18281845112145578,
"grad_norm": 0.20369713008403778,
"learning_rate": 0.00020180069957125544,
"loss": 1.8424,
"step": 108
},
{
"epoch": 0.18451121455776556,
"grad_norm": 0.20155616104602814,
"learning_rate": 0.0002017477824380433,
"loss": 1.8932,
"step": 109
},
{
"epoch": 0.18620397799407531,
"grad_norm": 0.242130309343338,
"learning_rate": 0.00020168865070704594,
"loss": 1.9801,
"step": 110
},
{
"epoch": 0.1878967414303851,
"grad_norm": 0.1840430349111557,
"learning_rate": 0.00020162330802578706,
"loss": 1.7834,
"step": 111
},
{
"epoch": 0.18958950486669487,
"grad_norm": 0.19342510402202606,
"learning_rate": 0.00020155175842491107,
"loss": 1.8983,
"step": 112
},
{
"epoch": 0.19128226830300465,
"grad_norm": 0.19883695244789124,
"learning_rate": 0.0002014740063179344,
"loss": 1.9457,
"step": 113
},
{
"epoch": 0.19297503173931443,
"grad_norm": 0.19686879217624664,
"learning_rate": 0.00020139005650097317,
"loss": 1.8999,
"step": 114
},
{
"epoch": 0.19466779517562421,
"grad_norm": 0.208403542637825,
"learning_rate": 0.00020129991415244756,
"loss": 1.8663,
"step": 115
},
{
"epoch": 0.196360558611934,
"grad_norm": 0.2095002382993698,
"learning_rate": 0.00020120358483276227,
"loss": 1.826,
"step": 116
},
{
"epoch": 0.19805332204824375,
"grad_norm": 0.21314266324043274,
"learning_rate": 0.00020110107448396346,
"loss": 1.8932,
"step": 117
},
{
"epoch": 0.19974608548455353,
"grad_norm": 0.17742839455604553,
"learning_rate": 0.0002009923894293723,
"loss": 1.8937,
"step": 118
},
{
"epoch": 0.2014388489208633,
"grad_norm": 0.21836084127426147,
"learning_rate": 0.00020087753637319499,
"loss": 1.8692,
"step": 119
},
{
"epoch": 0.20313161235717309,
"grad_norm": 0.22461658716201782,
"learning_rate": 0.00020075652240010892,
"loss": 1.8752,
"step": 120
},
{
"epoch": 0.20482437579348287,
"grad_norm": 0.19782739877700806,
"learning_rate": 0.00020062935497482606,
"loss": 1.9125,
"step": 121
},
{
"epoch": 0.20651713922979265,
"grad_norm": 0.19714659452438354,
"learning_rate": 0.00020049604194163217,
"loss": 1.9299,
"step": 122
},
{
"epoch": 0.20820990266610243,
"grad_norm": 0.22192247211933136,
"learning_rate": 0.00020035659152390313,
"loss": 1.9318,
"step": 123
},
{
"epoch": 0.20990266610241218,
"grad_norm": 0.18889577686786652,
"learning_rate": 0.00020021101232359757,
"loss": 1.7885,
"step": 124
},
{
"epoch": 0.21159542953872196,
"grad_norm": 0.20050236582756042,
"learning_rate": 0.0002000593133207263,
"loss": 1.8929,
"step": 125
},
{
"epoch": 0.21328819297503174,
"grad_norm": 0.20882593095302582,
"learning_rate": 0.00019990150387279835,
"loss": 1.9149,
"step": 126
},
{
"epoch": 0.21498095641134152,
"grad_norm": 0.20735543966293335,
"learning_rate": 0.00019973759371424388,
"loss": 1.8702,
"step": 127
},
{
"epoch": 0.2166737198476513,
"grad_norm": 0.2120111733675003,
"learning_rate": 0.0001995675929558135,
"loss": 1.8855,
"step": 128
},
{
"epoch": 0.21836648328396108,
"grad_norm": 0.19814302027225494,
"learning_rate": 0.0001993915120839548,
"loss": 1.931,
"step": 129
},
{
"epoch": 0.22005924672027083,
"grad_norm": 0.20039153099060059,
"learning_rate": 0.00019920936196016534,
"loss": 1.9007,
"step": 130
},
{
"epoch": 0.2217520101565806,
"grad_norm": 0.21088403463363647,
"learning_rate": 0.0001990211538203228,
"loss": 1.8372,
"step": 131
},
{
"epoch": 0.2234447735928904,
"grad_norm": 0.18757721781730652,
"learning_rate": 0.00019882689927399174,
"loss": 1.9023,
"step": 132
},
{
"epoch": 0.22513753702920017,
"grad_norm": 0.23472613096237183,
"learning_rate": 0.00019862661030370764,
"loss": 1.974,
"step": 133
},
{
"epoch": 0.22683030046550995,
"grad_norm": 0.20689590275287628,
"learning_rate": 0.00019842029926423762,
"loss": 1.906,
"step": 134
},
{
"epoch": 0.22852306390181973,
"grad_norm": 0.23491977155208588,
"learning_rate": 0.00019820797888181837,
"loss": 1.9676,
"step": 135
},
{
"epoch": 0.2302158273381295,
"grad_norm": 0.22469407320022583,
"learning_rate": 0.00019798966225337126,
"loss": 1.9104,
"step": 136
},
{
"epoch": 0.23190859077443926,
"grad_norm": 0.18836864829063416,
"learning_rate": 0.00019776536284569425,
"loss": 1.7995,
"step": 137
},
{
"epoch": 0.23360135421074904,
"grad_norm": 0.22445032000541687,
"learning_rate": 0.00019753509449463134,
"loss": 1.8465,
"step": 138
},
{
"epoch": 0.23529411764705882,
"grad_norm": 0.213129460811615,
"learning_rate": 0.00019729887140421912,
"loss": 1.8709,
"step": 139
},
{
"epoch": 0.2369868810833686,
"grad_norm": 0.19376549124717712,
"learning_rate": 0.00019705670814581052,
"loss": 1.8593,
"step": 140
},
{
"epoch": 0.23867964451967838,
"grad_norm": 0.21564675867557526,
"learning_rate": 0.00019680861965717597,
"loss": 1.8758,
"step": 141
},
{
"epoch": 0.24037240795598816,
"grad_norm": 0.19630011916160583,
"learning_rate": 0.0001965546212415821,
"loss": 1.876,
"step": 142
},
{
"epoch": 0.24206517139229794,
"grad_norm": 0.21326979994773865,
"learning_rate": 0.00019629472856684755,
"loss": 1.8627,
"step": 143
},
{
"epoch": 0.2437579348286077,
"grad_norm": 0.2283921092748642,
"learning_rate": 0.00019602895766437678,
"loss": 1.9001,
"step": 144
},
{
"epoch": 0.24545069826491747,
"grad_norm": 0.18760521709918976,
"learning_rate": 0.00019575732492817092,
"loss": 1.8366,
"step": 145
},
{
"epoch": 0.24714346170122725,
"grad_norm": 0.19644710421562195,
"learning_rate": 0.00019547984711381662,
"loss": 1.8523,
"step": 146
},
{
"epoch": 0.24883622513753703,
"grad_norm": 0.20750153064727783,
"learning_rate": 0.0001951965413374525,
"loss": 1.9252,
"step": 147
},
{
"epoch": 0.2505289885738468,
"grad_norm": 0.21898148953914642,
"learning_rate": 0.00019490742507471338,
"loss": 1.9337,
"step": 148
},
{
"epoch": 0.25222175201015656,
"grad_norm": 0.2055978775024414,
"learning_rate": 0.0001946125161596522,
"loss": 1.8522,
"step": 149
},
{
"epoch": 0.25391451544646637,
"grad_norm": 0.1978798359632492,
"learning_rate": 0.00019431183278363997,
"loss": 1.9232,
"step": 150
},
{
"epoch": 0.2556072788827761,
"grad_norm": 0.2158019244670868,
"learning_rate": 0.00019400539349424367,
"loss": 1.8611,
"step": 151
},
{
"epoch": 0.25730004231908593,
"grad_norm": 0.20386692881584167,
"learning_rate": 0.0001936932171940821,
"loss": 1.7308,
"step": 152
},
{
"epoch": 0.2589928057553957,
"grad_norm": 0.20035216212272644,
"learning_rate": 0.00019337532313966,
"loss": 1.8862,
"step": 153
},
{
"epoch": 0.26068556919170544,
"grad_norm": 0.23695775866508484,
"learning_rate": 0.00019305173094017996,
"loss": 1.8447,
"step": 154
},
{
"epoch": 0.26237833262801524,
"grad_norm": 0.1999625414609909,
"learning_rate": 0.0001927224605563332,
"loss": 1.8646,
"step": 155
},
{
"epoch": 0.264071096064325,
"grad_norm": 0.22056512534618378,
"learning_rate": 0.00019238753229906797,
"loss": 1.8067,
"step": 156
},
{
"epoch": 0.2657638595006348,
"grad_norm": 0.20931819081306458,
"learning_rate": 0.00019204696682833682,
"loss": 1.8779,
"step": 157
},
{
"epoch": 0.26745662293694455,
"grad_norm": 0.20790903270244598,
"learning_rate": 0.00019170078515182216,
"loss": 1.9015,
"step": 158
},
{
"epoch": 0.26914938637325436,
"grad_norm": 0.19034312665462494,
"learning_rate": 0.00019134900862364054,
"loss": 1.8891,
"step": 159
},
{
"epoch": 0.2708421498095641,
"grad_norm": 0.2115480899810791,
"learning_rate": 0.00019099165894302515,
"loss": 1.8202,
"step": 160
},
{
"epoch": 0.27253491324587387,
"grad_norm": 0.2177758514881134,
"learning_rate": 0.00019062875815298763,
"loss": 1.9587,
"step": 161
},
{
"epoch": 0.2742276766821837,
"grad_norm": 0.21036648750305176,
"learning_rate": 0.00019026032863895805,
"loss": 1.8691,
"step": 162
},
{
"epoch": 0.2759204401184934,
"grad_norm": 0.22222432494163513,
"learning_rate": 0.00018988639312740433,
"loss": 1.8823,
"step": 163
},
{
"epoch": 0.27761320355480323,
"grad_norm": 0.21436412632465363,
"learning_rate": 0.0001895069746844302,
"loss": 1.9104,
"step": 164
},
{
"epoch": 0.279305966991113,
"grad_norm": 0.20456653833389282,
"learning_rate": 0.00018912209671435252,
"loss": 1.8959,
"step": 165
},
{
"epoch": 0.2809987304274228,
"grad_norm": 0.2090640515089035,
"learning_rate": 0.00018873178295825732,
"loss": 1.8681,
"step": 166
},
{
"epoch": 0.28269149386373255,
"grad_norm": 0.21788451075553894,
"learning_rate": 0.00018833605749253566,
"loss": 1.8757,
"step": 167
},
{
"epoch": 0.2843842573000423,
"grad_norm": 0.1906866878271103,
"learning_rate": 0.00018793494472739831,
"loss": 1.8193,
"step": 168
},
{
"epoch": 0.2860770207363521,
"grad_norm": 0.19513285160064697,
"learning_rate": 0.00018752846940537003,
"loss": 1.795,
"step": 169
},
{
"epoch": 0.28776978417266186,
"grad_norm": 0.21061134338378906,
"learning_rate": 0.0001871166565997633,
"loss": 1.874,
"step": 170
},
{
"epoch": 0.28946254760897167,
"grad_norm": 0.1909717321395874,
"learning_rate": 0.00018669953171313188,
"loss": 1.9205,
"step": 171
},
{
"epoch": 0.2911553110452814,
"grad_norm": 0.21319589018821716,
"learning_rate": 0.00018627712047570352,
"loss": 1.9476,
"step": 172
},
{
"epoch": 0.2928480744815912,
"grad_norm": 0.1932004988193512,
"learning_rate": 0.0001858494489437931,
"loss": 1.9107,
"step": 173
},
{
"epoch": 0.294540837917901,
"grad_norm": 0.2236086130142212,
"learning_rate": 0.0001854165434981953,
"loss": 1.9591,
"step": 174
},
{
"epoch": 0.29623360135421073,
"grad_norm": 0.2074287086725235,
"learning_rate": 0.00018497843084255708,
"loss": 1.8827,
"step": 175
},
{
"epoch": 0.29792636479052054,
"grad_norm": 0.20944799482822418,
"learning_rate": 0.00018453513800173072,
"loss": 1.9349,
"step": 176
},
{
"epoch": 0.2996191282268303,
"grad_norm": 0.2134864628314972,
"learning_rate": 0.00018408669232010684,
"loss": 1.936,
"step": 177
},
{
"epoch": 0.3013118916631401,
"grad_norm": 0.19440272450447083,
"learning_rate": 0.00018363312145992737,
"loss": 1.9071,
"step": 178
},
{
"epoch": 0.30300465509944985,
"grad_norm": 0.20118582248687744,
"learning_rate": 0.0001831744533995795,
"loss": 1.8357,
"step": 179
},
{
"epoch": 0.3046974185357596,
"grad_norm": 0.19037730991840363,
"learning_rate": 0.00018271071643186968,
"loss": 1.8208,
"step": 180
},
{
"epoch": 0.3063901819720694,
"grad_norm": 0.23469118773937225,
"learning_rate": 0.00018224193916227852,
"loss": 1.91,
"step": 181
},
{
"epoch": 0.30808294540837916,
"grad_norm": 0.2068597376346588,
"learning_rate": 0.00018176815050719615,
"loss": 1.8396,
"step": 182
},
{
"epoch": 0.30977570884468897,
"grad_norm": 0.199380561709404,
"learning_rate": 0.00018128937969213852,
"loss": 1.9452,
"step": 183
},
{
"epoch": 0.3114684722809987,
"grad_norm": 0.21270886063575745,
"learning_rate": 0.00018080565624994474,
"loss": 1.8638,
"step": 184
},
{
"epoch": 0.31316123571730853,
"grad_norm": 0.2130834311246872,
"learning_rate": 0.00018031701001895524,
"loss": 1.8948,
"step": 185
},
{
"epoch": 0.3148539991536183,
"grad_norm": 0.23766449093818665,
"learning_rate": 0.0001798234711411713,
"loss": 1.8991,
"step": 186
},
{
"epoch": 0.31654676258992803,
"grad_norm": 0.22095240652561188,
"learning_rate": 0.00017932507006039567,
"loss": 1.8994,
"step": 187
},
{
"epoch": 0.31823952602623784,
"grad_norm": 0.21079136431217194,
"learning_rate": 0.0001788218375203547,
"loss": 1.8416,
"step": 188
},
{
"epoch": 0.3199322894625476,
"grad_norm": 0.21459782123565674,
"learning_rate": 0.00017831380456280192,
"loss": 1.8634,
"step": 189
},
{
"epoch": 0.3216250528988574,
"grad_norm": 0.20663154125213623,
"learning_rate": 0.00017780100252560313,
"loss": 1.8175,
"step": 190
},
{
"epoch": 0.32331781633516715,
"grad_norm": 0.19480010867118835,
"learning_rate": 0.00017728346304080357,
"loss": 1.8805,
"step": 191
},
{
"epoch": 0.32501057977147696,
"grad_norm": 0.19441437721252441,
"learning_rate": 0.0001767612180326764,
"loss": 1.8417,
"step": 192
},
{
"epoch": 0.3267033432077867,
"grad_norm": 0.19535009562969208,
"learning_rate": 0.00017623429971575384,
"loss": 1.8304,
"step": 193
},
{
"epoch": 0.32839610664409646,
"grad_norm": 0.1960291713476181,
"learning_rate": 0.0001757027405928396,
"loss": 1.8123,
"step": 194
},
{
"epoch": 0.33008887008040627,
"grad_norm": 0.20072749257087708,
"learning_rate": 0.00017516657345300425,
"loss": 1.8054,
"step": 195
},
{
"epoch": 0.331781633516716,
"grad_norm": 0.2007756382226944,
"learning_rate": 0.00017462583136956258,
"loss": 1.9027,
"step": 196
},
{
"epoch": 0.33347439695302583,
"grad_norm": 0.19728228449821472,
"learning_rate": 0.00017408054769803337,
"loss": 1.7665,
"step": 197
},
{
"epoch": 0.3351671603893356,
"grad_norm": 0.20155274868011475,
"learning_rate": 0.00017353075607408209,
"loss": 1.8861,
"step": 198
},
{
"epoch": 0.3368599238256454,
"grad_norm": 0.220042422413826,
"learning_rate": 0.00017297649041144575,
"loss": 1.8939,
"step": 199
},
{
"epoch": 0.33855268726195514,
"grad_norm": 0.198530912399292,
"learning_rate": 0.0001724177848998413,
"loss": 1.9187,
"step": 200
},
{
"epoch": 0.3402454506982649,
"grad_norm": 0.21299457550048828,
"learning_rate": 0.00017185467400285644,
"loss": 1.8911,
"step": 201
},
{
"epoch": 0.3419382141345747,
"grad_norm": 0.2029038816690445,
"learning_rate": 0.00017128719245582374,
"loss": 1.8675,
"step": 202
},
{
"epoch": 0.34363097757088445,
"grad_norm": 0.19144582748413086,
"learning_rate": 0.00017071537526367817,
"loss": 1.8579,
"step": 203
},
{
"epoch": 0.34532374100719426,
"grad_norm": 0.18448671698570251,
"learning_rate": 0.00017013925769879755,
"loss": 1.8343,
"step": 204
},
{
"epoch": 0.347016504443504,
"grad_norm": 0.19850729405879974,
"learning_rate": 0.00016955887529882714,
"loss": 1.908,
"step": 205
},
{
"epoch": 0.3487092678798138,
"grad_norm": 0.22133758664131165,
"learning_rate": 0.0001689742638644871,
"loss": 1.7839,
"step": 206
},
{
"epoch": 0.3504020313161236,
"grad_norm": 0.22666744887828827,
"learning_rate": 0.00016838545945736458,
"loss": 1.8686,
"step": 207
},
{
"epoch": 0.3520947947524333,
"grad_norm": 0.21209904551506042,
"learning_rate": 0.00016779249839768884,
"loss": 1.8597,
"step": 208
},
{
"epoch": 0.35378755818874313,
"grad_norm": 0.24644292891025543,
"learning_rate": 0.00016719541726209117,
"loss": 1.9405,
"step": 209
},
{
"epoch": 0.3554803216250529,
"grad_norm": 0.2024543285369873,
"learning_rate": 0.00016659425288134854,
"loss": 1.8438,
"step": 210
},
{
"epoch": 0.3571730850613627,
"grad_norm": 0.19772209227085114,
"learning_rate": 0.00016598904233811168,
"loss": 1.7444,
"step": 211
},
{
"epoch": 0.35886584849767245,
"grad_norm": 0.21736018359661102,
"learning_rate": 0.00016537982296461768,
"loss": 1.8738,
"step": 212
},
{
"epoch": 0.36055861193398225,
"grad_norm": 0.21007020771503448,
"learning_rate": 0.00016476663234038717,
"loss": 1.8198,
"step": 213
},
{
"epoch": 0.362251375370292,
"grad_norm": 0.19021974503993988,
"learning_rate": 0.00016414950828990625,
"loss": 1.8837,
"step": 214
},
{
"epoch": 0.36394413880660176,
"grad_norm": 0.19724875688552856,
"learning_rate": 0.00016352848888029326,
"loss": 1.82,
"step": 215
},
{
"epoch": 0.36563690224291157,
"grad_norm": 0.21668016910552979,
"learning_rate": 0.00016290361241895064,
"loss": 1.8376,
"step": 216
},
{
"epoch": 0.3673296656792213,
"grad_norm": 0.19902758300304413,
"learning_rate": 0.00016227491745120196,
"loss": 1.8129,
"step": 217
},
{
"epoch": 0.3690224291155311,
"grad_norm": 0.19672639667987823,
"learning_rate": 0.0001616424427579143,
"loss": 1.8121,
"step": 218
},
{
"epoch": 0.3707151925518409,
"grad_norm": 0.20111984014511108,
"learning_rate": 0.0001610062273531059,
"loss": 1.7883,
"step": 219
},
{
"epoch": 0.37240795598815063,
"grad_norm": 0.19124211370944977,
"learning_rate": 0.00016036631048153979,
"loss": 1.839,
"step": 220
},
{
"epoch": 0.37410071942446044,
"grad_norm": 0.1881026327610016,
"learning_rate": 0.0001597227316163029,
"loss": 1.7974,
"step": 221
},
{
"epoch": 0.3757934828607702,
"grad_norm": 0.2134140431880951,
"learning_rate": 0.00015907553045637116,
"loss": 1.8425,
"step": 222
},
{
"epoch": 0.37748624629708,
"grad_norm": 0.2233268767595291,
"learning_rate": 0.00015842474692416068,
"loss": 1.8192,
"step": 223
},
{
"epoch": 0.37917900973338975,
"grad_norm": 0.19751399755477905,
"learning_rate": 0.0001577704211630652,
"loss": 1.7833,
"step": 224
},
{
"epoch": 0.38087177316969956,
"grad_norm": 0.218443363904953,
"learning_rate": 0.00015711259353497981,
"loss": 1.9236,
"step": 225
},
{
"epoch": 0.3825645366060093,
"grad_norm": 0.20756369829177856,
"learning_rate": 0.0001564513046178113,
"loss": 1.906,
"step": 226
},
{
"epoch": 0.38425730004231906,
"grad_norm": 0.19934311509132385,
"learning_rate": 0.000155786595202975,
"loss": 1.8093,
"step": 227
},
{
"epoch": 0.38595006347862887,
"grad_norm": 0.20041096210479736,
"learning_rate": 0.00015511850629287865,
"loss": 1.7607,
"step": 228
},
{
"epoch": 0.3876428269149386,
"grad_norm": 0.18540289998054504,
"learning_rate": 0.00015444707909839325,
"loss": 1.8091,
"step": 229
},
{
"epoch": 0.38933559035124843,
"grad_norm": 0.22061359882354736,
"learning_rate": 0.00015377235503631083,
"loss": 1.782,
"step": 230
},
{
"epoch": 0.3910283537875582,
"grad_norm": 0.22130614519119263,
"learning_rate": 0.0001530943757267898,
"loss": 1.8557,
"step": 231
},
{
"epoch": 0.392721117223868,
"grad_norm": 0.1992771476507187,
"learning_rate": 0.00015241318299078751,
"loss": 1.8052,
"step": 232
},
{
"epoch": 0.39441388066017774,
"grad_norm": 0.22611509263515472,
"learning_rate": 0.00015172881884748063,
"loss": 1.8771,
"step": 233
},
{
"epoch": 0.3961066440964875,
"grad_norm": 0.21634873747825623,
"learning_rate": 0.00015104132551167318,
"loss": 1.8709,
"step": 234
},
{
"epoch": 0.3977994075327973,
"grad_norm": 0.1996215432882309,
"learning_rate": 0.00015035074539119248,
"loss": 1.8022,
"step": 235
},
{
"epoch": 0.39949217096910705,
"grad_norm": 0.2338496297597885,
"learning_rate": 0.00014965712108427323,
"loss": 1.8723,
"step": 236
},
{
"epoch": 0.40118493440541686,
"grad_norm": 0.21306854486465454,
"learning_rate": 0.00014896049537693005,
"loss": 1.8632,
"step": 237
},
{
"epoch": 0.4028776978417266,
"grad_norm": 0.19065231084823608,
"learning_rate": 0.00014826091124031792,
"loss": 1.7692,
"step": 238
},
{
"epoch": 0.4045704612780364,
"grad_norm": 0.30616074800491333,
"learning_rate": 0.0001475584118280817,
"loss": 1.8729,
"step": 239
},
{
"epoch": 0.40626322471434617,
"grad_norm": 0.20752687752246857,
"learning_rate": 0.00014685304047369423,
"loss": 1.7964,
"step": 240
},
{
"epoch": 0.4079559881506559,
"grad_norm": 0.200820654630661,
"learning_rate": 0.00014614484068778324,
"loss": 1.7949,
"step": 241
},
{
"epoch": 0.40964875158696573,
"grad_norm": 0.21263371407985687,
"learning_rate": 0.00014543385615544744,
"loss": 1.866,
"step": 242
},
{
"epoch": 0.4113415150232755,
"grad_norm": 0.23685312271118164,
"learning_rate": 0.00014472013073356184,
"loss": 1.8304,
"step": 243
},
{
"epoch": 0.4130342784595853,
"grad_norm": 0.21853387355804443,
"learning_rate": 0.00014400370844807234,
"loss": 1.8574,
"step": 244
},
{
"epoch": 0.41472704189589504,
"grad_norm": 0.2155625820159912,
"learning_rate": 0.00014328463349128025,
"loss": 1.8748,
"step": 245
},
{
"epoch": 0.41641980533220485,
"grad_norm": 0.2086298018693924,
"learning_rate": 0.000142562950219116,
"loss": 1.9206,
"step": 246
},
{
"epoch": 0.4181125687685146,
"grad_norm": 0.20329339802265167,
"learning_rate": 0.00014183870314840325,
"loss": 1.8398,
"step": 247
},
{
"epoch": 0.41980533220482436,
"grad_norm": 0.196868896484375,
"learning_rate": 0.00014111193695411285,
"loss": 1.8197,
"step": 248
},
{
"epoch": 0.42149809564113416,
"grad_norm": 0.1998075544834137,
"learning_rate": 0.00014038269646660703,
"loss": 1.804,
"step": 249
},
{
"epoch": 0.4231908590774439,
"grad_norm": 0.2248334139585495,
"learning_rate": 0.00013965102666887408,
"loss": 1.8629,
"step": 250
},
{
"epoch": 0.4248836225137537,
"grad_norm": 0.21032220125198364,
"learning_rate": 0.0001389169726937536,
"loss": 1.7899,
"step": 251
},
{
"epoch": 0.4265763859500635,
"grad_norm": 0.21330855786800385,
"learning_rate": 0.0001381805798211525,
"loss": 1.8903,
"step": 252
},
{
"epoch": 0.4282691493863732,
"grad_norm": 0.1978665292263031,
"learning_rate": 0.00013744189347525182,
"loss": 1.8784,
"step": 253
},
{
"epoch": 0.42996191282268303,
"grad_norm": 0.2091052383184433,
"learning_rate": 0.00013670095922170498,
"loss": 1.7486,
"step": 254
},
{
"epoch": 0.4316546762589928,
"grad_norm": 0.20555751025676727,
"learning_rate": 0.00013595782276482678,
"loss": 1.8544,
"step": 255
},
{
"epoch": 0.4333474396953026,
"grad_norm": 0.18778344988822937,
"learning_rate": 0.00013521252994477446,
"loss": 1.8234,
"step": 256
},
{
"epoch": 0.43504020313161235,
"grad_norm": 0.1997567117214203,
"learning_rate": 0.00013446512673471965,
"loss": 1.8087,
"step": 257
},
{
"epoch": 0.43673296656792215,
"grad_norm": 0.23277805745601654,
"learning_rate": 0.0001337156592380131,
"loss": 1.8419,
"step": 258
},
{
"epoch": 0.4384257300042319,
"grad_norm": 0.22513163089752197,
"learning_rate": 0.0001329641736853402,
"loss": 1.8437,
"step": 259
},
{
"epoch": 0.44011849344054166,
"grad_norm": 0.2149161845445633,
"learning_rate": 0.0001322107164318697,
"loss": 1.8383,
"step": 260
},
{
"epoch": 0.44181125687685147,
"grad_norm": 0.21721015870571136,
"learning_rate": 0.00013145533395439405,
"loss": 1.7647,
"step": 261
},
{
"epoch": 0.4435040203131612,
"grad_norm": 0.209782674908638,
"learning_rate": 0.0001306980728484627,
"loss": 1.8086,
"step": 262
},
{
"epoch": 0.445196783749471,
"grad_norm": 0.21785935759544373,
"learning_rate": 0.00012993897982550764,
"loss": 1.8221,
"step": 263
},
{
"epoch": 0.4468895471857808,
"grad_norm": 0.19847460091114044,
"learning_rate": 0.00012917810170996218,
"loss": 1.7695,
"step": 264
},
{
"epoch": 0.4485823106220906,
"grad_norm": 0.24909834563732147,
"learning_rate": 0.0001284154854363725,
"loss": 1.9249,
"step": 265
},
{
"epoch": 0.45027507405840034,
"grad_norm": 0.20455898344516754,
"learning_rate": 0.00012765117804650267,
"loss": 1.736,
"step": 266
},
{
"epoch": 0.4519678374947101,
"grad_norm": 0.2129652500152588,
"learning_rate": 0.00012688522668643268,
"loss": 1.8665,
"step": 267
},
{
"epoch": 0.4536606009310199,
"grad_norm": 0.23460032045841217,
"learning_rate": 0.00012611767860365038,
"loss": 1.8598,
"step": 268
},
{
"epoch": 0.45535336436732965,
"grad_norm": 0.1984863132238388,
"learning_rate": 0.00012534858114413692,
"loss": 1.8512,
"step": 269
},
{
"epoch": 0.45704612780363946,
"grad_norm": 0.22249212861061096,
"learning_rate": 0.00012457798174944645,
"loss": 1.8617,
"step": 270
},
{
"epoch": 0.4587388912399492,
"grad_norm": 0.1910618543624878,
"learning_rate": 0.0001238059279537795,
"loss": 1.8236,
"step": 271
},
{
"epoch": 0.460431654676259,
"grad_norm": 0.1930653601884842,
"learning_rate": 0.00012303246738105082,
"loss": 1.7204,
"step": 272
},
{
"epoch": 0.46212441811256877,
"grad_norm": 0.21550333499908447,
"learning_rate": 0.00012225764774195186,
"loss": 1.8523,
"step": 273
},
{
"epoch": 0.4638171815488785,
"grad_norm": 0.22164791822433472,
"learning_rate": 0.00012148151683100776,
"loss": 1.8166,
"step": 274
},
{
"epoch": 0.46550994498518833,
"grad_norm": 0.19043266773223877,
"learning_rate": 0.00012070412252362897,
"loss": 1.7265,
"step": 275
},
{
"epoch": 0.4672027084214981,
"grad_norm": 0.21201427280902863,
"learning_rate": 0.0001199255127731582,
"loss": 1.8403,
"step": 276
},
{
"epoch": 0.4688954718578079,
"grad_norm": 0.1951863020658493,
"learning_rate": 0.00011914573560791246,
"loss": 1.8029,
"step": 277
},
{
"epoch": 0.47058823529411764,
"grad_norm": 0.19758546352386475,
"learning_rate": 0.00011836483912822035,
"loss": 1.7447,
"step": 278
},
{
"epoch": 0.47228099873042745,
"grad_norm": 0.1987844705581665,
"learning_rate": 0.00011758287150345516,
"loss": 1.8123,
"step": 279
},
{
"epoch": 0.4739737621667372,
"grad_norm": 0.20801664888858795,
"learning_rate": 0.00011679988096906333,
"loss": 1.8099,
"step": 280
},
{
"epoch": 0.47566652560304695,
"grad_norm": 0.20373427867889404,
"learning_rate": 0.00011601591582358924,
"loss": 1.8075,
"step": 281
},
{
"epoch": 0.47735928903935676,
"grad_norm": 0.18766620755195618,
"learning_rate": 0.00011523102442569585,
"loss": 1.8565,
"step": 282
},
{
"epoch": 0.4790520524756665,
"grad_norm": 0.20334315299987793,
"learning_rate": 0.00011444525519118179,
"loss": 1.7725,
"step": 283
},
{
"epoch": 0.4807448159119763,
"grad_norm": 0.23168785870075226,
"learning_rate": 0.00011365865658999474,
"loss": 1.8644,
"step": 284
},
{
"epoch": 0.48243757934828607,
"grad_norm": 0.21688470244407654,
"learning_rate": 0.00011287127714324162,
"loss": 1.8269,
"step": 285
},
{
"epoch": 0.4841303427845959,
"grad_norm": 0.1990613490343094,
"learning_rate": 0.00011208316542019556,
"loss": 1.8364,
"step": 286
},
{
"epoch": 0.48582310622090563,
"grad_norm": 0.2150726169347763,
"learning_rate": 0.00011129437003530006,
"loss": 1.7863,
"step": 287
},
{
"epoch": 0.4875158696572154,
"grad_norm": 0.21324212849140167,
"learning_rate": 0.00011050493964516997,
"loss": 1.8465,
"step": 288
},
{
"epoch": 0.4892086330935252,
"grad_norm": 0.22838270664215088,
"learning_rate": 0.00010971492294559029,
"loss": 1.7879,
"step": 289
},
{
"epoch": 0.49090139652983494,
"grad_norm": 0.2122029811143875,
"learning_rate": 0.00010892436866851235,
"loss": 1.8314,
"step": 290
},
{
"epoch": 0.49259415996614475,
"grad_norm": 0.20107725262641907,
"learning_rate": 0.00010813332557904784,
"loss": 1.8476,
"step": 291
},
{
"epoch": 0.4942869234024545,
"grad_norm": 0.20374621450901031,
"learning_rate": 0.00010734184247246066,
"loss": 1.7898,
"step": 292
},
{
"epoch": 0.49597968683876426,
"grad_norm": 0.2181493192911148,
"learning_rate": 0.00010654996817115704,
"loss": 1.8615,
"step": 293
},
{
"epoch": 0.49767245027507406,
"grad_norm": 0.2149876058101654,
"learning_rate": 0.00010575775152167391,
"loss": 1.8864,
"step": 294
},
{
"epoch": 0.4993652137113838,
"grad_norm": 0.2074560672044754,
"learning_rate": 0.00010496524139166594,
"loss": 1.8098,
"step": 295
},
{
"epoch": 0.5010579771476936,
"grad_norm": 0.21023057401180267,
"learning_rate": 0.00010417248666689095,
"loss": 1.8146,
"step": 296
},
{
"epoch": 0.5027507405840034,
"grad_norm": 0.22075513005256653,
"learning_rate": 0.00010337953624819464,
"loss": 1.7364,
"step": 297
},
{
"epoch": 0.5044435040203131,
"grad_norm": 0.20402000844478607,
"learning_rate": 0.0001025864390484939,
"loss": 1.8982,
"step": 298
},
{
"epoch": 0.506136267456623,
"grad_norm": 0.20802898705005646,
"learning_rate": 0.00010179324398975984,
"loss": 1.8944,
"step": 299
},
{
"epoch": 0.5078290308929327,
"grad_norm": 0.21477678418159485,
"learning_rate": 0.000101,
"loss": 1.739,
"step": 300
},
{
"epoch": 0.5095217943292425,
"grad_norm": 0.21539942920207977,
"learning_rate": 0.00010020675601024019,
"loss": 1.8687,
"step": 301
},
{
"epoch": 0.5112145577655522,
"grad_norm": 0.1995563805103302,
"learning_rate": 9.941356095150613e-05,
"loss": 1.7643,
"step": 302
},
{
"epoch": 0.512907321201862,
"grad_norm": 0.22377008199691772,
"learning_rate": 9.862046375180539e-05,
"loss": 1.858,
"step": 303
},
{
"epoch": 0.5146000846381719,
"grad_norm": 0.22329548001289368,
"learning_rate": 9.782751333310905e-05,
"loss": 1.8245,
"step": 304
},
{
"epoch": 0.5162928480744816,
"grad_norm": 0.20432743430137634,
"learning_rate": 9.70347586083341e-05,
"loss": 1.8553,
"step": 305
},
{
"epoch": 0.5179856115107914,
"grad_norm": 0.19676503539085388,
"learning_rate": 9.62422484783261e-05,
"loss": 1.9008,
"step": 306
},
{
"epoch": 0.5196783749471011,
"grad_norm": 0.201835498213768,
"learning_rate": 9.5450031828843e-05,
"loss": 1.8466,
"step": 307
},
{
"epoch": 0.5213711383834109,
"grad_norm": 0.2252872735261917,
"learning_rate": 9.465815752753935e-05,
"loss": 1.7508,
"step": 308
},
{
"epoch": 0.5230639018197207,
"grad_norm": 0.20253726840019226,
"learning_rate": 9.386667442095219e-05,
"loss": 1.7062,
"step": 309
},
{
"epoch": 0.5247566652560305,
"grad_norm": 0.18099112808704376,
"learning_rate": 9.307563133148767e-05,
"loss": 1.7196,
"step": 310
},
{
"epoch": 0.5264494286923402,
"grad_norm": 0.20946381986141205,
"learning_rate": 9.228507705440976e-05,
"loss": 1.6923,
"step": 311
},
{
"epoch": 0.52814219212865,
"grad_norm": 0.19370995461940765,
"learning_rate": 9.149506035483005e-05,
"loss": 1.767,
"step": 312
},
{
"epoch": 0.5298349555649597,
"grad_norm": 0.23071925342082977,
"learning_rate": 9.070562996469997e-05,
"loss": 1.9319,
"step": 313
},
{
"epoch": 0.5315277190012696,
"grad_norm": 0.209041029214859,
"learning_rate": 8.991683457980443e-05,
"loss": 1.8223,
"step": 314
},
{
"epoch": 0.5332204824375794,
"grad_norm": 0.21399877965450287,
"learning_rate": 8.912872285675841e-05,
"loss": 1.8666,
"step": 315
},
{
"epoch": 0.5349132458738891,
"grad_norm": 0.19409359991550446,
"learning_rate": 8.834134341000527e-05,
"loss": 1.7784,
"step": 316
},
{
"epoch": 0.5366060093101989,
"grad_norm": 0.204691082239151,
"learning_rate": 8.755474480881823e-05,
"loss": 1.719,
"step": 317
},
{
"epoch": 0.5382987727465087,
"grad_norm": 0.2197725772857666,
"learning_rate": 8.676897557430415e-05,
"loss": 1.8214,
"step": 318
},
{
"epoch": 0.5399915361828185,
"grad_norm": 0.20693747699260712,
"learning_rate": 8.598408417641078e-05,
"loss": 1.9092,
"step": 319
},
{
"epoch": 0.5416842996191282,
"grad_norm": 0.21056115627288818,
"learning_rate": 8.520011903093666e-05,
"loss": 1.7916,
"step": 320
},
{
"epoch": 0.543377063055438,
"grad_norm": 0.2322707176208496,
"learning_rate": 8.441712849654485e-05,
"loss": 1.7776,
"step": 321
},
{
"epoch": 0.5450698264917477,
"grad_norm": 0.22040331363677979,
"learning_rate": 8.363516087177962e-05,
"loss": 1.7787,
"step": 322
},
{
"epoch": 0.5467625899280576,
"grad_norm": 0.20133259892463684,
"learning_rate": 8.285426439208755e-05,
"loss": 1.8502,
"step": 323
},
{
"epoch": 0.5484553533643673,
"grad_norm": 0.21346233785152435,
"learning_rate": 8.20744872268418e-05,
"loss": 1.8366,
"step": 324
},
{
"epoch": 0.5501481168006771,
"grad_norm": 0.23861512541770935,
"learning_rate": 8.129587747637105e-05,
"loss": 1.8267,
"step": 325
},
{
"epoch": 0.5518408802369869,
"grad_norm": 0.2035307139158249,
"learning_rate": 8.051848316899227e-05,
"loss": 1.8537,
"step": 326
},
{
"epoch": 0.5535336436732966,
"grad_norm": 0.2048177719116211,
"learning_rate": 7.974235225804814e-05,
"loss": 1.7852,
"step": 327
},
{
"epoch": 0.5552264071096065,
"grad_norm": 0.20414908230304718,
"learning_rate": 7.896753261894923e-05,
"loss": 1.8421,
"step": 328
},
{
"epoch": 0.5569191705459162,
"grad_norm": 0.24092479050159454,
"learning_rate": 7.819407204622054e-05,
"loss": 1.854,
"step": 329
},
{
"epoch": 0.558611933982226,
"grad_norm": 0.18901631236076355,
"learning_rate": 7.74220182505536e-05,
"loss": 1.8054,
"step": 330
},
{
"epoch": 0.5603046974185357,
"grad_norm": 0.2006632387638092,
"learning_rate": 7.665141885586312e-05,
"loss": 1.8048,
"step": 331
},
{
"epoch": 0.5619974608548456,
"grad_norm": 0.24550236761569977,
"learning_rate": 7.588232139634968e-05,
"loss": 1.925,
"step": 332
},
{
"epoch": 0.5636902242911553,
"grad_norm": 0.2135893553495407,
"learning_rate": 7.511477331356733e-05,
"loss": 1.8726,
"step": 333
},
{
"epoch": 0.5653829877274651,
"grad_norm": 0.2010648548603058,
"learning_rate": 7.434882195349736e-05,
"loss": 1.8045,
"step": 334
},
{
"epoch": 0.5670757511637748,
"grad_norm": 0.21286746859550476,
"learning_rate": 7.358451456362751e-05,
"loss": 1.7486,
"step": 335
},
{
"epoch": 0.5687685146000846,
"grad_norm": 0.21406236290931702,
"learning_rate": 7.282189829003785e-05,
"loss": 1.7529,
"step": 336
},
{
"epoch": 0.5704612780363945,
"grad_norm": 0.22069211304187775,
"learning_rate": 7.206102017449237e-05,
"loss": 1.8614,
"step": 337
},
{
"epoch": 0.5721540414727042,
"grad_norm": 0.21297217905521393,
"learning_rate": 7.130192715153731e-05,
"loss": 1.8435,
"step": 338
},
{
"epoch": 0.573846804909014,
"grad_norm": 0.21049076318740845,
"learning_rate": 7.054466604560595e-05,
"loss": 1.7618,
"step": 339
},
{
"epoch": 0.5755395683453237,
"grad_norm": 0.21273387968540192,
"learning_rate": 6.978928356813031e-05,
"loss": 1.7966,
"step": 340
},
{
"epoch": 0.5772323317816335,
"grad_norm": 0.21543648838996887,
"learning_rate": 6.90358263146598e-05,
"loss": 1.7777,
"step": 341
},
{
"epoch": 0.5789250952179433,
"grad_norm": 0.21663051843643188,
"learning_rate": 6.828434076198693e-05,
"loss": 1.8662,
"step": 342
},
{
"epoch": 0.5806178586542531,
"grad_norm": 0.2097054123878479,
"learning_rate": 6.753487326528033e-05,
"loss": 1.7905,
"step": 343
},
{
"epoch": 0.5823106220905628,
"grad_norm": 0.21476370096206665,
"learning_rate": 6.678747005522557e-05,
"loss": 1.868,
"step": 344
},
{
"epoch": 0.5840033855268726,
"grad_norm": 0.21085023880004883,
"learning_rate": 6.60421772351732e-05,
"loss": 1.7485,
"step": 345
},
{
"epoch": 0.5856961489631825,
"grad_norm": 0.20236246287822723,
"learning_rate": 6.529904077829505e-05,
"loss": 1.8017,
"step": 346
},
{
"epoch": 0.5873889123994922,
"grad_norm": 0.20598532259464264,
"learning_rate": 6.455810652474817e-05,
"loss": 1.8247,
"step": 347
},
{
"epoch": 0.589081675835802,
"grad_norm": 0.21530595421791077,
"learning_rate": 6.381942017884753e-05,
"loss": 1.7806,
"step": 348
},
{
"epoch": 0.5907744392721117,
"grad_norm": 0.20915140211582184,
"learning_rate": 6.30830273062464e-05,
"loss": 1.6916,
"step": 349
},
{
"epoch": 0.5924672027084215,
"grad_norm": 0.2102150022983551,
"learning_rate": 6.234897333112594e-05,
"loss": 1.7322,
"step": 350
},
{
"epoch": 0.5941599661447313,
"grad_norm": 0.2074473649263382,
"learning_rate": 6.161730353339302e-05,
"loss": 1.8016,
"step": 351
},
{
"epoch": 0.5958527295810411,
"grad_norm": 0.20407773554325104,
"learning_rate": 6.088806304588717e-05,
"loss": 1.7577,
"step": 352
},
{
"epoch": 0.5975454930173508,
"grad_norm": 0.19759750366210938,
"learning_rate": 6.0161296851596766e-05,
"loss": 1.7865,
"step": 353
},
{
"epoch": 0.5992382564536606,
"grad_norm": 0.1897537112236023,
"learning_rate": 5.943704978088402e-05,
"loss": 1.7259,
"step": 354
},
{
"epoch": 0.6009310198899703,
"grad_norm": 0.21245813369750977,
"learning_rate": 5.871536650871979e-05,
"loss": 1.7443,
"step": 355
},
{
"epoch": 0.6026237833262802,
"grad_norm": 0.21807269752025604,
"learning_rate": 5.7996291551927666e-05,
"loss": 1.8325,
"step": 356
},
{
"epoch": 0.60431654676259,
"grad_norm": 0.20956049859523773,
"learning_rate": 5.7279869266438234e-05,
"loss": 1.7937,
"step": 357
},
{
"epoch": 0.6060093101988997,
"grad_norm": 0.20313173532485962,
"learning_rate": 5.656614384455257e-05,
"loss": 1.7876,
"step": 358
},
{
"epoch": 0.6077020736352094,
"grad_norm": 0.20536667108535767,
"learning_rate": 5.585515931221677e-05,
"loss": 1.8179,
"step": 359
},
{
"epoch": 0.6093948370715192,
"grad_norm": 0.21091505885124207,
"learning_rate": 5.514695952630578e-05,
"loss": 1.7008,
"step": 360
},
{
"epoch": 0.6110876005078291,
"grad_norm": 0.22748170793056488,
"learning_rate": 5.444158817191832e-05,
"loss": 1.8367,
"step": 361
},
{
"epoch": 0.6127803639441388,
"grad_norm": 0.22794023156166077,
"learning_rate": 5.373908875968211e-05,
"loss": 1.7491,
"step": 362
},
{
"epoch": 0.6144731273804486,
"grad_norm": 0.20269587635993958,
"learning_rate": 5.3039504623069965e-05,
"loss": 1.7936,
"step": 363
},
{
"epoch": 0.6161658908167583,
"grad_norm": 0.2314659059047699,
"learning_rate": 5.234287891572674e-05,
"loss": 1.8786,
"step": 364
},
{
"epoch": 0.6178586542530682,
"grad_norm": 0.21339716017246246,
"learning_rate": 5.164925460880758e-05,
"loss": 1.7822,
"step": 365
},
{
"epoch": 0.6195514176893779,
"grad_norm": 0.2351083606481552,
"learning_rate": 5.095867448832683e-05,
"loss": 1.8096,
"step": 366
},
{
"epoch": 0.6212441811256877,
"grad_norm": 0.2355419397354126,
"learning_rate": 5.027118115251938e-05,
"loss": 1.8608,
"step": 367
},
{
"epoch": 0.6229369445619974,
"grad_norm": 0.20024722814559937,
"learning_rate": 4.95868170092125e-05,
"loss": 1.7936,
"step": 368
},
{
"epoch": 0.6246297079983072,
"grad_norm": 0.20535969734191895,
"learning_rate": 4.890562427321021e-05,
"loss": 1.8049,
"step": 369
},
{
"epoch": 0.6263224714346171,
"grad_norm": 0.23352813720703125,
"learning_rate": 4.822764496368917e-05,
"loss": 1.765,
"step": 370
},
{
"epoch": 0.6280152348709268,
"grad_norm": 0.1979178786277771,
"learning_rate": 4.755292090160676e-05,
"loss": 1.7403,
"step": 371
},
{
"epoch": 0.6297079983072366,
"grad_norm": 0.20019833743572235,
"learning_rate": 4.6881493707121315e-05,
"loss": 1.8232,
"step": 372
},
{
"epoch": 0.6314007617435463,
"grad_norm": 0.2228015512228012,
"learning_rate": 4.621340479702503e-05,
"loss": 1.7402,
"step": 373
},
{
"epoch": 0.6330935251798561,
"grad_norm": 0.21357794106006622,
"learning_rate": 4.554869538218868e-05,
"loss": 1.8108,
"step": 374
},
{
"epoch": 0.6347862886161659,
"grad_norm": 0.21230149269104004,
"learning_rate": 4.48874064650202e-05,
"loss": 1.8489,
"step": 375
},
{
"epoch": 0.6364790520524757,
"grad_norm": 0.24094673991203308,
"learning_rate": 4.422957883693483e-05,
"loss": 1.8017,
"step": 376
},
{
"epoch": 0.6381718154887854,
"grad_norm": 0.22956468164920807,
"learning_rate": 4.357525307583933e-05,
"loss": 1.8582,
"step": 377
},
{
"epoch": 0.6398645789250952,
"grad_norm": 0.2082371562719345,
"learning_rate": 4.29244695436289e-05,
"loss": 1.7844,
"step": 378
},
{
"epoch": 0.641557342361405,
"grad_norm": 0.19524511694908142,
"learning_rate": 4.227726838369711e-05,
"loss": 1.8427,
"step": 379
},
{
"epoch": 0.6432501057977148,
"grad_norm": 0.21189072728157043,
"learning_rate": 4.1633689518460225e-05,
"loss": 1.7981,
"step": 380
},
{
"epoch": 0.6449428692340246,
"grad_norm": 0.2074735313653946,
"learning_rate": 4.0993772646894116e-05,
"loss": 1.7982,
"step": 381
},
{
"epoch": 0.6466356326703343,
"grad_norm": 0.20359306037425995,
"learning_rate": 4.035755724208573e-05,
"loss": 1.8001,
"step": 382
},
{
"epoch": 0.6483283961066441,
"grad_norm": 0.1999865025281906,
"learning_rate": 3.972508254879805e-05,
"loss": 1.8001,
"step": 383
},
{
"epoch": 0.6500211595429539,
"grad_norm": 0.21898256242275238,
"learning_rate": 3.90963875810494e-05,
"loss": 1.8164,
"step": 384
},
{
"epoch": 0.6517139229792637,
"grad_norm": 0.21683290600776672,
"learning_rate": 3.847151111970676e-05,
"loss": 1.8172,
"step": 385
},
{
"epoch": 0.6534066864155734,
"grad_norm": 0.20884141325950623,
"learning_rate": 3.785049171009381e-05,
"loss": 1.8675,
"step": 386
},
{
"epoch": 0.6550994498518832,
"grad_norm": 0.21106429398059845,
"learning_rate": 3.723336765961285e-05,
"loss": 1.7616,
"step": 387
},
{
"epoch": 0.6567922132881929,
"grad_norm": 0.23011848330497742,
"learning_rate": 3.662017703538234e-05,
"loss": 1.8289,
"step": 388
},
{
"epoch": 0.6584849767245028,
"grad_norm": 0.2037750780582428,
"learning_rate": 3.601095766188833e-05,
"loss": 1.8335,
"step": 389
},
{
"epoch": 0.6601777401608125,
"grad_norm": 0.2219899743795395,
"learning_rate": 3.540574711865146e-05,
"loss": 1.9411,
"step": 390
},
{
"epoch": 0.6618705035971223,
"grad_norm": 0.21334752440452576,
"learning_rate": 3.4804582737908825e-05,
"loss": 1.8087,
"step": 391
},
{
"epoch": 0.663563267033432,
"grad_norm": 0.189884215593338,
"learning_rate": 3.420750160231118e-05,
"loss": 1.7682,
"step": 392
},
{
"epoch": 0.6652560304697418,
"grad_norm": 0.19877025485038757,
"learning_rate": 3.361454054263541e-05,
"loss": 1.6733,
"step": 393
},
{
"epoch": 0.6669487939060517,
"grad_norm": 0.2145155668258667,
"learning_rate": 3.302573613551292e-05,
"loss": 1.8208,
"step": 394
},
{
"epoch": 0.6686415573423614,
"grad_norm": 0.20586173236370087,
"learning_rate": 3.244112470117288e-05,
"loss": 1.7466,
"step": 395
},
{
"epoch": 0.6703343207786712,
"grad_norm": 0.21139511466026306,
"learning_rate": 3.186074230120244e-05,
"loss": 1.7321,
"step": 396
},
{
"epoch": 0.6720270842149809,
"grad_norm": 0.21532289683818817,
"learning_rate": 3.1284624736321846e-05,
"loss": 1.8668,
"step": 397
},
{
"epoch": 0.6737198476512908,
"grad_norm": 0.20813466608524323,
"learning_rate": 3.071280754417626e-05,
"loss": 1.9226,
"step": 398
},
{
"epoch": 0.6754126110876005,
"grad_norm": 0.21900610625743866,
"learning_rate": 3.0145325997143577e-05,
"loss": 1.8024,
"step": 399
},
{
"epoch": 0.6771053745239103,
"grad_norm": 0.22422060370445251,
"learning_rate": 2.9582215100158706e-05,
"loss": 1.8334,
"step": 400
},
{
"epoch": 0.67879813796022,
"grad_norm": 0.23467899858951569,
"learning_rate": 2.902350958855426e-05,
"loss": 1.8694,
"step": 401
},
{
"epoch": 0.6804909013965298,
"grad_norm": 0.21651369333267212,
"learning_rate": 2.846924392591794e-05,
"loss": 1.8401,
"step": 402
},
{
"epoch": 0.6821836648328397,
"grad_norm": 0.19963063299655914,
"learning_rate": 2.791945230196663e-05,
"loss": 1.7546,
"step": 403
},
{
"epoch": 0.6838764282691494,
"grad_norm": 0.19555777311325073,
"learning_rate": 2.7374168630437456e-05,
"loss": 1.7436,
"step": 404
},
{
"epoch": 0.6855691917054592,
"grad_norm": 0.22838395833969116,
"learning_rate": 2.6833426546995782e-05,
"loss": 1.7865,
"step": 405
},
{
"epoch": 0.6872619551417689,
"grad_norm": 0.21524296700954437,
"learning_rate": 2.629725940716041e-05,
"loss": 1.8273,
"step": 406
},
{
"epoch": 0.6889547185780787,
"grad_norm": 0.2013399302959442,
"learning_rate": 2.57657002842462e-05,
"loss": 1.8137,
"step": 407
},
{
"epoch": 0.6906474820143885,
"grad_norm": 0.21510232985019684,
"learning_rate": 2.523878196732358e-05,
"loss": 1.8143,
"step": 408
},
{
"epoch": 0.6923402454506983,
"grad_norm": 0.21713508665561676,
"learning_rate": 2.4716536959196462e-05,
"loss": 1.726,
"step": 409
},
{
"epoch": 0.694033008887008,
"grad_norm": 0.21626891195774078,
"learning_rate": 2.4198997474396877e-05,
"loss": 1.8512,
"step": 410
},
{
"epoch": 0.6957257723233178,
"grad_norm": 0.20656228065490723,
"learning_rate": 2.3686195437198112e-05,
"loss": 1.7622,
"step": 411
},
{
"epoch": 0.6974185357596276,
"grad_norm": 0.20512975752353668,
"learning_rate": 2.31781624796453e-05,
"loss": 1.8007,
"step": 412
},
{
"epoch": 0.6991112991959374,
"grad_norm": 0.211225688457489,
"learning_rate": 2.2674929939604332e-05,
"loss": 1.8128,
"step": 413
},
{
"epoch": 0.7008040626322471,
"grad_norm": 0.21974876523017883,
"learning_rate": 2.217652885882869e-05,
"loss": 1.883,
"step": 414
},
{
"epoch": 0.7024968260685569,
"grad_norm": 0.20600928366184235,
"learning_rate": 2.1682989981044783e-05,
"loss": 1.7697,
"step": 415
},
{
"epoch": 0.7041895895048667,
"grad_norm": 0.22947439551353455,
"learning_rate": 2.119434375005527e-05,
"loss": 1.8393,
"step": 416
},
{
"epoch": 0.7058823529411765,
"grad_norm": 0.20363295078277588,
"learning_rate": 2.071062030786149e-05,
"loss": 1.7937,
"step": 417
},
{
"epoch": 0.7075751163774863,
"grad_norm": 0.21072493493556976,
"learning_rate": 2.0231849492803852e-05,
"loss": 1.84,
"step": 418
},
{
"epoch": 0.709267879813796,
"grad_norm": 0.218157559633255,
"learning_rate": 1.9758060837721467e-05,
"loss": 1.8936,
"step": 419
},
{
"epoch": 0.7109606432501058,
"grad_norm": 0.22965873777866364,
"learning_rate": 1.928928356813032e-05,
"loss": 1.7123,
"step": 420
},
{
"epoch": 0.7126534066864155,
"grad_norm": 0.22897976636886597,
"learning_rate": 1.882554660042052e-05,
"loss": 1.78,
"step": 421
},
{
"epoch": 0.7143461701227254,
"grad_norm": 0.22148145735263824,
"learning_rate": 1.8366878540072614e-05,
"loss": 1.7913,
"step": 422
},
{
"epoch": 0.7160389335590351,
"grad_norm": 0.2105412781238556,
"learning_rate": 1.7913307679893173e-05,
"loss": 1.7588,
"step": 423
},
{
"epoch": 0.7177316969953449,
"grad_norm": 0.19640448689460754,
"learning_rate": 1.7464861998269243e-05,
"loss": 1.8379,
"step": 424
},
{
"epoch": 0.7194244604316546,
"grad_norm": 0.20884667336940765,
"learning_rate": 1.702156915744292e-05,
"loss": 1.8713,
"step": 425
},
{
"epoch": 0.7211172238679645,
"grad_norm": 0.20887801051139832,
"learning_rate": 1.6583456501804725e-05,
"loss": 1.7939,
"step": 426
},
{
"epoch": 0.7228099873042743,
"grad_norm": 0.21152956783771515,
"learning_rate": 1.6150551056206867e-05,
"loss": 1.7871,
"step": 427
},
{
"epoch": 0.724502750740584,
"grad_norm": 0.18513014912605286,
"learning_rate": 1.57228795242965e-05,
"loss": 1.7296,
"step": 428
},
{
"epoch": 0.7261955141768938,
"grad_norm": 0.19580882787704468,
"learning_rate": 1.5300468286868137e-05,
"loss": 1.7489,
"step": 429
},
{
"epoch": 0.7278882776132035,
"grad_norm": 0.21818384528160095,
"learning_rate": 1.488334340023669e-05,
"loss": 1.8618,
"step": 430
},
{
"epoch": 0.7295810410495134,
"grad_norm": 0.22403159737586975,
"learning_rate": 1.4471530594629996e-05,
"loss": 1.8694,
"step": 431
},
{
"epoch": 0.7312738044858231,
"grad_norm": 0.2089739292860031,
"learning_rate": 1.4065055272601703e-05,
"loss": 1.8291,
"step": 432
},
{
"epoch": 0.7329665679221329,
"grad_norm": 0.22134815156459808,
"learning_rate": 1.3663942507464348e-05,
"loss": 1.7524,
"step": 433
},
{
"epoch": 0.7346593313584426,
"grad_norm": 0.21070238947868347,
"learning_rate": 1.3268217041742701e-05,
"loss": 1.7339,
"step": 434
},
{
"epoch": 0.7363520947947524,
"grad_norm": 0.20640292763710022,
"learning_rate": 1.2877903285647486e-05,
"loss": 1.749,
"step": 435
},
{
"epoch": 0.7380448582310623,
"grad_norm": 0.21918413043022156,
"learning_rate": 1.2493025315569801e-05,
"loss": 1.8355,
"step": 436
},
{
"epoch": 0.739737621667372,
"grad_norm": 0.22140200436115265,
"learning_rate": 1.2113606872595673e-05,
"loss": 1.7544,
"step": 437
},
{
"epoch": 0.7414303851036818,
"grad_norm": 0.2224489450454712,
"learning_rate": 1.173967136104196e-05,
"loss": 1.7686,
"step": 438
},
{
"epoch": 0.7431231485399915,
"grad_norm": 0.21481674909591675,
"learning_rate": 1.1371241847012401e-05,
"loss": 1.7817,
"step": 439
},
{
"epoch": 0.7448159119763013,
"grad_norm": 0.20408138632774353,
"learning_rate": 1.1008341056974854e-05,
"loss": 1.748,
"step": 440
},
{
"epoch": 0.7465086754126111,
"grad_norm": 0.23499758541584015,
"learning_rate": 1.0650991376359473e-05,
"loss": 1.7775,
"step": 441
},
{
"epoch": 0.7482014388489209,
"grad_norm": 0.21035221219062805,
"learning_rate": 1.029921484817783e-05,
"loss": 1.8775,
"step": 442
},
{
"epoch": 0.7498942022852306,
"grad_norm": 0.20913664996623993,
"learning_rate": 9.953033171663175e-06,
"loss": 1.7602,
"step": 443
},
{
"epoch": 0.7515869657215404,
"grad_norm": 0.20781245827674866,
"learning_rate": 9.612467700932045e-06,
"loss": 1.7158,
"step": 444
},
{
"epoch": 0.7532797291578502,
"grad_norm": 0.20402781665325165,
"learning_rate": 9.277539443666783e-06,
"loss": 1.818,
"step": 445
},
{
"epoch": 0.75497249259416,
"grad_norm": 0.21362698078155518,
"learning_rate": 8.948269059820025e-06,
"loss": 1.8516,
"step": 446
},
{
"epoch": 0.7566652560304697,
"grad_norm": 0.2265281230211258,
"learning_rate": 8.624676860340025e-06,
"loss": 1.7944,
"step": 447
},
{
"epoch": 0.7583580194667795,
"grad_norm": 0.21393375098705292,
"learning_rate": 8.306782805917904e-06,
"loss": 1.7829,
"step": 448
},
{
"epoch": 0.7600507829030893,
"grad_norm": 0.20928075909614563,
"learning_rate": 7.994606505756355e-06,
"loss": 1.7777,
"step": 449
},
{
"epoch": 0.7617435463393991,
"grad_norm": 0.2121303230524063,
"learning_rate": 7.68816721636004e-06,
"loss": 1.8348,
"step": 450
},
{
"epoch": 0.7634363097757089,
"grad_norm": 0.21304333209991455,
"learning_rate": 7.3874838403478e-06,
"loss": 1.8322,
"step": 451
},
{
"epoch": 0.7651290732120186,
"grad_norm": 0.19794292747974396,
"learning_rate": 7.092574925286614e-06,
"loss": 1.7484,
"step": 452
},
{
"epoch": 0.7668218366483284,
"grad_norm": 0.23775118589401245,
"learning_rate": 6.803458662547507e-06,
"loss": 1.8244,
"step": 453
},
{
"epoch": 0.7685146000846381,
"grad_norm": 0.21358804404735565,
"learning_rate": 6.520152886183406e-06,
"loss": 1.7668,
"step": 454
},
{
"epoch": 0.770207363520948,
"grad_norm": 0.2213735729455948,
"learning_rate": 6.242675071829111e-06,
"loss": 1.8165,
"step": 455
},
{
"epoch": 0.7719001269572577,
"grad_norm": 0.20860306918621063,
"learning_rate": 5.971042335623229e-06,
"loss": 1.7456,
"step": 456
},
{
"epoch": 0.7735928903935675,
"grad_norm": 0.2030525654554367,
"learning_rate": 5.705271433152458e-06,
"loss": 1.7243,
"step": 457
},
{
"epoch": 0.7752856538298772,
"grad_norm": 0.23554547131061554,
"learning_rate": 5.445378758417925e-06,
"loss": 1.8786,
"step": 458
},
{
"epoch": 0.7769784172661871,
"grad_norm": 0.19026103615760803,
"learning_rate": 5.191380342824035e-06,
"loss": 1.7338,
"step": 459
},
{
"epoch": 0.7786711807024969,
"grad_norm": 0.21249499917030334,
"learning_rate": 4.943291854189493e-06,
"loss": 1.8831,
"step": 460
},
{
"epoch": 0.7803639441388066,
"grad_norm": 0.1983940303325653,
"learning_rate": 4.701128595780878e-06,
"loss": 1.8124,
"step": 461
},
{
"epoch": 0.7820567075751164,
"grad_norm": 0.2183755785226822,
"learning_rate": 4.464905505368658e-06,
"loss": 1.8125,
"step": 462
},
{
"epoch": 0.7837494710114261,
"grad_norm": 0.20469729602336884,
"learning_rate": 4.23463715430577e-06,
"loss": 1.7181,
"step": 463
},
{
"epoch": 0.785442234447736,
"grad_norm": 0.21118509769439697,
"learning_rate": 4.010337746628751e-06,
"loss": 1.8343,
"step": 464
},
{
"epoch": 0.7871349978840457,
"grad_norm": 0.20791935920715332,
"learning_rate": 3.792021118181636e-06,
"loss": 1.8717,
"step": 465
},
{
"epoch": 0.7888277613203555,
"grad_norm": 0.21682444214820862,
"learning_rate": 3.5797007357623945e-06,
"loss": 1.9463,
"step": 466
},
{
"epoch": 0.7905205247566652,
"grad_norm": 0.2028808295726776,
"learning_rate": 3.3733896962923658e-06,
"loss": 1.7656,
"step": 467
},
{
"epoch": 0.792213288192975,
"grad_norm": 0.20768266916275024,
"learning_rate": 3.1731007260082616e-06,
"loss": 1.8322,
"step": 468
},
{
"epoch": 0.7939060516292848,
"grad_norm": 0.22645053267478943,
"learning_rate": 2.9788461796772114e-06,
"loss": 1.7735,
"step": 469
},
{
"epoch": 0.7955988150655946,
"grad_norm": 0.20245122909545898,
"learning_rate": 2.790638039834668e-06,
"loss": 1.7191,
"step": 470
},
{
"epoch": 0.7972915785019044,
"grad_norm": 0.2117125540971756,
"learning_rate": 2.6084879160452166e-06,
"loss": 1.7797,
"step": 471
},
{
"epoch": 0.7989843419382141,
"grad_norm": 0.2047407627105713,
"learning_rate": 2.432407044186509e-06,
"loss": 1.8037,
"step": 472
},
{
"epoch": 0.8006771053745239,
"grad_norm": 0.19866344332695007,
"learning_rate": 2.26240628575615e-06,
"loss": 1.8208,
"step": 473
},
{
"epoch": 0.8023698688108337,
"grad_norm": 0.21329368650913239,
"learning_rate": 2.098496127201648e-06,
"loss": 1.7743,
"step": 474
},
{
"epoch": 0.8040626322471435,
"grad_norm": 0.2227088063955307,
"learning_rate": 1.9406866792737267e-06,
"loss": 1.802,
"step": 475
},
{
"epoch": 0.8057553956834532,
"grad_norm": 0.23095914721488953,
"learning_rate": 1.7889876764024505e-06,
"loss": 1.7875,
"step": 476
},
{
"epoch": 0.807448159119763,
"grad_norm": 0.19540473818778992,
"learning_rate": 1.6434084760968697e-06,
"loss": 1.7506,
"step": 477
},
{
"epoch": 0.8091409225560728,
"grad_norm": 0.22987684607505798,
"learning_rate": 1.5039580583678393e-06,
"loss": 1.8692,
"step": 478
},
{
"epoch": 0.8108336859923826,
"grad_norm": 0.21226081252098083,
"learning_rate": 1.3706450251739613e-06,
"loss": 1.8634,
"step": 479
},
{
"epoch": 0.8125264494286923,
"grad_norm": 0.22443637251853943,
"learning_rate": 1.2434775998910964e-06,
"loss": 1.7992,
"step": 480
},
{
"epoch": 0.8142192128650021,
"grad_norm": 0.2271965891122818,
"learning_rate": 1.1224636268050439e-06,
"loss": 1.8904,
"step": 481
},
{
"epoch": 0.8159119763013118,
"grad_norm": 0.20612284541130066,
"learning_rate": 1.0076105706276888e-06,
"loss": 1.8025,
"step": 482
},
{
"epoch": 0.8176047397376217,
"grad_norm": 0.2131970375776291,
"learning_rate": 8.989255160365527e-07,
"loss": 1.8113,
"step": 483
},
{
"epoch": 0.8192975031739315,
"grad_norm": 0.20513294637203217,
"learning_rate": 7.964151672377458e-07,
"loss": 1.7326,
"step": 484
},
{
"epoch": 0.8209902666102412,
"grad_norm": 0.19909213483333588,
"learning_rate": 7.000858475524444e-07,
"loss": 1.7877,
"step": 485
},
{
"epoch": 0.822683030046551,
"grad_norm": 0.2285769283771515,
"learning_rate": 6.099434990268609e-07,
"loss": 1.7713,
"step": 486
},
{
"epoch": 0.8243757934828607,
"grad_norm": 0.22476732730865479,
"learning_rate": 5.259936820656257e-07,
"loss": 1.8826,
"step": 487
},
{
"epoch": 0.8260685569191706,
"grad_norm": 0.19041244685649872,
"learning_rate": 4.482415750889204e-07,
"loss": 1.7251,
"step": 488
},
{
"epoch": 0.8277613203554803,
"grad_norm": 0.2075662761926651,
"learning_rate": 3.766919742129331e-07,
"loss": 1.7731,
"step": 489
},
{
"epoch": 0.8294540837917901,
"grad_norm": 0.18497450649738312,
"learning_rate": 3.1134929295407564e-07,
"loss": 1.8623,
"step": 490
},
{
"epoch": 0.8311468472280998,
"grad_norm": 0.219017893075943,
"learning_rate": 2.5221756195672563e-07,
"loss": 1.8737,
"step": 491
},
{
"epoch": 0.8328396106644097,
"grad_norm": 0.19198881089687347,
"learning_rate": 1.9930042874457254e-07,
"loss": 1.6552,
"step": 492
},
{
"epoch": 0.8345323741007195,
"grad_norm": 0.20981106162071228,
"learning_rate": 1.5260115749566882e-07,
"loss": 1.8265,
"step": 493
},
{
"epoch": 0.8362251375370292,
"grad_norm": 0.2261609137058258,
"learning_rate": 1.1212262884103974e-07,
"loss": 1.8204,
"step": 494
},
{
"epoch": 0.837917900973339,
"grad_norm": 0.2019382268190384,
"learning_rate": 7.7867339686987e-08,
"loss": 1.7678,
"step": 495
},
{
"epoch": 0.8396106644096487,
"grad_norm": 0.2012385129928589,
"learning_rate": 4.98374030611084e-08,
"loss": 1.8016,
"step": 496
},
{
"epoch": 0.8413034278459586,
"grad_norm": 0.21322940289974213,
"learning_rate": 2.8034547981943713e-08,
"loss": 1.8225,
"step": 497
},
{
"epoch": 0.8429961912822683,
"grad_norm": 0.24298058450222015,
"learning_rate": 1.246011935228064e-08,
"loss": 1.8557,
"step": 498
},
{
"epoch": 0.8446889547185781,
"grad_norm": 0.2144518941640854,
"learning_rate": 3.115077876243988e-09,
"loss": 1.795,
"step": 499
},
{
"epoch": 0.8463817181548878,
"grad_norm": 0.19734685122966766,
"learning_rate": 0.0,
"loss": 1.7337,
"step": 500
}
],
"logging_steps": 1,
"max_steps": 500,
"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": 7.881222559251825e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}