Files
SmolLM2-ablation-ultrachat-v2/trainer_state.json
ModelHub XC 49f370e49a 初始化项目,由ModelHub XC社区提供模型
Model: HuggingFaceTB/SmolLM2-ablation-ultrachat-v2
Source: Original Platform
2026-06-19 05:04:14 +08:00

2319 lines
56 KiB
JSON

{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 1624,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.003078817733990148,
"grad_norm": 50.38856645004861,
"learning_rate": 9.20245398773006e-06,
"loss": 4.0526,
"step": 5
},
{
"epoch": 0.006157635467980296,
"grad_norm": 12.286013651157218,
"learning_rate": 1.840490797546012e-05,
"loss": 3.0627,
"step": 10
},
{
"epoch": 0.009236453201970444,
"grad_norm": 6.229091125692427,
"learning_rate": 2.760736196319018e-05,
"loss": 2.1231,
"step": 15
},
{
"epoch": 0.012315270935960592,
"grad_norm": 1.510262475449192,
"learning_rate": 3.680981595092024e-05,
"loss": 1.5949,
"step": 20
},
{
"epoch": 0.01539408866995074,
"grad_norm": 0.6618855492730493,
"learning_rate": 4.60122699386503e-05,
"loss": 1.3888,
"step": 25
},
{
"epoch": 0.01847290640394089,
"grad_norm": 0.4736843480481073,
"learning_rate": 5.521472392638036e-05,
"loss": 1.271,
"step": 30
},
{
"epoch": 0.021551724137931036,
"grad_norm": 0.3635737841173173,
"learning_rate": 6.441717791411042e-05,
"loss": 1.2593,
"step": 35
},
{
"epoch": 0.024630541871921183,
"grad_norm": 0.27576356679138664,
"learning_rate": 7.361963190184048e-05,
"loss": 1.2037,
"step": 40
},
{
"epoch": 0.02770935960591133,
"grad_norm": 0.22384727283211767,
"learning_rate": 8.282208588957055e-05,
"loss": 1.2021,
"step": 45
},
{
"epoch": 0.03078817733990148,
"grad_norm": 0.16935834836653904,
"learning_rate": 9.20245398773006e-05,
"loss": 1.2002,
"step": 50
},
{
"epoch": 0.033866995073891626,
"grad_norm": 0.2044874391461979,
"learning_rate": 0.00010122699386503066,
"loss": 1.2212,
"step": 55
},
{
"epoch": 0.03694581280788178,
"grad_norm": 0.15672541508829854,
"learning_rate": 0.00011042944785276072,
"loss": 1.2053,
"step": 60
},
{
"epoch": 0.04002463054187192,
"grad_norm": 0.10049569066590024,
"learning_rate": 0.00011963190184049077,
"loss": 1.1966,
"step": 65
},
{
"epoch": 0.04310344827586207,
"grad_norm": 0.09332393449893372,
"learning_rate": 0.00012883435582822084,
"loss": 1.1395,
"step": 70
},
{
"epoch": 0.046182266009852216,
"grad_norm": 0.08550648092997092,
"learning_rate": 0.00013803680981595091,
"loss": 1.1936,
"step": 75
},
{
"epoch": 0.04926108374384237,
"grad_norm": 0.07979275616670344,
"learning_rate": 0.00014723926380368096,
"loss": 1.1523,
"step": 80
},
{
"epoch": 0.05233990147783251,
"grad_norm": 0.06778951811302282,
"learning_rate": 0.00015644171779141103,
"loss": 1.171,
"step": 85
},
{
"epoch": 0.05541871921182266,
"grad_norm": 0.07703231151249608,
"learning_rate": 0.0001656441717791411,
"loss": 1.1668,
"step": 90
},
{
"epoch": 0.058497536945812806,
"grad_norm": 0.07480457112227284,
"learning_rate": 0.00017484662576687114,
"loss": 1.1603,
"step": 95
},
{
"epoch": 0.06157635467980296,
"grad_norm": 0.07694321599425574,
"learning_rate": 0.0001840490797546012,
"loss": 1.1758,
"step": 100
},
{
"epoch": 0.06465517241379311,
"grad_norm": 0.07691795425666145,
"learning_rate": 0.00019325153374233125,
"loss": 1.1721,
"step": 105
},
{
"epoch": 0.06773399014778325,
"grad_norm": 0.07104189615579767,
"learning_rate": 0.00020245398773006132,
"loss": 1.1784,
"step": 110
},
{
"epoch": 0.0708128078817734,
"grad_norm": 0.08097916898067846,
"learning_rate": 0.0002116564417177914,
"loss": 1.1566,
"step": 115
},
{
"epoch": 0.07389162561576355,
"grad_norm": 0.0673934112765625,
"learning_rate": 0.00022085889570552144,
"loss": 1.1726,
"step": 120
},
{
"epoch": 0.0769704433497537,
"grad_norm": 0.07282789550913175,
"learning_rate": 0.0002300613496932515,
"loss": 1.1852,
"step": 125
},
{
"epoch": 0.08004926108374384,
"grad_norm": 0.06324289940159876,
"learning_rate": 0.00023926380368098155,
"loss": 1.1492,
"step": 130
},
{
"epoch": 0.08312807881773399,
"grad_norm": 0.08247261317742449,
"learning_rate": 0.00024846625766871165,
"loss": 1.1646,
"step": 135
},
{
"epoch": 0.08620689655172414,
"grad_norm": 0.060459213376611365,
"learning_rate": 0.0002576687116564417,
"loss": 1.1889,
"step": 140
},
{
"epoch": 0.08928571428571429,
"grad_norm": 0.06475876774988848,
"learning_rate": 0.00026687116564417173,
"loss": 1.1884,
"step": 145
},
{
"epoch": 0.09236453201970443,
"grad_norm": 0.06888154958019536,
"learning_rate": 0.00027607361963190183,
"loss": 1.1447,
"step": 150
},
{
"epoch": 0.09544334975369458,
"grad_norm": 0.07087855506242281,
"learning_rate": 0.00028527607361963187,
"loss": 1.1584,
"step": 155
},
{
"epoch": 0.09852216748768473,
"grad_norm": 0.08630901843660714,
"learning_rate": 0.0002944785276073619,
"loss": 1.1877,
"step": 160
},
{
"epoch": 0.10160098522167488,
"grad_norm": 0.08085583905909743,
"learning_rate": 0.00029999861286126634,
"loss": 1.187,
"step": 165
},
{
"epoch": 0.10467980295566502,
"grad_norm": 0.06552022024987636,
"learning_rate": 0.00029998300784514774,
"loss": 1.1929,
"step": 170
},
{
"epoch": 0.10775862068965517,
"grad_norm": 0.07138017367660032,
"learning_rate": 0.000299950065699352,
"loss": 1.1611,
"step": 175
},
{
"epoch": 0.11083743842364532,
"grad_norm": 0.06324807664388049,
"learning_rate": 0.00029989979023179234,
"loss": 1.1821,
"step": 180
},
{
"epoch": 0.11391625615763547,
"grad_norm": 0.0595570623364298,
"learning_rate": 0.0002998321872540089,
"loss": 1.1817,
"step": 185
},
{
"epoch": 0.11699507389162561,
"grad_norm": 0.06867364568753653,
"learning_rate": 0.0002997472645804977,
"loss": 1.1772,
"step": 190
},
{
"epoch": 0.12007389162561577,
"grad_norm": 0.0677068522831423,
"learning_rate": 0.0002996450320278067,
"loss": 1.1672,
"step": 195
},
{
"epoch": 0.12315270935960591,
"grad_norm": 0.06738815849967911,
"learning_rate": 0.00029952550141340155,
"loss": 1.1874,
"step": 200
},
{
"epoch": 0.12623152709359606,
"grad_norm": 0.05995130645240869,
"learning_rate": 0.00029938868655429897,
"loss": 1.2042,
"step": 205
},
{
"epoch": 0.12931034482758622,
"grad_norm": 0.06464236010529685,
"learning_rate": 0.00029923460326547035,
"loss": 1.1919,
"step": 210
},
{
"epoch": 0.13238916256157635,
"grad_norm": 0.05733587235791191,
"learning_rate": 0.0002990632693580131,
"loss": 1.1777,
"step": 215
},
{
"epoch": 0.1354679802955665,
"grad_norm": 0.05665181281853336,
"learning_rate": 0.00029887470463709176,
"loss": 1.1996,
"step": 220
},
{
"epoch": 0.13854679802955666,
"grad_norm": 0.06628653725141556,
"learning_rate": 0.0002986689308996491,
"loss": 1.1785,
"step": 225
},
{
"epoch": 0.1416256157635468,
"grad_norm": 0.07440201520356507,
"learning_rate": 0.00029844597193188615,
"loss": 1.2031,
"step": 230
},
{
"epoch": 0.14470443349753695,
"grad_norm": 0.05939052729628516,
"learning_rate": 0.0002982058535065126,
"loss": 1.199,
"step": 235
},
{
"epoch": 0.1477832512315271,
"grad_norm": 0.05934843340686866,
"learning_rate": 0.00029794860337976794,
"loss": 1.1934,
"step": 240
},
{
"epoch": 0.15086206896551724,
"grad_norm": 0.057591348817156815,
"learning_rate": 0.00029767425128821284,
"loss": 1.1744,
"step": 245
},
{
"epoch": 0.1539408866995074,
"grad_norm": 0.05826131255989992,
"learning_rate": 0.00029738282894529176,
"loss": 1.1783,
"step": 250
},
{
"epoch": 0.15701970443349753,
"grad_norm": 0.06871807959978063,
"learning_rate": 0.000297074370037667,
"loss": 1.1556,
"step": 255
},
{
"epoch": 0.16009852216748768,
"grad_norm": 0.052941725572119985,
"learning_rate": 0.00029674891022132496,
"loss": 1.1788,
"step": 260
},
{
"epoch": 0.16317733990147784,
"grad_norm": 0.06797129728332164,
"learning_rate": 0.00029640648711745437,
"loss": 1.1866,
"step": 265
},
{
"epoch": 0.16625615763546797,
"grad_norm": 0.04912141933875442,
"learning_rate": 0.0002960471403080975,
"loss": 1.1478,
"step": 270
},
{
"epoch": 0.16933497536945813,
"grad_norm": 0.05922816036305705,
"learning_rate": 0.0002956709113315748,
"loss": 1.1754,
"step": 275
},
{
"epoch": 0.1724137931034483,
"grad_norm": 0.05558679641070003,
"learning_rate": 0.00029527784367768304,
"loss": 1.1763,
"step": 280
},
{
"epoch": 0.17549261083743842,
"grad_norm": 0.050995724834403455,
"learning_rate": 0.00029486798278266865,
"loss": 1.1829,
"step": 285
},
{
"epoch": 0.17857142857142858,
"grad_norm": 0.06133067209638226,
"learning_rate": 0.00029444137602397514,
"loss": 1.1818,
"step": 290
},
{
"epoch": 0.1816502463054187,
"grad_norm": 0.05288482197409358,
"learning_rate": 0.0002939980727147667,
"loss": 1.1537,
"step": 295
},
{
"epoch": 0.18472906403940886,
"grad_norm": 0.06931970292251229,
"learning_rate": 0.00029353812409822804,
"loss": 1.1762,
"step": 300
},
{
"epoch": 0.18780788177339902,
"grad_norm": 0.06181342605951454,
"learning_rate": 0.0002930615833416406,
"loss": 1.1676,
"step": 305
},
{
"epoch": 0.19088669950738915,
"grad_norm": 0.06743746977094597,
"learning_rate": 0.00029256850553023724,
"loss": 1.1809,
"step": 310
},
{
"epoch": 0.1939655172413793,
"grad_norm": 0.0697665266218925,
"learning_rate": 0.00029205894766083423,
"loss": 1.1718,
"step": 315
},
{
"epoch": 0.19704433497536947,
"grad_norm": 0.05681707919103611,
"learning_rate": 0.00029153296863524314,
"loss": 1.1778,
"step": 320
},
{
"epoch": 0.2001231527093596,
"grad_norm": 0.05637558099273313,
"learning_rate": 0.000290990629253462,
"loss": 1.1753,
"step": 325
},
{
"epoch": 0.20320197044334976,
"grad_norm": 0.0542853294964714,
"learning_rate": 0.000290431992206647,
"loss": 1.2035,
"step": 330
},
{
"epoch": 0.2062807881773399,
"grad_norm": 0.05165783935463062,
"learning_rate": 0.00028985712206986623,
"loss": 1.1933,
"step": 335
},
{
"epoch": 0.20935960591133004,
"grad_norm": 0.058288364592485487,
"learning_rate": 0.0002892660852946347,
"loss": 1.1768,
"step": 340
},
{
"epoch": 0.2124384236453202,
"grad_norm": 0.05191963697431743,
"learning_rate": 0.00028865895020123325,
"loss": 1.1794,
"step": 345
},
{
"epoch": 0.21551724137931033,
"grad_norm": 0.05366438672538025,
"learning_rate": 0.00028803578697081107,
"loss": 1.1419,
"step": 350
},
{
"epoch": 0.2185960591133005,
"grad_norm": 0.05571255525900963,
"learning_rate": 0.00028739666763727314,
"loss": 1.1849,
"step": 355
},
{
"epoch": 0.22167487684729065,
"grad_norm": 0.061645059292380164,
"learning_rate": 0.0002867416660789535,
"loss": 1.1965,
"step": 360
},
{
"epoch": 0.22475369458128078,
"grad_norm": 0.05034992525169977,
"learning_rate": 0.0002860708580100756,
"loss": 1.1558,
"step": 365
},
{
"epoch": 0.22783251231527094,
"grad_norm": 0.050954387485294905,
"learning_rate": 0.00028538432097199997,
"loss": 1.2023,
"step": 370
},
{
"epoch": 0.2309113300492611,
"grad_norm": 0.04949930516295786,
"learning_rate": 0.0002846821343242608,
"loss": 1.1545,
"step": 375
},
{
"epoch": 0.23399014778325122,
"grad_norm": 0.04823554810066786,
"learning_rate": 0.00028396437923539276,
"loss": 1.1839,
"step": 380
},
{
"epoch": 0.23706896551724138,
"grad_norm": 0.051726967554164616,
"learning_rate": 0.0002832311386735483,
"loss": 1.1571,
"step": 385
},
{
"epoch": 0.24014778325123154,
"grad_norm": 0.049883532232990406,
"learning_rate": 0.0002824824973969069,
"loss": 1.1852,
"step": 390
},
{
"epoch": 0.24322660098522167,
"grad_norm": 0.05238097677905913,
"learning_rate": 0.00028171854194387766,
"loss": 1.1774,
"step": 395
},
{
"epoch": 0.24630541871921183,
"grad_norm": 0.05247463617085741,
"learning_rate": 0.0002809393606230961,
"loss": 1.1826,
"step": 400
},
{
"epoch": 0.24938423645320196,
"grad_norm": 0.04796046660573051,
"learning_rate": 0.0002801450435032159,
"loss": 1.1595,
"step": 405
},
{
"epoch": 0.2524630541871921,
"grad_norm": 0.05966845311794142,
"learning_rate": 0.0002793356824024977,
"loss": 1.1652,
"step": 410
},
{
"epoch": 0.2555418719211823,
"grad_norm": 0.048690088781763854,
"learning_rate": 0.00027851137087819556,
"loss": 1.2181,
"step": 415
},
{
"epoch": 0.25862068965517243,
"grad_norm": 0.056761235073461334,
"learning_rate": 0.00027767220421574205,
"loss": 1.1644,
"step": 420
},
{
"epoch": 0.2616995073891626,
"grad_norm": 0.052605316007136624,
"learning_rate": 0.0002768182794177341,
"loss": 1.1569,
"step": 425
},
{
"epoch": 0.2647783251231527,
"grad_norm": 0.05643227732551046,
"learning_rate": 0.00027594969519271985,
"loss": 1.1579,
"step": 430
},
{
"epoch": 0.26785714285714285,
"grad_norm": 0.05679901179486835,
"learning_rate": 0.0002750665519437887,
"loss": 1.1565,
"step": 435
},
{
"epoch": 0.270935960591133,
"grad_norm": 0.04705945476255655,
"learning_rate": 0.0002741689517569653,
"loss": 1.1621,
"step": 440
},
{
"epoch": 0.27401477832512317,
"grad_norm": 0.0533072614923673,
"learning_rate": 0.0002732569983894089,
"loss": 1.1501,
"step": 445
},
{
"epoch": 0.2770935960591133,
"grad_norm": 0.05214010746975868,
"learning_rate": 0.00027233079725741985,
"loss": 1.2095,
"step": 450
},
{
"epoch": 0.2801724137931034,
"grad_norm": 0.051512876075085604,
"learning_rate": 0.0002713904554242539,
"loss": 1.1632,
"step": 455
},
{
"epoch": 0.2832512315270936,
"grad_norm": 0.05449453644222859,
"learning_rate": 0.0002704360815877464,
"loss": 1.1578,
"step": 460
},
{
"epoch": 0.28633004926108374,
"grad_norm": 0.048712599005479404,
"learning_rate": 0.00026946778606774775,
"loss": 1.1914,
"step": 465
},
{
"epoch": 0.2894088669950739,
"grad_norm": 0.04917657608682948,
"learning_rate": 0.00026848568079337057,
"loss": 1.1916,
"step": 470
},
{
"epoch": 0.29248768472906406,
"grad_norm": 0.048210811471264416,
"learning_rate": 0.00026748987929005183,
"loss": 1.1727,
"step": 475
},
{
"epoch": 0.2955665024630542,
"grad_norm": 0.05132967485033094,
"learning_rate": 0.0002664804966664298,
"loss": 1.1367,
"step": 480
},
{
"epoch": 0.2986453201970443,
"grad_norm": 0.05263024844978328,
"learning_rate": 0.0002654576496010382,
"loss": 1.1866,
"step": 485
},
{
"epoch": 0.3017241379310345,
"grad_norm": 0.04680097562012947,
"learning_rate": 0.0002644214563288189,
"loss": 1.184,
"step": 490
},
{
"epoch": 0.30480295566502463,
"grad_norm": 0.04804900302680845,
"learning_rate": 0.00026337203662745465,
"loss": 1.1318,
"step": 495
},
{
"epoch": 0.3078817733990148,
"grad_norm": 0.051167685147898795,
"learning_rate": 0.0002623095118035235,
"loss": 1.147,
"step": 500
},
{
"epoch": 0.31096059113300495,
"grad_norm": 0.05176545627262626,
"learning_rate": 0.00026123400467847646,
"loss": 1.175,
"step": 505
},
{
"epoch": 0.31403940886699505,
"grad_norm": 0.06503594781066656,
"learning_rate": 0.00026014563957444027,
"loss": 1.1852,
"step": 510
},
{
"epoch": 0.3171182266009852,
"grad_norm": 0.06028116706319379,
"learning_rate": 0.0002590445422998462,
"loss": 1.1895,
"step": 515
},
{
"epoch": 0.32019704433497537,
"grad_norm": 0.051890202164141655,
"learning_rate": 0.00025793084013488757,
"loss": 1.1614,
"step": 520
},
{
"epoch": 0.3232758620689655,
"grad_norm": 0.049540807614816426,
"learning_rate": 0.000256804661816807,
"loss": 1.1711,
"step": 525
},
{
"epoch": 0.3263546798029557,
"grad_norm": 0.049089498561689225,
"learning_rate": 0.00025566613752501486,
"loss": 1.1523,
"step": 530
},
{
"epoch": 0.3294334975369458,
"grad_norm": 0.04641486867240031,
"learning_rate": 0.0002545153988660416,
"loss": 1.1366,
"step": 535
},
{
"epoch": 0.33251231527093594,
"grad_norm": 0.04421789649967022,
"learning_rate": 0.0002533525788583248,
"loss": 1.1491,
"step": 540
},
{
"epoch": 0.3355911330049261,
"grad_norm": 0.051201410076125324,
"learning_rate": 0.0002521778119168328,
"loss": 1.1712,
"step": 545
},
{
"epoch": 0.33866995073891626,
"grad_norm": 0.04844111678301553,
"learning_rate": 0.00025099123383752746,
"loss": 1.1395,
"step": 550
},
{
"epoch": 0.3417487684729064,
"grad_norm": 0.0455724606442663,
"learning_rate": 0.0002497929817816667,
"loss": 1.1473,
"step": 555
},
{
"epoch": 0.3448275862068966,
"grad_norm": 0.0460600518472407,
"learning_rate": 0.00024858319425994973,
"loss": 1.1458,
"step": 560
},
{
"epoch": 0.3479064039408867,
"grad_norm": 0.05506428913516847,
"learning_rate": 0.00024736201111650593,
"loss": 1.1538,
"step": 565
},
{
"epoch": 0.35098522167487683,
"grad_norm": 0.05563411490329983,
"learning_rate": 0.0002461295735127296,
"loss": 1.1961,
"step": 570
},
{
"epoch": 0.354064039408867,
"grad_norm": 0.056417869389575055,
"learning_rate": 0.00024488602391096266,
"loss": 1.1509,
"step": 575
},
{
"epoch": 0.35714285714285715,
"grad_norm": 0.044634671841241556,
"learning_rate": 0.000243631506058027,
"loss": 1.0967,
"step": 580
},
{
"epoch": 0.3602216748768473,
"grad_norm": 0.05681552839667373,
"learning_rate": 0.00024236616496860807,
"loss": 1.1583,
"step": 585
},
{
"epoch": 0.3633004926108374,
"grad_norm": 0.04885679789266538,
"learning_rate": 0.00024109014690849197,
"loss": 1.1584,
"step": 590
},
{
"epoch": 0.36637931034482757,
"grad_norm": 0.04341097125362442,
"learning_rate": 0.00023980359937765818,
"loss": 1.1324,
"step": 595
},
{
"epoch": 0.3694581280788177,
"grad_norm": 0.04553399519638483,
"learning_rate": 0.0002385066710932294,
"loss": 1.1298,
"step": 600
},
{
"epoch": 0.3725369458128079,
"grad_norm": 0.05184123935132177,
"learning_rate": 0.00023719951197228065,
"loss": 1.1572,
"step": 605
},
{
"epoch": 0.37561576354679804,
"grad_norm": 0.04624722077310968,
"learning_rate": 0.00023588227311451004,
"loss": 1.1133,
"step": 610
},
{
"epoch": 0.3786945812807882,
"grad_norm": 0.04390718695584042,
"learning_rate": 0.00023455510678477214,
"loss": 1.1502,
"step": 615
},
{
"epoch": 0.3817733990147783,
"grad_norm": 0.047100450393721,
"learning_rate": 0.00023321816639547746,
"loss": 1.1295,
"step": 620
},
{
"epoch": 0.38485221674876846,
"grad_norm": 0.041425234363904766,
"learning_rate": 0.00023187160648885862,
"loss": 1.1232,
"step": 625
},
{
"epoch": 0.3879310344827586,
"grad_norm": 0.05264101409128052,
"learning_rate": 0.00023051558271910657,
"loss": 1.1584,
"step": 630
},
{
"epoch": 0.3910098522167488,
"grad_norm": 0.05066181204127044,
"learning_rate": 0.00022915025183437737,
"loss": 1.1306,
"step": 635
},
{
"epoch": 0.39408866995073893,
"grad_norm": 0.04994315804883078,
"learning_rate": 0.00022777577165867353,
"loss": 1.1655,
"step": 640
},
{
"epoch": 0.39716748768472904,
"grad_norm": 0.05740175492244425,
"learning_rate": 0.00022639230107360033,
"loss": 1.1166,
"step": 645
},
{
"epoch": 0.4002463054187192,
"grad_norm": 0.0548825788764783,
"learning_rate": 0.000225,
"loss": 1.1437,
"step": 650
},
{
"epoch": 0.40332512315270935,
"grad_norm": 0.0508590133922253,
"learning_rate": 0.00022359902937946585,
"loss": 1.1367,
"step": 655
},
{
"epoch": 0.4064039408866995,
"grad_norm": 0.053268316131299134,
"learning_rate": 0.00022218955115573864,
"loss": 1.1493,
"step": 660
},
{
"epoch": 0.40948275862068967,
"grad_norm": 0.0478290413448589,
"learning_rate": 0.00022077172825598644,
"loss": 1.1292,
"step": 665
},
{
"epoch": 0.4125615763546798,
"grad_norm": 0.047348092203963646,
"learning_rate": 0.0002193457245719716,
"loss": 1.1793,
"step": 670
},
{
"epoch": 0.41564039408866993,
"grad_norm": 0.047405713247936423,
"learning_rate": 0.00021791170494110565,
"loss": 1.1408,
"step": 675
},
{
"epoch": 0.4187192118226601,
"grad_norm": 0.04628184019719908,
"learning_rate": 0.0002164698351273952,
"loss": 1.1664,
"step": 680
},
{
"epoch": 0.42179802955665024,
"grad_norm": 0.043861598174596936,
"learning_rate": 0.0002150202818022805,
"loss": 1.1239,
"step": 685
},
{
"epoch": 0.4248768472906404,
"grad_norm": 0.04576831333716289,
"learning_rate": 0.00021356321252536943,
"loss": 1.1575,
"step": 690
},
{
"epoch": 0.42795566502463056,
"grad_norm": 0.04308247251808224,
"learning_rate": 0.00021209879572506833,
"loss": 1.1277,
"step": 695
},
{
"epoch": 0.43103448275862066,
"grad_norm": 0.04592876136664352,
"learning_rate": 0.00021062720067911296,
"loss": 1.1289,
"step": 700
},
{
"epoch": 0.4341133004926108,
"grad_norm": 0.04546503142254463,
"learning_rate": 0.000209148597495001,
"loss": 1.1023,
"step": 705
},
{
"epoch": 0.437192118226601,
"grad_norm": 0.04773750839831541,
"learning_rate": 0.00020766315709032832,
"loss": 1.126,
"step": 710
},
{
"epoch": 0.44027093596059114,
"grad_norm": 0.05140791964457529,
"learning_rate": 0.00020617105117303245,
"loss": 1.1468,
"step": 715
},
{
"epoch": 0.4433497536945813,
"grad_norm": 0.04612841965738631,
"learning_rate": 0.0002046724522215437,
"loss": 1.1758,
"step": 720
},
{
"epoch": 0.44642857142857145,
"grad_norm": 0.04660673268461518,
"learning_rate": 0.000203167533464848,
"loss": 1.1386,
"step": 725
},
{
"epoch": 0.44950738916256155,
"grad_norm": 0.04964175004753263,
"learning_rate": 0.00020165646886246273,
"loss": 1.1259,
"step": 730
},
{
"epoch": 0.4525862068965517,
"grad_norm": 0.041815184975431824,
"learning_rate": 0.00020013943308432754,
"loss": 1.1076,
"step": 735
},
{
"epoch": 0.45566502463054187,
"grad_norm": 0.048586756912997346,
"learning_rate": 0.00019861660149061433,
"loss": 1.159,
"step": 740
},
{
"epoch": 0.45874384236453203,
"grad_norm": 0.045207025632546124,
"learning_rate": 0.000197088150111456,
"loss": 1.1398,
"step": 745
},
{
"epoch": 0.4618226600985222,
"grad_norm": 0.044617722580800434,
"learning_rate": 0.00019555425562659876,
"loss": 1.1265,
"step": 750
},
{
"epoch": 0.4649014778325123,
"grad_norm": 0.046190267598805346,
"learning_rate": 0.00019401509534497908,
"loss": 1.1628,
"step": 755
},
{
"epoch": 0.46798029556650245,
"grad_norm": 0.047836899630830924,
"learning_rate": 0.00019247084718422756,
"loss": 1.1233,
"step": 760
},
{
"epoch": 0.4710591133004926,
"grad_norm": 0.043922626344731396,
"learning_rate": 0.00019092168965010296,
"loss": 1.1303,
"step": 765
},
{
"epoch": 0.47413793103448276,
"grad_norm": 0.04461114507198429,
"learning_rate": 0.00018936780181585798,
"loss": 1.1282,
"step": 770
},
{
"epoch": 0.4772167487684729,
"grad_norm": 0.046557751408618064,
"learning_rate": 0.00018780936330153934,
"loss": 1.1319,
"step": 775
},
{
"epoch": 0.4802955665024631,
"grad_norm": 0.04774877915254769,
"learning_rate": 0.00018624655425322499,
"loss": 1.1416,
"step": 780
},
{
"epoch": 0.4833743842364532,
"grad_norm": 0.04221647867481708,
"learning_rate": 0.00018467955532220016,
"loss": 1.1206,
"step": 785
},
{
"epoch": 0.48645320197044334,
"grad_norm": 0.04617075121928804,
"learning_rate": 0.00018310854764407527,
"loss": 1.1496,
"step": 790
},
{
"epoch": 0.4895320197044335,
"grad_norm": 0.04529125572246932,
"learning_rate": 0.00018153371281784755,
"loss": 1.0997,
"step": 795
},
{
"epoch": 0.49261083743842365,
"grad_norm": 0.045582114128932955,
"learning_rate": 0.00017995523288490958,
"loss": 1.1447,
"step": 800
},
{
"epoch": 0.4956896551724138,
"grad_norm": 0.045798431153999675,
"learning_rate": 0.00017837329030800619,
"loss": 1.1234,
"step": 805
},
{
"epoch": 0.4987684729064039,
"grad_norm": 0.04824160475492181,
"learning_rate": 0.0001767880679501429,
"loss": 1.128,
"step": 810
},
{
"epoch": 0.5018472906403941,
"grad_norm": 0.04679748199549485,
"learning_rate": 0.00017519974905344816,
"loss": 1.1369,
"step": 815
},
{
"epoch": 0.5049261083743842,
"grad_norm": 0.04871713134562279,
"learning_rate": 0.00017360851721799162,
"loss": 1.1246,
"step": 820
},
{
"epoch": 0.5080049261083743,
"grad_norm": 0.044184960299547195,
"learning_rate": 0.00017201455638056094,
"loss": 1.1321,
"step": 825
},
{
"epoch": 0.5110837438423645,
"grad_norm": 0.040536708042946776,
"learning_rate": 0.00017041805079340004,
"loss": 1.1202,
"step": 830
},
{
"epoch": 0.5141625615763546,
"grad_norm": 0.04608053305469613,
"learning_rate": 0.0001688191850029105,
"loss": 1.1637,
"step": 835
},
{
"epoch": 0.5172413793103449,
"grad_norm": 0.044715413053021694,
"learning_rate": 0.00016721814382831908,
"loss": 1.1426,
"step": 840
},
{
"epoch": 0.520320197044335,
"grad_norm": 0.043453219206167196,
"learning_rate": 0.00016561511234031392,
"loss": 1.1574,
"step": 845
},
{
"epoch": 0.5233990147783252,
"grad_norm": 0.04279262289062732,
"learning_rate": 0.00016401027583965133,
"loss": 1.1421,
"step": 850
},
{
"epoch": 0.5264778325123153,
"grad_norm": 0.04093715529238329,
"learning_rate": 0.00016240381983573607,
"loss": 1.1228,
"step": 855
},
{
"epoch": 0.5295566502463054,
"grad_norm": 0.04306169563429485,
"learning_rate": 0.00016079593002517784,
"loss": 1.1353,
"step": 860
},
{
"epoch": 0.5326354679802956,
"grad_norm": 0.05187273357813354,
"learning_rate": 0.00015918679227032562,
"loss": 1.1361,
"step": 865
},
{
"epoch": 0.5357142857142857,
"grad_norm": 0.05101923741800583,
"learning_rate": 0.00015757659257778338,
"loss": 1.135,
"step": 870
},
{
"epoch": 0.5387931034482759,
"grad_norm": 0.04291106939412229,
"learning_rate": 0.00015596551707690838,
"loss": 1.1197,
"step": 875
},
{
"epoch": 0.541871921182266,
"grad_norm": 0.04559125575459384,
"learning_rate": 0.0001543537519982963,
"loss": 1.1607,
"step": 880
},
{
"epoch": 0.5449507389162561,
"grad_norm": 0.04201244642982363,
"learning_rate": 0.0001527414836522537,
"loss": 1.1255,
"step": 885
},
{
"epoch": 0.5480295566502463,
"grad_norm": 0.044043660674491586,
"learning_rate": 0.00015112889840726194,
"loss": 1.154,
"step": 890
},
{
"epoch": 0.5511083743842364,
"grad_norm": 0.0452152621741999,
"learning_rate": 0.0001495161826684338,
"loss": 1.1378,
"step": 895
},
{
"epoch": 0.5541871921182266,
"grad_norm": 0.04485340918926222,
"learning_rate": 0.00014790352285596654,
"loss": 1.1101,
"step": 900
},
{
"epoch": 0.5572660098522167,
"grad_norm": 0.046825327285685864,
"learning_rate": 0.00014629110538359248,
"loss": 1.1624,
"step": 905
},
{
"epoch": 0.5603448275862069,
"grad_norm": 0.045889981273966464,
"learning_rate": 0.00014467911663703116,
"loss": 1.1239,
"step": 910
},
{
"epoch": 0.5634236453201971,
"grad_norm": 0.04453915010182345,
"learning_rate": 0.0001430677429524437,
"loss": 1.1241,
"step": 915
},
{
"epoch": 0.5665024630541872,
"grad_norm": 0.04279916293208543,
"learning_rate": 0.00014145717059489403,
"loss": 1.1481,
"step": 920
},
{
"epoch": 0.5695812807881774,
"grad_norm": 0.04071953346630088,
"learning_rate": 0.00013984758573681738,
"loss": 1.1129,
"step": 925
},
{
"epoch": 0.5726600985221675,
"grad_norm": 0.04422283503178165,
"learning_rate": 0.00013823917443649993,
"loss": 1.0892,
"step": 930
},
{
"epoch": 0.5757389162561576,
"grad_norm": 0.042149718248337985,
"learning_rate": 0.0001366321226165719,
"loss": 1.1165,
"step": 935
},
{
"epoch": 0.5788177339901478,
"grad_norm": 0.04120662311881514,
"learning_rate": 0.0001350266160425156,
"loss": 1.1293,
"step": 940
},
{
"epoch": 0.5818965517241379,
"grad_norm": 0.04549665355171013,
"learning_rate": 0.00013342284030119233,
"loss": 1.1483,
"step": 945
},
{
"epoch": 0.5849753694581281,
"grad_norm": 0.04339851061208546,
"learning_rate": 0.00013182098077938953,
"loss": 1.1656,
"step": 950
},
{
"epoch": 0.5880541871921182,
"grad_norm": 0.041607843577072104,
"learning_rate": 0.0001302212226423913,
"loss": 1.1555,
"step": 955
},
{
"epoch": 0.5911330049261084,
"grad_norm": 0.0424950133510136,
"learning_rate": 0.00012862375081257438,
"loss": 1.1387,
"step": 960
},
{
"epoch": 0.5942118226600985,
"grad_norm": 0.04300771476243836,
"learning_rate": 0.00012702874994803204,
"loss": 1.1264,
"step": 965
},
{
"epoch": 0.5972906403940886,
"grad_norm": 0.04566603436728389,
"learning_rate": 0.0001254364044212291,
"loss": 1.1179,
"step": 970
},
{
"epoch": 0.6003694581280788,
"grad_norm": 0.04384679476800769,
"learning_rate": 0.00012384689829768926,
"loss": 1.0915,
"step": 975
},
{
"epoch": 0.603448275862069,
"grad_norm": 0.046499313834380746,
"learning_rate": 0.00012226041531471834,
"loss": 1.109,
"step": 980
},
{
"epoch": 0.6065270935960592,
"grad_norm": 0.04092308374981243,
"learning_rate": 0.00012067713886016547,
"loss": 1.1424,
"step": 985
},
{
"epoch": 0.6096059113300493,
"grad_norm": 0.04515635488422341,
"learning_rate": 0.00011909725195122441,
"loss": 1.122,
"step": 990
},
{
"epoch": 0.6126847290640394,
"grad_norm": 0.04214756506385618,
"learning_rate": 0.00011752093721327784,
"loss": 1.1376,
"step": 995
},
{
"epoch": 0.6157635467980296,
"grad_norm": 0.04302162710361374,
"learning_rate": 0.00011594837685878724,
"loss": 1.1261,
"step": 1000
},
{
"epoch": 0.6188423645320197,
"grad_norm": 0.04287033511685806,
"learning_rate": 0.00011437975266622989,
"loss": 1.1158,
"step": 1005
},
{
"epoch": 0.6219211822660099,
"grad_norm": 0.04792917861513863,
"learning_rate": 0.00011281524595908652,
"loss": 1.1257,
"step": 1010
},
{
"epoch": 0.625,
"grad_norm": 0.04734303937388139,
"learning_rate": 0.00011125503758488157,
"loss": 1.1312,
"step": 1015
},
{
"epoch": 0.6280788177339901,
"grad_norm": 0.04270294086187758,
"learning_rate": 0.00010969930789427797,
"loss": 1.1256,
"step": 1020
},
{
"epoch": 0.6311576354679803,
"grad_norm": 0.04130387760687185,
"learning_rate": 0.00010814823672023006,
"loss": 1.1015,
"step": 1025
},
{
"epoch": 0.6342364532019704,
"grad_norm": 0.041820000972043664,
"learning_rate": 0.00010660200335719567,
"loss": 1.1239,
"step": 1030
},
{
"epoch": 0.6373152709359606,
"grad_norm": 0.0431031355333031,
"learning_rate": 0.00010506078654041093,
"loss": 1.1158,
"step": 1035
},
{
"epoch": 0.6403940886699507,
"grad_norm": 0.044136231046209236,
"learning_rate": 0.00010352476442522962,
"loss": 1.0843,
"step": 1040
},
{
"epoch": 0.6434729064039408,
"grad_norm": 0.04170427324424424,
"learning_rate": 0.0001019941145665293,
"loss": 1.1268,
"step": 1045
},
{
"epoch": 0.646551724137931,
"grad_norm": 0.04439576000209051,
"learning_rate": 0.00010046901389818707,
"loss": 1.1164,
"step": 1050
},
{
"epoch": 0.6496305418719212,
"grad_norm": 0.04665761328886588,
"learning_rate": 9.894963871262739e-05,
"loss": 1.1797,
"step": 1055
},
{
"epoch": 0.6527093596059114,
"grad_norm": 0.043273693916828976,
"learning_rate": 9.743616464044317e-05,
"loss": 1.1278,
"step": 1060
},
{
"epoch": 0.6557881773399015,
"grad_norm": 0.04386070827853346,
"learning_rate": 9.59287666300946e-05,
"loss": 1.1471,
"step": 1065
},
{
"epoch": 0.6588669950738916,
"grad_norm": 0.04902401213885766,
"learning_rate": 9.44276189276856e-05,
"loss": 1.1113,
"step": 1070
},
{
"epoch": 0.6619458128078818,
"grad_norm": 0.04266210582134216,
"learning_rate": 9.293289505682222e-05,
"loss": 1.1258,
"step": 1075
},
{
"epoch": 0.6650246305418719,
"grad_norm": 0.04144763202101391,
"learning_rate": 9.144476779855461e-05,
"loss": 1.1238,
"step": 1080
},
{
"epoch": 0.6681034482758621,
"grad_norm": 0.04243593449766583,
"learning_rate": 8.996340917140419e-05,
"loss": 1.1047,
"step": 1085
},
{
"epoch": 0.6711822660098522,
"grad_norm": 0.0413416141157621,
"learning_rate": 8.848899041147946e-05,
"loss": 1.1184,
"step": 1090
},
{
"epoch": 0.6742610837438424,
"grad_norm": 0.046019069937229894,
"learning_rate": 8.702168195268239e-05,
"loss": 1.1033,
"step": 1095
},
{
"epoch": 0.6773399014778325,
"grad_norm": 0.04370283997000188,
"learning_rate": 8.556165340700688e-05,
"loss": 1.1303,
"step": 1100
},
{
"epoch": 0.6804187192118226,
"grad_norm": 0.04297630495859546,
"learning_rate": 8.410907354493302e-05,
"loss": 1.1419,
"step": 1105
},
{
"epoch": 0.6834975369458128,
"grad_norm": 0.04114328246979562,
"learning_rate": 8.2664110275918e-05,
"loss": 1.1022,
"step": 1110
},
{
"epoch": 0.6865763546798029,
"grad_norm": 0.0433771165633938,
"learning_rate": 8.122693062898678e-05,
"loss": 1.1292,
"step": 1115
},
{
"epoch": 0.6896551724137931,
"grad_norm": 0.040152416846321155,
"learning_rate": 7.979770073342483e-05,
"loss": 1.1225,
"step": 1120
},
{
"epoch": 0.6927339901477833,
"grad_norm": 0.04337601287416731,
"learning_rate": 7.837658579957421e-05,
"loss": 1.0862,
"step": 1125
},
{
"epoch": 0.6958128078817734,
"grad_norm": 0.041398039045623114,
"learning_rate": 7.696375009973642e-05,
"loss": 1.1293,
"step": 1130
},
{
"epoch": 0.6988916256157636,
"grad_norm": 0.04182896302514871,
"learning_rate": 7.55593569491837e-05,
"loss": 1.1,
"step": 1135
},
{
"epoch": 0.7019704433497537,
"grad_norm": 0.04065543277842893,
"learning_rate": 7.416356868728039e-05,
"loss": 1.0955,
"step": 1140
},
{
"epoch": 0.7050492610837439,
"grad_norm": 0.0418957684673326,
"learning_rate": 7.277654665871784e-05,
"loss": 1.0928,
"step": 1145
},
{
"epoch": 0.708128078817734,
"grad_norm": 0.04627301647032954,
"learning_rate": 7.13984511948637e-05,
"loss": 1.0859,
"step": 1150
},
{
"epoch": 0.7112068965517241,
"grad_norm": 0.040979100399232644,
"learning_rate": 7.002944159522858e-05,
"loss": 1.1294,
"step": 1155
},
{
"epoch": 0.7142857142857143,
"grad_norm": 0.0430112600197784,
"learning_rate": 6.866967610905233e-05,
"loss": 1.1111,
"step": 1160
},
{
"epoch": 0.7173645320197044,
"grad_norm": 0.04631737558793455,
"learning_rate": 6.731931191701087e-05,
"loss": 1.0893,
"step": 1165
},
{
"epoch": 0.7204433497536946,
"grad_norm": 0.04638863609412046,
"learning_rate": 6.597850511304737e-05,
"loss": 1.0821,
"step": 1170
},
{
"epoch": 0.7235221674876847,
"grad_norm": 0.04250842463920331,
"learning_rate": 6.464741068632882e-05,
"loss": 1.1344,
"step": 1175
},
{
"epoch": 0.7266009852216748,
"grad_norm": 0.04449020274712862,
"learning_rate": 6.332618250332987e-05,
"loss": 1.133,
"step": 1180
},
{
"epoch": 0.729679802955665,
"grad_norm": 0.039704386883419915,
"learning_rate": 6.201497329004718e-05,
"loss": 1.0954,
"step": 1185
},
{
"epoch": 0.7327586206896551,
"grad_norm": 0.043243561549705926,
"learning_rate": 6.071393461434487e-05,
"loss": 1.1219,
"step": 1190
},
{
"epoch": 0.7358374384236454,
"grad_norm": 0.045039321819015175,
"learning_rate": 5.942321686843443e-05,
"loss": 1.1167,
"step": 1195
},
{
"epoch": 0.7389162561576355,
"grad_norm": 0.039557148842893464,
"learning_rate": 5.814296925149025e-05,
"loss": 1.1046,
"step": 1200
},
{
"epoch": 0.7419950738916257,
"grad_norm": 0.04180043543118903,
"learning_rate": 5.6873339752403026e-05,
"loss": 1.1021,
"step": 1205
},
{
"epoch": 0.7450738916256158,
"grad_norm": 0.04192889048300918,
"learning_rate": 5.56144751326731e-05,
"loss": 1.1243,
"step": 1210
},
{
"epoch": 0.7481527093596059,
"grad_norm": 0.03977579606674208,
"learning_rate": 5.436652090944596e-05,
"loss": 1.1308,
"step": 1215
},
{
"epoch": 0.7512315270935961,
"grad_norm": 0.041207759285483224,
"learning_rate": 5.312962133869093e-05,
"loss": 1.1068,
"step": 1220
},
{
"epoch": 0.7543103448275862,
"grad_norm": 0.03993587810589233,
"learning_rate": 5.190391939852659e-05,
"loss": 1.097,
"step": 1225
},
{
"epoch": 0.7573891625615764,
"grad_norm": 0.04120789114575358,
"learning_rate": 5.06895567726928e-05,
"loss": 1.0633,
"step": 1230
},
{
"epoch": 0.7604679802955665,
"grad_norm": 0.040401046347087174,
"learning_rate": 4.948667383417331e-05,
"loss": 1.1273,
"step": 1235
},
{
"epoch": 0.7635467980295566,
"grad_norm": 0.04089337800800299,
"learning_rate": 4.8295409628969265e-05,
"loss": 1.076,
"step": 1240
},
{
"epoch": 0.7666256157635468,
"grad_norm": 0.04070816241047168,
"learning_rate": 4.7115901860026626e-05,
"loss": 1.1172,
"step": 1245
},
{
"epoch": 0.7697044334975369,
"grad_norm": 0.040318855090158624,
"learning_rate": 4.594828687131814e-05,
"loss": 1.0828,
"step": 1250
},
{
"epoch": 0.7727832512315271,
"grad_norm": 0.04508155286821903,
"learning_rate": 4.479269963208304e-05,
"loss": 1.1248,
"step": 1255
},
{
"epoch": 0.7758620689655172,
"grad_norm": 0.03995219192628373,
"learning_rate": 4.36492737212255e-05,
"loss": 1.1135,
"step": 1260
},
{
"epoch": 0.7789408866995073,
"grad_norm": 0.039941011523419105,
"learning_rate": 4.251814131187348e-05,
"loss": 1.0693,
"step": 1265
},
{
"epoch": 0.7820197044334976,
"grad_norm": 0.04036662006741658,
"learning_rate": 4.13994331561004e-05,
"loss": 1.1043,
"step": 1270
},
{
"epoch": 0.7850985221674877,
"grad_norm": 0.042755455161098,
"learning_rate": 4.0293278569811196e-05,
"loss": 1.118,
"step": 1275
},
{
"epoch": 0.7881773399014779,
"grad_norm": 0.04133440618697741,
"learning_rate": 3.919980541779383e-05,
"loss": 1.0899,
"step": 1280
},
{
"epoch": 0.791256157635468,
"grad_norm": 0.03930501250448446,
"learning_rate": 3.8119140098939074e-05,
"loss": 1.1012,
"step": 1285
},
{
"epoch": 0.7943349753694581,
"grad_norm": 0.04093443015461556,
"learning_rate": 3.705140753162973e-05,
"loss": 1.1119,
"step": 1290
},
{
"epoch": 0.7974137931034483,
"grad_norm": 0.040640552100214826,
"learning_rate": 3.599673113930047e-05,
"loss": 1.0768,
"step": 1295
},
{
"epoch": 0.8004926108374384,
"grad_norm": 0.040329145320771025,
"learning_rate": 3.495523283617105e-05,
"loss": 1.0901,
"step": 1300
},
{
"epoch": 0.8035714285714286,
"grad_norm": 0.040601907302338876,
"learning_rate": 3.39270330131538e-05,
"loss": 1.0721,
"step": 1305
},
{
"epoch": 0.8066502463054187,
"grad_norm": 0.04279584390563618,
"learning_rate": 3.2912250523936996e-05,
"loss": 1.0779,
"step": 1310
},
{
"epoch": 0.8097290640394089,
"grad_norm": 0.038733198431655264,
"learning_rate": 3.191100267124616e-05,
"loss": 1.0872,
"step": 1315
},
{
"epoch": 0.812807881773399,
"grad_norm": 0.03852439056078866,
"learning_rate": 3.0923405193284736e-05,
"loss": 1.0599,
"step": 1320
},
{
"epoch": 0.8158866995073891,
"grad_norm": 0.043517407120524466,
"learning_rate": 2.9949572250355176e-05,
"loss": 1.0735,
"step": 1325
},
{
"epoch": 0.8189655172413793,
"grad_norm": 0.03808040925500465,
"learning_rate": 2.8989616411662825e-05,
"loss": 1.0797,
"step": 1330
},
{
"epoch": 0.8220443349753694,
"grad_norm": 0.04020694606048214,
"learning_rate": 2.8043648642303713e-05,
"loss": 1.1173,
"step": 1335
},
{
"epoch": 0.8251231527093597,
"grad_norm": 0.039563508521763255,
"learning_rate": 2.7111778290437464e-05,
"loss": 1.1062,
"step": 1340
},
{
"epoch": 0.8282019704433498,
"grad_norm": 0.039381031183324824,
"learning_rate": 2.6194113074647465e-05,
"loss": 1.084,
"step": 1345
},
{
"epoch": 0.8312807881773399,
"grad_norm": 0.03946596220802881,
"learning_rate": 2.5290759071489157e-05,
"loss": 1.1227,
"step": 1350
},
{
"epoch": 0.8343596059113301,
"grad_norm": 0.03849482700977278,
"learning_rate": 2.4401820703228175e-05,
"loss": 1.0942,
"step": 1355
},
{
"epoch": 0.8374384236453202,
"grad_norm": 0.039117050183502325,
"learning_rate": 2.3527400725770018e-05,
"loss": 1.1251,
"step": 1360
},
{
"epoch": 0.8405172413793104,
"grad_norm": 0.04057422162412,
"learning_rate": 2.2667600216781755e-05,
"loss": 1.1211,
"step": 1365
},
{
"epoch": 0.8435960591133005,
"grad_norm": 0.03765711409730217,
"learning_rate": 2.1822518564008258e-05,
"loss": 1.1147,
"step": 1370
},
{
"epoch": 0.8466748768472906,
"grad_norm": 0.043123291529812646,
"learning_rate": 2.099225345378359e-05,
"loss": 1.135,
"step": 1375
},
{
"epoch": 0.8497536945812808,
"grad_norm": 0.04029852856465984,
"learning_rate": 2.0176900859738902e-05,
"loss": 1.0967,
"step": 1380
},
{
"epoch": 0.8528325123152709,
"grad_norm": 0.041977593516173986,
"learning_rate": 1.9376555031708696e-05,
"loss": 1.0774,
"step": 1385
},
{
"epoch": 0.8559113300492611,
"grad_norm": 0.04014002948094123,
"learning_rate": 1.8591308484835833e-05,
"loss": 1.0947,
"step": 1390
},
{
"epoch": 0.8589901477832512,
"grad_norm": 0.040132378595879384,
"learning_rate": 1.7821251988877556e-05,
"loss": 1.0973,
"step": 1395
},
{
"epoch": 0.8620689655172413,
"grad_norm": 0.04240262822321613,
"learning_rate": 1.7066474557713017e-05,
"loss": 1.1037,
"step": 1400
},
{
"epoch": 0.8651477832512315,
"grad_norm": 0.039888863240256416,
"learning_rate": 1.6327063439053674e-05,
"loss": 1.0866,
"step": 1405
},
{
"epoch": 0.8682266009852216,
"grad_norm": 0.039011831654239645,
"learning_rate": 1.56031041043582e-05,
"loss": 1.0865,
"step": 1410
},
{
"epoch": 0.8713054187192119,
"grad_norm": 0.04116164895870449,
"learning_rate": 1.4894680238952316e-05,
"loss": 1.0975,
"step": 1415
},
{
"epoch": 0.874384236453202,
"grad_norm": 0.04162964016440304,
"learning_rate": 1.420187373235534e-05,
"loss": 1.1208,
"step": 1420
},
{
"epoch": 0.8774630541871922,
"grad_norm": 0.04275706801553967,
"learning_rate": 1.3524764668814303e-05,
"loss": 1.118,
"step": 1425
},
{
"epoch": 0.8805418719211823,
"grad_norm": 0.039194770845201454,
"learning_rate": 1.2863431318046614e-05,
"loss": 1.115,
"step": 1430
},
{
"epoch": 0.8836206896551724,
"grad_norm": 0.038777826740170274,
"learning_rate": 1.2217950126192522e-05,
"loss": 1.0839,
"step": 1435
},
{
"epoch": 0.8866995073891626,
"grad_norm": 0.040512615022748576,
"learning_rate": 1.158839570697861e-05,
"loss": 1.0794,
"step": 1440
},
{
"epoch": 0.8897783251231527,
"grad_norm": 0.04023830936361266,
"learning_rate": 1.0974840833092602e-05,
"loss": 1.0794,
"step": 1445
},
{
"epoch": 0.8928571428571429,
"grad_norm": 0.04074087711443184,
"learning_rate": 1.0377356427771565e-05,
"loss": 1.1059,
"step": 1450
},
{
"epoch": 0.895935960591133,
"grad_norm": 0.04490752852168335,
"learning_rate": 9.796011556603418e-06,
"loss": 1.1164,
"step": 1455
},
{
"epoch": 0.8990147783251231,
"grad_norm": 0.03880253679837365,
"learning_rate": 9.230873419543372e-06,
"loss": 1.082,
"step": 1460
},
{
"epoch": 0.9020935960591133,
"grad_norm": 0.038012956733589,
"learning_rate": 8.682007343146196e-06,
"loss": 1.0974,
"step": 1465
},
{
"epoch": 0.9051724137931034,
"grad_norm": 0.042116813458087404,
"learning_rate": 8.14947677301468e-06,
"loss": 1.0838,
"step": 1470
},
{
"epoch": 0.9082512315270936,
"grad_norm": 0.04035754826496353,
"learning_rate": 7.63334326646573e-06,
"loss": 1.099,
"step": 1475
},
{
"epoch": 0.9113300492610837,
"grad_norm": 0.03861582924101178,
"learning_rate": 7.1336664854148575e-06,
"loss": 1.1191,
"step": 1480
},
{
"epoch": 0.9144088669950738,
"grad_norm": 0.0461316776177713,
"learning_rate": 6.650504189479416e-06,
"loss": 1.1121,
"step": 1485
},
{
"epoch": 0.9174876847290641,
"grad_norm": 0.04073043599510325,
"learning_rate": 6.1839122293021345e-06,
"loss": 1.0722,
"step": 1490
},
{
"epoch": 0.9205665024630542,
"grad_norm": 0.04221065551477172,
"learning_rate": 5.733944540094976e-06,
"loss": 1.0924,
"step": 1495
},
{
"epoch": 0.9236453201970444,
"grad_norm": 0.04046059842262868,
"learning_rate": 5.300653135404559e-06,
"loss": 1.1047,
"step": 1500
},
{
"epoch": 0.9267241379310345,
"grad_norm": 0.039745570925508907,
"learning_rate": 4.884088101099854e-06,
"loss": 1.0812,
"step": 1505
},
{
"epoch": 0.9298029556650246,
"grad_norm": 0.04064911719790208,
"learning_rate": 4.484297589582392e-06,
"loss": 1.0946,
"step": 1510
},
{
"epoch": 0.9328817733990148,
"grad_norm": 0.042527495825039,
"learning_rate": 4.10132781422019e-06,
"loss": 1.0773,
"step": 1515
},
{
"epoch": 0.9359605911330049,
"grad_norm": 0.03937320960563834,
"learning_rate": 3.735223044005853e-06,
"loss": 1.0862,
"step": 1520
},
{
"epoch": 0.9390394088669951,
"grad_norm": 0.04175381396720523,
"learning_rate": 3.386025598439185e-06,
"loss": 1.0932,
"step": 1525
},
{
"epoch": 0.9421182266009852,
"grad_norm": 0.038338615834160344,
"learning_rate": 3.053775842635453e-06,
"loss": 1.0717,
"step": 1530
},
{
"epoch": 0.9451970443349754,
"grad_norm": 0.03721540533470224,
"learning_rate": 2.738512182659336e-06,
"loss": 1.1004,
"step": 1535
},
{
"epoch": 0.9482758620689655,
"grad_norm": 0.03929274228981452,
"learning_rate": 2.440271061085458e-06,
"loss": 1.0894,
"step": 1540
},
{
"epoch": 0.9513546798029556,
"grad_norm": 0.04078678453532611,
"learning_rate": 2.1590869527858267e-06,
"loss": 1.0915,
"step": 1545
},
{
"epoch": 0.9544334975369458,
"grad_norm": 0.03961701339788748,
"learning_rate": 1.894992360944786e-06,
"loss": 1.0934,
"step": 1550
},
{
"epoch": 0.9575123152709359,
"grad_norm": 0.039518775061522744,
"learning_rate": 1.6480178133017386e-06,
"loss": 1.0709,
"step": 1555
},
{
"epoch": 0.9605911330049262,
"grad_norm": 0.036710240604112834,
"learning_rate": 1.4181918586225027e-06,
"loss": 1.091,
"step": 1560
},
{
"epoch": 0.9636699507389163,
"grad_norm": 0.04036474742342838,
"learning_rate": 1.2055410633990513e-06,
"loss": 1.1029,
"step": 1565
},
{
"epoch": 0.9667487684729064,
"grad_norm": 0.040306154399267685,
"learning_rate": 1.0100900087787357e-06,
"loss": 1.0796,
"step": 1570
},
{
"epoch": 0.9698275862068966,
"grad_norm": 0.03993954952246081,
"learning_rate": 8.318612877227571e-07,
"loss": 1.0749,
"step": 1575
},
{
"epoch": 0.9729064039408867,
"grad_norm": 0.041220915766970116,
"learning_rate": 6.708755023946244e-07,
"loss": 1.082,
"step": 1580
},
{
"epoch": 0.9759852216748769,
"grad_norm": 0.04003375509606215,
"learning_rate": 5.271512617786077e-07,
"loss": 1.1201,
"step": 1585
},
{
"epoch": 0.979064039408867,
"grad_norm": 0.039658812487889376,
"learning_rate": 4.0070517952870973e-07,
"loss": 1.0823,
"step": 1590
},
{
"epoch": 0.9821428571428571,
"grad_norm": 0.04282612584010836,
"learning_rate": 2.915518720482013e-07,
"loss": 1.105,
"step": 1595
},
{
"epoch": 0.9852216748768473,
"grad_norm": 0.038810987953770734,
"learning_rate": 1.9970395680004025e-07,
"loss": 1.084,
"step": 1600
},
{
"epoch": 0.9883004926108374,
"grad_norm": 0.0392747761517772,
"learning_rate": 1.2517205084837113e-07,
"loss": 1.0915,
"step": 1605
},
{
"epoch": 0.9913793103448276,
"grad_norm": 0.037467036015125,
"learning_rate": 6.796476963130682e-08,
"loss": 1.0957,
"step": 1610
},
{
"epoch": 0.9944581280788177,
"grad_norm": 0.038399940492356,
"learning_rate": 2.8088725964958703e-08,
"loss": 1.09,
"step": 1615
},
{
"epoch": 0.9975369458128078,
"grad_norm": 0.03913271753873893,
"learning_rate": 5.548529279081337e-09,
"loss": 1.0697,
"step": 1620
},
{
"epoch": 1.0,
"eval_loss": 1.1087726354599,
"eval_runtime": 150.5176,
"eval_samples_per_second": 153.537,
"eval_steps_per_second": 4.803,
"step": 1624
},
{
"epoch": 1.0,
"step": 1624,
"total_flos": 237087321751552.0,
"train_loss": 1.1564865382434113,
"train_runtime": 5664.6342,
"train_samples_per_second": 36.695,
"train_steps_per_second": 0.287
}
],
"logging_steps": 5,
"max_steps": 1624,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": false,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 237087321751552.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}