prxy5604's picture
Training in progress, step 200, checkpoint
0c5f6bc verified
{
"best_metric": 11.5,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.06754474839581223,
"eval_steps": 50,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00033772374197906115,
"grad_norm": 6.999200559221208e-05,
"learning_rate": 5e-06,
"loss": 46.0,
"step": 1
},
{
"epoch": 0.00033772374197906115,
"eval_loss": 11.5,
"eval_runtime": 38.0491,
"eval_samples_per_second": 131.067,
"eval_steps_per_second": 65.547,
"step": 1
},
{
"epoch": 0.0006754474839581223,
"grad_norm": 5.612642053165473e-05,
"learning_rate": 1e-05,
"loss": 46.0,
"step": 2
},
{
"epoch": 0.0010131712259371835,
"grad_norm": 0.00011171244841534644,
"learning_rate": 1.5e-05,
"loss": 46.0,
"step": 3
},
{
"epoch": 0.0013508949679162446,
"grad_norm": 6.527295772684738e-05,
"learning_rate": 2e-05,
"loss": 46.0,
"step": 4
},
{
"epoch": 0.0016886187098953055,
"grad_norm": 0.00010032207501353696,
"learning_rate": 2.5e-05,
"loss": 46.0,
"step": 5
},
{
"epoch": 0.002026342451874367,
"grad_norm": 6.297726213233545e-05,
"learning_rate": 3e-05,
"loss": 46.0,
"step": 6
},
{
"epoch": 0.002364066193853428,
"grad_norm": 0.00010159278463106602,
"learning_rate": 3.5e-05,
"loss": 46.0,
"step": 7
},
{
"epoch": 0.002701789935832489,
"grad_norm": 6.908881186973304e-05,
"learning_rate": 4e-05,
"loss": 46.0,
"step": 8
},
{
"epoch": 0.00303951367781155,
"grad_norm": 0.00010548412683419883,
"learning_rate": 4.5e-05,
"loss": 46.0,
"step": 9
},
{
"epoch": 0.003377237419790611,
"grad_norm": 0.00010045844101114199,
"learning_rate": 5e-05,
"loss": 46.0,
"step": 10
},
{
"epoch": 0.0037149611617696724,
"grad_norm": 0.00010918975749518722,
"learning_rate": 5.500000000000001e-05,
"loss": 46.0,
"step": 11
},
{
"epoch": 0.004052684903748734,
"grad_norm": 0.00010634872887749225,
"learning_rate": 6e-05,
"loss": 46.0,
"step": 12
},
{
"epoch": 0.004390408645727794,
"grad_norm": 6.084080450818874e-05,
"learning_rate": 6.500000000000001e-05,
"loss": 46.0,
"step": 13
},
{
"epoch": 0.004728132387706856,
"grad_norm": 8.961093408288434e-05,
"learning_rate": 7e-05,
"loss": 46.0,
"step": 14
},
{
"epoch": 0.005065856129685917,
"grad_norm": 7.892983558122069e-05,
"learning_rate": 7.500000000000001e-05,
"loss": 46.0,
"step": 15
},
{
"epoch": 0.005403579871664978,
"grad_norm": 7.510028081014752e-05,
"learning_rate": 8e-05,
"loss": 46.0,
"step": 16
},
{
"epoch": 0.005741303613644039,
"grad_norm": 0.00010316520638298243,
"learning_rate": 8.5e-05,
"loss": 46.0,
"step": 17
},
{
"epoch": 0.0060790273556231,
"grad_norm": 0.00015889042697381228,
"learning_rate": 9e-05,
"loss": 46.0,
"step": 18
},
{
"epoch": 0.006416751097602162,
"grad_norm": 9.389503247803077e-05,
"learning_rate": 9.5e-05,
"loss": 46.0,
"step": 19
},
{
"epoch": 0.006754474839581222,
"grad_norm": 0.00012303520634304732,
"learning_rate": 0.0001,
"loss": 46.0,
"step": 20
},
{
"epoch": 0.0070921985815602835,
"grad_norm": 0.00016235452494584024,
"learning_rate": 9.999238475781957e-05,
"loss": 46.0,
"step": 21
},
{
"epoch": 0.007429922323539345,
"grad_norm": 0.00012188320397399366,
"learning_rate": 9.99695413509548e-05,
"loss": 46.0,
"step": 22
},
{
"epoch": 0.007767646065518406,
"grad_norm": 0.00015171366976574063,
"learning_rate": 9.99314767377287e-05,
"loss": 46.0,
"step": 23
},
{
"epoch": 0.008105369807497468,
"grad_norm": 9.316073555964977e-05,
"learning_rate": 9.987820251299122e-05,
"loss": 46.0,
"step": 24
},
{
"epoch": 0.008443093549476529,
"grad_norm": 0.00014290536637417972,
"learning_rate": 9.980973490458728e-05,
"loss": 46.0,
"step": 25
},
{
"epoch": 0.008780817291455589,
"grad_norm": 0.00015599915059283376,
"learning_rate": 9.972609476841367e-05,
"loss": 46.0,
"step": 26
},
{
"epoch": 0.00911854103343465,
"grad_norm": 0.00015680905198678374,
"learning_rate": 9.962730758206611e-05,
"loss": 46.0,
"step": 27
},
{
"epoch": 0.009456264775413711,
"grad_norm": 0.00016664821305312216,
"learning_rate": 9.951340343707852e-05,
"loss": 46.0,
"step": 28
},
{
"epoch": 0.009793988517392773,
"grad_norm": 0.0001463688095100224,
"learning_rate": 9.938441702975689e-05,
"loss": 46.0,
"step": 29
},
{
"epoch": 0.010131712259371834,
"grad_norm": 0.0001783478946890682,
"learning_rate": 9.924038765061042e-05,
"loss": 46.0,
"step": 30
},
{
"epoch": 0.010469436001350895,
"grad_norm": 0.0001655457599554211,
"learning_rate": 9.908135917238321e-05,
"loss": 46.0,
"step": 31
},
{
"epoch": 0.010807159743329957,
"grad_norm": 0.00018240793724544346,
"learning_rate": 9.890738003669029e-05,
"loss": 46.0,
"step": 32
},
{
"epoch": 0.011144883485309016,
"grad_norm": 0.00016705192683730274,
"learning_rate": 9.871850323926177e-05,
"loss": 46.0,
"step": 33
},
{
"epoch": 0.011482607227288078,
"grad_norm": 0.0002768947451841086,
"learning_rate": 9.851478631379982e-05,
"loss": 46.0,
"step": 34
},
{
"epoch": 0.01182033096926714,
"grad_norm": 0.00024317330098710954,
"learning_rate": 9.829629131445342e-05,
"loss": 46.0,
"step": 35
},
{
"epoch": 0.0121580547112462,
"grad_norm": 0.00013411836698651314,
"learning_rate": 9.806308479691595e-05,
"loss": 46.0,
"step": 36
},
{
"epoch": 0.012495778453225262,
"grad_norm": 0.00028809363720938563,
"learning_rate": 9.781523779815179e-05,
"loss": 46.0,
"step": 37
},
{
"epoch": 0.012833502195204323,
"grad_norm": 0.00029307673685252666,
"learning_rate": 9.755282581475769e-05,
"loss": 46.0,
"step": 38
},
{
"epoch": 0.013171225937183385,
"grad_norm": 0.0002233909472124651,
"learning_rate": 9.727592877996585e-05,
"loss": 46.0,
"step": 39
},
{
"epoch": 0.013508949679162444,
"grad_norm": 0.0002125003666151315,
"learning_rate": 9.698463103929542e-05,
"loss": 46.0,
"step": 40
},
{
"epoch": 0.013846673421141506,
"grad_norm": 0.00015506868658121675,
"learning_rate": 9.667902132486009e-05,
"loss": 46.0,
"step": 41
},
{
"epoch": 0.014184397163120567,
"grad_norm": 0.00023671003873459995,
"learning_rate": 9.635919272833938e-05,
"loss": 46.0,
"step": 42
},
{
"epoch": 0.014522120905099628,
"grad_norm": 0.00023820622300263494,
"learning_rate": 9.602524267262203e-05,
"loss": 46.0,
"step": 43
},
{
"epoch": 0.01485984464707869,
"grad_norm": 0.00013906476669944823,
"learning_rate": 9.567727288213005e-05,
"loss": 46.0,
"step": 44
},
{
"epoch": 0.015197568389057751,
"grad_norm": 0.00024479327839799225,
"learning_rate": 9.53153893518325e-05,
"loss": 46.0,
"step": 45
},
{
"epoch": 0.015535292131036813,
"grad_norm": 0.0002795088803395629,
"learning_rate": 9.493970231495835e-05,
"loss": 46.0,
"step": 46
},
{
"epoch": 0.015873015873015872,
"grad_norm": 0.00026209637871943414,
"learning_rate": 9.45503262094184e-05,
"loss": 46.0,
"step": 47
},
{
"epoch": 0.016210739614994935,
"grad_norm": 0.00022261285630520433,
"learning_rate": 9.414737964294636e-05,
"loss": 46.0,
"step": 48
},
{
"epoch": 0.016548463356973995,
"grad_norm": 0.0002231644029961899,
"learning_rate": 9.373098535696979e-05,
"loss": 46.0,
"step": 49
},
{
"epoch": 0.016886187098953058,
"grad_norm": 0.00023359505576081574,
"learning_rate": 9.330127018922194e-05,
"loss": 46.0,
"step": 50
},
{
"epoch": 0.016886187098953058,
"eval_loss": 11.5,
"eval_runtime": 38.1051,
"eval_samples_per_second": 130.875,
"eval_steps_per_second": 65.451,
"step": 50
},
{
"epoch": 0.017223910840932118,
"grad_norm": 0.0004388255765661597,
"learning_rate": 9.285836503510562e-05,
"loss": 46.0,
"step": 51
},
{
"epoch": 0.017561634582911177,
"grad_norm": 0.00034231445170007646,
"learning_rate": 9.24024048078213e-05,
"loss": 46.0,
"step": 52
},
{
"epoch": 0.01789935832489024,
"grad_norm": 0.00040279701352119446,
"learning_rate": 9.193352839727121e-05,
"loss": 46.0,
"step": 53
},
{
"epoch": 0.0182370820668693,
"grad_norm": 0.00048692570999264717,
"learning_rate": 9.145187862775209e-05,
"loss": 46.0,
"step": 54
},
{
"epoch": 0.018574805808848363,
"grad_norm": 0.0004796187567990273,
"learning_rate": 9.09576022144496e-05,
"loss": 46.0,
"step": 55
},
{
"epoch": 0.018912529550827423,
"grad_norm": 0.0004256981483194977,
"learning_rate": 9.045084971874738e-05,
"loss": 46.0,
"step": 56
},
{
"epoch": 0.019250253292806486,
"grad_norm": 0.0003702337562572211,
"learning_rate": 8.993177550236464e-05,
"loss": 46.0,
"step": 57
},
{
"epoch": 0.019587977034785545,
"grad_norm": 0.00028856948483735323,
"learning_rate": 8.940053768033609e-05,
"loss": 46.0,
"step": 58
},
{
"epoch": 0.019925700776764605,
"grad_norm": 0.00043020248995162547,
"learning_rate": 8.885729807284856e-05,
"loss": 46.0,
"step": 59
},
{
"epoch": 0.020263424518743668,
"grad_norm": 0.00032656811526976526,
"learning_rate": 8.83022221559489e-05,
"loss": 46.0,
"step": 60
},
{
"epoch": 0.020601148260722728,
"grad_norm": 0.00044006985262967646,
"learning_rate": 8.773547901113862e-05,
"loss": 46.0,
"step": 61
},
{
"epoch": 0.02093887200270179,
"grad_norm": 0.0005264987121336162,
"learning_rate": 8.715724127386972e-05,
"loss": 46.0,
"step": 62
},
{
"epoch": 0.02127659574468085,
"grad_norm": 0.0005930354818701744,
"learning_rate": 8.656768508095853e-05,
"loss": 46.0,
"step": 63
},
{
"epoch": 0.021614319486659914,
"grad_norm": 0.0004631902265828103,
"learning_rate": 8.596699001693255e-05,
"loss": 46.0,
"step": 64
},
{
"epoch": 0.021952043228638973,
"grad_norm": 0.0004996751667931676,
"learning_rate": 8.535533905932738e-05,
"loss": 46.0,
"step": 65
},
{
"epoch": 0.022289766970618033,
"grad_norm": 0.0005587644409388304,
"learning_rate": 8.473291852294987e-05,
"loss": 46.0,
"step": 66
},
{
"epoch": 0.022627490712597096,
"grad_norm": 0.0005852883914485574,
"learning_rate": 8.409991800312493e-05,
"loss": 46.0,
"step": 67
},
{
"epoch": 0.022965214454576156,
"grad_norm": 0.0007204718422144651,
"learning_rate": 8.345653031794292e-05,
"loss": 46.0,
"step": 68
},
{
"epoch": 0.02330293819655522,
"grad_norm": 0.0005952971987426281,
"learning_rate": 8.280295144952536e-05,
"loss": 46.0,
"step": 69
},
{
"epoch": 0.02364066193853428,
"grad_norm": 0.0005659193848259747,
"learning_rate": 8.213938048432697e-05,
"loss": 46.0,
"step": 70
},
{
"epoch": 0.02397838568051334,
"grad_norm": 0.0004821221227757633,
"learning_rate": 8.146601955249188e-05,
"loss": 46.0,
"step": 71
},
{
"epoch": 0.0243161094224924,
"grad_norm": 0.00043129047844558954,
"learning_rate": 8.07830737662829e-05,
"loss": 46.0,
"step": 72
},
{
"epoch": 0.02465383316447146,
"grad_norm": 0.0007432058919221163,
"learning_rate": 8.009075115760243e-05,
"loss": 46.0,
"step": 73
},
{
"epoch": 0.024991556906450524,
"grad_norm": 0.0005778361228294671,
"learning_rate": 7.938926261462366e-05,
"loss": 46.0,
"step": 74
},
{
"epoch": 0.025329280648429583,
"grad_norm": 0.0006119939498603344,
"learning_rate": 7.86788218175523e-05,
"loss": 46.0,
"step": 75
},
{
"epoch": 0.025667004390408647,
"grad_norm": 0.0006990509573370218,
"learning_rate": 7.795964517353735e-05,
"loss": 46.0,
"step": 76
},
{
"epoch": 0.026004728132387706,
"grad_norm": 0.000691780005581677,
"learning_rate": 7.723195175075136e-05,
"loss": 46.0,
"step": 77
},
{
"epoch": 0.02634245187436677,
"grad_norm": 0.0007424818468280137,
"learning_rate": 7.649596321166024e-05,
"loss": 46.0,
"step": 78
},
{
"epoch": 0.02668017561634583,
"grad_norm": 0.0009253322496078908,
"learning_rate": 7.575190374550272e-05,
"loss": 46.0,
"step": 79
},
{
"epoch": 0.02701789935832489,
"grad_norm": 0.0006558927707374096,
"learning_rate": 7.500000000000001e-05,
"loss": 46.0,
"step": 80
},
{
"epoch": 0.02735562310030395,
"grad_norm": 0.000801301037427038,
"learning_rate": 7.424048101231686e-05,
"loss": 46.0,
"step": 81
},
{
"epoch": 0.02769334684228301,
"grad_norm": 0.0007340286974795163,
"learning_rate": 7.347357813929454e-05,
"loss": 46.0,
"step": 82
},
{
"epoch": 0.028031070584262074,
"grad_norm": 0.0005543944425880909,
"learning_rate": 7.269952498697734e-05,
"loss": 46.0,
"step": 83
},
{
"epoch": 0.028368794326241134,
"grad_norm": 0.0004185195139143616,
"learning_rate": 7.191855733945387e-05,
"loss": 46.0,
"step": 84
},
{
"epoch": 0.028706518068220197,
"grad_norm": 0.0008723873761482537,
"learning_rate": 7.113091308703498e-05,
"loss": 46.0,
"step": 85
},
{
"epoch": 0.029044241810199257,
"grad_norm": 0.0006252967286854982,
"learning_rate": 7.033683215379002e-05,
"loss": 46.0,
"step": 86
},
{
"epoch": 0.029381965552178316,
"grad_norm": 0.0008132215589284897,
"learning_rate": 6.953655642446368e-05,
"loss": 46.0,
"step": 87
},
{
"epoch": 0.02971968929415738,
"grad_norm": 0.0006520528695546091,
"learning_rate": 6.873032967079561e-05,
"loss": 46.0,
"step": 88
},
{
"epoch": 0.03005741303613644,
"grad_norm": 0.0006046611815690994,
"learning_rate": 6.7918397477265e-05,
"loss": 46.0,
"step": 89
},
{
"epoch": 0.030395136778115502,
"grad_norm": 0.0007351114763878286,
"learning_rate": 6.710100716628344e-05,
"loss": 46.0,
"step": 90
},
{
"epoch": 0.030732860520094562,
"grad_norm": 0.0005443833651952446,
"learning_rate": 6.627840772285784e-05,
"loss": 46.0,
"step": 91
},
{
"epoch": 0.031070584262073625,
"grad_norm": 0.0007517460617236793,
"learning_rate": 6.545084971874738e-05,
"loss": 46.0,
"step": 92
},
{
"epoch": 0.031408308004052685,
"grad_norm": 0.0006298055523075163,
"learning_rate": 6.461858523613684e-05,
"loss": 46.0,
"step": 93
},
{
"epoch": 0.031746031746031744,
"grad_norm": 0.0006449134671129286,
"learning_rate": 6.378186779084995e-05,
"loss": 46.0,
"step": 94
},
{
"epoch": 0.032083755488010804,
"grad_norm": 0.0005613227258436382,
"learning_rate": 6.294095225512603e-05,
"loss": 46.0,
"step": 95
},
{
"epoch": 0.03242147922998987,
"grad_norm": 0.0006533685373142362,
"learning_rate": 6.209609477998338e-05,
"loss": 46.0,
"step": 96
},
{
"epoch": 0.03275920297196893,
"grad_norm": 0.000610053539276123,
"learning_rate": 6.124755271719325e-05,
"loss": 46.0,
"step": 97
},
{
"epoch": 0.03309692671394799,
"grad_norm": 0.0006236035260371864,
"learning_rate": 6.0395584540887963e-05,
"loss": 46.0,
"step": 98
},
{
"epoch": 0.03343465045592705,
"grad_norm": 0.0006816457607783377,
"learning_rate": 5.9540449768827246e-05,
"loss": 46.0,
"step": 99
},
{
"epoch": 0.033772374197906116,
"grad_norm": 0.0008262648480013013,
"learning_rate": 5.868240888334653e-05,
"loss": 46.0,
"step": 100
},
{
"epoch": 0.033772374197906116,
"eval_loss": 11.5,
"eval_runtime": 38.395,
"eval_samples_per_second": 129.887,
"eval_steps_per_second": 64.956,
"step": 100
},
{
"epoch": 0.034110097939885176,
"grad_norm": 0.0007305089384317398,
"learning_rate": 5.782172325201155e-05,
"loss": 46.0,
"step": 101
},
{
"epoch": 0.034447821681864235,
"grad_norm": 0.0010143495164811611,
"learning_rate": 5.695865504800327e-05,
"loss": 46.0,
"step": 102
},
{
"epoch": 0.034785545423843295,
"grad_norm": 0.000756265944801271,
"learning_rate": 5.6093467170257374e-05,
"loss": 46.0,
"step": 103
},
{
"epoch": 0.035123269165822354,
"grad_norm": 0.0008156715193763375,
"learning_rate": 5.522642316338268e-05,
"loss": 46.0,
"step": 104
},
{
"epoch": 0.03546099290780142,
"grad_norm": 0.0009573604329489172,
"learning_rate": 5.435778713738292e-05,
"loss": 46.0,
"step": 105
},
{
"epoch": 0.03579871664978048,
"grad_norm": 0.0008011315367184579,
"learning_rate": 5.348782368720626e-05,
"loss": 46.0,
"step": 106
},
{
"epoch": 0.03613644039175954,
"grad_norm": 0.0010019487235695124,
"learning_rate": 5.26167978121472e-05,
"loss": 46.0,
"step": 107
},
{
"epoch": 0.0364741641337386,
"grad_norm": 0.0008329348056577146,
"learning_rate": 5.174497483512506e-05,
"loss": 46.0,
"step": 108
},
{
"epoch": 0.03681188787571766,
"grad_norm": 0.0009144492214545608,
"learning_rate": 5.0872620321864185e-05,
"loss": 46.0,
"step": 109
},
{
"epoch": 0.037149611617696726,
"grad_norm": 0.0006390439230017364,
"learning_rate": 5e-05,
"loss": 46.0,
"step": 110
},
{
"epoch": 0.037487335359675786,
"grad_norm": 0.001059593167155981,
"learning_rate": 4.912737967813583e-05,
"loss": 46.0,
"step": 111
},
{
"epoch": 0.037825059101654845,
"grad_norm": 0.0006486097117885947,
"learning_rate": 4.825502516487497e-05,
"loss": 46.0,
"step": 112
},
{
"epoch": 0.038162782843633905,
"grad_norm": 0.000764590164180845,
"learning_rate": 4.738320218785281e-05,
"loss": 46.0,
"step": 113
},
{
"epoch": 0.03850050658561297,
"grad_norm": 0.0013067929539829493,
"learning_rate": 4.6512176312793736e-05,
"loss": 46.0,
"step": 114
},
{
"epoch": 0.03883823032759203,
"grad_norm": 0.0011828240239992738,
"learning_rate": 4.564221286261709e-05,
"loss": 46.0,
"step": 115
},
{
"epoch": 0.03917595406957109,
"grad_norm": 0.0008867242140695453,
"learning_rate": 4.477357683661734e-05,
"loss": 46.0,
"step": 116
},
{
"epoch": 0.03951367781155015,
"grad_norm": 0.000849198317155242,
"learning_rate": 4.390653282974264e-05,
"loss": 46.0,
"step": 117
},
{
"epoch": 0.03985140155352921,
"grad_norm": 0.0011799026979133487,
"learning_rate": 4.3041344951996746e-05,
"loss": 46.0,
"step": 118
},
{
"epoch": 0.04018912529550828,
"grad_norm": 0.0015928293578326702,
"learning_rate": 4.2178276747988446e-05,
"loss": 46.0,
"step": 119
},
{
"epoch": 0.040526849037487336,
"grad_norm": 0.0006499377777799964,
"learning_rate": 4.131759111665349e-05,
"loss": 46.0,
"step": 120
},
{
"epoch": 0.040864572779466396,
"grad_norm": 0.0010604766430333257,
"learning_rate": 4.045955023117276e-05,
"loss": 46.0,
"step": 121
},
{
"epoch": 0.041202296521445456,
"grad_norm": 0.0006666944245807827,
"learning_rate": 3.960441545911204e-05,
"loss": 46.0,
"step": 122
},
{
"epoch": 0.04154002026342452,
"grad_norm": 0.001197998528368771,
"learning_rate": 3.875244728280676e-05,
"loss": 46.0,
"step": 123
},
{
"epoch": 0.04187774400540358,
"grad_norm": 0.0011294663418084383,
"learning_rate": 3.790390522001662e-05,
"loss": 46.0,
"step": 124
},
{
"epoch": 0.04221546774738264,
"grad_norm": 0.0009281404782086611,
"learning_rate": 3.705904774487396e-05,
"loss": 46.0,
"step": 125
},
{
"epoch": 0.0425531914893617,
"grad_norm": 0.0008012927719391882,
"learning_rate": 3.6218132209150045e-05,
"loss": 46.0,
"step": 126
},
{
"epoch": 0.04289091523134076,
"grad_norm": 0.0012234264286234975,
"learning_rate": 3.5381414763863166e-05,
"loss": 46.0,
"step": 127
},
{
"epoch": 0.04322863897331983,
"grad_norm": 0.0011153658851981163,
"learning_rate": 3.4549150281252636e-05,
"loss": 46.0,
"step": 128
},
{
"epoch": 0.04356636271529889,
"grad_norm": 0.0008695648284628987,
"learning_rate": 3.372159227714218e-05,
"loss": 46.0,
"step": 129
},
{
"epoch": 0.04390408645727795,
"grad_norm": 0.0010590883903205395,
"learning_rate": 3.289899283371657e-05,
"loss": 46.0,
"step": 130
},
{
"epoch": 0.044241810199257006,
"grad_norm": 0.0011277355952188373,
"learning_rate": 3.2081602522734986e-05,
"loss": 46.0,
"step": 131
},
{
"epoch": 0.044579533941236066,
"grad_norm": 0.0008733632857911289,
"learning_rate": 3.12696703292044e-05,
"loss": 46.0,
"step": 132
},
{
"epoch": 0.04491725768321513,
"grad_norm": 0.0009897883282974362,
"learning_rate": 3.046344357553632e-05,
"loss": 46.0,
"step": 133
},
{
"epoch": 0.04525498142519419,
"grad_norm": 0.0009033156675286591,
"learning_rate": 2.9663167846209998e-05,
"loss": 46.0,
"step": 134
},
{
"epoch": 0.04559270516717325,
"grad_norm": 0.0009513600380159914,
"learning_rate": 2.886908691296504e-05,
"loss": 46.0,
"step": 135
},
{
"epoch": 0.04593042890915231,
"grad_norm": 0.0009552270639687777,
"learning_rate": 2.8081442660546125e-05,
"loss": 46.0,
"step": 136
},
{
"epoch": 0.04626815265113138,
"grad_norm": 0.0007903517107479274,
"learning_rate": 2.7300475013022663e-05,
"loss": 46.0,
"step": 137
},
{
"epoch": 0.04660587639311044,
"grad_norm": 0.001167718437500298,
"learning_rate": 2.6526421860705473e-05,
"loss": 46.0,
"step": 138
},
{
"epoch": 0.0469436001350895,
"grad_norm": 0.0008934563957154751,
"learning_rate": 2.575951898768315e-05,
"loss": 46.0,
"step": 139
},
{
"epoch": 0.04728132387706856,
"grad_norm": 0.0007390851387754083,
"learning_rate": 2.500000000000001e-05,
"loss": 46.0,
"step": 140
},
{
"epoch": 0.047619047619047616,
"grad_norm": 0.001171390525996685,
"learning_rate": 2.4248096254497288e-05,
"loss": 46.0,
"step": 141
},
{
"epoch": 0.04795677136102668,
"grad_norm": 0.0009869023924693465,
"learning_rate": 2.350403678833976e-05,
"loss": 46.0,
"step": 142
},
{
"epoch": 0.04829449510300574,
"grad_norm": 0.00077177828643471,
"learning_rate": 2.2768048249248648e-05,
"loss": 46.0,
"step": 143
},
{
"epoch": 0.0486322188449848,
"grad_norm": 0.0006903486209921539,
"learning_rate": 2.2040354826462668e-05,
"loss": 46.0,
"step": 144
},
{
"epoch": 0.04896994258696386,
"grad_norm": 0.0008814368047751486,
"learning_rate": 2.132117818244771e-05,
"loss": 46.0,
"step": 145
},
{
"epoch": 0.04930766632894292,
"grad_norm": 0.001011370331980288,
"learning_rate": 2.061073738537635e-05,
"loss": 46.0,
"step": 146
},
{
"epoch": 0.04964539007092199,
"grad_norm": 0.0010025115916505456,
"learning_rate": 1.9909248842397584e-05,
"loss": 46.0,
"step": 147
},
{
"epoch": 0.04998311381290105,
"grad_norm": 0.0007225372246466577,
"learning_rate": 1.9216926233717085e-05,
"loss": 46.0,
"step": 148
},
{
"epoch": 0.05032083755488011,
"grad_norm": 0.0006715228664688766,
"learning_rate": 1.8533980447508137e-05,
"loss": 46.0,
"step": 149
},
{
"epoch": 0.05065856129685917,
"grad_norm": 0.0009384732111357152,
"learning_rate": 1.7860619515673033e-05,
"loss": 46.0,
"step": 150
},
{
"epoch": 0.05065856129685917,
"eval_loss": 11.5,
"eval_runtime": 38.1688,
"eval_samples_per_second": 130.656,
"eval_steps_per_second": 65.341,
"step": 150
},
{
"epoch": 0.050996285038838234,
"grad_norm": 0.0008989636553451419,
"learning_rate": 1.7197048550474643e-05,
"loss": 46.0,
"step": 151
},
{
"epoch": 0.05133400878081729,
"grad_norm": 0.0011067570885643363,
"learning_rate": 1.6543469682057106e-05,
"loss": 46.0,
"step": 152
},
{
"epoch": 0.05167173252279635,
"grad_norm": 0.0007851620321162045,
"learning_rate": 1.5900081996875083e-05,
"loss": 46.0,
"step": 153
},
{
"epoch": 0.05200945626477541,
"grad_norm": 0.001054355758242309,
"learning_rate": 1.526708147705013e-05,
"loss": 46.0,
"step": 154
},
{
"epoch": 0.05234718000675447,
"grad_norm": 0.0011224844492971897,
"learning_rate": 1.4644660940672627e-05,
"loss": 46.0,
"step": 155
},
{
"epoch": 0.05268490374873354,
"grad_norm": 0.0006852549267932773,
"learning_rate": 1.4033009983067452e-05,
"loss": 46.0,
"step": 156
},
{
"epoch": 0.0530226274907126,
"grad_norm": 0.0009039295255206525,
"learning_rate": 1.3432314919041478e-05,
"loss": 46.0,
"step": 157
},
{
"epoch": 0.05336035123269166,
"grad_norm": 0.000982744968496263,
"learning_rate": 1.2842758726130283e-05,
"loss": 46.0,
"step": 158
},
{
"epoch": 0.05369807497467072,
"grad_norm": 0.0011061737313866615,
"learning_rate": 1.22645209888614e-05,
"loss": 46.0,
"step": 159
},
{
"epoch": 0.05403579871664978,
"grad_norm": 0.0010985388653352857,
"learning_rate": 1.1697777844051105e-05,
"loss": 46.0,
"step": 160
},
{
"epoch": 0.054373522458628844,
"grad_norm": 0.0011543540749698877,
"learning_rate": 1.1142701927151456e-05,
"loss": 46.0,
"step": 161
},
{
"epoch": 0.0547112462006079,
"grad_norm": 0.0010955431498587132,
"learning_rate": 1.0599462319663905e-05,
"loss": 46.0,
"step": 162
},
{
"epoch": 0.05504896994258696,
"grad_norm": 0.0009253566386178136,
"learning_rate": 1.006822449763537e-05,
"loss": 46.0,
"step": 163
},
{
"epoch": 0.05538669368456602,
"grad_norm": 0.0011247299844399095,
"learning_rate": 9.549150281252633e-06,
"loss": 46.0,
"step": 164
},
{
"epoch": 0.05572441742654509,
"grad_norm": 0.0009286398999392986,
"learning_rate": 9.042397785550405e-06,
"loss": 46.0,
"step": 165
},
{
"epoch": 0.05606214116852415,
"grad_norm": 0.0014445815468207002,
"learning_rate": 8.548121372247918e-06,
"loss": 46.0,
"step": 166
},
{
"epoch": 0.05639986491050321,
"grad_norm": 0.0010441597551107407,
"learning_rate": 8.066471602728803e-06,
"loss": 46.0,
"step": 167
},
{
"epoch": 0.05673758865248227,
"grad_norm": 0.001206619548611343,
"learning_rate": 7.597595192178702e-06,
"loss": 46.0,
"step": 168
},
{
"epoch": 0.05707531239446133,
"grad_norm": 0.0011592115042731166,
"learning_rate": 7.1416349648943894e-06,
"loss": 46.0,
"step": 169
},
{
"epoch": 0.057413036136440394,
"grad_norm": 0.0009685884579084814,
"learning_rate": 6.698729810778065e-06,
"loss": 46.0,
"step": 170
},
{
"epoch": 0.057750759878419454,
"grad_norm": 0.0010882606729865074,
"learning_rate": 6.269014643030213e-06,
"loss": 46.0,
"step": 171
},
{
"epoch": 0.058088483620398514,
"grad_norm": 0.0008229081286117435,
"learning_rate": 5.852620357053651e-06,
"loss": 46.0,
"step": 172
},
{
"epoch": 0.05842620736237757,
"grad_norm": 0.0009584272629581392,
"learning_rate": 5.449673790581611e-06,
"loss": 46.0,
"step": 173
},
{
"epoch": 0.05876393110435663,
"grad_norm": 0.001024397206492722,
"learning_rate": 5.060297685041659e-06,
"loss": 46.0,
"step": 174
},
{
"epoch": 0.0591016548463357,
"grad_norm": 0.0010323076276108623,
"learning_rate": 4.684610648167503e-06,
"loss": 46.0,
"step": 175
},
{
"epoch": 0.05943937858831476,
"grad_norm": 0.0008894839556887746,
"learning_rate": 4.322727117869951e-06,
"loss": 46.0,
"step": 176
},
{
"epoch": 0.05977710233029382,
"grad_norm": 0.0008847026037983596,
"learning_rate": 3.974757327377981e-06,
"loss": 46.0,
"step": 177
},
{
"epoch": 0.06011482607227288,
"grad_norm": 0.000998921343125403,
"learning_rate": 3.6408072716606346e-06,
"loss": 46.0,
"step": 178
},
{
"epoch": 0.060452549814251945,
"grad_norm": 0.0008716392330825329,
"learning_rate": 3.3209786751399187e-06,
"loss": 46.0,
"step": 179
},
{
"epoch": 0.060790273556231005,
"grad_norm": 0.0013428525999188423,
"learning_rate": 3.0153689607045845e-06,
"loss": 46.0,
"step": 180
},
{
"epoch": 0.061127997298210064,
"grad_norm": 0.001158152474090457,
"learning_rate": 2.724071220034158e-06,
"loss": 46.0,
"step": 181
},
{
"epoch": 0.061465721040189124,
"grad_norm": 0.0012302974937483668,
"learning_rate": 2.4471741852423237e-06,
"loss": 46.0,
"step": 182
},
{
"epoch": 0.06180344478216818,
"grad_norm": 0.0008794470340944827,
"learning_rate": 2.1847622018482283e-06,
"loss": 46.0,
"step": 183
},
{
"epoch": 0.06214116852414725,
"grad_norm": 0.0013389174127951264,
"learning_rate": 1.9369152030840556e-06,
"loss": 46.0,
"step": 184
},
{
"epoch": 0.06247889226612631,
"grad_norm": 0.0008797872578725219,
"learning_rate": 1.70370868554659e-06,
"loss": 46.0,
"step": 185
},
{
"epoch": 0.06281661600810537,
"grad_norm": 0.0009669195278547704,
"learning_rate": 1.4852136862001764e-06,
"loss": 46.0,
"step": 186
},
{
"epoch": 0.06315433975008443,
"grad_norm": 0.0011810335563495755,
"learning_rate": 1.2814967607382432e-06,
"loss": 46.0,
"step": 187
},
{
"epoch": 0.06349206349206349,
"grad_norm": 0.0011306331725791097,
"learning_rate": 1.0926199633097157e-06,
"loss": 46.0,
"step": 188
},
{
"epoch": 0.06382978723404255,
"grad_norm": 0.000884878565557301,
"learning_rate": 9.186408276168013e-07,
"loss": 46.0,
"step": 189
},
{
"epoch": 0.06416751097602161,
"grad_norm": 0.0013046838575974107,
"learning_rate": 7.596123493895991e-07,
"loss": 46.0,
"step": 190
},
{
"epoch": 0.06450523471800068,
"grad_norm": 0.0008018773514777422,
"learning_rate": 6.15582970243117e-07,
"loss": 46.0,
"step": 191
},
{
"epoch": 0.06484295845997974,
"grad_norm": 0.000674662587698549,
"learning_rate": 4.865965629214819e-07,
"loss": 46.0,
"step": 192
},
{
"epoch": 0.0651806822019588,
"grad_norm": 0.000894166121724993,
"learning_rate": 3.7269241793390085e-07,
"loss": 46.0,
"step": 193
},
{
"epoch": 0.06551840594393786,
"grad_norm": 0.0007813581614755094,
"learning_rate": 2.7390523158633554e-07,
"loss": 46.0,
"step": 194
},
{
"epoch": 0.06585612968591692,
"grad_norm": 0.0007691160426475108,
"learning_rate": 1.9026509541272275e-07,
"loss": 46.0,
"step": 195
},
{
"epoch": 0.06619385342789598,
"grad_norm": 0.0009770386386662722,
"learning_rate": 1.2179748700879012e-07,
"loss": 46.0,
"step": 196
},
{
"epoch": 0.06653157716987504,
"grad_norm": 0.0008022322435863316,
"learning_rate": 6.852326227130834e-08,
"loss": 46.0,
"step": 197
},
{
"epoch": 0.0668693009118541,
"grad_norm": 0.0009312187903560698,
"learning_rate": 3.04586490452119e-08,
"loss": 46.0,
"step": 198
},
{
"epoch": 0.06720702465383316,
"grad_norm": 0.0011881066020578146,
"learning_rate": 7.615242180436522e-09,
"loss": 46.0,
"step": 199
},
{
"epoch": 0.06754474839581223,
"grad_norm": 0.001179297105409205,
"learning_rate": 0.0,
"loss": 46.0,
"step": 200
},
{
"epoch": 0.06754474839581223,
"eval_loss": 11.5,
"eval_runtime": 38.3354,
"eval_samples_per_second": 130.089,
"eval_steps_per_second": 65.057,
"step": 200
}
],
"logging_steps": 1,
"max_steps": 200,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 3
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 46026799841280.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}