think_8b_full / trainer_state.json
modrill's picture
Upload folder using huggingface_hub
2735954 verified
Raw
History Blame Contribute Delete
39.2 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 500,
"global_step": 2050,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00976145445671405,
"grad_norm": 2.7171718937708893,
"learning_rate": 2.903225806451613e-06,
"loss": 0.836665153503418,
"step": 10
},
{
"epoch": 0.0195229089134281,
"grad_norm": 2.07278967505522,
"learning_rate": 6.129032258064517e-06,
"loss": 0.7774394035339356,
"step": 20
},
{
"epoch": 0.02928436337014215,
"grad_norm": 0.8052418041946412,
"learning_rate": 9.35483870967742e-06,
"loss": 0.7118394851684571,
"step": 30
},
{
"epoch": 0.0390458178268562,
"grad_norm": 0.48425847572228153,
"learning_rate": 1.2580645161290324e-05,
"loss": 0.6741247177124023,
"step": 40
},
{
"epoch": 0.04880727228357025,
"grad_norm": 0.46915653943519686,
"learning_rate": 1.5806451612903226e-05,
"loss": 0.6543425559997559,
"step": 50
},
{
"epoch": 0.0585687267402843,
"grad_norm": 0.4655546322355271,
"learning_rate": 1.903225806451613e-05,
"loss": 0.6383125305175781,
"step": 60
},
{
"epoch": 0.06833018119699835,
"grad_norm": 0.5385119940038303,
"learning_rate": 1.9999388172996495e-05,
"loss": 0.631153678894043,
"step": 70
},
{
"epoch": 0.0780916356537124,
"grad_norm": 0.48632725158098256,
"learning_rate": 1.9996391649532744e-05,
"loss": 0.620881175994873,
"step": 80
},
{
"epoch": 0.08785309011042645,
"grad_norm": 0.5147422480903651,
"learning_rate": 1.999089880058469e-05,
"loss": 0.6154061794281006,
"step": 90
},
{
"epoch": 0.0976145445671405,
"grad_norm": 0.4859310369557681,
"learning_rate": 1.9982910997841175e-05,
"loss": 0.608434009552002,
"step": 100
},
{
"epoch": 0.10737599902385456,
"grad_norm": 0.49855799612783797,
"learning_rate": 1.9972430236037522e-05,
"loss": 0.6053113460540771,
"step": 110
},
{
"epoch": 0.1171374534805686,
"grad_norm": 0.4389090045007552,
"learning_rate": 1.9959459132457415e-05,
"loss": 0.6017628192901612,
"step": 120
},
{
"epoch": 0.12689890793728265,
"grad_norm": 0.656672526601482,
"learning_rate": 1.9944000926279304e-05,
"loss": 0.5999305725097657,
"step": 130
},
{
"epoch": 0.1366603623939967,
"grad_norm": 0.4397790605918159,
"learning_rate": 1.992605947776752e-05,
"loss": 0.5955329895019531,
"step": 140
},
{
"epoch": 0.14642181685071076,
"grad_norm": 0.4826398780157024,
"learning_rate": 1.9905639267308244e-05,
"loss": 0.5946754932403564,
"step": 150
},
{
"epoch": 0.1561832713074248,
"grad_norm": 0.445880792065111,
"learning_rate": 1.9882745394290705e-05,
"loss": 0.5919600009918213,
"step": 160
},
{
"epoch": 0.16594472576413885,
"grad_norm": 0.4224995436975534,
"learning_rate": 1.9857383575833693e-05,
"loss": 0.591130542755127,
"step": 170
},
{
"epoch": 0.1757061802208529,
"grad_norm": 0.489317471321096,
"learning_rate": 1.9829560145357906e-05,
"loss": 0.5881345748901368,
"step": 180
},
{
"epoch": 0.18546763467756697,
"grad_norm": 0.391013199589406,
"learning_rate": 1.979928205100434e-05,
"loss": 0.5874452114105224,
"step": 190
},
{
"epoch": 0.195229089134281,
"grad_norm": 0.5132703421819202,
"learning_rate": 1.9766556853899153e-05,
"loss": 0.5850434303283691,
"step": 200
},
{
"epoch": 0.20499054359099506,
"grad_norm": 0.4317384739639613,
"learning_rate": 1.9731392726265538e-05,
"loss": 0.5791005611419677,
"step": 210
},
{
"epoch": 0.21475199804770911,
"grad_norm": 0.5450508704505641,
"learning_rate": 1.9693798449382873e-05,
"loss": 0.5837528228759765,
"step": 220
},
{
"epoch": 0.22451345250442317,
"grad_norm": 0.3995851796223643,
"learning_rate": 1.9653783411393875e-05,
"loss": 0.5809955596923828,
"step": 230
},
{
"epoch": 0.2342749069611372,
"grad_norm": 0.515662880685764,
"learning_rate": 1.9611357604960156e-05,
"loss": 0.5800333499908448,
"step": 240
},
{
"epoch": 0.24403636141785126,
"grad_norm": 0.5467899695375602,
"learning_rate": 1.956653162476683e-05,
"loss": 0.5769859313964844,
"step": 250
},
{
"epoch": 0.2537978158745653,
"grad_norm": 0.5737871165214032,
"learning_rate": 1.9519316664876782e-05,
"loss": 0.5788938999176025,
"step": 260
},
{
"epoch": 0.26355927033127935,
"grad_norm": 0.4010513125091312,
"learning_rate": 1.9469724515935242e-05,
"loss": 0.5743288993835449,
"step": 270
},
{
"epoch": 0.2733207247879934,
"grad_norm": 0.4230903232640434,
"learning_rate": 1.9417767562225422e-05,
"loss": 0.574954605102539,
"step": 280
},
{
"epoch": 0.28308217924470747,
"grad_norm": 0.3663575439721741,
"learning_rate": 1.9363458778575857e-05,
"loss": 0.5711943149566651,
"step": 290
},
{
"epoch": 0.2928436337014215,
"grad_norm": 0.3917259340992501,
"learning_rate": 1.9306811727120305e-05,
"loss": 0.5710340976715088,
"step": 300
},
{
"epoch": 0.3026050881581356,
"grad_norm": 0.3906911977658059,
"learning_rate": 1.9247840553910974e-05,
"loss": 0.5703779220581054,
"step": 310
},
{
"epoch": 0.3123665426148496,
"grad_norm": 0.3869882324226975,
"learning_rate": 1.918655998538593e-05,
"loss": 0.5712218761444092,
"step": 320
},
{
"epoch": 0.32212799707156364,
"grad_norm": 0.42061349121115077,
"learning_rate": 1.9122985324691576e-05,
"loss": 0.5702820777893066,
"step": 330
},
{
"epoch": 0.3318894515282777,
"grad_norm": 0.3490137440957352,
"learning_rate": 1.9057132447861104e-05,
"loss": 0.5708161354064941,
"step": 340
},
{
"epoch": 0.34165090598499176,
"grad_norm": 0.3818865656026688,
"learning_rate": 1.8989017799849896e-05,
"loss": 0.5661185264587403,
"step": 350
},
{
"epoch": 0.3514123604417058,
"grad_norm": 0.4120345721034505,
"learning_rate": 1.891865839042884e-05,
"loss": 0.567262077331543,
"step": 360
},
{
"epoch": 0.3611738148984199,
"grad_norm": 0.43217811509239235,
"learning_rate": 1.8846071789936614e-05,
"loss": 0.5655131340026855,
"step": 370
},
{
"epoch": 0.37093526935513393,
"grad_norm": 0.4701369380275007,
"learning_rate": 1.8771276124891957e-05,
"loss": 0.5688438892364502,
"step": 380
},
{
"epoch": 0.380696723811848,
"grad_norm": 0.46742334095939286,
"learning_rate": 1.8694290073467095e-05,
"loss": 0.5635671138763427,
"step": 390
},
{
"epoch": 0.390458178268562,
"grad_norm": 0.3883819468179728,
"learning_rate": 1.861513286082334e-05,
"loss": 0.565738296508789,
"step": 400
},
{
"epoch": 0.40021963272527605,
"grad_norm": 0.3827208108942853,
"learning_rate": 1.853382425431017e-05,
"loss": 0.559232521057129,
"step": 410
},
{
"epoch": 0.4099810871819901,
"grad_norm": 0.4254061229161546,
"learning_rate": 1.8450384558528848e-05,
"loss": 0.5624125003814697,
"step": 420
},
{
"epoch": 0.41974254163870417,
"grad_norm": 0.35465965142588046,
"learning_rate": 1.8364834610261916e-05,
"loss": 0.5655581474304199,
"step": 430
},
{
"epoch": 0.42950399609541823,
"grad_norm": 0.4281031584614048,
"learning_rate": 1.8277195773269766e-05,
"loss": 0.5620370388031006,
"step": 440
},
{
"epoch": 0.4392654505521323,
"grad_norm": 0.4804782555657488,
"learning_rate": 1.818748993295564e-05,
"loss": 0.5620602607727051,
"step": 450
},
{
"epoch": 0.44902690500884634,
"grad_norm": 0.38870985648173306,
"learning_rate": 1.8095739490900344e-05,
"loss": 0.5619917392730713,
"step": 460
},
{
"epoch": 0.45878835946556035,
"grad_norm": 0.3609209290714297,
"learning_rate": 1.8001967359268057e-05,
"loss": 0.5599178314208985,
"step": 470
},
{
"epoch": 0.4685498139222744,
"grad_norm": 0.4060075614643235,
"learning_rate": 1.7906196955084655e-05,
"loss": 0.5566294193267822,
"step": 480
},
{
"epoch": 0.47831126837898846,
"grad_norm": 0.354932964564927,
"learning_rate": 1.780845219438994e-05,
"loss": 0.5581831932067871,
"step": 490
},
{
"epoch": 0.4880727228357025,
"grad_norm": 0.45534621360021393,
"learning_rate": 1.7708757486265272e-05,
"loss": 0.5574597358703614,
"step": 500
},
{
"epoch": 0.4978341772924166,
"grad_norm": 0.40068634910147427,
"learning_rate": 1.7607137726738074e-05,
"loss": 0.5564365863800049,
"step": 510
},
{
"epoch": 0.5075956317491306,
"grad_norm": 0.34894544504616437,
"learning_rate": 1.7503618292564698e-05,
"loss": 0.5602200984954834,
"step": 520
},
{
"epoch": 0.5173570862058446,
"grad_norm": 0.37009751996998264,
"learning_rate": 1.7398225034893316e-05,
"loss": 0.5574421882629395,
"step": 530
},
{
"epoch": 0.5271185406625587,
"grad_norm": 0.4134599279143897,
"learning_rate": 1.7290984272808276e-05,
"loss": 0.5567829132080078,
"step": 540
},
{
"epoch": 0.5368799951192728,
"grad_norm": 0.332174943430511,
"learning_rate": 1.718192278675763e-05,
"loss": 0.5541606426239014,
"step": 550
},
{
"epoch": 0.5466414495759868,
"grad_norm": 0.33602414898403216,
"learning_rate": 1.7071067811865477e-05,
"loss": 0.5544651985168457,
"step": 560
},
{
"epoch": 0.5564029040327009,
"grad_norm": 0.33647281770469845,
"learning_rate": 1.695844703113069e-05,
"loss": 0.5550961971282959,
"step": 570
},
{
"epoch": 0.5661643584894149,
"grad_norm": 0.3715339963292226,
"learning_rate": 1.6844088568513885e-05,
"loss": 0.5519819259643555,
"step": 580
},
{
"epoch": 0.575925812946129,
"grad_norm": 0.40192776010408143,
"learning_rate": 1.6728020981914207e-05,
"loss": 0.5516290664672852,
"step": 590
},
{
"epoch": 0.585687267402843,
"grad_norm": 0.43597621131226744,
"learning_rate": 1.661027325603779e-05,
"loss": 0.5543393611907959,
"step": 600
},
{
"epoch": 0.5954487218595571,
"grad_norm": 0.3551114083289793,
"learning_rate": 1.6490874795159613e-05,
"loss": 0.5514196395874024,
"step": 610
},
{
"epoch": 0.6052101763162712,
"grad_norm": 0.33284570590742457,
"learning_rate": 1.6369855415780577e-05,
"loss": 0.5529036045074462,
"step": 620
},
{
"epoch": 0.6149716307729852,
"grad_norm": 0.34597390793742416,
"learning_rate": 1.624724533918166e-05,
"loss": 0.5506466388702392,
"step": 630
},
{
"epoch": 0.6247330852296992,
"grad_norm": 0.41047533039337214,
"learning_rate": 1.612307518387699e-05,
"loss": 0.5541812896728515,
"step": 640
},
{
"epoch": 0.6344945396864132,
"grad_norm": 0.42638581477939697,
"learning_rate": 1.5997375957967672e-05,
"loss": 0.5505136966705322,
"step": 650
},
{
"epoch": 0.6442559941431273,
"grad_norm": 0.3472164806411414,
"learning_rate": 1.5870179051398405e-05,
"loss": 0.5473326683044434,
"step": 660
},
{
"epoch": 0.6540174485998413,
"grad_norm": 0.4198356949808895,
"learning_rate": 1.5741516228118677e-05,
"loss": 0.5478506088256836,
"step": 670
},
{
"epoch": 0.6637789030565554,
"grad_norm": 0.4438126537908133,
"learning_rate": 1.561141961815058e-05,
"loss": 0.5543909072875977,
"step": 680
},
{
"epoch": 0.6735403575132695,
"grad_norm": 0.33771998620183863,
"learning_rate": 1.5479921709565244e-05,
"loss": 0.5508096218109131,
"step": 690
},
{
"epoch": 0.6833018119699835,
"grad_norm": 0.340535151725663,
"learning_rate": 1.5347055340369806e-05,
"loss": 0.5471370220184326,
"step": 700
},
{
"epoch": 0.6930632664266976,
"grad_norm": 0.4340557843782887,
"learning_rate": 1.521285369030702e-05,
"loss": 0.5477546691894531,
"step": 710
},
{
"epoch": 0.7028247208834116,
"grad_norm": 0.36480023918471327,
"learning_rate": 1.5077350272569531e-05,
"loss": 0.5477032661437988,
"step": 720
},
{
"epoch": 0.7125861753401257,
"grad_norm": 0.3173237839308878,
"learning_rate": 1.4940578925430866e-05,
"loss": 0.547743844985962,
"step": 730
},
{
"epoch": 0.7223476297968398,
"grad_norm": 0.3798598286861374,
"learning_rate": 1.480257380379525e-05,
"loss": 0.544849967956543,
"step": 740
},
{
"epoch": 0.7321090842535538,
"grad_norm": 0.32520027859246653,
"learning_rate": 1.4663369370668348e-05,
"loss": 0.5443988800048828,
"step": 750
},
{
"epoch": 0.7418705387102679,
"grad_norm": 0.42154822049578927,
"learning_rate": 1.4523000388551089e-05,
"loss": 0.5458567619323731,
"step": 760
},
{
"epoch": 0.7516319931669819,
"grad_norm": 0.35290152971174465,
"learning_rate": 1.4381501910758662e-05,
"loss": 0.5455081939697266,
"step": 770
},
{
"epoch": 0.761393447623696,
"grad_norm": 0.36092224743501783,
"learning_rate": 1.4238909272666919e-05,
"loss": 0.5444242477416992,
"step": 780
},
{
"epoch": 0.7711549020804099,
"grad_norm": 0.33599605389036247,
"learning_rate": 1.409525808288833e-05,
"loss": 0.5462691307067871,
"step": 790
},
{
"epoch": 0.780916356537124,
"grad_norm": 0.28914267872490046,
"learning_rate": 1.3950584214379703e-05,
"loss": 0.5470402717590332,
"step": 800
},
{
"epoch": 0.790677810993838,
"grad_norm": 0.31535694158721245,
"learning_rate": 1.38049237954839e-05,
"loss": 0.5445716381072998,
"step": 810
},
{
"epoch": 0.8004392654505521,
"grad_norm": 0.3928771588299645,
"learning_rate": 1.365831320090776e-05,
"loss": 0.5462616920471192,
"step": 820
},
{
"epoch": 0.8102007199072662,
"grad_norm": 0.3047321449256657,
"learning_rate": 1.3510789042638525e-05,
"loss": 0.5432579040527343,
"step": 830
},
{
"epoch": 0.8199621743639802,
"grad_norm": 0.3068462237254663,
"learning_rate": 1.3362388160800992e-05,
"loss": 0.5435873985290527,
"step": 840
},
{
"epoch": 0.8297236288206943,
"grad_norm": 0.34358206165151545,
"learning_rate": 1.321314761445768e-05,
"loss": 0.5405595302581787,
"step": 850
},
{
"epoch": 0.8394850832774083,
"grad_norm": 0.42312860515314266,
"learning_rate": 1.3063104672354384e-05,
"loss": 0.5467127799987793,
"step": 860
},
{
"epoch": 0.8492465377341224,
"grad_norm": 0.3673885167838325,
"learning_rate": 1.2912296803613275e-05,
"loss": 0.5438889026641845,
"step": 870
},
{
"epoch": 0.8590079921908365,
"grad_norm": 0.36921788638943953,
"learning_rate": 1.2760761668376063e-05,
"loss": 0.5435795783996582,
"step": 880
},
{
"epoch": 0.8687694466475505,
"grad_norm": 0.32043541605358555,
"learning_rate": 1.2608537108399354e-05,
"loss": 0.5429807662963867,
"step": 890
},
{
"epoch": 0.8785309011042646,
"grad_norm": 0.5009575102224276,
"learning_rate": 1.245566113760475e-05,
"loss": 0.5389288902282715,
"step": 900
},
{
"epoch": 0.8882923555609786,
"grad_norm": 0.2979746358811125,
"learning_rate": 1.2302171932585885e-05,
"loss": 0.5378171920776367,
"step": 910
},
{
"epoch": 0.8980538100176927,
"grad_norm": 0.28399182752163593,
"learning_rate": 1.2148107823074873e-05,
"loss": 0.5402212142944336,
"step": 920
},
{
"epoch": 0.9078152644744066,
"grad_norm": 0.3370739446485531,
"learning_rate": 1.1993507282370514e-05,
"loss": 0.5409811019897461,
"step": 930
},
{
"epoch": 0.9175767189311207,
"grad_norm": 0.3550432507180414,
"learning_rate": 1.183840891773062e-05,
"loss": 0.539578914642334,
"step": 940
},
{
"epoch": 0.9273381733878348,
"grad_norm": 0.34671610827130145,
"learning_rate": 1.168285146073092e-05,
"loss": 0.5414035797119141,
"step": 950
},
{
"epoch": 0.9370996278445488,
"grad_norm": 0.37188884026877206,
"learning_rate": 1.1526873757592918e-05,
"loss": 0.5388407230377197,
"step": 960
},
{
"epoch": 0.9468610823012629,
"grad_norm": 0.3200151532383385,
"learning_rate": 1.1370514759483082e-05,
"loss": 0.5389005184173584,
"step": 970
},
{
"epoch": 0.9566225367579769,
"grad_norm": 0.32261766442972056,
"learning_rate": 1.1213813512785897e-05,
"loss": 0.5396491050720215,
"step": 980
},
{
"epoch": 0.966383991214691,
"grad_norm": 0.34539226916656524,
"learning_rate": 1.1056809149353054e-05,
"loss": 0.5376710891723633,
"step": 990
},
{
"epoch": 0.976145445671405,
"grad_norm": 0.2641656693803474,
"learning_rate": 1.0899540876731366e-05,
"loss": 0.5359292984008789,
"step": 1000
},
{
"epoch": 0.9859069001281191,
"grad_norm": 0.3181162211492277,
"learning_rate": 1.074204796837176e-05,
"loss": 0.539863920211792,
"step": 1010
},
{
"epoch": 0.9956683545848332,
"grad_norm": 0.3150477781887309,
"learning_rate": 1.0584369753821781e-05,
"loss": 0.53628511428833,
"step": 1020
},
{
"epoch": 1.004880727228357,
"grad_norm": 0.29779537591859595,
"learning_rate": 1.0426545608904141e-05,
"loss": 0.5282849788665771,
"step": 1030
},
{
"epoch": 1.014642181685071,
"grad_norm": 0.2966743319834602,
"learning_rate": 1.0268614945883664e-05,
"loss": 0.5184188842773437,
"step": 1040
},
{
"epoch": 1.0244036361417852,
"grad_norm": 0.3260541525878062,
"learning_rate": 1.011061720362516e-05,
"loss": 0.5220568656921387,
"step": 1050
},
{
"epoch": 1.0341650905984991,
"grad_norm": 0.31299117990102804,
"learning_rate": 9.952591837744642e-06,
"loss": 0.5197721004486084,
"step": 1060
},
{
"epoch": 1.0439265450552133,
"grad_norm": 0.34448199483903647,
"learning_rate": 9.794578310756374e-06,
"loss": 0.5208293914794921,
"step": 1070
},
{
"epoch": 1.0536879995119273,
"grad_norm": 0.2638359119791302,
"learning_rate": 9.63661608221817e-06,
"loss": 0.5157252788543701,
"step": 1080
},
{
"epoch": 1.0634494539686412,
"grad_norm": 0.2903025405775747,
"learning_rate": 9.478744598877469e-06,
"loss": 0.5209471702575683,
"step": 1090
},
{
"epoch": 1.0732109084253554,
"grad_norm": 0.2932303464794665,
"learning_rate": 9.321003284820576e-06,
"loss": 0.5197690963745117,
"step": 1100
},
{
"epoch": 1.0829723628820693,
"grad_norm": 0.2662280101895485,
"learning_rate": 9.163431531627569e-06,
"loss": 0.5224910736083984,
"step": 1110
},
{
"epoch": 1.0927338173387835,
"grad_norm": 0.28431364201602966,
"learning_rate": 9.006068688535342e-06,
"loss": 0.5179880619049072,
"step": 1120
},
{
"epoch": 1.1024952717954974,
"grad_norm": 0.2973709269157597,
"learning_rate": 8.848954052611206e-06,
"loss": 0.5165664672851562,
"step": 1130
},
{
"epoch": 1.1122567262522116,
"grad_norm": 0.314239603184092,
"learning_rate": 8.692126858939515e-06,
"loss": 0.5158205986022949,
"step": 1140
},
{
"epoch": 1.1220181807089256,
"grad_norm": 0.2922205576849918,
"learning_rate": 8.535626270823782e-06,
"loss": 0.5197366714477539,
"step": 1150
},
{
"epoch": 1.1317796351656397,
"grad_norm": 0.27987339622032165,
"learning_rate": 8.379491370006711e-06,
"loss": 0.5200955390930175,
"step": 1160
},
{
"epoch": 1.1415410896223537,
"grad_norm": 0.3320797014169903,
"learning_rate": 8.223761146910603e-06,
"loss": 0.5186254024505615,
"step": 1170
},
{
"epoch": 1.1513025440790678,
"grad_norm": 0.26868857833224674,
"learning_rate": 8.068474490900558e-06,
"loss": 0.5169284820556641,
"step": 1180
},
{
"epoch": 1.1610639985357818,
"grad_norm": 0.27906695212992894,
"learning_rate": 7.913670180572936e-06,
"loss": 0.5188753128051757,
"step": 1190
},
{
"epoch": 1.170825452992496,
"grad_norm": 0.2499968634248986,
"learning_rate": 7.759386874071444e-06,
"loss": 0.5169572353363037,
"step": 1200
},
{
"epoch": 1.18058690744921,
"grad_norm": 0.25669523715148324,
"learning_rate": 7.60566309943333e-06,
"loss": 0.5177628040313721,
"step": 1210
},
{
"epoch": 1.190348361905924,
"grad_norm": 0.3127411523406545,
"learning_rate": 7.4525372449680555e-06,
"loss": 0.5184590339660644,
"step": 1220
},
{
"epoch": 1.200109816362638,
"grad_norm": 0.29021698280349795,
"learning_rate": 7.300047549670871e-06,
"loss": 0.5188806533813477,
"step": 1230
},
{
"epoch": 1.209871270819352,
"grad_norm": 0.28856677054504354,
"learning_rate": 7.148232093673672e-06,
"loss": 0.515787410736084,
"step": 1240
},
{
"epoch": 1.2196327252760661,
"grad_norm": 0.3023289378181344,
"learning_rate": 6.9971287887355254e-06,
"loss": 0.5163328647613525,
"step": 1250
},
{
"epoch": 1.22939417973278,
"grad_norm": 0.26247524274089795,
"learning_rate": 6.846775368775231e-06,
"loss": 0.5181135177612305,
"step": 1260
},
{
"epoch": 1.2391556341894943,
"grad_norm": 0.2990280458656863,
"learning_rate": 6.697209380448333e-06,
"loss": 0.5180223464965821,
"step": 1270
},
{
"epoch": 1.2489170886462082,
"grad_norm": 0.27826406563749756,
"learning_rate": 6.548468173770845e-06,
"loss": 0.5206103801727295,
"step": 1280
},
{
"epoch": 1.2586785431029224,
"grad_norm": 0.2509774400736038,
"learning_rate": 6.400588892792127e-06,
"loss": 0.5194956302642822,
"step": 1290
},
{
"epoch": 1.2684399975596363,
"grad_norm": 0.3003807314209112,
"learning_rate": 6.253608466319157e-06,
"loss": 0.5183727264404296,
"step": 1300
},
{
"epoch": 1.2782014520163505,
"grad_norm": 0.28566950902389265,
"learning_rate": 6.107563598694577e-06,
"loss": 0.5115070343017578,
"step": 1310
},
{
"epoch": 1.2879629064730644,
"grad_norm": 0.2775455085835586,
"learning_rate": 5.962490760630787e-06,
"loss": 0.5156794548034668,
"step": 1320
},
{
"epoch": 1.2977243609297786,
"grad_norm": 0.24707871015785107,
"learning_rate": 5.818426180102382e-06,
"loss": 0.5146899223327637,
"step": 1330
},
{
"epoch": 1.3074858153864926,
"grad_norm": 0.2431650508539672,
"learning_rate": 5.675405833299215e-06,
"loss": 0.516709280014038,
"step": 1340
},
{
"epoch": 1.3172472698432065,
"grad_norm": 0.2484262146803382,
"learning_rate": 5.533465435642305e-06,
"loss": 0.5153475761413574,
"step": 1350
},
{
"epoch": 1.3270087242999207,
"grad_norm": 0.2580363818385725,
"learning_rate": 5.392640432864913e-06,
"loss": 0.5175045013427735,
"step": 1360
},
{
"epoch": 1.3367701787566348,
"grad_norm": 0.2703904724879195,
"learning_rate": 5.252965992160914e-06,
"loss": 0.5145888328552246,
"step": 1370
},
{
"epoch": 1.3465316332133488,
"grad_norm": 0.2731121542706405,
"learning_rate": 5.114476993402772e-06,
"loss": 0.5174077033996582,
"step": 1380
},
{
"epoch": 1.3562930876700627,
"grad_norm": 0.2789434054296118,
"learning_rate": 4.977208020431246e-06,
"loss": 0.5140918731689453,
"step": 1390
},
{
"epoch": 1.366054542126777,
"grad_norm": 0.25224799646541446,
"learning_rate": 4.841193352419003e-06,
"loss": 0.5124314785003662,
"step": 1400
},
{
"epoch": 1.375815996583491,
"grad_norm": 0.23367404244092368,
"learning_rate": 4.706466955310343e-06,
"loss": 0.5177772521972657,
"step": 1410
},
{
"epoch": 1.385577451040205,
"grad_norm": 0.25239349321695426,
"learning_rate": 4.573062473339135e-06,
"loss": 0.5172656059265137,
"step": 1420
},
{
"epoch": 1.395338905496919,
"grad_norm": 0.25085980708060507,
"learning_rate": 4.441013220627087e-06,
"loss": 0.5163529396057129,
"step": 1430
},
{
"epoch": 1.4051003599536331,
"grad_norm": 0.25699494935708533,
"learning_rate": 4.310352172864468e-06,
"loss": 0.5130033016204834,
"step": 1440
},
{
"epoch": 1.414861814410347,
"grad_norm": 0.30451562530875587,
"learning_rate": 4.181111959075295e-06,
"loss": 0.5169584274291992,
"step": 1450
},
{
"epoch": 1.4246232688670613,
"grad_norm": 0.22347789229405868,
"learning_rate": 4.053324853469164e-06,
"loss": 0.5177071571350098,
"step": 1460
},
{
"epoch": 1.4343847233237752,
"grad_norm": 0.22872455022553068,
"learning_rate": 3.927022767381634e-06,
"loss": 0.5152188301086426,
"step": 1470
},
{
"epoch": 1.4441461777804894,
"grad_norm": 0.25388484440810843,
"learning_rate": 3.8022372413052424e-06,
"loss": 0.5127427101135253,
"step": 1480
},
{
"epoch": 1.4539076322372033,
"grad_norm": 0.25866952949094735,
"learning_rate": 3.678999437013129e-06,
"loss": 0.5151724338531494,
"step": 1490
},
{
"epoch": 1.4636690866939173,
"grad_norm": 0.24712009382832717,
"learning_rate": 3.5573401297772404e-06,
"loss": 0.5154451370239258,
"step": 1500
},
{
"epoch": 1.4734305411506314,
"grad_norm": 0.2500686833810677,
"learning_rate": 3.437289700683042e-06,
"loss": 0.5136337280273438,
"step": 1510
},
{
"epoch": 1.4831919956073456,
"grad_norm": 0.24386033509991423,
"learning_rate": 3.318878129042675e-06,
"loss": 0.5164509296417237,
"step": 1520
},
{
"epoch": 1.4929534500640596,
"grad_norm": 0.21789060953672507,
"learning_rate": 3.2021349849084425e-06,
"loss": 0.5164978504180908,
"step": 1530
},
{
"epoch": 1.5027149045207735,
"grad_norm": 0.23279008504583068,
"learning_rate": 3.0870894216884994e-06,
"loss": 0.5138144493103027,
"step": 1540
},
{
"epoch": 1.5124763589774877,
"grad_norm": 0.23798382143370084,
"learning_rate": 2.97377016886658e-06,
"loss": 0.5130619049072266,
"step": 1550
},
{
"epoch": 1.5222378134342018,
"grad_norm": 0.22614472917954062,
"learning_rate": 2.8622055248276037e-06,
"loss": 0.5171074867248535,
"step": 1560
},
{
"epoch": 1.5319992678909158,
"grad_norm": 0.22130974012180282,
"learning_rate": 2.7524233497909183e-06,
"loss": 0.5185530185699463,
"step": 1570
},
{
"epoch": 1.5417607223476297,
"grad_norm": 0.24403616744222512,
"learning_rate": 2.644451058852979e-06,
"loss": 0.5162991046905517,
"step": 1580
},
{
"epoch": 1.551522176804344,
"grad_norm": 0.22243870099915153,
"learning_rate": 2.5383156151411736e-06,
"loss": 0.5156514644622803,
"step": 1590
},
{
"epoch": 1.5612836312610578,
"grad_norm": 0.2140937785595596,
"learning_rate": 2.4340435230805235e-06,
"loss": 0.5116523742675781,
"step": 1600
},
{
"epoch": 1.5710450857177718,
"grad_norm": 0.22846166989495398,
"learning_rate": 2.331660821774915e-06,
"loss": 0.5128523826599121,
"step": 1610
},
{
"epoch": 1.580806540174486,
"grad_norm": 0.23853426482035037,
"learning_rate": 2.231193078504561e-06,
"loss": 0.5140191078186035,
"step": 1620
},
{
"epoch": 1.5905679946312001,
"grad_norm": 0.2546194675779906,
"learning_rate": 2.1326653823412703e-06,
"loss": 0.5155912876129151,
"step": 1630
},
{
"epoch": 1.600329449087914,
"grad_norm": 0.21571313679227117,
"learning_rate": 2.036102337883129e-06,
"loss": 0.513617467880249,
"step": 1640
},
{
"epoch": 1.610090903544628,
"grad_norm": 0.21005916699635413,
"learning_rate": 1.9415280591101738e-06,
"loss": 0.5121469974517823,
"step": 1650
},
{
"epoch": 1.6198523580013422,
"grad_norm": 0.21340720820134304,
"learning_rate": 1.8489661633625955e-06,
"loss": 0.5160678863525391,
"step": 1660
},
{
"epoch": 1.6296138124580564,
"grad_norm": 0.21247785817165615,
"learning_rate": 1.7584397654429475e-06,
"loss": 0.5125009059906006,
"step": 1670
},
{
"epoch": 1.6393752669147703,
"grad_norm": 0.22116699930479886,
"learning_rate": 1.6699714718438643e-06,
"loss": 0.5144219398498535,
"step": 1680
},
{
"epoch": 1.6491367213714843,
"grad_norm": 0.21584368154418007,
"learning_rate": 1.5835833751026853e-06,
"loss": 0.5139463424682618,
"step": 1690
},
{
"epoch": 1.6588981758281984,
"grad_norm": 0.19776671497752707,
"learning_rate": 1.4992970482844759e-06,
"loss": 0.5122383117675782,
"step": 1700
},
{
"epoch": 1.6686596302849126,
"grad_norm": 0.20581304506094591,
"learning_rate": 1.4171335395947272e-06,
"loss": 0.5123903274536132,
"step": 1710
},
{
"epoch": 1.6784210847416265,
"grad_norm": 0.18158853274045864,
"learning_rate": 1.3371133671231473e-06,
"loss": 0.512973690032959,
"step": 1720
},
{
"epoch": 1.6881825391983405,
"grad_norm": 0.20825010878190528,
"learning_rate": 1.2592565137198298e-06,
"loss": 0.5119497299194335,
"step": 1730
},
{
"epoch": 1.6979439936550547,
"grad_norm": 0.1929130458685117,
"learning_rate": 1.1835824220050796e-06,
"loss": 0.5152641296386719,
"step": 1740
},
{
"epoch": 1.7077054481117686,
"grad_norm": 0.2048451686581624,
"learning_rate": 1.1101099895141542e-06,
"loss": 0.5131969451904297,
"step": 1750
},
{
"epoch": 1.7174669025684826,
"grad_norm": 0.20763283463158677,
"learning_rate": 1.0388575639781217e-06,
"loss": 0.5137289047241211,
"step": 1760
},
{
"epoch": 1.7272283570251967,
"grad_norm": 0.2248311820725527,
"learning_rate": 9.698429387420126e-07,
"loss": 0.513949966430664,
"step": 1770
},
{
"epoch": 1.736989811481911,
"grad_norm": 0.21038849674395077,
"learning_rate": 9.030833483214208e-07,
"loss": 0.5135007858276367,
"step": 1780
},
{
"epoch": 1.7467512659386248,
"grad_norm": 0.20000937826548337,
"learning_rate": 8.385954640986538e-07,
"loss": 0.5094645023345947,
"step": 1790
},
{
"epoch": 1.7565127203953388,
"grad_norm": 0.20796482171526587,
"learning_rate": 7.763953901595111e-07,
"loss": 0.5141811847686768,
"step": 1800
},
{
"epoch": 1.766274174852053,
"grad_norm": 0.20836986545080005,
"learning_rate": 7.164986592717327e-07,
"loss": 0.5138214111328125,
"step": 1810
},
{
"epoch": 1.7760356293087671,
"grad_norm": 0.19539889121407583,
"learning_rate": 6.589202290061015e-07,
"loss": 0.5120339393615723,
"step": 1820
},
{
"epoch": 1.785797083765481,
"grad_norm": 0.1945833663604816,
"learning_rate": 6.036744780012227e-07,
"loss": 0.5104346752166748,
"step": 1830
},
{
"epoch": 1.795558538222195,
"grad_norm": 0.21461561202531795,
"learning_rate": 5.507752023728286e-07,
"loss": 0.5140288829803467,
"step": 1840
},
{
"epoch": 1.8053199926789092,
"grad_norm": 0.2233570865176135,
"learning_rate": 5.002356122685914e-07,
"loss": 0.5119523048400879,
"step": 1850
},
{
"epoch": 1.8150814471356234,
"grad_norm": 0.2140208043729751,
"learning_rate": 4.5206832856923845e-07,
"loss": 0.5112673759460449,
"step": 1860
},
{
"epoch": 1.8248429015923373,
"grad_norm": 0.1939353070117794,
"learning_rate": 4.0628537973684046e-07,
"loss": 0.5132551193237305,
"step": 1870
},
{
"epoch": 1.8346043560490513,
"grad_norm": 0.27662385856633,
"learning_rate": 3.628981988110336e-07,
"loss": 0.5113656997680665,
"step": 1880
},
{
"epoch": 1.8443658105057654,
"grad_norm": 0.1873684185676719,
"learning_rate": 3.219176205539243e-07,
"loss": 0.5143997192382812,
"step": 1890
},
{
"epoch": 1.8541272649624794,
"grad_norm": 0.20006694507765596,
"learning_rate": 2.8335387874440124e-07,
"loss": 0.5133038520812988,
"step": 1900
},
{
"epoch": 1.8638887194191933,
"grad_norm": 0.19111674150717217,
"learning_rate": 2.4721660362253875e-07,
"loss": 0.5143795013427734,
"step": 1910
},
{
"epoch": 1.8736501738759075,
"grad_norm": 0.19076088219226814,
"learning_rate": 2.1351481948470142e-07,
"loss": 0.5107194900512695,
"step": 1920
},
{
"epoch": 1.8834116283326217,
"grad_norm": 0.18506982350558332,
"learning_rate": 1.8225694242997583e-07,
"loss": 0.5127174377441406,
"step": 1930
},
{
"epoch": 1.8931730827893356,
"grad_norm": 0.1927401327626226,
"learning_rate": 1.5345077825847266e-07,
"loss": 0.5101862907409668,
"step": 1940
},
{
"epoch": 1.9029345372460496,
"grad_norm": 0.20294868114498626,
"learning_rate": 1.2710352052205166e-07,
"loss": 0.5122389316558837,
"step": 1950
},
{
"epoch": 1.9126959917027637,
"grad_norm": 0.20549210839176393,
"learning_rate": 1.032217487279219e-07,
"loss": 0.5123374938964844,
"step": 1960
},
{
"epoch": 1.922457446159478,
"grad_norm": 0.19146983404482038,
"learning_rate": 8.181142669559383e-08,
"loss": 0.5149818420410156,
"step": 1970
},
{
"epoch": 1.9322189006161918,
"grad_norm": 0.17721381649523446,
"learning_rate": 6.287790106757396e-08,
"loss": 0.5127687454223633,
"step": 1980
},
{
"epoch": 1.9419803550729058,
"grad_norm": 0.2043110697294413,
"learning_rate": 4.642589997419178e-08,
"loss": 0.5103424549102783,
"step": 1990
},
{
"epoch": 1.95174180952962,
"grad_norm": 0.1853816182353607,
"learning_rate": 3.2459531852873094e-08,
"loss": 0.5141597747802734,
"step": 2000
},
{
"epoch": 1.9615032639863341,
"grad_norm": 0.19375887604251124,
"learning_rate": 2.0982284422177424e-08,
"loss": 0.512387752532959,
"step": 2010
},
{
"epoch": 1.971264718443048,
"grad_norm": 0.18628635952710476,
"learning_rate": 1.1997023810829122e-08,
"loss": 0.5112565994262696,
"step": 2020
},
{
"epoch": 1.981026172899762,
"grad_norm": 0.18661183658691527,
"learning_rate": 5.505993841982138e-09,
"loss": 0.5109218120574951,
"step": 2030
},
{
"epoch": 1.9907876273564762,
"grad_norm": 0.19195728014363997,
"learning_rate": 1.5108154728882273e-09,
"loss": 0.5125418186187745,
"step": 2040
},
{
"epoch": 2.0,
"grad_norm": 0.27523895648188323,
"learning_rate": 1.2486390105204138e-11,
"loss": 0.5148112297058105,
"step": 2050
},
{
"epoch": 2.0,
"step": 2050,
"total_flos": 4770492701474816.0,
"train_loss": 0.5427387805101348,
"train_runtime": 247087.7187,
"train_samples_per_second": 0.531,
"train_steps_per_second": 0.008
}
],
"logging_steps": 10,
"max_steps": 2050,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 4770492701474816.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null,
"train_runtime": 259200.0
}