Files
armv8-o2-full-qwen-epoch1-AMD/checkpoint-2000/trainer_state.json
ModelHub XC e52770167e 初始化项目,由ModelHub XC社区提供模型
Model: adpretko/armv8-o2-full-qwen-epoch1-AMD
Source: Original Platform
2026-09-20 08:52:18 +08:00

1435 lines
35 KiB
JSON

{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9793120332966091,
"eval_steps": 500,
"global_step": 2000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0048965601664830456,
"grad_norm": 6.383250713348389,
"learning_rate": 8.780487804878049e-07,
"loss": 0.8106,
"step": 10
},
{
"epoch": 0.009793120332966091,
"grad_norm": 3.3995654582977295,
"learning_rate": 1.853658536585366e-06,
"loss": 0.7096,
"step": 20
},
{
"epoch": 0.014689680499449137,
"grad_norm": 1.785426378250122,
"learning_rate": 2.8292682926829266e-06,
"loss": 0.4537,
"step": 30
},
{
"epoch": 0.019586240665932182,
"grad_norm": 0.8869879841804504,
"learning_rate": 3.804878048780488e-06,
"loss": 0.2479,
"step": 40
},
{
"epoch": 0.02448280083241523,
"grad_norm": 0.470714271068573,
"learning_rate": 4.780487804878049e-06,
"loss": 0.1631,
"step": 50
},
{
"epoch": 0.029379360998898273,
"grad_norm": 0.29301097989082336,
"learning_rate": 5.7560975609756095e-06,
"loss": 0.126,
"step": 60
},
{
"epoch": 0.03427592116538132,
"grad_norm": 0.21835149824619293,
"learning_rate": 6.731707317073171e-06,
"loss": 0.1057,
"step": 70
},
{
"epoch": 0.039172481331864364,
"grad_norm": 0.24420903623104095,
"learning_rate": 7.707317073170732e-06,
"loss": 0.0903,
"step": 80
},
{
"epoch": 0.04406904149834741,
"grad_norm": 0.2334676831960678,
"learning_rate": 8.682926829268294e-06,
"loss": 0.0817,
"step": 90
},
{
"epoch": 0.04896560166483046,
"grad_norm": 0.20716902613639832,
"learning_rate": 9.658536585365855e-06,
"loss": 0.0748,
"step": 100
},
{
"epoch": 0.0538621618313135,
"grad_norm": 0.226122185587883,
"learning_rate": 1.0634146341463416e-05,
"loss": 0.0681,
"step": 110
},
{
"epoch": 0.05875872199779655,
"grad_norm": 0.22283057868480682,
"learning_rate": 1.1609756097560975e-05,
"loss": 0.0657,
"step": 120
},
{
"epoch": 0.0636552821642796,
"grad_norm": 0.20474107563495636,
"learning_rate": 1.2585365853658538e-05,
"loss": 0.0622,
"step": 130
},
{
"epoch": 0.06855184233076264,
"grad_norm": 0.24621577560901642,
"learning_rate": 1.3560975609756099e-05,
"loss": 0.0557,
"step": 140
},
{
"epoch": 0.07344840249724569,
"grad_norm": 0.49712473154067993,
"learning_rate": 1.4536585365853658e-05,
"loss": 0.0564,
"step": 150
},
{
"epoch": 0.07834496266372873,
"grad_norm": 0.24351441860198975,
"learning_rate": 1.551219512195122e-05,
"loss": 0.0614,
"step": 160
},
{
"epoch": 0.08324152283021177,
"grad_norm": 0.2458556741476059,
"learning_rate": 1.6487804878048782e-05,
"loss": 0.0527,
"step": 170
},
{
"epoch": 0.08813808299669482,
"grad_norm": 0.2893470823764801,
"learning_rate": 1.7463414634146342e-05,
"loss": 0.0505,
"step": 180
},
{
"epoch": 0.09303464316317787,
"grad_norm": 0.23106378316879272,
"learning_rate": 1.8439024390243905e-05,
"loss": 0.048,
"step": 190
},
{
"epoch": 0.09793120332966092,
"grad_norm": 0.19553372263908386,
"learning_rate": 1.9414634146341464e-05,
"loss": 0.0467,
"step": 200
},
{
"epoch": 0.10282776349614396,
"grad_norm": 0.1637805849313736,
"learning_rate": 1.9999766279381703e-05,
"loss": 0.0434,
"step": 210
},
{
"epoch": 0.107724323662627,
"grad_norm": 0.2260979861021042,
"learning_rate": 1.999713704789179e-05,
"loss": 0.0444,
"step": 220
},
{
"epoch": 0.11262088382911005,
"grad_norm": 0.17891009151935577,
"learning_rate": 1.9991587204815973e-05,
"loss": 0.0428,
"step": 230
},
{
"epoch": 0.1175174439955931,
"grad_norm": 0.1792241483926773,
"learning_rate": 1.9983118371512026e-05,
"loss": 0.0422,
"step": 240
},
{
"epoch": 0.12241400416207614,
"grad_norm": 0.21294087171554565,
"learning_rate": 1.997173302210555e-05,
"loss": 0.0406,
"step": 250
},
{
"epoch": 0.1273105643285592,
"grad_norm": 0.18142680823802948,
"learning_rate": 1.9957434482767153e-05,
"loss": 0.0403,
"step": 260
},
{
"epoch": 0.13220712449504224,
"grad_norm": 0.1625054031610489,
"learning_rate": 1.994022693074072e-05,
"loss": 0.04,
"step": 270
},
{
"epoch": 0.13710368466152528,
"grad_norm": 0.13797277212142944,
"learning_rate": 1.9920115393123075e-05,
"loss": 0.0384,
"step": 280
},
{
"epoch": 0.14200024482800833,
"grad_norm": 0.1518547087907791,
"learning_rate": 1.9897105745395312e-05,
"loss": 0.0386,
"step": 290
},
{
"epoch": 0.14689680499449137,
"grad_norm": 0.15719467401504517,
"learning_rate": 1.9871204709706326e-05,
"loss": 0.038,
"step": 300
},
{
"epoch": 0.15179336516097441,
"grad_norm": 0.14285016059875488,
"learning_rate": 1.9842419852908957e-05,
"loss": 0.0361,
"step": 310
},
{
"epoch": 0.15668992532745746,
"grad_norm": 0.17457254230976105,
"learning_rate": 1.9810759584349394e-05,
"loss": 0.0373,
"step": 320
},
{
"epoch": 0.1615864854939405,
"grad_norm": 0.1794549822807312,
"learning_rate": 1.9776233153410402e-05,
"loss": 0.0348,
"step": 330
},
{
"epoch": 0.16648304566042355,
"grad_norm": 0.1884181797504425,
"learning_rate": 1.9738850646809187e-05,
"loss": 0.0352,
"step": 340
},
{
"epoch": 0.1713796058269066,
"grad_norm": 0.152182936668396,
"learning_rate": 1.9698622985650595e-05,
"loss": 0.0355,
"step": 350
},
{
"epoch": 0.17627616599338963,
"grad_norm": 0.1398647427558899,
"learning_rate": 1.965556192223658e-05,
"loss": 0.0339,
"step": 360
},
{
"epoch": 0.18117272615987268,
"grad_norm": 0.1632954180240631,
"learning_rate": 1.9609680036632825e-05,
"loss": 0.0334,
"step": 370
},
{
"epoch": 0.18606928632635575,
"grad_norm": 0.13727767765522003,
"learning_rate": 1.9560990732993544e-05,
"loss": 0.0341,
"step": 380
},
{
"epoch": 0.1909658464928388,
"grad_norm": 0.14081917703151703,
"learning_rate": 1.9509508235645523e-05,
"loss": 0.0328,
"step": 390
},
{
"epoch": 0.19586240665932184,
"grad_norm": 0.14375124871730804,
"learning_rate": 1.945524758493257e-05,
"loss": 0.0329,
"step": 400
},
{
"epoch": 0.20075896682580488,
"grad_norm": 0.1366111934185028,
"learning_rate": 1.9398224632821533e-05,
"loss": 0.0319,
"step": 410
},
{
"epoch": 0.20565552699228792,
"grad_norm": 0.15036387741565704,
"learning_rate": 1.933845603827125e-05,
"loss": 0.0314,
"step": 420
},
{
"epoch": 0.21055208715877097,
"grad_norm": 0.14054791629314423,
"learning_rate": 1.9275959262365726e-05,
"loss": 0.0321,
"step": 430
},
{
"epoch": 0.215448647325254,
"grad_norm": 0.13310673832893372,
"learning_rate": 1.9210752563212943e-05,
"loss": 0.0307,
"step": 440
},
{
"epoch": 0.22034520749173706,
"grad_norm": 0.13355876505374908,
"learning_rate": 1.914285499061087e-05,
"loss": 0.0312,
"step": 450
},
{
"epoch": 0.2252417676582201,
"grad_norm": 0.1345948874950409,
"learning_rate": 1.907228638048216e-05,
"loss": 0.0315,
"step": 460
},
{
"epoch": 0.23013832782470314,
"grad_norm": 0.12103156745433807,
"learning_rate": 1.8999067349079176e-05,
"loss": 0.0299,
"step": 470
},
{
"epoch": 0.2350348879911862,
"grad_norm": 0.11836036294698715,
"learning_rate": 1.8923219286961082e-05,
"loss": 0.0307,
"step": 480
},
{
"epoch": 0.23993144815766923,
"grad_norm": 0.11383108049631119,
"learning_rate": 1.8844764352744676e-05,
"loss": 0.0303,
"step": 490
},
{
"epoch": 0.24482800832415227,
"grad_norm": 0.12652988731861115,
"learning_rate": 1.8763725466630887e-05,
"loss": 0.0301,
"step": 500
},
{
"epoch": 0.24972456849063532,
"grad_norm": 0.12377447634935379,
"learning_rate": 1.8680126303708754e-05,
"loss": 0.0286,
"step": 510
},
{
"epoch": 0.2546211286571184,
"grad_norm": 0.126932293176651,
"learning_rate": 1.8593991287038863e-05,
"loss": 0.0291,
"step": 520
},
{
"epoch": 0.25951768882360143,
"grad_norm": 0.12359266728162766,
"learning_rate": 1.8505345580518273e-05,
"loss": 0.031,
"step": 530
},
{
"epoch": 0.2644142489900845,
"grad_norm": 0.13360409438610077,
"learning_rate": 1.8414215081529037e-05,
"loss": 0.0286,
"step": 540
},
{
"epoch": 0.2693108091565675,
"grad_norm": 0.15316234529018402,
"learning_rate": 1.8320626413372397e-05,
"loss": 0.0285,
"step": 550
},
{
"epoch": 0.27420736932305056,
"grad_norm": 0.12463656812906265,
"learning_rate": 1.8224606917490925e-05,
"loss": 0.0295,
"step": 560
},
{
"epoch": 0.2791039294895336,
"grad_norm": 0.12367699295282364,
"learning_rate": 1.8126184645480877e-05,
"loss": 0.0284,
"step": 570
},
{
"epoch": 0.28400048965601665,
"grad_norm": 0.11267518252134323,
"learning_rate": 1.802538835089705e-05,
"loss": 0.0287,
"step": 580
},
{
"epoch": 0.2888970498224997,
"grad_norm": 0.10819130390882492,
"learning_rate": 1.7922247480852596e-05,
"loss": 0.0276,
"step": 590
},
{
"epoch": 0.29379360998898274,
"grad_norm": 0.13291765749454498,
"learning_rate": 1.781679216741618e-05,
"loss": 0.0284,
"step": 600
},
{
"epoch": 0.2986901701554658,
"grad_norm": 0.14306820929050446,
"learning_rate": 1.7709053218809065e-05,
"loss": 0.0275,
"step": 610
},
{
"epoch": 0.30358673032194883,
"grad_norm": 0.12088426947593689,
"learning_rate": 1.7599062110404665e-05,
"loss": 0.0276,
"step": 620
},
{
"epoch": 0.30848329048843187,
"grad_norm": 0.11670047789812088,
"learning_rate": 1.7486850975533148e-05,
"loss": 0.0283,
"step": 630
},
{
"epoch": 0.3133798506549149,
"grad_norm": 0.10697685927152634,
"learning_rate": 1.7372452596093875e-05,
"loss": 0.0273,
"step": 640
},
{
"epoch": 0.31827641082139796,
"grad_norm": 0.10840044170618057,
"learning_rate": 1.7255900392978326e-05,
"loss": 0.0275,
"step": 650
},
{
"epoch": 0.323172970987881,
"grad_norm": 0.10406330227851868,
"learning_rate": 1.7137228416306362e-05,
"loss": 0.0253,
"step": 660
},
{
"epoch": 0.32806953115436405,
"grad_norm": 0.1260177046060562,
"learning_rate": 1.701647133547867e-05,
"loss": 0.0265,
"step": 670
},
{
"epoch": 0.3329660913208471,
"grad_norm": 0.11356191337108612,
"learning_rate": 1.6893664429048265e-05,
"loss": 0.0261,
"step": 680
},
{
"epoch": 0.33786265148733013,
"grad_norm": 0.11121688783168793,
"learning_rate": 1.6768843574414047e-05,
"loss": 0.0264,
"step": 690
},
{
"epoch": 0.3427592116538132,
"grad_norm": 0.10894258320331573,
"learning_rate": 1.6642045237339412e-05,
"loss": 0.0263,
"step": 700
},
{
"epoch": 0.3476557718202962,
"grad_norm": 0.10510087013244629,
"learning_rate": 1.6513306461298964e-05,
"loss": 0.0248,
"step": 710
},
{
"epoch": 0.35255233198677927,
"grad_norm": 0.12031841278076172,
"learning_rate": 1.6382664856656454e-05,
"loss": 0.0257,
"step": 720
},
{
"epoch": 0.3574488921532623,
"grad_norm": 0.09680049121379852,
"learning_rate": 1.625015858967711e-05,
"loss": 0.0256,
"step": 730
},
{
"epoch": 0.36234545231974535,
"grad_norm": 0.11472257226705551,
"learning_rate": 1.6115826371377578e-05,
"loss": 0.0254,
"step": 740
},
{
"epoch": 0.3672420124862284,
"grad_norm": 0.1562274843454361,
"learning_rate": 1.5979707446216653e-05,
"loss": 0.0266,
"step": 750
},
{
"epoch": 0.3721385726527115,
"grad_norm": 0.10354311019182205,
"learning_rate": 1.5841841580630277e-05,
"loss": 0.0254,
"step": 760
},
{
"epoch": 0.37703513281919454,
"grad_norm": 0.10595281422138214,
"learning_rate": 1.5702269051413933e-05,
"loss": 0.0255,
"step": 770
},
{
"epoch": 0.3819316929856776,
"grad_norm": 0.10392176359891891,
"learning_rate": 1.5561030633956007e-05,
"loss": 0.0252,
"step": 780
},
{
"epoch": 0.38682825315216063,
"grad_norm": 0.10846757888793945,
"learning_rate": 1.5418167590325478e-05,
"loss": 0.0252,
"step": 790
},
{
"epoch": 0.39172481331864367,
"grad_norm": 0.11040454357862473,
"learning_rate": 1.52737216572174e-05,
"loss": 0.0251,
"step": 800
},
{
"epoch": 0.3966213734851267,
"grad_norm": 0.1029830053448677,
"learning_rate": 1.5127735033759758e-05,
"loss": 0.0258,
"step": 810
},
{
"epoch": 0.40151793365160976,
"grad_norm": 0.09572988003492355,
"learning_rate": 1.4980250369185213e-05,
"loss": 0.0249,
"step": 820
},
{
"epoch": 0.4064144938180928,
"grad_norm": 0.09946920722723007,
"learning_rate": 1.4831310750371342e-05,
"loss": 0.0253,
"step": 830
},
{
"epoch": 0.41131105398457585,
"grad_norm": 0.109929658472538,
"learning_rate": 1.4680959689253032e-05,
"loss": 0.0239,
"step": 840
},
{
"epoch": 0.4162076141510589,
"grad_norm": 0.0906352773308754,
"learning_rate": 1.4529241110110694e-05,
"loss": 0.0247,
"step": 850
},
{
"epoch": 0.42110417431754193,
"grad_norm": 0.08638842403888702,
"learning_rate": 1.437619933673803e-05,
"loss": 0.0232,
"step": 860
},
{
"epoch": 0.426000734484025,
"grad_norm": 0.09401821345090866,
"learning_rate": 1.4221879079493044e-05,
"loss": 0.025,
"step": 870
},
{
"epoch": 0.430897294650508,
"grad_norm": 0.10134172439575195,
"learning_rate": 1.4066325422236154e-05,
"loss": 0.0248,
"step": 880
},
{
"epoch": 0.43579385481699107,
"grad_norm": 0.08755648881196976,
"learning_rate": 1.3909583809159175e-05,
"loss": 0.0245,
"step": 890
},
{
"epoch": 0.4406904149834741,
"grad_norm": 0.102289579808712,
"learning_rate": 1.3751700031509037e-05,
"loss": 0.0234,
"step": 900
},
{
"epoch": 0.44558697514995715,
"grad_norm": 0.10510256141424179,
"learning_rate": 1.3592720214210107e-05,
"loss": 0.0242,
"step": 910
},
{
"epoch": 0.4504835353164402,
"grad_norm": 0.09114789217710495,
"learning_rate": 1.3432690802389038e-05,
"loss": 0.0237,
"step": 920
},
{
"epoch": 0.45538009548292324,
"grad_norm": 0.09517126530408859,
"learning_rate": 1.3271658547806059e-05,
"loss": 0.0234,
"step": 930
},
{
"epoch": 0.4602766556494063,
"grad_norm": 0.09465792030096054,
"learning_rate": 1.3109670495196693e-05,
"loss": 0.024,
"step": 940
},
{
"epoch": 0.46517321581588933,
"grad_norm": 0.09391965717077255,
"learning_rate": 1.2946773968527893e-05,
"loss": 0.0223,
"step": 950
},
{
"epoch": 0.4700697759823724,
"grad_norm": 0.09540935605764389,
"learning_rate": 1.2783016557172574e-05,
"loss": 0.0229,
"step": 960
},
{
"epoch": 0.4749663361488554,
"grad_norm": 0.09557565301656723,
"learning_rate": 1.2618446102006643e-05,
"loss": 0.0237,
"step": 970
},
{
"epoch": 0.47986289631533846,
"grad_norm": 0.09849447757005692,
"learning_rate": 1.2453110681432516e-05,
"loss": 0.0236,
"step": 980
},
{
"epoch": 0.4847594564818215,
"grad_norm": 0.10435578972101212,
"learning_rate": 1.2287058597333286e-05,
"loss": 0.0233,
"step": 990
},
{
"epoch": 0.48965601664830455,
"grad_norm": 0.10057486593723297,
"learning_rate": 1.2120338360961553e-05,
"loss": 0.0236,
"step": 1000
},
{
"epoch": 0.4945525768147876,
"grad_norm": 0.0885319784283638,
"learning_rate": 1.1952998678767145e-05,
"loss": 0.0221,
"step": 1010
},
{
"epoch": 0.49944913698127064,
"grad_norm": 0.09798266738653183,
"learning_rate": 1.1785088438167747e-05,
"loss": 0.0234,
"step": 1020
},
{
"epoch": 0.5043456971477537,
"grad_norm": 0.09901165962219238,
"learning_rate": 1.1616656693266728e-05,
"loss": 0.0234,
"step": 1030
},
{
"epoch": 0.5092422573142368,
"grad_norm": 0.09118998050689697,
"learning_rate": 1.1447752650522218e-05,
"loss": 0.0219,
"step": 1040
},
{
"epoch": 0.5141388174807198,
"grad_norm": 0.09011399745941162,
"learning_rate": 1.1278425654371707e-05,
"loss": 0.0232,
"step": 1050
},
{
"epoch": 0.5190353776472029,
"grad_norm": 0.09064587205648422,
"learning_rate": 1.1108725172816328e-05,
"loss": 0.0216,
"step": 1060
},
{
"epoch": 0.5239319378136859,
"grad_norm": 0.10561744123697281,
"learning_rate": 1.0938700782969022e-05,
"loss": 0.0228,
"step": 1070
},
{
"epoch": 0.528828497980169,
"grad_norm": 0.10432001203298569,
"learning_rate": 1.0768402156570861e-05,
"loss": 0.0218,
"step": 1080
},
{
"epoch": 0.5337250581466519,
"grad_norm": 0.1011541560292244,
"learning_rate": 1.0597879045479698e-05,
"loss": 0.0238,
"step": 1090
},
{
"epoch": 0.538621618313135,
"grad_norm": 0.1057533547282219,
"learning_rate": 1.0427181267135415e-05,
"loss": 0.0217,
"step": 1100
},
{
"epoch": 0.543518178479618,
"grad_norm": 0.08704596757888794,
"learning_rate": 1.025635869000603e-05,
"loss": 0.0216,
"step": 1110
},
{
"epoch": 0.5484147386461011,
"grad_norm": 0.10060853511095047,
"learning_rate": 1.0085461219018873e-05,
"loss": 0.0215,
"step": 1120
},
{
"epoch": 0.5533112988125841,
"grad_norm": 0.09965676814317703,
"learning_rate": 9.914538780981129e-06,
"loss": 0.0229,
"step": 1130
},
{
"epoch": 0.5582078589790672,
"grad_norm": 0.08902792632579803,
"learning_rate": 9.74364130999397e-06,
"loss": 0.0208,
"step": 1140
},
{
"epoch": 0.5631044191455502,
"grad_norm": 0.08035479485988617,
"learning_rate": 9.572818732864587e-06,
"loss": 0.0226,
"step": 1150
},
{
"epoch": 0.5680009793120333,
"grad_norm": 0.09304884076118469,
"learning_rate": 9.402120954520304e-06,
"loss": 0.0225,
"step": 1160
},
{
"epoch": 0.5728975394785163,
"grad_norm": 0.11040584743022919,
"learning_rate": 9.23159784342914e-06,
"loss": 0.0219,
"step": 1170
},
{
"epoch": 0.5777940996449994,
"grad_norm": 0.08557133376598358,
"learning_rate": 9.061299217030981e-06,
"loss": 0.0223,
"step": 1180
},
{
"epoch": 0.5826906598114824,
"grad_norm": 0.08016768842935562,
"learning_rate": 8.891274827183678e-06,
"loss": 0.0216,
"step": 1190
},
{
"epoch": 0.5875872199779655,
"grad_norm": 0.08237303793430328,
"learning_rate": 8.721574345628296e-06,
"loss": 0.0214,
"step": 1200
},
{
"epoch": 0.5924837801444486,
"grad_norm": 0.08774357289075851,
"learning_rate": 8.552247349477784e-06,
"loss": 0.0214,
"step": 1210
},
{
"epoch": 0.5973803403109316,
"grad_norm": 0.08636177331209183,
"learning_rate": 8.383343306733276e-06,
"loss": 0.0207,
"step": 1220
},
{
"epoch": 0.6022769004774147,
"grad_norm": 0.09675206989049911,
"learning_rate": 8.214911561832258e-06,
"loss": 0.0216,
"step": 1230
},
{
"epoch": 0.6071734606438977,
"grad_norm": 0.07771232724189758,
"learning_rate": 8.04700132123286e-06,
"loss": 0.0215,
"step": 1240
},
{
"epoch": 0.6120700208103808,
"grad_norm": 0.086356021463871,
"learning_rate": 7.87966163903845e-06,
"loss": 0.0214,
"step": 1250
},
{
"epoch": 0.6169665809768637,
"grad_norm": 0.08160339295864105,
"learning_rate": 7.71294140266672e-06,
"loss": 0.0212,
"step": 1260
},
{
"epoch": 0.6218631411433468,
"grad_norm": 0.08717664331197739,
"learning_rate": 7.5468893185674885e-06,
"loss": 0.0214,
"step": 1270
},
{
"epoch": 0.6267597013098298,
"grad_norm": 0.09434729069471359,
"learning_rate": 7.38155389799336e-06,
"loss": 0.0221,
"step": 1280
},
{
"epoch": 0.6316562614763129,
"grad_norm": 0.07950156182050705,
"learning_rate": 7.216983442827428e-06,
"loss": 0.0209,
"step": 1290
},
{
"epoch": 0.6365528216427959,
"grad_norm": 0.09840266406536102,
"learning_rate": 7.053226031472111e-06,
"loss": 0.022,
"step": 1300
},
{
"epoch": 0.641449381809279,
"grad_norm": 0.09558066725730896,
"learning_rate": 6.89032950480331e-06,
"loss": 0.0209,
"step": 1310
},
{
"epoch": 0.646345941975762,
"grad_norm": 0.08704229444265366,
"learning_rate": 6.728341452193945e-06,
"loss": 0.0216,
"step": 1320
},
{
"epoch": 0.6512425021422451,
"grad_norm": 0.08100052177906036,
"learning_rate": 6.567309197610966e-06,
"loss": 0.0205,
"step": 1330
},
{
"epoch": 0.6561390623087281,
"grad_norm": 0.08176932483911514,
"learning_rate": 6.407279785789895e-06,
"loss": 0.0207,
"step": 1340
},
{
"epoch": 0.6610356224752112,
"grad_norm": 0.0904957726597786,
"learning_rate": 6.248299968490967e-06,
"loss": 0.021,
"step": 1350
},
{
"epoch": 0.6659321826416942,
"grad_norm": 0.0746573805809021,
"learning_rate": 6.0904161908408266e-06,
"loss": 0.0208,
"step": 1360
},
{
"epoch": 0.6708287428081773,
"grad_norm": 0.08013690263032913,
"learning_rate": 5.933674577763847e-06,
"loss": 0.0203,
"step": 1370
},
{
"epoch": 0.6757253029746603,
"grad_norm": 0.08136908710002899,
"learning_rate": 5.7781209205069554e-06,
"loss": 0.021,
"step": 1380
},
{
"epoch": 0.6806218631411434,
"grad_norm": 0.08329195529222488,
"learning_rate": 5.623800663261971e-06,
"loss": 0.0217,
"step": 1390
},
{
"epoch": 0.6855184233076264,
"grad_norm": 0.08549469709396362,
"learning_rate": 5.47075888988931e-06,
"loss": 0.0207,
"step": 1400
},
{
"epoch": 0.6904149834741095,
"grad_norm": 0.0912628248333931,
"learning_rate": 5.319040310746972e-06,
"loss": 0.0207,
"step": 1410
},
{
"epoch": 0.6953115436405924,
"grad_norm": 0.0736273005604744,
"learning_rate": 5.1686892496286615e-06,
"loss": 0.0198,
"step": 1420
},
{
"epoch": 0.7002081038070755,
"grad_norm": 0.07901625335216522,
"learning_rate": 5.019749630814785e-06,
"loss": 0.0199,
"step": 1430
},
{
"epoch": 0.7051046639735585,
"grad_norm": 0.08135338127613068,
"learning_rate": 4.872264966240242e-06,
"loss": 0.0199,
"step": 1440
},
{
"epoch": 0.7100012241400416,
"grad_norm": 0.08084066957235336,
"learning_rate": 4.726278342782603e-06,
"loss": 0.0201,
"step": 1450
},
{
"epoch": 0.7148977843065246,
"grad_norm": 0.091062992811203,
"learning_rate": 4.581832409674524e-06,
"loss": 0.0204,
"step": 1460
},
{
"epoch": 0.7197943444730077,
"grad_norm": 0.08555598556995392,
"learning_rate": 4.438969366043995e-06,
"loss": 0.0209,
"step": 1470
},
{
"epoch": 0.7246909046394907,
"grad_norm": 0.09011142700910568,
"learning_rate": 4.297730948586072e-06,
"loss": 0.0199,
"step": 1480
},
{
"epoch": 0.7295874648059738,
"grad_norm": 0.08594122529029846,
"learning_rate": 4.158158419369725e-06,
"loss": 0.0212,
"step": 1490
},
{
"epoch": 0.7344840249724568,
"grad_norm": 0.08000506460666656,
"learning_rate": 4.02029255378335e-06,
"loss": 0.0199,
"step": 1500
},
{
"epoch": 0.7393805851389399,
"grad_norm": 0.07965367287397385,
"learning_rate": 3.8841736286224266e-06,
"loss": 0.02,
"step": 1510
},
{
"epoch": 0.744277145305423,
"grad_norm": 0.07805147022008896,
"learning_rate": 3.7498414103228895e-06,
"loss": 0.0196,
"step": 1520
},
{
"epoch": 0.749173705471906,
"grad_norm": 0.07793158292770386,
"learning_rate": 3.61733514334355e-06,
"loss": 0.0198,
"step": 1530
},
{
"epoch": 0.7540702656383891,
"grad_norm": 0.07638546079397202,
"learning_rate": 3.486693538701038e-06,
"loss": 0.0207,
"step": 1540
},
{
"epoch": 0.7589668258048721,
"grad_norm": 0.07980620115995407,
"learning_rate": 3.3579547626605903e-06,
"loss": 0.0207,
"step": 1550
},
{
"epoch": 0.7638633859713552,
"grad_norm": 0.07835979759693146,
"learning_rate": 3.2311564255859574e-06,
"loss": 0.02,
"step": 1560
},
{
"epoch": 0.7687599461378382,
"grad_norm": 0.07357361912727356,
"learning_rate": 3.1063355709517405e-06,
"loss": 0.0191,
"step": 1570
},
{
"epoch": 0.7736565063043213,
"grad_norm": 0.07483252882957458,
"learning_rate": 2.9835286645213336e-06,
"loss": 0.0193,
"step": 1580
},
{
"epoch": 0.7785530664708042,
"grad_norm": 0.07509680092334747,
"learning_rate": 2.86277158369364e-06,
"loss": 0.0198,
"step": 1590
},
{
"epoch": 0.7834496266372873,
"grad_norm": 0.07577355951070786,
"learning_rate": 2.7440996070216786e-06,
"loss": 0.0199,
"step": 1600
},
{
"epoch": 0.7883461868037703,
"grad_norm": 0.07335933297872543,
"learning_rate": 2.6275474039061287e-06,
"loss": 0.0199,
"step": 1610
},
{
"epoch": 0.7932427469702534,
"grad_norm": 0.07359113544225693,
"learning_rate": 2.513149024466852e-06,
"loss": 0.0187,
"step": 1620
},
{
"epoch": 0.7981393071367364,
"grad_norm": 0.07391523569822311,
"learning_rate": 2.400937889595336e-06,
"loss": 0.0193,
"step": 1630
},
{
"epoch": 0.8030358673032195,
"grad_norm": 0.07307987660169601,
"learning_rate": 2.2909467811909358e-06,
"loss": 0.0194,
"step": 1640
},
{
"epoch": 0.8079324274697025,
"grad_norm": 0.07649096101522446,
"learning_rate": 2.1832078325838257e-06,
"loss": 0.019,
"step": 1650
},
{
"epoch": 0.8128289876361856,
"grad_norm": 0.07769432663917542,
"learning_rate": 2.0777525191474024e-06,
"loss": 0.0192,
"step": 1660
},
{
"epoch": 0.8177255478026686,
"grad_norm": 0.07669816166162491,
"learning_rate": 1.974611649102948e-06,
"loss": 0.0193,
"step": 1670
},
{
"epoch": 0.8226221079691517,
"grad_norm": 0.07635673135519028,
"learning_rate": 1.873815354519124e-06,
"loss": 0.0191,
"step": 1680
},
{
"epoch": 0.8275186681356347,
"grad_norm": 0.07668386399745941,
"learning_rate": 1.775393082509078e-06,
"loss": 0.0193,
"step": 1690
},
{
"epoch": 0.8324152283021178,
"grad_norm": 0.07667011022567749,
"learning_rate": 1.6793735866276062e-06,
"loss": 0.0197,
"step": 1700
},
{
"epoch": 0.8373117884686008,
"grad_norm": 0.07939690351486206,
"learning_rate": 1.5857849184709663e-06,
"loss": 0.0204,
"step": 1710
},
{
"epoch": 0.8422083486350839,
"grad_norm": 0.07528191804885864,
"learning_rate": 1.4946544194817313e-06,
"loss": 0.02,
"step": 1720
},
{
"epoch": 0.8471049088015669,
"grad_norm": 0.08050674200057983,
"learning_rate": 1.4060087129611433e-06,
"loss": 0.0202,
"step": 1730
},
{
"epoch": 0.85200146896805,
"grad_norm": 0.07322754710912704,
"learning_rate": 1.3198736962912473e-06,
"loss": 0.0187,
"step": 1740
},
{
"epoch": 0.856898029134533,
"grad_norm": 0.08674272894859314,
"learning_rate": 1.2362745333691128e-06,
"loss": 0.0194,
"step": 1750
},
{
"epoch": 0.861794589301016,
"grad_norm": 0.07837942242622375,
"learning_rate": 1.1552356472553283e-06,
"loss": 0.0195,
"step": 1760
},
{
"epoch": 0.866691149467499,
"grad_norm": 0.0758034959435463,
"learning_rate": 1.0767807130389229e-06,
"loss": 0.0204,
"step": 1770
},
{
"epoch": 0.8715877096339821,
"grad_norm": 0.07408754527568817,
"learning_rate": 1.000932650920825e-06,
"loss": 0.019,
"step": 1780
},
{
"epoch": 0.8764842698004651,
"grad_norm": 0.07121218740940094,
"learning_rate": 9.277136195178427e-07,
"loss": 0.0193,
"step": 1790
},
{
"epoch": 0.8813808299669482,
"grad_norm": 0.0695531889796257,
"learning_rate": 8.57145009389132e-07,
"loss": 0.0187,
"step": 1800
},
{
"epoch": 0.8862773901334313,
"grad_norm": 0.07386163622140884,
"learning_rate": 7.892474367870595e-07,
"loss": 0.0196,
"step": 1810
},
{
"epoch": 0.8911739502999143,
"grad_norm": 0.07514061033725739,
"learning_rate": 7.240407376342762e-07,
"loss": 0.019,
"step": 1820
},
{
"epoch": 0.8960705104663974,
"grad_norm": 0.07292406260967255,
"learning_rate": 6.6154396172875e-07,
"loss": 0.0191,
"step": 1830
},
{
"epoch": 0.9009670706328804,
"grad_norm": 0.07954388856887817,
"learning_rate": 6.017753671784709e-07,
"loss": 0.019,
"step": 1840
},
{
"epoch": 0.9058636307993635,
"grad_norm": 0.07357421517372131,
"learning_rate": 5.447524150674333e-07,
"loss": 0.0186,
"step": 1850
},
{
"epoch": 0.9107601909658465,
"grad_norm": 0.06809236109256744,
"learning_rate": 4.904917643544749e-07,
"loss": 0.019,
"step": 1860
},
{
"epoch": 0.9156567511323296,
"grad_norm": 0.07782679796218872,
"learning_rate": 4.390092670064572e-07,
"loss": 0.0189,
"step": 1870
},
{
"epoch": 0.9205533112988126,
"grad_norm": 0.08242752403020859,
"learning_rate": 3.9031996336717617e-07,
"loss": 0.0201,
"step": 1880
},
{
"epoch": 0.9254498714652957,
"grad_norm": 0.07631160318851471,
"learning_rate": 3.444380777634204e-07,
"loss": 0.0206,
"step": 1890
},
{
"epoch": 0.9303464316317787,
"grad_norm": 0.07500147074460983,
"learning_rate": 3.013770143494066e-07,
"loss": 0.0191,
"step": 1900
},
{
"epoch": 0.9352429917982618,
"grad_norm": 0.07438549399375916,
"learning_rate": 2.6114935319081494e-07,
"loss": 0.0192,
"step": 1910
},
{
"epoch": 0.9401395519647447,
"grad_norm": 0.07018297910690308,
"learning_rate": 2.2376684658959924e-07,
"loss": 0.0195,
"step": 1920
},
{
"epoch": 0.9450361121312278,
"grad_norm": 0.07748360931873322,
"learning_rate": 1.8924041565061002e-07,
"loss": 0.0205,
"step": 1930
},
{
"epoch": 0.9499326722977108,
"grad_norm": 0.06801605969667435,
"learning_rate": 1.5758014709104542e-07,
"loss": 0.0181,
"step": 1940
},
{
"epoch": 0.9548292324641939,
"grad_norm": 0.07736648619174957,
"learning_rate": 1.2879529029367842e-07,
"loss": 0.0186,
"step": 1950
},
{
"epoch": 0.9597257926306769,
"grad_norm": 0.07450318336486816,
"learning_rate": 1.028942546046896e-07,
"loss": 0.0183,
"step": 1960
},
{
"epoch": 0.96462235279716,
"grad_norm": 0.07568732649087906,
"learning_rate": 7.988460687692546e-08,
"loss": 0.0191,
"step": 1970
},
{
"epoch": 0.969518912963643,
"grad_norm": 0.07286310195922852,
"learning_rate": 5.977306925927795e-08,
"loss": 0.0194,
"step": 1980
},
{
"epoch": 0.9744154731301261,
"grad_norm": 0.0776013731956482,
"learning_rate": 4.256551723284874e-08,
"loss": 0.02,
"step": 1990
},
{
"epoch": 0.9793120332966091,
"grad_norm": 0.07332026213407516,
"learning_rate": 2.8266977894451096e-08,
"loss": 0.0195,
"step": 2000
}
],
"logging_steps": 10,
"max_steps": 2043,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 3.3808051176038466e+19,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}