prxy5606's picture
Training in progress, step 200, checkpoint
7832e50 verified
{
"best_metric": 0.9295676946640015,
"best_model_checkpoint": "miner_id_24/checkpoint-200",
"epoch": 0.042659841092091935,
"eval_steps": 50,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00021329920546045967,
"grad_norm": 0.4889717996120453,
"learning_rate": 5e-06,
"loss": 1.1541,
"step": 1
},
{
"epoch": 0.00021329920546045967,
"eval_loss": 1.3311876058578491,
"eval_runtime": 193.5704,
"eval_samples_per_second": 40.791,
"eval_steps_per_second": 20.396,
"step": 1
},
{
"epoch": 0.00042659841092091935,
"grad_norm": 0.45240214467048645,
"learning_rate": 1e-05,
"loss": 1.3002,
"step": 2
},
{
"epoch": 0.0006398976163813789,
"grad_norm": 0.4729762077331543,
"learning_rate": 1.5e-05,
"loss": 1.2334,
"step": 3
},
{
"epoch": 0.0008531968218418387,
"grad_norm": 0.48300838470458984,
"learning_rate": 2e-05,
"loss": 1.2363,
"step": 4
},
{
"epoch": 0.0010664960273022983,
"grad_norm": 0.46940040588378906,
"learning_rate": 2.5e-05,
"loss": 1.156,
"step": 5
},
{
"epoch": 0.0012797952327627579,
"grad_norm": 0.4578542709350586,
"learning_rate": 3e-05,
"loss": 1.2202,
"step": 6
},
{
"epoch": 0.0014930944382232176,
"grad_norm": 0.46893829107284546,
"learning_rate": 3.5e-05,
"loss": 1.3289,
"step": 7
},
{
"epoch": 0.0017063936436836774,
"grad_norm": 0.4128904938697815,
"learning_rate": 4e-05,
"loss": 1.331,
"step": 8
},
{
"epoch": 0.001919692849144137,
"grad_norm": 0.5264115929603577,
"learning_rate": 4.5e-05,
"loss": 1.2029,
"step": 9
},
{
"epoch": 0.0021329920546045967,
"grad_norm": 0.5400672554969788,
"learning_rate": 5e-05,
"loss": 1.244,
"step": 10
},
{
"epoch": 0.002346291260065056,
"grad_norm": 0.5268250703811646,
"learning_rate": 5.500000000000001e-05,
"loss": 1.3097,
"step": 11
},
{
"epoch": 0.0025595904655255157,
"grad_norm": 0.4096634089946747,
"learning_rate": 6e-05,
"loss": 1.1846,
"step": 12
},
{
"epoch": 0.0027728896709859757,
"grad_norm": 0.3764404058456421,
"learning_rate": 6.500000000000001e-05,
"loss": 1.0895,
"step": 13
},
{
"epoch": 0.0029861888764464353,
"grad_norm": 0.4485396146774292,
"learning_rate": 7e-05,
"loss": 1.1241,
"step": 14
},
{
"epoch": 0.003199488081906895,
"grad_norm": 0.3677101731300354,
"learning_rate": 7.500000000000001e-05,
"loss": 1.05,
"step": 15
},
{
"epoch": 0.0034127872873673548,
"grad_norm": 0.31273096799850464,
"learning_rate": 8e-05,
"loss": 1.0426,
"step": 16
},
{
"epoch": 0.0036260864928278143,
"grad_norm": 0.33157649636268616,
"learning_rate": 8.5e-05,
"loss": 1.072,
"step": 17
},
{
"epoch": 0.003839385698288274,
"grad_norm": 0.3081548810005188,
"learning_rate": 9e-05,
"loss": 1.1552,
"step": 18
},
{
"epoch": 0.004052684903748734,
"grad_norm": 0.30431386828422546,
"learning_rate": 9.5e-05,
"loss": 1.1341,
"step": 19
},
{
"epoch": 0.004265984109209193,
"grad_norm": 0.3565789461135864,
"learning_rate": 0.0001,
"loss": 1.2314,
"step": 20
},
{
"epoch": 0.004479283314669653,
"grad_norm": 0.30596891045570374,
"learning_rate": 9.999238475781957e-05,
"loss": 1.0621,
"step": 21
},
{
"epoch": 0.004692582520130112,
"grad_norm": 0.3264557719230652,
"learning_rate": 9.99695413509548e-05,
"loss": 1.0075,
"step": 22
},
{
"epoch": 0.004905881725590572,
"grad_norm": 0.2670353055000305,
"learning_rate": 9.99314767377287e-05,
"loss": 0.8905,
"step": 23
},
{
"epoch": 0.0051191809310510315,
"grad_norm": 0.35703352093696594,
"learning_rate": 9.987820251299122e-05,
"loss": 1.1189,
"step": 24
},
{
"epoch": 0.005332480136511492,
"grad_norm": 0.32691025733947754,
"learning_rate": 9.980973490458728e-05,
"loss": 0.9613,
"step": 25
},
{
"epoch": 0.0055457793419719514,
"grad_norm": 0.31508925557136536,
"learning_rate": 9.972609476841367e-05,
"loss": 1.0339,
"step": 26
},
{
"epoch": 0.005759078547432411,
"grad_norm": 0.2960086464881897,
"learning_rate": 9.962730758206611e-05,
"loss": 1.0747,
"step": 27
},
{
"epoch": 0.0059723777528928705,
"grad_norm": 0.3089136779308319,
"learning_rate": 9.951340343707852e-05,
"loss": 1.1023,
"step": 28
},
{
"epoch": 0.00618567695835333,
"grad_norm": 0.33887767791748047,
"learning_rate": 9.938441702975689e-05,
"loss": 1.075,
"step": 29
},
{
"epoch": 0.00639897616381379,
"grad_norm": 0.3024013042449951,
"learning_rate": 9.924038765061042e-05,
"loss": 1.0643,
"step": 30
},
{
"epoch": 0.006612275369274249,
"grad_norm": 0.26423823833465576,
"learning_rate": 9.908135917238321e-05,
"loss": 0.984,
"step": 31
},
{
"epoch": 0.0068255745747347095,
"grad_norm": 0.3321572542190552,
"learning_rate": 9.890738003669029e-05,
"loss": 0.9507,
"step": 32
},
{
"epoch": 0.007038873780195169,
"grad_norm": 0.33192047476768494,
"learning_rate": 9.871850323926177e-05,
"loss": 1.1432,
"step": 33
},
{
"epoch": 0.007252172985655629,
"grad_norm": 0.2856525778770447,
"learning_rate": 9.851478631379982e-05,
"loss": 0.9586,
"step": 34
},
{
"epoch": 0.007465472191116088,
"grad_norm": 0.3510894775390625,
"learning_rate": 9.829629131445342e-05,
"loss": 1.0734,
"step": 35
},
{
"epoch": 0.007678771396576548,
"grad_norm": 0.3441113531589508,
"learning_rate": 9.806308479691595e-05,
"loss": 1.1277,
"step": 36
},
{
"epoch": 0.007892070602037008,
"grad_norm": 0.33906152844429016,
"learning_rate": 9.781523779815179e-05,
"loss": 0.946,
"step": 37
},
{
"epoch": 0.008105369807497468,
"grad_norm": 0.2947957217693329,
"learning_rate": 9.755282581475769e-05,
"loss": 0.9868,
"step": 38
},
{
"epoch": 0.008318669012957927,
"grad_norm": 0.3095934987068176,
"learning_rate": 9.727592877996585e-05,
"loss": 1.1242,
"step": 39
},
{
"epoch": 0.008531968218418387,
"grad_norm": 0.29008540511131287,
"learning_rate": 9.698463103929542e-05,
"loss": 1.0002,
"step": 40
},
{
"epoch": 0.008745267423878846,
"grad_norm": 0.3008119761943817,
"learning_rate": 9.667902132486009e-05,
"loss": 0.9385,
"step": 41
},
{
"epoch": 0.008958566629339306,
"grad_norm": 0.3274795114994049,
"learning_rate": 9.635919272833938e-05,
"loss": 1.1308,
"step": 42
},
{
"epoch": 0.009171865834799765,
"grad_norm": 0.30111584067344666,
"learning_rate": 9.602524267262203e-05,
"loss": 0.8305,
"step": 43
},
{
"epoch": 0.009385165040260225,
"grad_norm": 0.32425105571746826,
"learning_rate": 9.567727288213005e-05,
"loss": 1.0669,
"step": 44
},
{
"epoch": 0.009598464245720684,
"grad_norm": 0.3228484094142914,
"learning_rate": 9.53153893518325e-05,
"loss": 1.0983,
"step": 45
},
{
"epoch": 0.009811763451181144,
"grad_norm": 0.31862518191337585,
"learning_rate": 9.493970231495835e-05,
"loss": 1.0798,
"step": 46
},
{
"epoch": 0.010025062656641603,
"grad_norm": 0.31603214144706726,
"learning_rate": 9.45503262094184e-05,
"loss": 1.0202,
"step": 47
},
{
"epoch": 0.010238361862102063,
"grad_norm": 0.34538108110427856,
"learning_rate": 9.414737964294636e-05,
"loss": 1.0098,
"step": 48
},
{
"epoch": 0.010451661067562523,
"grad_norm": 0.3631366491317749,
"learning_rate": 9.373098535696979e-05,
"loss": 1.0367,
"step": 49
},
{
"epoch": 0.010664960273022984,
"grad_norm": 0.47178760170936584,
"learning_rate": 9.330127018922194e-05,
"loss": 0.9188,
"step": 50
},
{
"epoch": 0.010664960273022984,
"eval_loss": 1.0061397552490234,
"eval_runtime": 195.5718,
"eval_samples_per_second": 40.374,
"eval_steps_per_second": 20.187,
"step": 50
},
{
"epoch": 0.010878259478483443,
"grad_norm": 0.6506192088127136,
"learning_rate": 9.285836503510562e-05,
"loss": 0.9548,
"step": 51
},
{
"epoch": 0.011091558683943903,
"grad_norm": 0.4420522451400757,
"learning_rate": 9.24024048078213e-05,
"loss": 1.0695,
"step": 52
},
{
"epoch": 0.011304857889404362,
"grad_norm": 0.4965808689594269,
"learning_rate": 9.193352839727121e-05,
"loss": 1.003,
"step": 53
},
{
"epoch": 0.011518157094864822,
"grad_norm": 0.3443991243839264,
"learning_rate": 9.145187862775209e-05,
"loss": 0.986,
"step": 54
},
{
"epoch": 0.011731456300325281,
"grad_norm": 0.3400571644306183,
"learning_rate": 9.09576022144496e-05,
"loss": 0.9614,
"step": 55
},
{
"epoch": 0.011944755505785741,
"grad_norm": 0.2666758596897125,
"learning_rate": 9.045084971874738e-05,
"loss": 0.9794,
"step": 56
},
{
"epoch": 0.0121580547112462,
"grad_norm": 0.25332409143447876,
"learning_rate": 8.993177550236464e-05,
"loss": 0.9875,
"step": 57
},
{
"epoch": 0.01237135391670666,
"grad_norm": 0.32057127356529236,
"learning_rate": 8.940053768033609e-05,
"loss": 1.065,
"step": 58
},
{
"epoch": 0.01258465312216712,
"grad_norm": 0.26575368642807007,
"learning_rate": 8.885729807284856e-05,
"loss": 1.0041,
"step": 59
},
{
"epoch": 0.01279795232762758,
"grad_norm": 0.3032527565956116,
"learning_rate": 8.83022221559489e-05,
"loss": 1.1914,
"step": 60
},
{
"epoch": 0.013011251533088039,
"grad_norm": 0.2899107336997986,
"learning_rate": 8.773547901113862e-05,
"loss": 1.0327,
"step": 61
},
{
"epoch": 0.013224550738548498,
"grad_norm": 0.32682493329048157,
"learning_rate": 8.715724127386972e-05,
"loss": 0.9508,
"step": 62
},
{
"epoch": 0.013437849944008958,
"grad_norm": 0.27625924348831177,
"learning_rate": 8.656768508095853e-05,
"loss": 0.9384,
"step": 63
},
{
"epoch": 0.013651149149469419,
"grad_norm": 0.3117460608482361,
"learning_rate": 8.596699001693255e-05,
"loss": 0.9831,
"step": 64
},
{
"epoch": 0.013864448354929879,
"grad_norm": 0.25224539637565613,
"learning_rate": 8.535533905932738e-05,
"loss": 1.0514,
"step": 65
},
{
"epoch": 0.014077747560390338,
"grad_norm": 0.27435991168022156,
"learning_rate": 8.473291852294987e-05,
"loss": 1.001,
"step": 66
},
{
"epoch": 0.014291046765850798,
"grad_norm": 0.2682814300060272,
"learning_rate": 8.409991800312493e-05,
"loss": 0.8872,
"step": 67
},
{
"epoch": 0.014504345971311257,
"grad_norm": 0.234930157661438,
"learning_rate": 8.345653031794292e-05,
"loss": 0.9487,
"step": 68
},
{
"epoch": 0.014717645176771717,
"grad_norm": 0.2471337616443634,
"learning_rate": 8.280295144952536e-05,
"loss": 0.9371,
"step": 69
},
{
"epoch": 0.014930944382232176,
"grad_norm": 0.24594557285308838,
"learning_rate": 8.213938048432697e-05,
"loss": 0.9335,
"step": 70
},
{
"epoch": 0.015144243587692636,
"grad_norm": 0.28513291478157043,
"learning_rate": 8.146601955249188e-05,
"loss": 0.9458,
"step": 71
},
{
"epoch": 0.015357542793153095,
"grad_norm": 0.2593214511871338,
"learning_rate": 8.07830737662829e-05,
"loss": 0.9347,
"step": 72
},
{
"epoch": 0.015570841998613555,
"grad_norm": 0.29922282695770264,
"learning_rate": 8.009075115760243e-05,
"loss": 1.1422,
"step": 73
},
{
"epoch": 0.015784141204074016,
"grad_norm": 0.23679997026920319,
"learning_rate": 7.938926261462366e-05,
"loss": 0.9634,
"step": 74
},
{
"epoch": 0.015997440409534474,
"grad_norm": 0.2807924747467041,
"learning_rate": 7.86788218175523e-05,
"loss": 0.8637,
"step": 75
},
{
"epoch": 0.016210739614994935,
"grad_norm": 0.27109989523887634,
"learning_rate": 7.795964517353735e-05,
"loss": 0.9623,
"step": 76
},
{
"epoch": 0.016424038820455393,
"grad_norm": 0.24362675845623016,
"learning_rate": 7.723195175075136e-05,
"loss": 0.9125,
"step": 77
},
{
"epoch": 0.016637338025915854,
"grad_norm": 0.2466438263654709,
"learning_rate": 7.649596321166024e-05,
"loss": 0.8541,
"step": 78
},
{
"epoch": 0.016850637231376312,
"grad_norm": 0.26747453212738037,
"learning_rate": 7.575190374550272e-05,
"loss": 0.9808,
"step": 79
},
{
"epoch": 0.017063936436836773,
"grad_norm": 0.30162152647972107,
"learning_rate": 7.500000000000001e-05,
"loss": 1.0652,
"step": 80
},
{
"epoch": 0.01727723564229723,
"grad_norm": 0.2805198132991791,
"learning_rate": 7.424048101231686e-05,
"loss": 0.9398,
"step": 81
},
{
"epoch": 0.017490534847757692,
"grad_norm": 0.24456410109996796,
"learning_rate": 7.347357813929454e-05,
"loss": 0.8937,
"step": 82
},
{
"epoch": 0.01770383405321815,
"grad_norm": 0.30062973499298096,
"learning_rate": 7.269952498697734e-05,
"loss": 0.9366,
"step": 83
},
{
"epoch": 0.01791713325867861,
"grad_norm": 0.29891955852508545,
"learning_rate": 7.191855733945387e-05,
"loss": 1.0465,
"step": 84
},
{
"epoch": 0.018130432464139073,
"grad_norm": 0.3127273619174957,
"learning_rate": 7.113091308703498e-05,
"loss": 1.032,
"step": 85
},
{
"epoch": 0.01834373166959953,
"grad_norm": 0.28285863995552063,
"learning_rate": 7.033683215379002e-05,
"loss": 0.9588,
"step": 86
},
{
"epoch": 0.018557030875059992,
"grad_norm": 0.290503591299057,
"learning_rate": 6.953655642446368e-05,
"loss": 0.9794,
"step": 87
},
{
"epoch": 0.01877033008052045,
"grad_norm": 0.2825004458427429,
"learning_rate": 6.873032967079561e-05,
"loss": 0.8743,
"step": 88
},
{
"epoch": 0.01898362928598091,
"grad_norm": 0.30106398463249207,
"learning_rate": 6.7918397477265e-05,
"loss": 1.0355,
"step": 89
},
{
"epoch": 0.01919692849144137,
"grad_norm": 0.30432212352752686,
"learning_rate": 6.710100716628344e-05,
"loss": 0.9656,
"step": 90
},
{
"epoch": 0.01941022769690183,
"grad_norm": 0.28930991888046265,
"learning_rate": 6.627840772285784e-05,
"loss": 0.8612,
"step": 91
},
{
"epoch": 0.019623526902362288,
"grad_norm": 0.2875548303127289,
"learning_rate": 6.545084971874738e-05,
"loss": 0.8079,
"step": 92
},
{
"epoch": 0.01983682610782275,
"grad_norm": 0.3163555860519409,
"learning_rate": 6.461858523613684e-05,
"loss": 0.9051,
"step": 93
},
{
"epoch": 0.020050125313283207,
"grad_norm": 0.3344813287258148,
"learning_rate": 6.378186779084995e-05,
"loss": 0.9722,
"step": 94
},
{
"epoch": 0.020263424518743668,
"grad_norm": 0.30937156081199646,
"learning_rate": 6.294095225512603e-05,
"loss": 1.0128,
"step": 95
},
{
"epoch": 0.020476723724204126,
"grad_norm": 0.2907969057559967,
"learning_rate": 6.209609477998338e-05,
"loss": 0.8346,
"step": 96
},
{
"epoch": 0.020690022929664587,
"grad_norm": 0.318782776594162,
"learning_rate": 6.124755271719325e-05,
"loss": 0.8988,
"step": 97
},
{
"epoch": 0.020903322135125045,
"grad_norm": 0.3549700081348419,
"learning_rate": 6.0395584540887963e-05,
"loss": 0.9299,
"step": 98
},
{
"epoch": 0.021116621340585506,
"grad_norm": 0.3160276710987091,
"learning_rate": 5.9540449768827246e-05,
"loss": 0.9525,
"step": 99
},
{
"epoch": 0.021329920546045968,
"grad_norm": 0.47316688299179077,
"learning_rate": 5.868240888334653e-05,
"loss": 0.9719,
"step": 100
},
{
"epoch": 0.021329920546045968,
"eval_loss": 0.9516631960868835,
"eval_runtime": 194.6219,
"eval_samples_per_second": 40.571,
"eval_steps_per_second": 20.285,
"step": 100
},
{
"epoch": 0.021543219751506425,
"grad_norm": 0.355265349149704,
"learning_rate": 5.782172325201155e-05,
"loss": 1.0614,
"step": 101
},
{
"epoch": 0.021756518956966887,
"grad_norm": 0.3831828534603119,
"learning_rate": 5.695865504800327e-05,
"loss": 0.9951,
"step": 102
},
{
"epoch": 0.021969818162427344,
"grad_norm": 0.3315833508968353,
"learning_rate": 5.6093467170257374e-05,
"loss": 0.9057,
"step": 103
},
{
"epoch": 0.022183117367887806,
"grad_norm": 0.2796443998813629,
"learning_rate": 5.522642316338268e-05,
"loss": 0.8379,
"step": 104
},
{
"epoch": 0.022396416573348264,
"grad_norm": 0.3008687496185303,
"learning_rate": 5.435778713738292e-05,
"loss": 0.9172,
"step": 105
},
{
"epoch": 0.022609715778808725,
"grad_norm": 0.23267973959445953,
"learning_rate": 5.348782368720626e-05,
"loss": 0.841,
"step": 106
},
{
"epoch": 0.022823014984269183,
"grad_norm": 0.2733173668384552,
"learning_rate": 5.26167978121472e-05,
"loss": 0.9093,
"step": 107
},
{
"epoch": 0.023036314189729644,
"grad_norm": 0.2535065710544586,
"learning_rate": 5.174497483512506e-05,
"loss": 0.9442,
"step": 108
},
{
"epoch": 0.0232496133951901,
"grad_norm": 0.2553474009037018,
"learning_rate": 5.0872620321864185e-05,
"loss": 1.0607,
"step": 109
},
{
"epoch": 0.023462912600650563,
"grad_norm": 0.2369348704814911,
"learning_rate": 5e-05,
"loss": 0.9073,
"step": 110
},
{
"epoch": 0.02367621180611102,
"grad_norm": 0.2561231851577759,
"learning_rate": 4.912737967813583e-05,
"loss": 1.0031,
"step": 111
},
{
"epoch": 0.023889511011571482,
"grad_norm": 0.2755792438983917,
"learning_rate": 4.825502516487497e-05,
"loss": 0.9531,
"step": 112
},
{
"epoch": 0.02410281021703194,
"grad_norm": 0.3029363751411438,
"learning_rate": 4.738320218785281e-05,
"loss": 0.9881,
"step": 113
},
{
"epoch": 0.0243161094224924,
"grad_norm": 0.27506956458091736,
"learning_rate": 4.6512176312793736e-05,
"loss": 0.9784,
"step": 114
},
{
"epoch": 0.024529408627952862,
"grad_norm": 0.30184289813041687,
"learning_rate": 4.564221286261709e-05,
"loss": 1.0044,
"step": 115
},
{
"epoch": 0.02474270783341332,
"grad_norm": 0.33883678913116455,
"learning_rate": 4.477357683661734e-05,
"loss": 1.0522,
"step": 116
},
{
"epoch": 0.02495600703887378,
"grad_norm": 0.30035409331321716,
"learning_rate": 4.390653282974264e-05,
"loss": 0.8848,
"step": 117
},
{
"epoch": 0.02516930624433424,
"grad_norm": 0.30106550455093384,
"learning_rate": 4.3041344951996746e-05,
"loss": 1.0947,
"step": 118
},
{
"epoch": 0.0253826054497947,
"grad_norm": 0.29889124631881714,
"learning_rate": 4.2178276747988446e-05,
"loss": 0.9041,
"step": 119
},
{
"epoch": 0.02559590465525516,
"grad_norm": 0.2549803555011749,
"learning_rate": 4.131759111665349e-05,
"loss": 0.9632,
"step": 120
},
{
"epoch": 0.02580920386071562,
"grad_norm": 0.27938392758369446,
"learning_rate": 4.045955023117276e-05,
"loss": 0.934,
"step": 121
},
{
"epoch": 0.026022503066176077,
"grad_norm": 0.2797248363494873,
"learning_rate": 3.960441545911204e-05,
"loss": 0.9475,
"step": 122
},
{
"epoch": 0.02623580227163654,
"grad_norm": 0.28871628642082214,
"learning_rate": 3.875244728280676e-05,
"loss": 0.972,
"step": 123
},
{
"epoch": 0.026449101477096996,
"grad_norm": 0.30452898144721985,
"learning_rate": 3.790390522001662e-05,
"loss": 0.8667,
"step": 124
},
{
"epoch": 0.026662400682557458,
"grad_norm": 0.2984020411968231,
"learning_rate": 3.705904774487396e-05,
"loss": 0.9119,
"step": 125
},
{
"epoch": 0.026875699888017916,
"grad_norm": 0.26833754777908325,
"learning_rate": 3.6218132209150045e-05,
"loss": 1.0051,
"step": 126
},
{
"epoch": 0.027088999093478377,
"grad_norm": 0.2745654284954071,
"learning_rate": 3.5381414763863166e-05,
"loss": 0.9698,
"step": 127
},
{
"epoch": 0.027302298298938838,
"grad_norm": 0.28041306138038635,
"learning_rate": 3.4549150281252636e-05,
"loss": 0.9021,
"step": 128
},
{
"epoch": 0.027515597504399296,
"grad_norm": 0.2919355034828186,
"learning_rate": 3.372159227714218e-05,
"loss": 1.0522,
"step": 129
},
{
"epoch": 0.027728896709859757,
"grad_norm": 0.27209892868995667,
"learning_rate": 3.289899283371657e-05,
"loss": 0.8706,
"step": 130
},
{
"epoch": 0.027942195915320215,
"grad_norm": 0.28089284896850586,
"learning_rate": 3.2081602522734986e-05,
"loss": 0.8929,
"step": 131
},
{
"epoch": 0.028155495120780676,
"grad_norm": 0.26712432503700256,
"learning_rate": 3.12696703292044e-05,
"loss": 0.9431,
"step": 132
},
{
"epoch": 0.028368794326241134,
"grad_norm": 0.3111507296562195,
"learning_rate": 3.046344357553632e-05,
"loss": 0.9279,
"step": 133
},
{
"epoch": 0.028582093531701595,
"grad_norm": 0.2614944279193878,
"learning_rate": 2.9663167846209998e-05,
"loss": 0.8773,
"step": 134
},
{
"epoch": 0.028795392737162053,
"grad_norm": 0.2566675543785095,
"learning_rate": 2.886908691296504e-05,
"loss": 0.8574,
"step": 135
},
{
"epoch": 0.029008691942622514,
"grad_norm": 0.26692256331443787,
"learning_rate": 2.8081442660546125e-05,
"loss": 0.8803,
"step": 136
},
{
"epoch": 0.029221991148082972,
"grad_norm": 0.30085262656211853,
"learning_rate": 2.7300475013022663e-05,
"loss": 0.8579,
"step": 137
},
{
"epoch": 0.029435290353543433,
"grad_norm": 0.3874056935310364,
"learning_rate": 2.6526421860705473e-05,
"loss": 0.8966,
"step": 138
},
{
"epoch": 0.02964858955900389,
"grad_norm": 0.3222864866256714,
"learning_rate": 2.575951898768315e-05,
"loss": 0.948,
"step": 139
},
{
"epoch": 0.029861888764464353,
"grad_norm": 0.2842833697795868,
"learning_rate": 2.500000000000001e-05,
"loss": 0.898,
"step": 140
},
{
"epoch": 0.03007518796992481,
"grad_norm": 0.31163346767425537,
"learning_rate": 2.4248096254497288e-05,
"loss": 1.0028,
"step": 141
},
{
"epoch": 0.03028848717538527,
"grad_norm": 0.33155760169029236,
"learning_rate": 2.350403678833976e-05,
"loss": 1.0265,
"step": 142
},
{
"epoch": 0.030501786380845733,
"grad_norm": 0.31235241889953613,
"learning_rate": 2.2768048249248648e-05,
"loss": 0.9573,
"step": 143
},
{
"epoch": 0.03071508558630619,
"grad_norm": 0.33971816301345825,
"learning_rate": 2.2040354826462668e-05,
"loss": 1.0178,
"step": 144
},
{
"epoch": 0.030928384791766652,
"grad_norm": 0.3050580322742462,
"learning_rate": 2.132117818244771e-05,
"loss": 0.8363,
"step": 145
},
{
"epoch": 0.03114168399722711,
"grad_norm": 0.3527008593082428,
"learning_rate": 2.061073738537635e-05,
"loss": 0.9609,
"step": 146
},
{
"epoch": 0.03135498320268757,
"grad_norm": 0.38827890157699585,
"learning_rate": 1.9909248842397584e-05,
"loss": 1.0968,
"step": 147
},
{
"epoch": 0.03156828240814803,
"grad_norm": 0.3300125300884247,
"learning_rate": 1.9216926233717085e-05,
"loss": 0.8794,
"step": 148
},
{
"epoch": 0.03178158161360849,
"grad_norm": 0.3898104429244995,
"learning_rate": 1.8533980447508137e-05,
"loss": 0.7935,
"step": 149
},
{
"epoch": 0.03199488081906895,
"grad_norm": 0.43341726064682007,
"learning_rate": 1.7860619515673033e-05,
"loss": 0.8853,
"step": 150
},
{
"epoch": 0.03199488081906895,
"eval_loss": 0.9324145913124084,
"eval_runtime": 194.6807,
"eval_samples_per_second": 40.559,
"eval_steps_per_second": 20.279,
"step": 150
},
{
"epoch": 0.03220818002452941,
"grad_norm": 0.3090205192565918,
"learning_rate": 1.7197048550474643e-05,
"loss": 0.9487,
"step": 151
},
{
"epoch": 0.03242147922998987,
"grad_norm": 0.2869451344013214,
"learning_rate": 1.6543469682057106e-05,
"loss": 0.8774,
"step": 152
},
{
"epoch": 0.032634778435450325,
"grad_norm": 0.2702740430831909,
"learning_rate": 1.5900081996875083e-05,
"loss": 0.904,
"step": 153
},
{
"epoch": 0.032848077640910786,
"grad_norm": 0.28590455651283264,
"learning_rate": 1.526708147705013e-05,
"loss": 0.847,
"step": 154
},
{
"epoch": 0.03306137684637125,
"grad_norm": 0.3107563853263855,
"learning_rate": 1.4644660940672627e-05,
"loss": 0.9352,
"step": 155
},
{
"epoch": 0.03327467605183171,
"grad_norm": 0.27143728733062744,
"learning_rate": 1.4033009983067452e-05,
"loss": 0.9133,
"step": 156
},
{
"epoch": 0.03348797525729217,
"grad_norm": 0.3370876610279083,
"learning_rate": 1.3432314919041478e-05,
"loss": 0.9738,
"step": 157
},
{
"epoch": 0.033701274462752624,
"grad_norm": 0.28119489550590515,
"learning_rate": 1.2842758726130283e-05,
"loss": 0.9446,
"step": 158
},
{
"epoch": 0.033914573668213085,
"grad_norm": 0.28721117973327637,
"learning_rate": 1.22645209888614e-05,
"loss": 0.8338,
"step": 159
},
{
"epoch": 0.03412787287367355,
"grad_norm": 0.27180376648902893,
"learning_rate": 1.1697777844051105e-05,
"loss": 0.8711,
"step": 160
},
{
"epoch": 0.03434117207913401,
"grad_norm": 0.2990672290325165,
"learning_rate": 1.1142701927151456e-05,
"loss": 0.8987,
"step": 161
},
{
"epoch": 0.03455447128459446,
"grad_norm": 0.2657076120376587,
"learning_rate": 1.0599462319663905e-05,
"loss": 0.835,
"step": 162
},
{
"epoch": 0.034767770490054924,
"grad_norm": 0.2753151059150696,
"learning_rate": 1.006822449763537e-05,
"loss": 0.8787,
"step": 163
},
{
"epoch": 0.034981069695515385,
"grad_norm": 0.24264605343341827,
"learning_rate": 9.549150281252633e-06,
"loss": 0.8039,
"step": 164
},
{
"epoch": 0.035194368900975846,
"grad_norm": 0.2836618721485138,
"learning_rate": 9.042397785550405e-06,
"loss": 0.9646,
"step": 165
},
{
"epoch": 0.0354076681064363,
"grad_norm": 0.2683239281177521,
"learning_rate": 8.548121372247918e-06,
"loss": 0.8385,
"step": 166
},
{
"epoch": 0.03562096731189676,
"grad_norm": 0.3092481791973114,
"learning_rate": 8.066471602728803e-06,
"loss": 1.0863,
"step": 167
},
{
"epoch": 0.03583426651735722,
"grad_norm": 0.2643248438835144,
"learning_rate": 7.597595192178702e-06,
"loss": 1.0088,
"step": 168
},
{
"epoch": 0.036047565722817684,
"grad_norm": 0.26527926325798035,
"learning_rate": 7.1416349648943894e-06,
"loss": 0.8617,
"step": 169
},
{
"epoch": 0.036260864928278146,
"grad_norm": 0.2804737687110901,
"learning_rate": 6.698729810778065e-06,
"loss": 0.9505,
"step": 170
},
{
"epoch": 0.0364741641337386,
"grad_norm": 0.2629363238811493,
"learning_rate": 6.269014643030213e-06,
"loss": 0.863,
"step": 171
},
{
"epoch": 0.03668746333919906,
"grad_norm": 0.259554386138916,
"learning_rate": 5.852620357053651e-06,
"loss": 0.9012,
"step": 172
},
{
"epoch": 0.03690076254465952,
"grad_norm": 0.26305103302001953,
"learning_rate": 5.449673790581611e-06,
"loss": 0.8577,
"step": 173
},
{
"epoch": 0.037114061750119984,
"grad_norm": 0.25721949338912964,
"learning_rate": 5.060297685041659e-06,
"loss": 0.7926,
"step": 174
},
{
"epoch": 0.03732736095558044,
"grad_norm": 0.2769482135772705,
"learning_rate": 4.684610648167503e-06,
"loss": 1.0422,
"step": 175
},
{
"epoch": 0.0375406601610409,
"grad_norm": 0.25869259238243103,
"learning_rate": 4.322727117869951e-06,
"loss": 0.8076,
"step": 176
},
{
"epoch": 0.03775395936650136,
"grad_norm": 0.2649659514427185,
"learning_rate": 3.974757327377981e-06,
"loss": 1.0166,
"step": 177
},
{
"epoch": 0.03796725857196182,
"grad_norm": 0.3241524398326874,
"learning_rate": 3.6408072716606346e-06,
"loss": 0.8947,
"step": 178
},
{
"epoch": 0.038180557777422276,
"grad_norm": 0.294283926486969,
"learning_rate": 3.3209786751399187e-06,
"loss": 0.9898,
"step": 179
},
{
"epoch": 0.03839385698288274,
"grad_norm": 0.2929731607437134,
"learning_rate": 3.0153689607045845e-06,
"loss": 0.9818,
"step": 180
},
{
"epoch": 0.0386071561883432,
"grad_norm": 0.296636700630188,
"learning_rate": 2.724071220034158e-06,
"loss": 0.9857,
"step": 181
},
{
"epoch": 0.03882045539380366,
"grad_norm": 0.30064740777015686,
"learning_rate": 2.4471741852423237e-06,
"loss": 1.0286,
"step": 182
},
{
"epoch": 0.039033754599264114,
"grad_norm": 0.3110153079032898,
"learning_rate": 2.1847622018482283e-06,
"loss": 0.9406,
"step": 183
},
{
"epoch": 0.039247053804724576,
"grad_norm": 0.27653342485427856,
"learning_rate": 1.9369152030840556e-06,
"loss": 0.7909,
"step": 184
},
{
"epoch": 0.03946035301018504,
"grad_norm": 0.30750012397766113,
"learning_rate": 1.70370868554659e-06,
"loss": 1.0222,
"step": 185
},
{
"epoch": 0.0396736522156455,
"grad_norm": 0.30614930391311646,
"learning_rate": 1.4852136862001764e-06,
"loss": 0.9453,
"step": 186
},
{
"epoch": 0.03988695142110596,
"grad_norm": 0.30748337507247925,
"learning_rate": 1.2814967607382432e-06,
"loss": 0.9321,
"step": 187
},
{
"epoch": 0.040100250626566414,
"grad_norm": 0.29685619473457336,
"learning_rate": 1.0926199633097157e-06,
"loss": 1.0097,
"step": 188
},
{
"epoch": 0.040313549832026875,
"grad_norm": 0.28955867886543274,
"learning_rate": 9.186408276168013e-07,
"loss": 0.8718,
"step": 189
},
{
"epoch": 0.040526849037487336,
"grad_norm": 0.32059964537620544,
"learning_rate": 7.596123493895991e-07,
"loss": 1.1336,
"step": 190
},
{
"epoch": 0.0407401482429478,
"grad_norm": 0.2944739758968353,
"learning_rate": 6.15582970243117e-07,
"loss": 0.8502,
"step": 191
},
{
"epoch": 0.04095344744840825,
"grad_norm": 0.29552388191223145,
"learning_rate": 4.865965629214819e-07,
"loss": 0.924,
"step": 192
},
{
"epoch": 0.04116674665386871,
"grad_norm": 0.33115655183792114,
"learning_rate": 3.7269241793390085e-07,
"loss": 1.0864,
"step": 193
},
{
"epoch": 0.041380045859329175,
"grad_norm": 0.3240742087364197,
"learning_rate": 2.7390523158633554e-07,
"loss": 0.8503,
"step": 194
},
{
"epoch": 0.041593345064789636,
"grad_norm": 0.3207777738571167,
"learning_rate": 1.9026509541272275e-07,
"loss": 0.9338,
"step": 195
},
{
"epoch": 0.04180664427025009,
"grad_norm": 0.3911765515804291,
"learning_rate": 1.2179748700879012e-07,
"loss": 0.9379,
"step": 196
},
{
"epoch": 0.04201994347571055,
"grad_norm": 0.40316149592399597,
"learning_rate": 6.852326227130834e-08,
"loss": 1.0956,
"step": 197
},
{
"epoch": 0.04223324268117101,
"grad_norm": 0.3598689138889313,
"learning_rate": 3.04586490452119e-08,
"loss": 0.9025,
"step": 198
},
{
"epoch": 0.042446541886631474,
"grad_norm": 0.4109581410884857,
"learning_rate": 7.615242180436522e-09,
"loss": 0.9733,
"step": 199
},
{
"epoch": 0.042659841092091935,
"grad_norm": 0.6376791596412659,
"learning_rate": 0.0,
"loss": 0.933,
"step": 200
},
{
"epoch": 0.042659841092091935,
"eval_loss": 0.9295676946640015,
"eval_runtime": 196.2203,
"eval_samples_per_second": 40.24,
"eval_steps_per_second": 20.12,
"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": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 5006156491653120.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}