Files
Xunzi-Qwen2-1.5B/trainer_state.json
ModelHub XC e5869ca554 初始化项目,由ModelHub XC社区提供模型
Model: XunziALLM/Xunzi-Qwen2-1.5B
Source: Original Platform
2026-07-31 12:40:15 +08:00

2255 lines
55 KiB
JSON
Executable File

{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9995064068392269,
"eval_steps": 500,
"global_step": 1582,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0031589962289482517,
"grad_norm": 5.4547529220581055,
"learning_rate": 2.9999260591410936e-05,
"loss": 3.8536,
"step": 5
},
{
"epoch": 0.006317992457896503,
"grad_norm": 1.3009593486785889,
"learning_rate": 2.9997042438540428e-05,
"loss": 3.681,
"step": 10
},
{
"epoch": 0.009476988686844755,
"grad_norm": 0.9018126726150513,
"learning_rate": 2.9993345760071313e-05,
"loss": 3.61,
"step": 15
},
{
"epoch": 0.012635984915793007,
"grad_norm": 0.7603598237037659,
"learning_rate": 2.998817092045103e-05,
"loss": 3.5495,
"step": 20
},
{
"epoch": 0.015794981144741257,
"grad_norm": 0.6061694622039795,
"learning_rate": 2.998151842985569e-05,
"loss": 3.5143,
"step": 25
},
{
"epoch": 0.01895397737368951,
"grad_norm": 0.5295926928520203,
"learning_rate": 2.9973388944139786e-05,
"loss": 3.5072,
"step": 30
},
{
"epoch": 0.02211297360263776,
"grad_norm": 0.46827778220176697,
"learning_rate": 2.996378326477153e-05,
"loss": 3.4699,
"step": 35
},
{
"epoch": 0.025271969831586014,
"grad_norm": 0.4419858157634735,
"learning_rate": 2.9952702338753833e-05,
"loss": 3.4615,
"step": 40
},
{
"epoch": 0.028430966060534264,
"grad_norm": 0.4636269211769104,
"learning_rate": 2.9940147258530942e-05,
"loss": 3.4532,
"step": 45
},
{
"epoch": 0.031589962289482514,
"grad_norm": 1.6979502439498901,
"learning_rate": 2.9926119261880744e-05,
"loss": 3.429,
"step": 50
},
{
"epoch": 0.03474895851843077,
"grad_norm": 0.5432493090629578,
"learning_rate": 2.9910619731792736e-05,
"loss": 3.4082,
"step": 55
},
{
"epoch": 0.03790795474737902,
"grad_norm": 0.5126500725746155,
"learning_rate": 2.989365019633167e-05,
"loss": 3.4024,
"step": 60
},
{
"epoch": 0.041066950976327274,
"grad_norm": 0.50709468126297,
"learning_rate": 2.987521232848692e-05,
"loss": 3.3977,
"step": 65
},
{
"epoch": 0.04422594720527552,
"grad_norm": 0.45997342467308044,
"learning_rate": 2.9855307946007532e-05,
"loss": 3.4002,
"step": 70
},
{
"epoch": 0.047384943434223774,
"grad_norm": 0.6527863144874573,
"learning_rate": 2.983393901122302e-05,
"loss": 3.3982,
"step": 75
},
{
"epoch": 0.05054393966317203,
"grad_norm": 0.6626459360122681,
"learning_rate": 2.9811107630849908e-05,
"loss": 3.3655,
"step": 80
},
{
"epoch": 0.05370293589212028,
"grad_norm": 0.6589984893798828,
"learning_rate": 2.9786816055784026e-05,
"loss": 3.3758,
"step": 85
},
{
"epoch": 0.05686193212106853,
"grad_norm": 0.6672041416168213,
"learning_rate": 2.9761066680878608e-05,
"loss": 3.3463,
"step": 90
},
{
"epoch": 0.06002092835001678,
"grad_norm": 0.4873623251914978,
"learning_rate": 2.9733862044708187e-05,
"loss": 3.3519,
"step": 95
},
{
"epoch": 0.06317992457896503,
"grad_norm": 0.6229231953620911,
"learning_rate": 2.9705204829318313e-05,
"loss": 3.3588,
"step": 100
},
{
"epoch": 0.06633892080791329,
"grad_norm": 2.492616891860962,
"learning_rate": 2.967509785996114e-05,
"loss": 3.3492,
"step": 105
},
{
"epoch": 0.06949791703686153,
"grad_norm": 0.8541843295097351,
"learning_rate": 2.9643544104816907e-05,
"loss": 3.3246,
"step": 110
},
{
"epoch": 0.0726569132658098,
"grad_norm": 0.5927584767341614,
"learning_rate": 2.9610546674701292e-05,
"loss": 3.3359,
"step": 115
},
{
"epoch": 0.07581590949475804,
"grad_norm": 0.7915903329849243,
"learning_rate": 2.957610882275872e-05,
"loss": 3.3319,
"step": 120
},
{
"epoch": 0.07897490572370629,
"grad_norm": 0.5421105027198792,
"learning_rate": 2.9540233944141662e-05,
"loss": 3.3249,
"step": 125
},
{
"epoch": 0.08213390195265455,
"grad_norm": 0.5522976517677307,
"learning_rate": 2.9502925575675904e-05,
"loss": 3.2992,
"step": 130
},
{
"epoch": 0.0852928981816028,
"grad_norm": 0.4449402987957001,
"learning_rate": 2.9464187395511856e-05,
"loss": 3.2979,
"step": 135
},
{
"epoch": 0.08845189441055104,
"grad_norm": 0.4442364275455475,
"learning_rate": 2.9424023222761938e-05,
"loss": 3.2871,
"step": 140
},
{
"epoch": 0.0916108906394993,
"grad_norm": 0.4465540945529938,
"learning_rate": 2.9382437017124055e-05,
"loss": 3.2865,
"step": 145
},
{
"epoch": 0.09476988686844755,
"grad_norm": 0.5532798171043396,
"learning_rate": 2.9339432878491226e-05,
"loss": 3.2948,
"step": 150
},
{
"epoch": 0.09792888309739581,
"grad_norm": 0.414792537689209,
"learning_rate": 2.929501504654738e-05,
"loss": 3.2908,
"step": 155
},
{
"epoch": 0.10108787932634405,
"grad_norm": 0.509645402431488,
"learning_rate": 2.924918790034938e-05,
"loss": 3.2878,
"step": 160
},
{
"epoch": 0.1042468755552923,
"grad_norm": 0.44900578260421753,
"learning_rate": 2.920195595789529e-05,
"loss": 3.2882,
"step": 165
},
{
"epoch": 0.10740587178424056,
"grad_norm": 0.45925071835517883,
"learning_rate": 2.9153323875678965e-05,
"loss": 3.2789,
"step": 170
},
{
"epoch": 0.11056486801318881,
"grad_norm": 0.4317935109138489,
"learning_rate": 2.9103296448230986e-05,
"loss": 3.2584,
"step": 175
},
{
"epoch": 0.11372386424213705,
"grad_norm": 0.49977853894233704,
"learning_rate": 2.9051878607645955e-05,
"loss": 3.2706,
"step": 180
},
{
"epoch": 0.11688286047108531,
"grad_norm": 0.605815052986145,
"learning_rate": 2.899907542309626e-05,
"loss": 3.2691,
"step": 185
},
{
"epoch": 0.12004185670003356,
"grad_norm": 0.6688348650932312,
"learning_rate": 2.8944892100332336e-05,
"loss": 3.2595,
"step": 190
},
{
"epoch": 0.12320085292898182,
"grad_norm": 0.5728278160095215,
"learning_rate": 2.888933398116941e-05,
"loss": 3.2618,
"step": 195
},
{
"epoch": 0.12635984915793005,
"grad_norm": 0.4474872648715973,
"learning_rate": 2.8832406542960877e-05,
"loss": 3.2652,
"step": 200
},
{
"epoch": 0.12951884538687833,
"grad_norm": 0.5116688013076782,
"learning_rate": 2.8774115398058313e-05,
"loss": 3.2579,
"step": 205
},
{
"epoch": 0.13267784161582657,
"grad_norm": 0.4465239346027374,
"learning_rate": 2.8714466293258142e-05,
"loss": 3.2385,
"step": 210
},
{
"epoch": 0.13583683784477482,
"grad_norm": 0.4429784119129181,
"learning_rate": 2.8653465109235087e-05,
"loss": 3.2469,
"step": 215
},
{
"epoch": 0.13899583407372307,
"grad_norm": 0.49847137928009033,
"learning_rate": 2.8591117859962405e-05,
"loss": 3.2595,
"step": 220
},
{
"epoch": 0.14215483030267131,
"grad_norm": 0.5313963294029236,
"learning_rate": 2.852743069211898e-05,
"loss": 3.2502,
"step": 225
},
{
"epoch": 0.1453138265316196,
"grad_norm": 0.5370007157325745,
"learning_rate": 2.8462409884483325e-05,
"loss": 3.2247,
"step": 230
},
{
"epoch": 0.14847282276056784,
"grad_norm": 0.5197588205337524,
"learning_rate": 2.83960618473146e-05,
"loss": 3.2376,
"step": 235
},
{
"epoch": 0.15163181898951608,
"grad_norm": 0.4718385338783264,
"learning_rate": 2.832839312172061e-05,
"loss": 3.2197,
"step": 240
},
{
"epoch": 0.15479081521846433,
"grad_norm": 0.46028411388397217,
"learning_rate": 2.825941037901294e-05,
"loss": 3.2306,
"step": 245
},
{
"epoch": 0.15794981144741257,
"grad_norm": 0.5366470813751221,
"learning_rate": 2.8189120420049245e-05,
"loss": 3.2231,
"step": 250
},
{
"epoch": 0.16110880767636085,
"grad_norm": 0.5422227382659912,
"learning_rate": 2.8117530174562793e-05,
"loss": 3.2265,
"step": 255
},
{
"epoch": 0.1642678039053091,
"grad_norm": 0.5088212490081787,
"learning_rate": 2.8044646700479224e-05,
"loss": 3.2248,
"step": 260
},
{
"epoch": 0.16742680013425734,
"grad_norm": 0.48751604557037354,
"learning_rate": 2.7970477183220782e-05,
"loss": 3.2067,
"step": 265
},
{
"epoch": 0.1705857963632056,
"grad_norm": 0.4716982841491699,
"learning_rate": 2.7895028934997867e-05,
"loss": 3.2148,
"step": 270
},
{
"epoch": 0.17374479259215383,
"grad_norm": 0.5249848365783691,
"learning_rate": 2.781830939408819e-05,
"loss": 3.2262,
"step": 275
},
{
"epoch": 0.17690378882110208,
"grad_norm": 0.45049384236335754,
"learning_rate": 2.7740326124103416e-05,
"loss": 3.2206,
"step": 280
},
{
"epoch": 0.18006278505005036,
"grad_norm": 0.4129708409309387,
"learning_rate": 2.7661086813243492e-05,
"loss": 3.2217,
"step": 285
},
{
"epoch": 0.1832217812789986,
"grad_norm": 0.43842828273773193,
"learning_rate": 2.75805992735387e-05,
"loss": 3.2165,
"step": 290
},
{
"epoch": 0.18638077750794685,
"grad_norm": 0.44792863726615906,
"learning_rate": 2.7498871440079447e-05,
"loss": 3.208,
"step": 295
},
{
"epoch": 0.1895397737368951,
"grad_norm": 0.4602539539337158,
"learning_rate": 2.7415911370234018e-05,
"loss": 3.2023,
"step": 300
},
{
"epoch": 0.19269876996584334,
"grad_norm": 0.48890477418899536,
"learning_rate": 2.7331727242854167e-05,
"loss": 3.2083,
"step": 305
},
{
"epoch": 0.19585776619479162,
"grad_norm": 0.3967636227607727,
"learning_rate": 2.72463273574688e-05,
"loss": 3.1896,
"step": 310
},
{
"epoch": 0.19901676242373986,
"grad_norm": 0.45667341351509094,
"learning_rate": 2.715972013346576e-05,
"loss": 3.1984,
"step": 315
},
{
"epoch": 0.2021757586526881,
"grad_norm": 0.44837695360183716,
"learning_rate": 2.707191410926175e-05,
"loss": 3.1922,
"step": 320
},
{
"epoch": 0.20533475488163636,
"grad_norm": 0.46816104650497437,
"learning_rate": 2.698291794146057e-05,
"loss": 3.2034,
"step": 325
},
{
"epoch": 0.2084937511105846,
"grad_norm": 0.5171133875846863,
"learning_rate": 2.6892740403999666e-05,
"loss": 3.1916,
"step": 330
},
{
"epoch": 0.21165274733953288,
"grad_norm": 0.46516111493110657,
"learning_rate": 2.680139038728513e-05,
"loss": 3.1939,
"step": 335
},
{
"epoch": 0.21481174356848112,
"grad_norm": 0.4466981589794159,
"learning_rate": 2.6708876897315237e-05,
"loss": 3.194,
"step": 340
},
{
"epoch": 0.21797073979742937,
"grad_norm": 0.47058606147766113,
"learning_rate": 2.6615209054792525e-05,
"loss": 3.1842,
"step": 345
},
{
"epoch": 0.22112973602637762,
"grad_norm": 0.42421820759773254,
"learning_rate": 2.652039609422463e-05,
"loss": 3.1765,
"step": 350
},
{
"epoch": 0.22428873225532586,
"grad_norm": 0.4202456474304199,
"learning_rate": 2.642444736301388e-05,
"loss": 3.1887,
"step": 355
},
{
"epoch": 0.2274477284842741,
"grad_norm": 0.4121611416339874,
"learning_rate": 2.6327372320535727e-05,
"loss": 3.1694,
"step": 360
},
{
"epoch": 0.23060672471322238,
"grad_norm": 0.4271106719970703,
"learning_rate": 2.62291805372062e-05,
"loss": 3.1682,
"step": 365
},
{
"epoch": 0.23376572094217063,
"grad_norm": 0.42588379979133606,
"learning_rate": 2.6129881693538363e-05,
"loss": 3.1759,
"step": 370
},
{
"epoch": 0.23692471717111888,
"grad_norm": 0.40799328684806824,
"learning_rate": 2.6029485579187937e-05,
"loss": 3.1591,
"step": 375
},
{
"epoch": 0.24008371340006712,
"grad_norm": 0.5254926681518555,
"learning_rate": 2.5928002091988153e-05,
"loss": 3.1774,
"step": 380
},
{
"epoch": 0.24324270962901537,
"grad_norm": 0.470021516084671,
"learning_rate": 2.582544123697395e-05,
"loss": 3.18,
"step": 385
},
{
"epoch": 0.24640170585796364,
"grad_norm": 0.49047040939331055,
"learning_rate": 2.5721813125395622e-05,
"loss": 3.1667,
"step": 390
},
{
"epoch": 0.2495607020869119,
"grad_norm": 0.47164517641067505,
"learning_rate": 2.561712797372193e-05,
"loss": 3.166,
"step": 395
},
{
"epoch": 0.2527196983158601,
"grad_norm": 0.45902010798454285,
"learning_rate": 2.5511396102632912e-05,
"loss": 3.1628,
"step": 400
},
{
"epoch": 0.2558786945448084,
"grad_norm": 0.4785389006137848,
"learning_rate": 2.5404627936002386e-05,
"loss": 3.1682,
"step": 405
},
{
"epoch": 0.25903769077375666,
"grad_norm": 0.5290773510932922,
"learning_rate": 2.5296833999870276e-05,
"loss": 3.1519,
"step": 410
},
{
"epoch": 0.2621966870027049,
"grad_norm": 0.6423753499984741,
"learning_rate": 2.5188024921404885e-05,
"loss": 3.1445,
"step": 415
},
{
"epoch": 0.26535568323165315,
"grad_norm": 0.5454652905464172,
"learning_rate": 2.507821142785516e-05,
"loss": 3.1551,
"step": 420
},
{
"epoch": 0.26851467946060137,
"grad_norm": 0.35622674226760864,
"learning_rate": 2.4967404345493157e-05,
"loss": 3.1445,
"step": 425
},
{
"epoch": 0.27167367568954964,
"grad_norm": 0.4588085114955902,
"learning_rate": 2.4855614598546655e-05,
"loss": 3.1422,
"step": 430
},
{
"epoch": 0.2748326719184979,
"grad_norm": 0.4413850009441376,
"learning_rate": 2.4742853208122204e-05,
"loss": 3.1709,
"step": 435
},
{
"epoch": 0.27799166814744614,
"grad_norm": 0.5014812350273132,
"learning_rate": 2.4629131291118545e-05,
"loss": 3.1511,
"step": 440
},
{
"epoch": 0.2811506643763944,
"grad_norm": 0.4468047022819519,
"learning_rate": 2.4514460059130643e-05,
"loss": 3.1389,
"step": 445
},
{
"epoch": 0.28430966060534263,
"grad_norm": 0.4030034840106964,
"learning_rate": 2.4398850817344335e-05,
"loss": 3.148,
"step": 450
},
{
"epoch": 0.2874686568342909,
"grad_norm": 0.43451905250549316,
"learning_rate": 2.428231496342181e-05,
"loss": 3.1458,
"step": 455
},
{
"epoch": 0.2906276530632392,
"grad_norm": 0.39871373772621155,
"learning_rate": 2.416486398637791e-05,
"loss": 3.1457,
"step": 460
},
{
"epoch": 0.2937866492921874,
"grad_norm": 0.44384175539016724,
"learning_rate": 2.404650946544746e-05,
"loss": 3.1513,
"step": 465
},
{
"epoch": 0.29694564552113567,
"grad_norm": 0.5744538903236389,
"learning_rate": 2.3927263068943707e-05,
"loss": 3.1456,
"step": 470
},
{
"epoch": 0.3001046417500839,
"grad_norm": 0.41833463311195374,
"learning_rate": 2.3807136553107957e-05,
"loss": 3.1486,
"step": 475
},
{
"epoch": 0.30326363797903216,
"grad_norm": 0.45373785495758057,
"learning_rate": 2.3686141760950556e-05,
"loss": 3.1361,
"step": 480
},
{
"epoch": 0.30642263420798044,
"grad_norm": 0.3925414979457855,
"learning_rate": 2.3564290621083304e-05,
"loss": 3.1359,
"step": 485
},
{
"epoch": 0.30958163043692866,
"grad_norm": 0.41434600949287415,
"learning_rate": 2.3441595146543458e-05,
"loss": 3.1373,
"step": 490
},
{
"epoch": 0.31274062666587693,
"grad_norm": 0.38978660106658936,
"learning_rate": 2.3318067433609382e-05,
"loss": 3.1478,
"step": 495
},
{
"epoch": 0.31589962289482515,
"grad_norm": 0.4078003764152527,
"learning_rate": 2.3193719660608002e-05,
"loss": 3.1399,
"step": 500
},
{
"epoch": 0.3190586191237734,
"grad_norm": 0.4279017448425293,
"learning_rate": 2.3068564086714167e-05,
"loss": 3.1471,
"step": 505
},
{
"epoch": 0.3222176153527217,
"grad_norm": 0.39451780915260315,
"learning_rate": 2.294261305074205e-05,
"loss": 3.1243,
"step": 510
},
{
"epoch": 0.3253766115816699,
"grad_norm": 0.49184396862983704,
"learning_rate": 2.281587896992869e-05,
"loss": 3.1251,
"step": 515
},
{
"epoch": 0.3285356078106182,
"grad_norm": 0.46036773920059204,
"learning_rate": 2.2688374338709807e-05,
"loss": 3.125,
"step": 520
},
{
"epoch": 0.3316946040395664,
"grad_norm": 0.5152999758720398,
"learning_rate": 2.2560111727488e-05,
"loss": 3.1209,
"step": 525
},
{
"epoch": 0.3348536002685147,
"grad_norm": 0.3766791522502899,
"learning_rate": 2.2431103781393448e-05,
"loss": 3.1253,
"step": 530
},
{
"epoch": 0.33801259649746296,
"grad_norm": 0.5221071839332581,
"learning_rate": 2.230136321903727e-05,
"loss": 3.1218,
"step": 535
},
{
"epoch": 0.3411715927264112,
"grad_norm": 0.41231483221054077,
"learning_rate": 2.217090283125763e-05,
"loss": 3.1197,
"step": 540
},
{
"epoch": 0.34433058895535945,
"grad_norm": 0.4129316508769989,
"learning_rate": 2.2039735479858684e-05,
"loss": 3.1278,
"step": 545
},
{
"epoch": 0.34748958518430767,
"grad_norm": 0.35055166482925415,
"learning_rate": 2.19078740963426e-05,
"loss": 3.1159,
"step": 550
},
{
"epoch": 0.35064858141325594,
"grad_norm": 0.3946894109249115,
"learning_rate": 2.177533168063466e-05,
"loss": 3.1237,
"step": 555
},
{
"epoch": 0.35380757764220416,
"grad_norm": 0.3616543412208557,
"learning_rate": 2.1642121299801594e-05,
"loss": 3.1196,
"step": 560
},
{
"epoch": 0.35696657387115244,
"grad_norm": 0.4239869713783264,
"learning_rate": 2.1508256086763372e-05,
"loss": 3.1193,
"step": 565
},
{
"epoch": 0.3601255701001007,
"grad_norm": 0.3845061659812927,
"learning_rate": 2.1373749238998436e-05,
"loss": 3.1115,
"step": 570
},
{
"epoch": 0.36328456632904893,
"grad_norm": 0.4048169255256653,
"learning_rate": 2.123861401724259e-05,
"loss": 3.1167,
"step": 575
},
{
"epoch": 0.3664435625579972,
"grad_norm": 0.41142508387565613,
"learning_rate": 2.1102863744181653e-05,
"loss": 3.1133,
"step": 580
},
{
"epoch": 0.3696025587869454,
"grad_norm": 0.41957658529281616,
"learning_rate": 2.0966511803138006e-05,
"loss": 3.113,
"step": 585
},
{
"epoch": 0.3727615550158937,
"grad_norm": 0.48445215821266174,
"learning_rate": 2.082957163675116e-05,
"loss": 3.1127,
"step": 590
},
{
"epoch": 0.37592055124484197,
"grad_norm": 0.46747225522994995,
"learning_rate": 2.0692056745652483e-05,
"loss": 3.0998,
"step": 595
},
{
"epoch": 0.3790795474737902,
"grad_norm": 0.43239614367485046,
"learning_rate": 2.0553980687134183e-05,
"loss": 3.108,
"step": 600
},
{
"epoch": 0.38223854370273846,
"grad_norm": 0.4191133379936218,
"learning_rate": 2.041535707381274e-05,
"loss": 3.1027,
"step": 605
},
{
"epoch": 0.3853975399316867,
"grad_norm": 0.3832011818885803,
"learning_rate": 2.0276199572286872e-05,
"loss": 3.084,
"step": 610
},
{
"epoch": 0.38855653616063496,
"grad_norm": 0.4251471757888794,
"learning_rate": 2.0136521901790158e-05,
"loss": 3.0959,
"step": 615
},
{
"epoch": 0.39171553238958323,
"grad_norm": 0.4120692312717438,
"learning_rate": 1.99963378328385e-05,
"loss": 3.1029,
"step": 620
},
{
"epoch": 0.39487452861853145,
"grad_norm": 0.3763813078403473,
"learning_rate": 1.985566118587251e-05,
"loss": 3.0932,
"step": 625
},
{
"epoch": 0.3980335248474797,
"grad_norm": 0.37210220098495483,
"learning_rate": 1.9714505829895004e-05,
"loss": 3.1041,
"step": 630
},
{
"epoch": 0.40119252107642794,
"grad_norm": 0.38982659578323364,
"learning_rate": 1.957288568110366e-05,
"loss": 3.093,
"step": 635
},
{
"epoch": 0.4043515173053762,
"grad_norm": 0.4042922854423523,
"learning_rate": 1.943081470151906e-05,
"loss": 3.0993,
"step": 640
},
{
"epoch": 0.4075105135343245,
"grad_norm": 0.3988935947418213,
"learning_rate": 1.928830689760821e-05,
"loss": 3.1051,
"step": 645
},
{
"epoch": 0.4106695097632727,
"grad_norm": 0.41843679547309875,
"learning_rate": 1.914537631890368e-05,
"loss": 3.0889,
"step": 650
},
{
"epoch": 0.413828505992221,
"grad_norm": 0.366599440574646,
"learning_rate": 1.9002037056618474e-05,
"loss": 3.1024,
"step": 655
},
{
"epoch": 0.4169875022211692,
"grad_norm": 0.3499836027622223,
"learning_rate": 1.8858303242256814e-05,
"loss": 3.1053,
"step": 660
},
{
"epoch": 0.4201464984501175,
"grad_norm": 0.36143290996551514,
"learning_rate": 1.8714189046220946e-05,
"loss": 3.0976,
"step": 665
},
{
"epoch": 0.42330549467906575,
"grad_norm": 0.3504003882408142,
"learning_rate": 1.8569708676414123e-05,
"loss": 3.1102,
"step": 670
},
{
"epoch": 0.42646449090801397,
"grad_norm": 0.3740462362766266,
"learning_rate": 1.8424876376839864e-05,
"loss": 3.0849,
"step": 675
},
{
"epoch": 0.42962348713696225,
"grad_norm": 0.37972983717918396,
"learning_rate": 1.827970642619767e-05,
"loss": 3.0775,
"step": 680
},
{
"epoch": 0.43278248336591046,
"grad_norm": 0.34270837903022766,
"learning_rate": 1.8134213136475323e-05,
"loss": 3.0895,
"step": 685
},
{
"epoch": 0.43594147959485874,
"grad_norm": 0.3466212749481201,
"learning_rate": 1.79884108515379e-05,
"loss": 3.0832,
"step": 690
},
{
"epoch": 0.439100475823807,
"grad_norm": 0.36446908116340637,
"learning_rate": 1.7842313945713647e-05,
"loss": 3.091,
"step": 695
},
{
"epoch": 0.44225947205275523,
"grad_norm": 0.3832855224609375,
"learning_rate": 1.769593682237682e-05,
"loss": 3.0942,
"step": 700
},
{
"epoch": 0.4454184682817035,
"grad_norm": 0.3667459189891815,
"learning_rate": 1.7549293912527726e-05,
"loss": 3.0852,
"step": 705
},
{
"epoch": 0.4485774645106517,
"grad_norm": 0.4119127690792084,
"learning_rate": 1.740239967336997e-05,
"loss": 3.0908,
"step": 710
},
{
"epoch": 0.4517364607396,
"grad_norm": 0.36058080196380615,
"learning_rate": 1.7255268586885165e-05,
"loss": 3.0836,
"step": 715
},
{
"epoch": 0.4548954569685482,
"grad_norm": 0.3911276161670685,
"learning_rate": 1.7107915158405187e-05,
"loss": 3.086,
"step": 720
},
{
"epoch": 0.4580544531974965,
"grad_norm": 0.38079550862312317,
"learning_rate": 1.6960353915182127e-05,
"loss": 3.0855,
"step": 725
},
{
"epoch": 0.46121344942644477,
"grad_norm": 0.38464805483818054,
"learning_rate": 1.681259940495607e-05,
"loss": 3.077,
"step": 730
},
{
"epoch": 0.464372445655393,
"grad_norm": 0.4101375639438629,
"learning_rate": 1.6664666194520873e-05,
"loss": 3.0732,
"step": 735
},
{
"epoch": 0.46753144188434126,
"grad_norm": 0.36215919256210327,
"learning_rate": 1.6516568868288053e-05,
"loss": 3.0814,
"step": 740
},
{
"epoch": 0.4706904381132895,
"grad_norm": 0.3624699115753174,
"learning_rate": 1.636832202684895e-05,
"loss": 3.0817,
"step": 745
},
{
"epoch": 0.47384943434223775,
"grad_norm": 0.37232911586761475,
"learning_rate": 1.6219940285535287e-05,
"loss": 3.0843,
"step": 750
},
{
"epoch": 0.477008430571186,
"grad_norm": 0.38332194089889526,
"learning_rate": 1.607143827297825e-05,
"loss": 3.0788,
"step": 755
},
{
"epoch": 0.48016742680013424,
"grad_norm": 0.37166598439216614,
"learning_rate": 1.592283062966632e-05,
"loss": 3.0672,
"step": 760
},
{
"epoch": 0.4833264230290825,
"grad_norm": 0.37084612250328064,
"learning_rate": 1.5774132006501885e-05,
"loss": 3.0759,
"step": 765
},
{
"epoch": 0.48648541925803074,
"grad_norm": 0.3931644558906555,
"learning_rate": 1.5625357063356825e-05,
"loss": 3.0642,
"step": 770
},
{
"epoch": 0.489644415486979,
"grad_norm": 0.3733079731464386,
"learning_rate": 1.5476520467627244e-05,
"loss": 3.0707,
"step": 775
},
{
"epoch": 0.4928034117159273,
"grad_norm": 0.3540187478065491,
"learning_rate": 1.5327636892787445e-05,
"loss": 3.068,
"step": 780
},
{
"epoch": 0.4959624079448755,
"grad_norm": 0.3657519519329071,
"learning_rate": 1.5178721016943305e-05,
"loss": 3.069,
"step": 785
},
{
"epoch": 0.4991214041738238,
"grad_norm": 0.3364481031894684,
"learning_rate": 1.5029787521385165e-05,
"loss": 3.0698,
"step": 790
},
{
"epoch": 0.502280400402772,
"grad_norm": 0.3556075692176819,
"learning_rate": 1.4880851089140468e-05,
"loss": 3.0692,
"step": 795
},
{
"epoch": 0.5054393966317202,
"grad_norm": 0.338679701089859,
"learning_rate": 1.473192640352618e-05,
"loss": 3.0595,
"step": 800
},
{
"epoch": 0.5085983928606685,
"grad_norm": 0.37861868739128113,
"learning_rate": 1.4583028146701191e-05,
"loss": 3.0738,
"step": 805
},
{
"epoch": 0.5117573890896168,
"grad_norm": 0.37240612506866455,
"learning_rate": 1.4434170998218834e-05,
"loss": 3.0591,
"step": 810
},
{
"epoch": 0.514916385318565,
"grad_norm": 0.36659571528434753,
"learning_rate": 1.4285369633579653e-05,
"loss": 3.0698,
"step": 815
},
{
"epoch": 0.5180753815475133,
"grad_norm": 0.3414934277534485,
"learning_rate": 1.41366387227846e-05,
"loss": 3.0696,
"step": 820
},
{
"epoch": 0.5212343777764615,
"grad_norm": 0.3869072496891022,
"learning_rate": 1.3987992928888728e-05,
"loss": 3.0682,
"step": 825
},
{
"epoch": 0.5243933740054098,
"grad_norm": 0.3495336174964905,
"learning_rate": 1.3839446906555591e-05,
"loss": 3.0404,
"step": 830
},
{
"epoch": 0.5275523702343581,
"grad_norm": 0.4046941101551056,
"learning_rate": 1.3691015300612509e-05,
"loss": 3.0633,
"step": 835
},
{
"epoch": 0.5307113664633063,
"grad_norm": 0.36706477403640747,
"learning_rate": 1.3542712744606712e-05,
"loss": 3.0631,
"step": 840
},
{
"epoch": 0.5338703626922545,
"grad_norm": 0.33146992325782776,
"learning_rate": 1.3394553859362701e-05,
"loss": 3.0674,
"step": 845
},
{
"epoch": 0.5370293589212027,
"grad_norm": 0.38201820850372314,
"learning_rate": 1.3246553251540778e-05,
"loss": 3.0605,
"step": 850
},
{
"epoch": 0.5401883551501511,
"grad_norm": 0.39073649048805237,
"learning_rate": 1.3098725512197019e-05,
"loss": 3.0677,
"step": 855
},
{
"epoch": 0.5433473513790993,
"grad_norm": 0.31767648458480835,
"learning_rate": 1.2951085215344794e-05,
"loss": 3.0747,
"step": 860
},
{
"epoch": 0.5465063476080475,
"grad_norm": 0.3284844160079956,
"learning_rate": 1.2803646916517906e-05,
"loss": 3.0673,
"step": 865
},
{
"epoch": 0.5496653438369958,
"grad_norm": 0.3267665505409241,
"learning_rate": 1.2656425151335616e-05,
"loss": 3.0587,
"step": 870
},
{
"epoch": 0.552824340065944,
"grad_norm": 0.3200699985027313,
"learning_rate": 1.2509434434069625e-05,
"loss": 3.0687,
"step": 875
},
{
"epoch": 0.5559833362948923,
"grad_norm": 0.3257604241371155,
"learning_rate": 1.2362689256213107e-05,
"loss": 3.0498,
"step": 880
},
{
"epoch": 0.5591423325238406,
"grad_norm": 0.3359987139701843,
"learning_rate": 1.2216204085052056e-05,
"loss": 3.0603,
"step": 885
},
{
"epoch": 0.5623013287527888,
"grad_norm": 0.35924768447875977,
"learning_rate": 1.2069993362238968e-05,
"loss": 3.06,
"step": 890
},
{
"epoch": 0.565460324981737,
"grad_norm": 0.3555845022201538,
"learning_rate": 1.1924071502369067e-05,
"loss": 3.0426,
"step": 895
},
{
"epoch": 0.5686193212106853,
"grad_norm": 0.3523537218570709,
"learning_rate": 1.1778452891559238e-05,
"loss": 3.0539,
"step": 900
},
{
"epoch": 0.5717783174396336,
"grad_norm": 0.3172820210456848,
"learning_rate": 1.1633151886029678e-05,
"loss": 3.0576,
"step": 905
},
{
"epoch": 0.5749373136685818,
"grad_norm": 0.31360894441604614,
"learning_rate": 1.1488182810688593e-05,
"loss": 3.0436,
"step": 910
},
{
"epoch": 0.57809630989753,
"grad_norm": 0.3215031325817108,
"learning_rate": 1.1343559957719906e-05,
"loss": 3.0608,
"step": 915
},
{
"epoch": 0.5812553061264784,
"grad_norm": 0.3421837091445923,
"learning_rate": 1.1199297585174234e-05,
"loss": 3.0635,
"step": 920
},
{
"epoch": 0.5844143023554266,
"grad_norm": 0.3177051246166229,
"learning_rate": 1.1055409915563234e-05,
"loss": 3.0504,
"step": 925
},
{
"epoch": 0.5875732985843748,
"grad_norm": 0.3425046503543854,
"learning_rate": 1.09119111344574e-05,
"loss": 3.0476,
"step": 930
},
{
"epoch": 0.590732294813323,
"grad_norm": 0.34836167097091675,
"learning_rate": 1.0768815389087563e-05,
"loss": 3.056,
"step": 935
},
{
"epoch": 0.5938912910422713,
"grad_norm": 0.33330801129341125,
"learning_rate": 1.0626136786950166e-05,
"loss": 3.0644,
"step": 940
},
{
"epoch": 0.5970502872712196,
"grad_norm": 0.3366113007068634,
"learning_rate": 1.0483889394416373e-05,
"loss": 3.0566,
"step": 945
},
{
"epoch": 0.6002092835001678,
"grad_norm": 0.3356780409812927,
"learning_rate": 1.0342087235345375e-05,
"loss": 3.0383,
"step": 950
},
{
"epoch": 0.6033682797291161,
"grad_norm": 0.3282509744167328,
"learning_rate": 1.0200744289701747e-05,
"loss": 3.0348,
"step": 955
},
{
"epoch": 0.6065272759580643,
"grad_norm": 0.37249842286109924,
"learning_rate": 1.0059874492177222e-05,
"loss": 3.0542,
"step": 960
},
{
"epoch": 0.6096862721870125,
"grad_norm": 0.35184526443481445,
"learning_rate": 9.919491730816904e-06,
"loss": 3.0485,
"step": 965
},
{
"epoch": 0.6128452684159609,
"grad_norm": 0.3398050367832184,
"learning_rate": 9.77960984565005e-06,
"loss": 3.0457,
"step": 970
},
{
"epoch": 0.6160042646449091,
"grad_norm": 0.326440691947937,
"learning_rate": 9.640242627325656e-06,
"loss": 3.0495,
"step": 975
},
{
"epoch": 0.6191632608738573,
"grad_norm": 0.3242528736591339,
"learning_rate": 9.501403815752813e-06,
"loss": 3.0381,
"step": 980
},
{
"epoch": 0.6223222571028055,
"grad_norm": 0.3606809377670288,
"learning_rate": 9.36310709874615e-06,
"loss": 3.0484,
"step": 985
},
{
"epoch": 0.6254812533317539,
"grad_norm": 0.3369554579257965,
"learning_rate": 9.225366110676398e-06,
"loss": 3.0434,
"step": 990
},
{
"epoch": 0.6286402495607021,
"grad_norm": 0.34008821845054626,
"learning_rate": 9.088194431126176e-06,
"loss": 3.0495,
"step": 995
},
{
"epoch": 0.6317992457896503,
"grad_norm": 0.3000885546207428,
"learning_rate": 8.951605583551216e-06,
"loss": 3.0373,
"step": 1000
},
{
"epoch": 0.6349582420185986,
"grad_norm": 0.30115771293640137,
"learning_rate": 8.81561303394713e-06,
"loss": 3.0423,
"step": 1005
},
{
"epoch": 0.6381172382475468,
"grad_norm": 0.3016274571418762,
"learning_rate": 8.680230189521813e-06,
"loss": 3.0379,
"step": 1010
},
{
"epoch": 0.6412762344764951,
"grad_norm": 0.3383743166923523,
"learning_rate": 8.545470397373665e-06,
"loss": 3.0276,
"step": 1015
},
{
"epoch": 0.6444352307054434,
"grad_norm": 0.3135747015476227,
"learning_rate": 8.411346943175725e-06,
"loss": 3.0423,
"step": 1020
},
{
"epoch": 0.6475942269343916,
"grad_norm": 0.2969207465648651,
"learning_rate": 8.277873049865853e-06,
"loss": 3.0403,
"step": 1025
},
{
"epoch": 0.6507532231633398,
"grad_norm": 0.2934272587299347,
"learning_rate": 8.145061876343141e-06,
"loss": 3.0505,
"step": 1030
},
{
"epoch": 0.653912219392288,
"grad_norm": 0.30191436409950256,
"learning_rate": 8.012926516170579e-06,
"loss": 3.035,
"step": 1035
},
{
"epoch": 0.6570712156212364,
"grad_norm": 0.3008503019809723,
"learning_rate": 7.881479996284194e-06,
"loss": 3.0539,
"step": 1040
},
{
"epoch": 0.6602302118501846,
"grad_norm": 0.3256731331348419,
"learning_rate": 7.75073527570877e-06,
"loss": 3.0289,
"step": 1045
},
{
"epoch": 0.6633892080791328,
"grad_norm": 0.30159568786621094,
"learning_rate": 7.620705244280208e-06,
"loss": 3.0498,
"step": 1050
},
{
"epoch": 0.6665482043080811,
"grad_norm": 0.30907905101776123,
"learning_rate": 7.491402721374793e-06,
"loss": 3.0492,
"step": 1055
},
{
"epoch": 0.6697072005370294,
"grad_norm": 0.3054351806640625,
"learning_rate": 7.362840454645331e-06,
"loss": 3.037,
"step": 1060
},
{
"epoch": 0.6728661967659776,
"grad_norm": 0.30218011140823364,
"learning_rate": 7.23503111876438e-06,
"loss": 3.0459,
"step": 1065
},
{
"epoch": 0.6760251929949259,
"grad_norm": 0.29774144291877747,
"learning_rate": 7.107987314174706e-06,
"loss": 3.0382,
"step": 1070
},
{
"epoch": 0.6791841892238741,
"grad_norm": 0.3157255947589874,
"learning_rate": 6.981721565847017e-06,
"loss": 3.0459,
"step": 1075
},
{
"epoch": 0.6823431854528224,
"grad_norm": 0.3200543224811554,
"learning_rate": 6.8562463220451585e-06,
"loss": 3.0521,
"step": 1080
},
{
"epoch": 0.6855021816817706,
"grad_norm": 0.29882606863975525,
"learning_rate": 6.731573953098851e-06,
"loss": 3.0431,
"step": 1085
},
{
"epoch": 0.6886611779107189,
"grad_norm": 0.303469717502594,
"learning_rate": 6.607716750184158e-06,
"loss": 3.0421,
"step": 1090
},
{
"epoch": 0.6918201741396671,
"grad_norm": 0.2811189293861389,
"learning_rate": 6.484686924111696e-06,
"loss": 3.0365,
"step": 1095
},
{
"epoch": 0.6949791703686153,
"grad_norm": 0.29376232624053955,
"learning_rate": 6.362496604122816e-06,
"loss": 3.0309,
"step": 1100
},
{
"epoch": 0.6981381665975637,
"grad_norm": 0.29709020256996155,
"learning_rate": 6.241157836693803e-06,
"loss": 3.0284,
"step": 1105
},
{
"epoch": 0.7012971628265119,
"grad_norm": 0.29917705059051514,
"learning_rate": 6.120682584348221e-06,
"loss": 3.0294,
"step": 1110
},
{
"epoch": 0.7044561590554601,
"grad_norm": 0.29564398527145386,
"learning_rate": 6.0010827244775915e-06,
"loss": 3.0373,
"step": 1115
},
{
"epoch": 0.7076151552844083,
"grad_norm": 0.2984314560890198,
"learning_rate": 5.882370048170403e-06,
"loss": 3.0334,
"step": 1120
},
{
"epoch": 0.7107741515133567,
"grad_norm": 0.29895520210266113,
"learning_rate": 5.764556259049643e-06,
"loss": 3.0292,
"step": 1125
},
{
"epoch": 0.7139331477423049,
"grad_norm": 0.3032156229019165,
"learning_rate": 5.647652972118998e-06,
"loss": 3.0404,
"step": 1130
},
{
"epoch": 0.7170921439712531,
"grad_norm": 0.2889643907546997,
"learning_rate": 5.531671712617725e-06,
"loss": 3.0342,
"step": 1135
},
{
"epoch": 0.7202511402002014,
"grad_norm": 0.2965550422668457,
"learning_rate": 5.4166239148844185e-06,
"loss": 3.0412,
"step": 1140
},
{
"epoch": 0.7234101364291496,
"grad_norm": 0.29429641366004944,
"learning_rate": 5.302520921229721e-06,
"loss": 3.0379,
"step": 1145
},
{
"epoch": 0.7265691326580979,
"grad_norm": 0.2893580198287964,
"learning_rate": 5.1893739808180965e-06,
"loss": 3.0371,
"step": 1150
},
{
"epoch": 0.7297281288870462,
"grad_norm": 0.2843281328678131,
"learning_rate": 5.077194248558827e-06,
"loss": 3.0319,
"step": 1155
},
{
"epoch": 0.7328871251159944,
"grad_norm": 0.29293811321258545,
"learning_rate": 4.965992784006255e-06,
"loss": 3.027,
"step": 1160
},
{
"epoch": 0.7360461213449426,
"grad_norm": 0.28303977847099304,
"learning_rate": 4.8557805502694345e-06,
"loss": 3.0489,
"step": 1165
},
{
"epoch": 0.7392051175738908,
"grad_norm": 0.29590263962745667,
"learning_rate": 4.746568412931349e-06,
"loss": 3.0308,
"step": 1170
},
{
"epoch": 0.7423641138028392,
"grad_norm": 0.28532105684280396,
"learning_rate": 4.6383671389776365e-06,
"loss": 3.0332,
"step": 1175
},
{
"epoch": 0.7455231100317874,
"grad_norm": 0.30602291226387024,
"learning_rate": 4.531187395735143e-06,
"loss": 3.0379,
"step": 1180
},
{
"epoch": 0.7486821062607356,
"grad_norm": 0.28215503692626953,
"learning_rate": 4.425039749820238e-06,
"loss": 3.0316,
"step": 1185
},
{
"epoch": 0.7518411024896839,
"grad_norm": 0.28266972303390503,
"learning_rate": 4.319934666097055e-06,
"loss": 3.041,
"step": 1190
},
{
"epoch": 0.7550000987186322,
"grad_norm": 0.2868536412715912,
"learning_rate": 4.2158825066458216e-06,
"loss": 3.0323,
"step": 1195
},
{
"epoch": 0.7581590949475804,
"grad_norm": 0.2871454358100891,
"learning_rate": 4.112893529741264e-06,
"loss": 3.0404,
"step": 1200
},
{
"epoch": 0.7613180911765287,
"grad_norm": 0.28296205401420593,
"learning_rate": 4.010977888841249e-06,
"loss": 3.0323,
"step": 1205
},
{
"epoch": 0.7644770874054769,
"grad_norm": 0.2762405574321747,
"learning_rate": 3.910145631585825e-06,
"loss": 3.0283,
"step": 1210
},
{
"epoch": 0.7676360836344251,
"grad_norm": 0.28861716389656067,
"learning_rate": 3.810406698806594e-06,
"loss": 3.0331,
"step": 1215
},
{
"epoch": 0.7707950798633734,
"grad_norm": 0.27512839436531067,
"learning_rate": 3.711770923546688e-06,
"loss": 3.0367,
"step": 1220
},
{
"epoch": 0.7739540760923217,
"grad_norm": 0.28101062774658203,
"learning_rate": 3.6142480300913805e-06,
"loss": 3.031,
"step": 1225
},
{
"epoch": 0.7771130723212699,
"grad_norm": 0.28071752190589905,
"learning_rate": 3.5178476330093312e-06,
"loss": 3.0308,
"step": 1230
},
{
"epoch": 0.7802720685502181,
"grad_norm": 0.28007423877716064,
"learning_rate": 3.422579236204757e-06,
"loss": 3.0402,
"step": 1235
},
{
"epoch": 0.7834310647791665,
"grad_norm": 0.274509996175766,
"learning_rate": 3.328452231980443e-06,
"loss": 3.0337,
"step": 1240
},
{
"epoch": 0.7865900610081147,
"grad_norm": 0.28391996026039124,
"learning_rate": 3.2354759001117635e-06,
"loss": 3.0242,
"step": 1245
},
{
"epoch": 0.7897490572370629,
"grad_norm": 0.2775535583496094,
"learning_rate": 3.143659406931848e-06,
"loss": 3.0376,
"step": 1250
},
{
"epoch": 0.7929080534660111,
"grad_norm": 0.28023502230644226,
"learning_rate": 3.0530118044278455e-06,
"loss": 3.0298,
"step": 1255
},
{
"epoch": 0.7960670496949594,
"grad_norm": 0.2751924991607666,
"learning_rate": 2.96354202934853e-06,
"loss": 3.0241,
"step": 1260
},
{
"epoch": 0.7992260459239077,
"grad_norm": 0.26889199018478394,
"learning_rate": 2.8752589023232735e-06,
"loss": 3.0331,
"step": 1265
},
{
"epoch": 0.8023850421528559,
"grad_norm": 0.28309908509254456,
"learning_rate": 2.7881711269923824e-06,
"loss": 3.035,
"step": 1270
},
{
"epoch": 0.8055440383818042,
"grad_norm": 0.2800524830818176,
"learning_rate": 2.702287289149071e-06,
"loss": 3.0275,
"step": 1275
},
{
"epoch": 0.8087030346107524,
"grad_norm": 0.27946799993515015,
"learning_rate": 2.617615855892991e-06,
"loss": 3.0206,
"step": 1280
},
{
"epoch": 0.8118620308397007,
"grad_norm": 0.2663476765155792,
"learning_rate": 2.5341651747954667e-06,
"loss": 3.0292,
"step": 1285
},
{
"epoch": 0.815021027068649,
"grad_norm": 0.28470319509506226,
"learning_rate": 2.4519434730765542e-06,
"loss": 3.0225,
"step": 1290
},
{
"epoch": 0.8181800232975972,
"grad_norm": 0.28149184584617615,
"learning_rate": 2.3709588567939118e-06,
"loss": 3.023,
"step": 1295
},
{
"epoch": 0.8213390195265454,
"grad_norm": 0.2756572961807251,
"learning_rate": 2.2912193100436562e-06,
"loss": 3.0196,
"step": 1300
},
{
"epoch": 0.8244980157554936,
"grad_norm": 0.2727470099925995,
"learning_rate": 2.2127326941732227e-06,
"loss": 3.0342,
"step": 1305
},
{
"epoch": 0.827657011984442,
"grad_norm": 0.2859768271446228,
"learning_rate": 2.1355067470063266e-06,
"loss": 3.0145,
"step": 1310
},
{
"epoch": 0.8308160082133902,
"grad_norm": 0.26792463660240173,
"learning_rate": 2.0595490820801216e-06,
"loss": 3.0304,
"step": 1315
},
{
"epoch": 0.8339750044423384,
"grad_norm": 0.270282119512558,
"learning_rate": 1.9848671878945912e-06,
"loss": 3.0247,
"step": 1320
},
{
"epoch": 0.8371340006712867,
"grad_norm": 0.26440465450286865,
"learning_rate": 1.9114684271742624e-06,
"loss": 3.0307,
"step": 1325
},
{
"epoch": 0.840292996900235,
"grad_norm": 0.2747109830379486,
"learning_rate": 1.8393600361423534e-06,
"loss": 3.0229,
"step": 1330
},
{
"epoch": 0.8434519931291832,
"grad_norm": 0.2679141163825989,
"learning_rate": 1.7685491238073536e-06,
"loss": 3.0358,
"step": 1335
},
{
"epoch": 0.8466109893581315,
"grad_norm": 0.2704603970050812,
"learning_rate": 1.6990426712621682e-06,
"loss": 3.0391,
"step": 1340
},
{
"epoch": 0.8497699855870797,
"grad_norm": 0.26251110434532166,
"learning_rate": 1.6308475309958649e-06,
"loss": 3.0221,
"step": 1345
},
{
"epoch": 0.8529289818160279,
"grad_norm": 0.2637297809123993,
"learning_rate": 1.5639704262180992e-06,
"loss": 3.0314,
"step": 1350
},
{
"epoch": 0.8560879780449762,
"grad_norm": 0.2691202163696289,
"learning_rate": 1.4984179501962986e-06,
"loss": 3.0292,
"step": 1355
},
{
"epoch": 0.8592469742739245,
"grad_norm": 0.26560717821121216,
"learning_rate": 1.434196565605636e-06,
"loss": 3.0226,
"step": 1360
},
{
"epoch": 0.8624059705028727,
"grad_norm": 0.27092891931533813,
"learning_rate": 1.3713126038918977e-06,
"loss": 3.0277,
"step": 1365
},
{
"epoch": 0.8655649667318209,
"grad_norm": 0.26712465286254883,
"learning_rate": 1.3097722646472648e-06,
"loss": 3.0172,
"step": 1370
},
{
"epoch": 0.8687239629607693,
"grad_norm": 0.26693254709243774,
"learning_rate": 1.249581614999128e-06,
"loss": 3.0124,
"step": 1375
},
{
"epoch": 0.8718829591897175,
"grad_norm": 0.27066269516944885,
"learning_rate": 1.1907465890119317e-06,
"loss": 3.0208,
"step": 1380
},
{
"epoch": 0.8750419554186657,
"grad_norm": 0.26320889592170715,
"learning_rate": 1.133272987102152e-06,
"loss": 3.0159,
"step": 1385
},
{
"epoch": 0.878200951647614,
"grad_norm": 0.26721543073654175,
"learning_rate": 1.0771664754664368e-06,
"loss": 3.014,
"step": 1390
},
{
"epoch": 0.8813599478765622,
"grad_norm": 0.2641960680484772,
"learning_rate": 1.0224325855230048e-06,
"loss": 3.0226,
"step": 1395
},
{
"epoch": 0.8845189441055105,
"grad_norm": 0.2574079632759094,
"learning_rate": 9.690767133662976e-07,
"loss": 3.0271,
"step": 1400
},
{
"epoch": 0.8876779403344587,
"grad_norm": 0.2600894570350647,
"learning_rate": 9.171041192350044e-07,
"loss": 3.033,
"step": 1405
},
{
"epoch": 0.890836936563407,
"grad_norm": 0.2640480697154999,
"learning_rate": 8.665199269934565e-07,
"loss": 3.038,
"step": 1410
},
{
"epoch": 0.8939959327923552,
"grad_norm": 0.25655144453048706,
"learning_rate": 8.173291236264824e-07,
"loss": 3.0152,
"step": 1415
},
{
"epoch": 0.8971549290213034,
"grad_norm": 0.2634841501712799,
"learning_rate": 7.695365587477493e-07,
"loss": 3.0173,
"step": 1420
},
{
"epoch": 0.9003139252502518,
"grad_norm": 0.27021026611328125,
"learning_rate": 7.231469441216559e-07,
"loss": 3.0226,
"step": 1425
},
{
"epoch": 0.9034729214792,
"grad_norm": 0.25862905383110046,
"learning_rate": 6.781648531988005e-07,
"loss": 3.038,
"step": 1430
},
{
"epoch": 0.9066319177081482,
"grad_norm": 0.2609373927116394,
"learning_rate": 6.345947206650981e-07,
"loss": 3.0254,
"step": 1435
},
{
"epoch": 0.9097909139370964,
"grad_norm": 0.25673699378967285,
"learning_rate": 5.924408420045824e-07,
"loss": 3.0265,
"step": 1440
},
{
"epoch": 0.9129499101660448,
"grad_norm": 0.261257141828537,
"learning_rate": 5.517073730759104e-07,
"loss": 3.0197,
"step": 1445
},
{
"epoch": 0.916108906394993,
"grad_norm": 0.2595859467983246,
"learning_rate": 5.123983297026524e-07,
"loss": 3.0241,
"step": 1450
},
{
"epoch": 0.9192679026239412,
"grad_norm": 0.2619357109069824,
"learning_rate": 4.7451758727738383e-07,
"loss": 3.0239,
"step": 1455
},
{
"epoch": 0.9224268988528895,
"grad_norm": 0.263183057308197,
"learning_rate": 4.3806888037961345e-07,
"loss": 3.0252,
"step": 1460
},
{
"epoch": 0.9255858950818378,
"grad_norm": 0.2598302960395813,
"learning_rate": 4.030558024075953e-07,
"loss": 3.0296,
"step": 1465
},
{
"epoch": 0.928744891310786,
"grad_norm": 0.2560511529445648,
"learning_rate": 3.6948180522408006e-07,
"loss": 3.0178,
"step": 1470
},
{
"epoch": 0.9319038875397343,
"grad_norm": 0.25940224528312683,
"learning_rate": 3.373501988159805e-07,
"loss": 3.0206,
"step": 1475
},
{
"epoch": 0.9350628837686825,
"grad_norm": 0.25709107518196106,
"learning_rate": 3.066641509680662e-07,
"loss": 3.0219,
"step": 1480
},
{
"epoch": 0.9382218799976307,
"grad_norm": 0.2602931261062622,
"learning_rate": 2.774266869506531e-07,
"loss": 3.0213,
"step": 1485
},
{
"epoch": 0.941380876226579,
"grad_norm": 0.2598787546157837,
"learning_rate": 2.4964068922133544e-07,
"loss": 3.0306,
"step": 1490
},
{
"epoch": 0.9445398724555273,
"grad_norm": 0.2602579891681671,
"learning_rate": 2.2330889714083813e-07,
"loss": 3.0324,
"step": 1495
},
{
"epoch": 0.9476988686844755,
"grad_norm": 0.25871706008911133,
"learning_rate": 1.9843390670292283e-07,
"loss": 3.0231,
"step": 1500
},
{
"epoch": 0.9508578649134237,
"grad_norm": 0.2544022798538208,
"learning_rate": 1.7501817027846255e-07,
"loss": 3.0277,
"step": 1505
},
{
"epoch": 0.954016861142372,
"grad_norm": 0.2634129226207733,
"learning_rate": 1.5306399637368186e-07,
"loss": 3.0116,
"step": 1510
},
{
"epoch": 0.9571758573713203,
"grad_norm": 0.25936150550842285,
"learning_rate": 1.3257354940254207e-07,
"loss": 3.0421,
"step": 1515
},
{
"epoch": 0.9603348536002685,
"grad_norm": 0.25823086500167847,
"learning_rate": 1.1354884947337718e-07,
"loss": 3.0217,
"step": 1520
},
{
"epoch": 0.9634938498292168,
"grad_norm": 0.25231119990348816,
"learning_rate": 9.599177218972632e-08,
"loss": 3.0275,
"step": 1525
},
{
"epoch": 0.966652846058165,
"grad_norm": 0.25375425815582275,
"learning_rate": 7.990404846541677e-08,
"loss": 3.0233,
"step": 1530
},
{
"epoch": 0.9698118422871133,
"grad_norm": 0.2607172429561615,
"learning_rate": 6.528726435393374e-08,
"loss": 3.0282,
"step": 1535
},
{
"epoch": 0.9729708385160615,
"grad_norm": 0.25377362966537476,
"learning_rate": 5.214286089203546e-08,
"loss": 3.0203,
"step": 1540
},
{
"epoch": 0.9761298347450098,
"grad_norm": 0.25957322120666504,
"learning_rate": 4.0472133957700217e-08,
"loss": 3.0145,
"step": 1545
},
{
"epoch": 0.979288830973958,
"grad_norm": 0.2576935887336731,
"learning_rate": 3.027623414235847e-08,
"loss": 3.0342,
"step": 1550
},
{
"epoch": 0.9824478272029062,
"grad_norm": 0.2527149021625519,
"learning_rate": 2.155616663746196e-08,
"loss": 3.0237,
"step": 1555
},
{
"epoch": 0.9856068234318546,
"grad_norm": 0.25763994455337524,
"learning_rate": 1.431279113538797e-08,
"loss": 3.0257,
"step": 1560
},
{
"epoch": 0.9887658196608028,
"grad_norm": 0.25259748101234436,
"learning_rate": 8.546821744677136e-09,
"loss": 3.032,
"step": 1565
},
{
"epoch": 0.991924815889751,
"grad_norm": 0.25837600231170654,
"learning_rate": 4.258826919633085e-09,
"loss": 3.032,
"step": 1570
},
{
"epoch": 0.9950838121186992,
"grad_norm": 0.25577282905578613,
"learning_rate": 1.4492294042839361e-09,
"loss": 3.0152,
"step": 1575
},
{
"epoch": 0.9982428083476476,
"grad_norm": 0.25475648045539856,
"learning_rate": 1.1830619070229975e-10,
"loss": 3.0267,
"step": 1580
},
{
"epoch": 0.9995064068392269,
"step": 1582,
"total_flos": 2.608385800809113e+19,
"train_loss": 3.119904022602607,
"train_runtime": 95935.4971,
"train_samples_per_second": 16.894,
"train_steps_per_second": 0.016
}
],
"logging_steps": 5,
"max_steps": 1582,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 1000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2.608385800809113e+19,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}