{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 1780, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0028097780275358245, "grad_norm": 1.6289448738098145, "learning_rate": 7.4074074074074075e-06, "loss": 2.9507366180419923, "step": 5 }, { "epoch": 0.005619556055071649, "grad_norm": 1.0632959604263306, "learning_rate": 1.6666666666666667e-05, "loss": 2.8418886184692385, "step": 10 }, { "epoch": 0.008429334082607475, "grad_norm": 0.46306225657463074, "learning_rate": 2.5925925925925925e-05, "loss": 2.6990007400512694, "step": 15 }, { "epoch": 0.011239112110143298, "grad_norm": 0.30506059527397156, "learning_rate": 3.518518518518519e-05, "loss": 2.5129268646240233, "step": 20 }, { "epoch": 0.014048890137679123, "grad_norm": 0.33695265650749207, "learning_rate": 4.4444444444444447e-05, "loss": 2.4396335601806642, "step": 25 }, { "epoch": 0.01685866816521495, "grad_norm": 0.23116245865821838, "learning_rate": 5.370370370370371e-05, "loss": 2.332992744445801, "step": 30 }, { "epoch": 0.019668446192750773, "grad_norm": 0.1972494125366211, "learning_rate": 6.296296296296296e-05, "loss": 2.2365184783935548, "step": 35 }, { "epoch": 0.022478224220286596, "grad_norm": 0.1908838003873825, "learning_rate": 7.222222222222222e-05, "loss": 2.0834888458251952, "step": 40 }, { "epoch": 0.025288002247822423, "grad_norm": 0.20938199758529663, "learning_rate": 8.148148148148148e-05, "loss": 2.086268997192383, "step": 45 }, { "epoch": 0.028097780275358246, "grad_norm": 0.1902182698249817, "learning_rate": 9.074074074074075e-05, "loss": 2.0025943756103515, "step": 50 }, { "epoch": 0.030907558302894073, "grad_norm": 0.1865706890821457, "learning_rate": 0.0001, "loss": 1.9506149291992188, "step": 55 }, { "epoch": 0.0337173363304299, "grad_norm": 0.17671418190002441, "learning_rate": 9.99979294048975e-05, "loss": 1.9160898208618165, "step": 60 }, { "epoch": 0.03652711435796572, "grad_norm": 0.19594523310661316, "learning_rate": 9.999171779108454e-05, "loss": 1.8680227279663086, "step": 65 }, { "epoch": 0.039336892385501546, "grad_norm": 0.17783083021640778, "learning_rate": 9.99813656730306e-05, "loss": 1.8635513305664062, "step": 70 }, { "epoch": 0.04214667041303737, "grad_norm": 0.1810583472251892, "learning_rate": 9.99668739081375e-05, "loss": 1.7857038497924804, "step": 75 }, { "epoch": 0.04495644844057319, "grad_norm": 0.1851920336484909, "learning_rate": 9.994824369666833e-05, "loss": 1.7770612716674805, "step": 80 }, { "epoch": 0.04776622646810902, "grad_norm": 0.18314684927463531, "learning_rate": 9.992547658164808e-05, "loss": 1.7640869140625, "step": 85 }, { "epoch": 0.050576004495644845, "grad_norm": 0.20469045639038086, "learning_rate": 9.989857444873581e-05, "loss": 1.7009542465209961, "step": 90 }, { "epoch": 0.05338578252318067, "grad_norm": 0.1992325782775879, "learning_rate": 9.986753952606851e-05, "loss": 1.7479610443115234, "step": 95 }, { "epoch": 0.05619556055071649, "grad_norm": 0.21884913742542267, "learning_rate": 9.983237438407653e-05, "loss": 1.7157772064208985, "step": 100 }, { "epoch": 0.05900533857825232, "grad_norm": 0.2072392851114273, "learning_rate": 9.979308193527073e-05, "loss": 1.7055923461914062, "step": 105 }, { "epoch": 0.061815116605788145, "grad_norm": 0.20317302644252777, "learning_rate": 9.974966543400115e-05, "loss": 1.6449745178222657, "step": 110 }, { "epoch": 0.06462489463332396, "grad_norm": 0.21741721034049988, "learning_rate": 9.970212847618762e-05, "loss": 1.695828628540039, "step": 115 }, { "epoch": 0.0674346726608598, "grad_norm": 0.2295437753200531, "learning_rate": 9.96504749990218e-05, "loss": 1.6520286560058595, "step": 120 }, { "epoch": 0.07024445068839562, "grad_norm": 0.2638772130012512, "learning_rate": 9.959470928064119e-05, "loss": 1.6352027893066405, "step": 125 }, { "epoch": 0.07305422871593144, "grad_norm": 0.23515670001506805, "learning_rate": 9.953483593977469e-05, "loss": 1.6228309631347657, "step": 130 }, { "epoch": 0.07586400674346727, "grad_norm": 0.20004181563854218, "learning_rate": 9.947085993536018e-05, "loss": 1.6132959365844726, "step": 135 }, { "epoch": 0.07867378477100309, "grad_norm": 0.23254144191741943, "learning_rate": 9.940278656613371e-05, "loss": 1.6272554397583008, "step": 140 }, { "epoch": 0.08148356279853891, "grad_norm": 0.23951372504234314, "learning_rate": 9.933062147019067e-05, "loss": 1.6076766967773437, "step": 145 }, { "epoch": 0.08429334082607474, "grad_norm": 0.23857900500297546, "learning_rate": 9.925437062451885e-05, "loss": 1.611730194091797, "step": 150 }, { "epoch": 0.08710311885361056, "grad_norm": 0.215589240193367, "learning_rate": 9.917404034450333e-05, "loss": 1.5481966018676758, "step": 155 }, { "epoch": 0.08991289688114638, "grad_norm": 0.2216414213180542, "learning_rate": 9.90896372834035e-05, "loss": 1.6655614852905274, "step": 160 }, { "epoch": 0.09272267490868222, "grad_norm": 0.21356715261936188, "learning_rate": 9.900116843180194e-05, "loss": 1.6119371414184571, "step": 165 }, { "epoch": 0.09553245293621804, "grad_norm": 0.22898134589195251, "learning_rate": 9.890864111702551e-05, "loss": 1.5728928565979003, "step": 170 }, { "epoch": 0.09834223096375386, "grad_norm": 0.2358662188053131, "learning_rate": 9.881206300253838e-05, "loss": 1.5763687133789062, "step": 175 }, { "epoch": 0.10115200899128969, "grad_norm": 0.2212115079164505, "learning_rate": 9.87114420873074e-05, "loss": 1.5677942276000976, "step": 180 }, { "epoch": 0.10396178701882551, "grad_norm": 0.23425285518169403, "learning_rate": 9.860678670513955e-05, "loss": 1.5658489227294923, "step": 185 }, { "epoch": 0.10677156504636134, "grad_norm": 0.21634911000728607, "learning_rate": 9.849810552399168e-05, "loss": 1.5426702499389648, "step": 190 }, { "epoch": 0.10958134307389716, "grad_norm": 0.24340081214904785, "learning_rate": 9.838540754525265e-05, "loss": 1.5594231605529785, "step": 195 }, { "epoch": 0.11239112110143298, "grad_norm": 0.21039007604122162, "learning_rate": 9.826870210299777e-05, "loss": 1.4964357376098634, "step": 200 }, { "epoch": 0.11520089912896882, "grad_norm": 0.19469091296195984, "learning_rate": 9.814799886321575e-05, "loss": 1.567495059967041, "step": 205 }, { "epoch": 0.11801067715650464, "grad_norm": 0.21783208847045898, "learning_rate": 9.802330782300806e-05, "loss": 1.538626480102539, "step": 210 }, { "epoch": 0.12082045518404046, "grad_norm": 0.25423628091812134, "learning_rate": 9.789463930976098e-05, "loss": 1.523953914642334, "step": 215 }, { "epoch": 0.12363023321157629, "grad_norm": 0.22557374835014343, "learning_rate": 9.776200398029025e-05, "loss": 1.5379796028137207, "step": 220 }, { "epoch": 0.1264400112391121, "grad_norm": 0.2541823983192444, "learning_rate": 9.762541281995842e-05, "loss": 1.580143642425537, "step": 225 }, { "epoch": 0.12924978926664793, "grad_norm": 0.24614353477954865, "learning_rate": 9.748487714176501e-05, "loss": 1.52008113861084, "step": 230 }, { "epoch": 0.13205956729418375, "grad_norm": 0.24722082912921906, "learning_rate": 9.734040858540947e-05, "loss": 1.5099851608276367, "step": 235 }, { "epoch": 0.1348693453217196, "grad_norm": 0.24121952056884766, "learning_rate": 9.719201911632721e-05, "loss": 1.540484619140625, "step": 240 }, { "epoch": 0.13767912334925542, "grad_norm": 0.235436350107193, "learning_rate": 9.703972102469858e-05, "loss": 1.4760989189147948, "step": 245 }, { "epoch": 0.14048890137679124, "grad_norm": 0.25092536211013794, "learning_rate": 9.688352692443086e-05, "loss": 1.516911506652832, "step": 250 }, { "epoch": 0.14329867940432706, "grad_norm": 0.25076285004615784, "learning_rate": 9.67234497521136e-05, "loss": 1.4533663749694825, "step": 255 }, { "epoch": 0.14610845743186288, "grad_norm": 0.22647278010845184, "learning_rate": 9.655950276594721e-05, "loss": 1.5102020263671876, "step": 260 }, { "epoch": 0.1489182354593987, "grad_norm": 0.219405859708786, "learning_rate": 9.639169954464471e-05, "loss": 1.5235158920288085, "step": 265 }, { "epoch": 0.15172801348693454, "grad_norm": 0.2568018436431885, "learning_rate": 9.622005398630724e-05, "loss": 1.491180992126465, "step": 270 }, { "epoch": 0.15453779151447036, "grad_norm": 0.2327928990125656, "learning_rate": 9.604458030727291e-05, "loss": 1.4845741271972657, "step": 275 }, { "epoch": 0.15734756954200618, "grad_norm": 0.22331872582435608, "learning_rate": 9.586529304093932e-05, "loss": 1.4715895652770996, "step": 280 }, { "epoch": 0.160157347569542, "grad_norm": 0.26905468106269836, "learning_rate": 9.568220703655992e-05, "loss": 1.5091493606567383, "step": 285 }, { "epoch": 0.16296712559707782, "grad_norm": 0.2424578219652176, "learning_rate": 9.549533745801404e-05, "loss": 1.5012011528015137, "step": 290 }, { "epoch": 0.16577690362461364, "grad_norm": 0.24450263381004333, "learning_rate": 9.530469978255106e-05, "loss": 1.4875009536743165, "step": 295 }, { "epoch": 0.1685866816521495, "grad_norm": 0.24728688597679138, "learning_rate": 9.511030979950848e-05, "loss": 1.4819246292114259, "step": 300 }, { "epoch": 0.1713964596796853, "grad_norm": 0.26538094878196716, "learning_rate": 9.491218360900413e-05, "loss": 1.4883533477783204, "step": 305 }, { "epoch": 0.17420623770722113, "grad_norm": 0.25660061836242676, "learning_rate": 9.471033762060287e-05, "loss": 1.5102843284606933, "step": 310 }, { "epoch": 0.17701601573475695, "grad_norm": 0.24674417078495026, "learning_rate": 9.450478855195724e-05, "loss": 1.4748383522033692, "step": 315 }, { "epoch": 0.17982579376229277, "grad_norm": 0.2228434830904007, "learning_rate": 9.429555342742305e-05, "loss": 1.5046045303344726, "step": 320 }, { "epoch": 0.18263557178982862, "grad_norm": 0.2564845383167267, "learning_rate": 9.408264957664928e-05, "loss": 1.4651358604431153, "step": 325 }, { "epoch": 0.18544534981736444, "grad_norm": 0.22460462152957916, "learning_rate": 9.386609463314275e-05, "loss": 1.4702699661254883, "step": 330 }, { "epoch": 0.18825512784490026, "grad_norm": 0.24229742586612701, "learning_rate": 9.364590653280767e-05, "loss": 1.4648225784301758, "step": 335 }, { "epoch": 0.19106490587243607, "grad_norm": 0.23315708339214325, "learning_rate": 9.342210351246015e-05, "loss": 1.5242671966552734, "step": 340 }, { "epoch": 0.1938746838999719, "grad_norm": 0.23358993232250214, "learning_rate": 9.319470410831767e-05, "loss": 1.470159912109375, "step": 345 }, { "epoch": 0.19668446192750771, "grad_norm": 0.24706602096557617, "learning_rate": 9.296372715446397e-05, "loss": 1.4640435218811034, "step": 350 }, { "epoch": 0.19949423995504356, "grad_norm": 0.22664587199687958, "learning_rate": 9.272919178128901e-05, "loss": 1.4770112991333009, "step": 355 }, { "epoch": 0.20230401798257938, "grad_norm": 0.2556981146335602, "learning_rate": 9.249111741390459e-05, "loss": 1.4944699287414551, "step": 360 }, { "epoch": 0.2051137960101152, "grad_norm": 0.22786934673786163, "learning_rate": 9.224952377053547e-05, "loss": 1.4612249374389648, "step": 365 }, { "epoch": 0.20792357403765102, "grad_norm": 0.2529759109020233, "learning_rate": 9.200443086088624e-05, "loss": 1.479280376434326, "step": 370 }, { "epoch": 0.21073335206518684, "grad_norm": 0.25296035408973694, "learning_rate": 9.175585898448407e-05, "loss": 1.471806812286377, "step": 375 }, { "epoch": 0.2135431300927227, "grad_norm": 0.2513638138771057, "learning_rate": 9.15038287289973e-05, "loss": 1.4636999130249024, "step": 380 }, { "epoch": 0.2163529081202585, "grad_norm": 0.23294827342033386, "learning_rate": 9.124836096853047e-05, "loss": 1.4804457664489745, "step": 385 }, { "epoch": 0.21916268614779433, "grad_norm": 0.26942452788352966, "learning_rate": 9.098947686189534e-05, "loss": 1.4610935211181642, "step": 390 }, { "epoch": 0.22197246417533015, "grad_norm": 0.23874208331108093, "learning_rate": 9.072719785085842e-05, "loss": 1.448134708404541, "step": 395 }, { "epoch": 0.22478224220286597, "grad_norm": 0.24278782308101654, "learning_rate": 9.046154565836513e-05, "loss": 1.4597469329833985, "step": 400 }, { "epoch": 0.2275920202304018, "grad_norm": 0.22703032195568085, "learning_rate": 9.019254228674065e-05, "loss": 1.4504196166992187, "step": 405 }, { "epoch": 0.23040179825793763, "grad_norm": 0.2390393316745758, "learning_rate": 8.992021001586752e-05, "loss": 1.4622425079345702, "step": 410 }, { "epoch": 0.23321157628547345, "grad_norm": 0.23668386042118073, "learning_rate": 8.96445714013404e-05, "loss": 1.4316769599914552, "step": 415 }, { "epoch": 0.23602135431300927, "grad_norm": 0.28246161341667175, "learning_rate": 8.936564927259787e-05, "loss": 1.4297088623046874, "step": 420 }, { "epoch": 0.2388311323405451, "grad_norm": 0.2236463874578476, "learning_rate": 8.908346673103171e-05, "loss": 1.4460888862609864, "step": 425 }, { "epoch": 0.2416409103680809, "grad_norm": 0.2621622085571289, "learning_rate": 8.879804714807348e-05, "loss": 1.4378287315368652, "step": 430 }, { "epoch": 0.24445068839561673, "grad_norm": 0.24958811700344086, "learning_rate": 8.850941416325876e-05, "loss": 1.4260978698730469, "step": 435 }, { "epoch": 0.24726046642315258, "grad_norm": 0.2543869614601135, "learning_rate": 8.821759168226937e-05, "loss": 1.4358414649963378, "step": 440 }, { "epoch": 0.2500702444506884, "grad_norm": 0.254582941532135, "learning_rate": 8.79226038749533e-05, "loss": 1.4310947418212892, "step": 445 }, { "epoch": 0.2528800224782242, "grad_norm": 0.2545122504234314, "learning_rate": 8.762447517332293e-05, "loss": 1.4282516479492187, "step": 450 }, { "epoch": 0.25568980050576007, "grad_norm": 0.2451508790254593, "learning_rate": 8.73232302695314e-05, "loss": 1.4267480850219727, "step": 455 }, { "epoch": 0.25849957853329586, "grad_norm": 0.25954335927963257, "learning_rate": 8.701889411382767e-05, "loss": 1.3984512329101562, "step": 460 }, { "epoch": 0.2613093565608317, "grad_norm": 0.22720246016979218, "learning_rate": 8.671149191248982e-05, "loss": 1.4049585342407227, "step": 465 }, { "epoch": 0.2641191345883675, "grad_norm": 0.27274274826049805, "learning_rate": 8.640104912573759e-05, "loss": 1.3944781303405762, "step": 470 }, { "epoch": 0.26692891261590335, "grad_norm": 0.2655753195285797, "learning_rate": 8.608759146562351e-05, "loss": 1.3959108352661134, "step": 475 }, { "epoch": 0.2697386906434392, "grad_norm": 0.23971225321292877, "learning_rate": 8.577114489390344e-05, "loss": 1.4363460540771484, "step": 480 }, { "epoch": 0.272548468670975, "grad_norm": 0.23764324188232422, "learning_rate": 8.545173561988625e-05, "loss": 1.3852863311767578, "step": 485 }, { "epoch": 0.27535824669851083, "grad_norm": 0.25562721490859985, "learning_rate": 8.512939009826304e-05, "loss": 1.3966311454772948, "step": 490 }, { "epoch": 0.2781680247260466, "grad_norm": 0.2456141710281372, "learning_rate": 8.480413502691617e-05, "loss": 1.3672188758850097, "step": 495 }, { "epoch": 0.2809778027535825, "grad_norm": 0.25161007046699524, "learning_rate": 8.447599734470795e-05, "loss": 1.3913189888000488, "step": 500 }, { "epoch": 0.28378758078111826, "grad_norm": 0.2566136419773102, "learning_rate": 8.41450042292495e-05, "loss": 1.4139434814453125, "step": 505 }, { "epoch": 0.2865973588086541, "grad_norm": 0.26992174983024597, "learning_rate": 8.381118309464975e-05, "loss": 1.407020378112793, "step": 510 }, { "epoch": 0.28940713683618996, "grad_norm": 0.24573948979377747, "learning_rate": 8.347456158924496e-05, "loss": 1.398155403137207, "step": 515 }, { "epoch": 0.29221691486372575, "grad_norm": 0.23457784950733185, "learning_rate": 8.313516759330877e-05, "loss": 1.3848190307617188, "step": 520 }, { "epoch": 0.2950266928912616, "grad_norm": 0.25475621223449707, "learning_rate": 8.2793029216743e-05, "loss": 1.4146154403686524, "step": 525 }, { "epoch": 0.2978364709187974, "grad_norm": 0.2788631319999695, "learning_rate": 8.244817479674954e-05, "loss": 1.3467634201049805, "step": 530 }, { "epoch": 0.30064624894633324, "grad_norm": 0.26954489946365356, "learning_rate": 8.210063289548327e-05, "loss": 1.3805333137512208, "step": 535 }, { "epoch": 0.3034560269738691, "grad_norm": 0.300576388835907, "learning_rate": 8.17504322976866e-05, "loss": 1.3968722343444824, "step": 540 }, { "epoch": 0.3062658050014049, "grad_norm": 0.26363468170166016, "learning_rate": 8.139760200830518e-05, "loss": 1.382734775543213, "step": 545 }, { "epoch": 0.3090755830289407, "grad_norm": 0.28157341480255127, "learning_rate": 8.104217125008582e-05, "loss": 1.4139301300048828, "step": 550 }, { "epoch": 0.3118853610564765, "grad_norm": 0.25193077325820923, "learning_rate": 8.068416946115599e-05, "loss": 1.412569808959961, "step": 555 }, { "epoch": 0.31469513908401237, "grad_norm": 0.24244800209999084, "learning_rate": 8.032362629258573e-05, "loss": 1.381496047973633, "step": 560 }, { "epoch": 0.3175049171115482, "grad_norm": 0.25475868582725525, "learning_rate": 7.99605716059318e-05, "loss": 1.406557273864746, "step": 565 }, { "epoch": 0.320314695139084, "grad_norm": 0.26255717873573303, "learning_rate": 7.959503547076444e-05, "loss": 1.4104562759399415, "step": 570 }, { "epoch": 0.32312447316661985, "grad_norm": 0.2617985010147095, "learning_rate": 7.922704816217692e-05, "loss": 1.3779755592346192, "step": 575 }, { "epoch": 0.32593425119415564, "grad_norm": 0.24702060222625732, "learning_rate": 7.885664015827798e-05, "loss": 1.368150520324707, "step": 580 }, { "epoch": 0.3287440292216915, "grad_norm": 0.24377106130123138, "learning_rate": 7.848384213766757e-05, "loss": 1.3767106056213378, "step": 585 }, { "epoch": 0.3315538072492273, "grad_norm": 0.2493419498205185, "learning_rate": 7.810868497689594e-05, "loss": 1.370073127746582, "step": 590 }, { "epoch": 0.33436358527676313, "grad_norm": 0.2380317896604538, "learning_rate": 7.773119974790626e-05, "loss": 1.3727679252624512, "step": 595 }, { "epoch": 0.337173363304299, "grad_norm": 0.2518773674964905, "learning_rate": 7.735141771546118e-05, "loss": 1.3738811492919922, "step": 600 }, { "epoch": 0.33998314133183477, "grad_norm": 0.24269169569015503, "learning_rate": 7.696937033455338e-05, "loss": 1.389716911315918, "step": 605 }, { "epoch": 0.3427929193593706, "grad_norm": 0.2416677623987198, "learning_rate": 7.658508924780028e-05, "loss": 1.3902549743652344, "step": 610 }, { "epoch": 0.3456026973869064, "grad_norm": 0.26407837867736816, "learning_rate": 7.619860628282332e-05, "loss": 1.3917917251586913, "step": 615 }, { "epoch": 0.34841247541444226, "grad_norm": 0.23252025246620178, "learning_rate": 7.580995344961191e-05, "loss": 1.4026402473449706, "step": 620 }, { "epoch": 0.3512222534419781, "grad_norm": 0.24471025168895721, "learning_rate": 7.541916293787214e-05, "loss": 1.4272449493408204, "step": 625 }, { "epoch": 0.3540320314695139, "grad_norm": 0.32870998978614807, "learning_rate": 7.50262671143608e-05, "loss": 1.3970580101013184, "step": 630 }, { "epoch": 0.35684180949704974, "grad_norm": 0.26824265718460083, "learning_rate": 7.463129852020465e-05, "loss": 1.3581701278686524, "step": 635 }, { "epoch": 0.35965158752458554, "grad_norm": 0.28376635909080505, "learning_rate": 7.42342898682051e-05, "loss": 1.3811410903930663, "step": 640 }, { "epoch": 0.3624613655521214, "grad_norm": 0.2355026751756668, "learning_rate": 7.3835274040129e-05, "loss": 1.358842658996582, "step": 645 }, { "epoch": 0.36527114357965723, "grad_norm": 0.2571251094341278, "learning_rate": 7.343428408398511e-05, "loss": 1.356274700164795, "step": 650 }, { "epoch": 0.368080921607193, "grad_norm": 0.27267321944236755, "learning_rate": 7.303135321128704e-05, "loss": 1.4049511909484864, "step": 655 }, { "epoch": 0.37089069963472887, "grad_norm": 0.2539229094982147, "learning_rate": 7.262651479430242e-05, "loss": 1.3627485275268554, "step": 660 }, { "epoch": 0.37370047766226466, "grad_norm": 0.23842009902000427, "learning_rate": 7.221980236328902e-05, "loss": 1.3284945487976074, "step": 665 }, { "epoch": 0.3765102556898005, "grad_norm": 0.28760826587677, "learning_rate": 7.181124960371752e-05, "loss": 1.3900004386901856, "step": 670 }, { "epoch": 0.37932003371733636, "grad_norm": 0.2665930390357971, "learning_rate": 7.140089035348166e-05, "loss": 1.3838679313659668, "step": 675 }, { "epoch": 0.38212981174487215, "grad_norm": 0.24732042849063873, "learning_rate": 7.098875860009559e-05, "loss": 1.3578229904174806, "step": 680 }, { "epoch": 0.384939589772408, "grad_norm": 0.24101758003234863, "learning_rate": 7.057488847787892e-05, "loss": 1.3452487945556642, "step": 685 }, { "epoch": 0.3877493677999438, "grad_norm": 0.26382312178611755, "learning_rate": 7.015931426512958e-05, "loss": 1.3589553833007812, "step": 690 }, { "epoch": 0.39055914582747964, "grad_norm": 0.2548581063747406, "learning_rate": 6.974207038128471e-05, "loss": 1.3739323616027832, "step": 695 }, { "epoch": 0.39336892385501543, "grad_norm": 0.21790075302124023, "learning_rate": 6.932319138407009e-05, "loss": 1.3837099075317383, "step": 700 }, { "epoch": 0.3961787018825513, "grad_norm": 0.2790248394012451, "learning_rate": 6.890271196663766e-05, "loss": 1.3707796096801759, "step": 705 }, { "epoch": 0.3989884799100871, "grad_norm": 0.21612432599067688, "learning_rate": 6.848066695469236e-05, "loss": 1.3845596313476562, "step": 710 }, { "epoch": 0.4017982579376229, "grad_norm": 0.2857745587825775, "learning_rate": 6.805709130360754e-05, "loss": 1.3426000595092773, "step": 715 }, { "epoch": 0.40460803596515876, "grad_norm": 0.2341742217540741, "learning_rate": 6.763202009552998e-05, "loss": 1.3480137825012206, "step": 720 }, { "epoch": 0.40741781399269456, "grad_norm": 0.2691285014152527, "learning_rate": 6.720548853647414e-05, "loss": 1.3277750968933106, "step": 725 }, { "epoch": 0.4102275920202304, "grad_norm": 0.265024870634079, "learning_rate": 6.677753195340628e-05, "loss": 1.3744802474975586, "step": 730 }, { "epoch": 0.41303737004776625, "grad_norm": 0.23040884733200073, "learning_rate": 6.634818579131865e-05, "loss": 1.3474268913269043, "step": 735 }, { "epoch": 0.41584714807530204, "grad_norm": 0.26001518964767456, "learning_rate": 6.591748561029363e-05, "loss": 1.3584138870239257, "step": 740 }, { "epoch": 0.4186569261028379, "grad_norm": 0.23940986394882202, "learning_rate": 6.548546708255867e-05, "loss": 1.278660488128662, "step": 745 }, { "epoch": 0.4214667041303737, "grad_norm": 0.2891477942466736, "learning_rate": 6.505216598953164e-05, "loss": 1.34426851272583, "step": 750 }, { "epoch": 0.42427648215790953, "grad_norm": 0.21738266944885254, "learning_rate": 6.461761821885742e-05, "loss": 1.3268919944763184, "step": 755 }, { "epoch": 0.4270862601854454, "grad_norm": 0.2540494501590729, "learning_rate": 6.418185976143543e-05, "loss": 1.371140193939209, "step": 760 }, { "epoch": 0.42989603821298117, "grad_norm": 0.2826739251613617, "learning_rate": 6.374492670843876e-05, "loss": 1.3271225929260253, "step": 765 }, { "epoch": 0.432705816240517, "grad_norm": 0.25972551107406616, "learning_rate": 6.330685524832505e-05, "loss": 1.3500648498535157, "step": 770 }, { "epoch": 0.4355155942680528, "grad_norm": 0.2701602280139923, "learning_rate": 6.286768166383904e-05, "loss": 1.3494492530822755, "step": 775 }, { "epoch": 0.43832537229558866, "grad_norm": 0.26368218660354614, "learning_rate": 6.24274423290077e-05, "loss": 1.3437108039855956, "step": 780 }, { "epoch": 0.44113515032312445, "grad_norm": 0.28960785269737244, "learning_rate": 6.19861737061274e-05, "loss": 1.334970760345459, "step": 785 }, { "epoch": 0.4439449283506603, "grad_norm": 0.298348069190979, "learning_rate": 6.154391234274418e-05, "loss": 1.2848273277282716, "step": 790 }, { "epoch": 0.44675470637819614, "grad_norm": 0.26482343673706055, "learning_rate": 6.110069486862651e-05, "loss": 1.3792757034301757, "step": 795 }, { "epoch": 0.44956448440573193, "grad_norm": 0.25783082842826843, "learning_rate": 6.0656557992731674e-05, "loss": 1.344842529296875, "step": 800 }, { "epoch": 0.4523742624332678, "grad_norm": 0.296077698469162, "learning_rate": 6.021153850016528e-05, "loss": 1.3527093887329102, "step": 805 }, { "epoch": 0.4551840404608036, "grad_norm": 0.26111283898353577, "learning_rate": 5.976567324913456e-05, "loss": 1.34829683303833, "step": 810 }, { "epoch": 0.4579938184883394, "grad_norm": 0.26267966628074646, "learning_rate": 5.9318999167895764e-05, "loss": 1.3214719772338868, "step": 815 }, { "epoch": 0.46080359651587527, "grad_norm": 0.23440779745578766, "learning_rate": 5.8871553251695466e-05, "loss": 1.3179278373718262, "step": 820 }, { "epoch": 0.46361337454341106, "grad_norm": 0.26581263542175293, "learning_rate": 5.842337255970658e-05, "loss": 1.359808349609375, "step": 825 }, { "epoch": 0.4664231525709469, "grad_norm": 0.23575808107852936, "learning_rate": 5.7974494211958966e-05, "loss": 1.37355318069458, "step": 830 }, { "epoch": 0.4692329305984827, "grad_norm": 0.2384994626045227, "learning_rate": 5.752495538626492e-05, "loss": 1.3252643585205077, "step": 835 }, { "epoch": 0.47204270862601855, "grad_norm": 0.23110541701316833, "learning_rate": 5.70747933151401e-05, "loss": 1.3559125900268554, "step": 840 }, { "epoch": 0.4748524866535544, "grad_norm": 0.2603874206542969, "learning_rate": 5.6624045282719704e-05, "loss": 1.3404882431030274, "step": 845 }, { "epoch": 0.4776622646810902, "grad_norm": 0.26102665066719055, "learning_rate": 5.6172748621670456e-05, "loss": 1.3259580612182618, "step": 850 }, { "epoch": 0.48047204270862603, "grad_norm": 0.25294220447540283, "learning_rate": 5.57209407100986e-05, "loss": 1.3012885093688964, "step": 855 }, { "epoch": 0.4832818207361618, "grad_norm": 0.26874586939811707, "learning_rate": 5.5268658968454124e-05, "loss": 1.2920028686523437, "step": 860 }, { "epoch": 0.4860915987636977, "grad_norm": 0.2751091718673706, "learning_rate": 5.481594085643137e-05, "loss": 1.350577163696289, "step": 865 }, { "epoch": 0.48890137679123347, "grad_norm": 0.24553517997264862, "learning_rate": 5.436282386986654e-05, "loss": 1.3344749450683593, "step": 870 }, { "epoch": 0.4917111548187693, "grad_norm": 0.28348687291145325, "learning_rate": 5.390934553763221e-05, "loss": 1.3341694831848145, "step": 875 }, { "epoch": 0.49452093284630516, "grad_norm": 0.2462996244430542, "learning_rate": 5.3455543418528894e-05, "loss": 1.3213212966918946, "step": 880 }, { "epoch": 0.49733071087384095, "grad_norm": 0.2514338195323944, "learning_rate": 5.300145509817443e-05, "loss": 1.2878404617309571, "step": 885 }, { "epoch": 0.5001404889013767, "grad_norm": 0.2813120186328888, "learning_rate": 5.25471181858909e-05, "loss": 1.3055540084838868, "step": 890 }, { "epoch": 0.5029502669289126, "grad_norm": 0.2575701177120209, "learning_rate": 5.209257031158972e-05, "loss": 1.3369397163391112, "step": 895 }, { "epoch": 0.5057600449564484, "grad_norm": 0.2442939579486847, "learning_rate": 5.163784912265499e-05, "loss": 1.3082851409912108, "step": 900 }, { "epoch": 0.5085698229839842, "grad_norm": 0.2723119556903839, "learning_rate": 5.118299228082537e-05, "loss": 1.3405383110046387, "step": 905 }, { "epoch": 0.5113796010115201, "grad_norm": 0.27727973461151123, "learning_rate": 5.072803745907484e-05, "loss": 1.3699199676513671, "step": 910 }, { "epoch": 0.5141893790390559, "grad_norm": 0.26802992820739746, "learning_rate": 5.027302233849242e-05, "loss": 1.3112585067749023, "step": 915 }, { "epoch": 0.5169991570665917, "grad_norm": 0.25242841243743896, "learning_rate": 4.981798460516132e-05, "loss": 1.30908260345459, "step": 920 }, { "epoch": 0.5198089350941275, "grad_norm": 0.31909218430519104, "learning_rate": 4.936296194703762e-05, "loss": 1.3245658874511719, "step": 925 }, { "epoch": 0.5226187131216634, "grad_norm": 0.2384137213230133, "learning_rate": 4.8907992050828826e-05, "loss": 1.3414633750915528, "step": 930 }, { "epoch": 0.5254284911491992, "grad_norm": 0.24525491893291473, "learning_rate": 4.845311259887251e-05, "loss": 1.3210116386413575, "step": 935 }, { "epoch": 0.528238269176735, "grad_norm": 0.2671036124229431, "learning_rate": 4.799836126601524e-05, "loss": 1.2895827293395996, "step": 940 }, { "epoch": 0.5310480472042709, "grad_norm": 0.2723873257637024, "learning_rate": 4.754377571649236e-05, "loss": 1.336540126800537, "step": 945 }, { "epoch": 0.5338578252318067, "grad_norm": 0.25233784317970276, "learning_rate": 4.708939360080839e-05, "loss": 1.2895150184631348, "step": 950 }, { "epoch": 0.5366676032593425, "grad_norm": 0.2767149806022644, "learning_rate": 4.663525255261861e-05, "loss": 1.305629825592041, "step": 955 }, { "epoch": 0.5394773812868784, "grad_norm": 0.25542566180229187, "learning_rate": 4.618139018561228e-05, "loss": 1.3334477424621582, "step": 960 }, { "epoch": 0.5422871593144142, "grad_norm": 0.22227060794830322, "learning_rate": 4.572784409039714e-05, "loss": 1.3218696594238282, "step": 965 }, { "epoch": 0.54509693734195, "grad_norm": 0.2286464273929596, "learning_rate": 4.5274651831386136e-05, "loss": 1.303337860107422, "step": 970 }, { "epoch": 0.5479067153694858, "grad_norm": 0.22979024052619934, "learning_rate": 4.4821850943686164e-05, "loss": 1.2957594871520997, "step": 975 }, { "epoch": 0.5507164933970217, "grad_norm": 0.2746727764606476, "learning_rate": 4.4369478929989236e-05, "loss": 1.2993772506713868, "step": 980 }, { "epoch": 0.5535262714245575, "grad_norm": 0.23358559608459473, "learning_rate": 4.3917573257466385e-05, "loss": 1.2819868087768556, "step": 985 }, { "epoch": 0.5563360494520933, "grad_norm": 0.28666388988494873, "learning_rate": 4.346617135466453e-05, "loss": 1.3590084075927735, "step": 990 }, { "epoch": 0.5591458274796292, "grad_norm": 0.25617775321006775, "learning_rate": 4.30153106084064e-05, "loss": 1.308148193359375, "step": 995 }, { "epoch": 0.561955605507165, "grad_norm": 0.284833699464798, "learning_rate": 4.256502836069415e-05, "loss": 1.2775846481323243, "step": 1000 }, { "epoch": 0.5647653835347007, "grad_norm": 0.26119059324264526, "learning_rate": 4.211536190561644e-05, "loss": 1.2948189735412599, "step": 1005 }, { "epoch": 0.5675751615622365, "grad_norm": 0.27653321623802185, "learning_rate": 4.166634848625967e-05, "loss": 1.318446731567383, "step": 1010 }, { "epoch": 0.5703849395897724, "grad_norm": 0.2888035476207733, "learning_rate": 4.1218025291623306e-05, "loss": 1.3086650848388672, "step": 1015 }, { "epoch": 0.5731947176173082, "grad_norm": 0.30303582549095154, "learning_rate": 4.0770429453539825e-05, "loss": 1.321122169494629, "step": 1020 }, { "epoch": 0.576004495644844, "grad_norm": 0.2563258707523346, "learning_rate": 4.032359804359918e-05, "loss": 1.3109655380249023, "step": 1025 }, { "epoch": 0.5788142736723799, "grad_norm": 0.25399813055992126, "learning_rate": 3.9877568070078585e-05, "loss": 1.280045509338379, "step": 1030 }, { "epoch": 0.5816240516999157, "grad_norm": 0.26106250286102295, "learning_rate": 3.9432376474877184e-05, "loss": 1.2822449684143067, "step": 1035 }, { "epoch": 0.5844338297274515, "grad_norm": 0.28419098258018494, "learning_rate": 3.898806013045642e-05, "loss": 1.3058096885681152, "step": 1040 }, { "epoch": 0.5872436077549874, "grad_norm": 0.25204065442085266, "learning_rate": 3.854465583678617e-05, "loss": 1.3337356567382812, "step": 1045 }, { "epoch": 0.5900533857825232, "grad_norm": 0.2610354423522949, "learning_rate": 3.810220031829682e-05, "loss": 1.3192598342895507, "step": 1050 }, { "epoch": 0.592863163810059, "grad_norm": 0.26190638542175293, "learning_rate": 3.766073022083751e-05, "loss": 1.326909637451172, "step": 1055 }, { "epoch": 0.5956729418375948, "grad_norm": 0.22364261746406555, "learning_rate": 3.722028210864113e-05, "loss": 1.2797254562377929, "step": 1060 }, { "epoch": 0.5984827198651307, "grad_norm": 0.24798913300037384, "learning_rate": 3.6780892461295854e-05, "loss": 1.3070457458496094, "step": 1065 }, { "epoch": 0.6012924978926665, "grad_norm": 0.2828684449195862, "learning_rate": 3.6342597670723736e-05, "loss": 1.3325798034667968, "step": 1070 }, { "epoch": 0.6041022759202023, "grad_norm": 0.25071781873703003, "learning_rate": 3.590543403816665e-05, "loss": 1.2972282409667968, "step": 1075 }, { "epoch": 0.6069120539477382, "grad_norm": 0.2985232174396515, "learning_rate": 3.546943777117968e-05, "loss": 1.3522053718566895, "step": 1080 }, { "epoch": 0.609721831975274, "grad_norm": 0.2662253975868225, "learning_rate": 3.5034644980632214e-05, "loss": 1.2833660125732422, "step": 1085 }, { "epoch": 0.6125316100028098, "grad_norm": 0.2524658143520355, "learning_rate": 3.460109167771716e-05, "loss": 1.2834291458129883, "step": 1090 }, { "epoch": 0.6153413880303455, "grad_norm": 0.2675623893737793, "learning_rate": 3.416881377096836e-05, "loss": 1.299980354309082, "step": 1095 }, { "epoch": 0.6181511660578815, "grad_norm": 0.2667762339115143, "learning_rate": 3.3737847063286456e-05, "loss": 1.2842544555664062, "step": 1100 }, { "epoch": 0.6209609440854172, "grad_norm": 0.2562688887119293, "learning_rate": 3.330822724897365e-05, "loss": 1.3295822143554688, "step": 1105 }, { "epoch": 0.623770722112953, "grad_norm": 0.2753613293170929, "learning_rate": 3.2879989910777245e-05, "loss": 1.348409652709961, "step": 1110 }, { "epoch": 0.6265805001404889, "grad_norm": 0.23819799721240997, "learning_rate": 3.245317051694266e-05, "loss": 1.300943946838379, "step": 1115 }, { "epoch": 0.6293902781680247, "grad_norm": 0.2727886736392975, "learning_rate": 3.202780441827579e-05, "loss": 1.3181438446044922, "step": 1120 }, { "epoch": 0.6322000561955605, "grad_norm": 0.23667563498020172, "learning_rate": 3.1603926845215006e-05, "loss": 1.2812738418579102, "step": 1125 }, { "epoch": 0.6350098342230964, "grad_norm": 0.25604286789894104, "learning_rate": 3.1181572904913415e-05, "loss": 1.306494903564453, "step": 1130 }, { "epoch": 0.6378196122506322, "grad_norm": 0.2725841999053955, "learning_rate": 3.076077757833103e-05, "loss": 1.2986560821533204, "step": 1135 }, { "epoch": 0.640629390278168, "grad_norm": 0.2724528908729553, "learning_rate": 3.0341575717337535e-05, "loss": 1.3132526397705078, "step": 1140 }, { "epoch": 0.6434391683057038, "grad_norm": 0.2603621184825897, "learning_rate": 2.9924002041825737e-05, "loss": 1.2907075881958008, "step": 1145 }, { "epoch": 0.6462489463332397, "grad_norm": 0.2957921624183655, "learning_rate": 2.950809113683597e-05, "loss": 1.2987354278564454, "step": 1150 }, { "epoch": 0.6490587243607755, "grad_norm": 0.26997771859169006, "learning_rate": 2.909387744969152e-05, "loss": 1.2699929237365724, "step": 1155 }, { "epoch": 0.6518685023883113, "grad_norm": 0.24933463335037231, "learning_rate": 2.8681395287145652e-05, "loss": 1.3049560546875, "step": 1160 }, { "epoch": 0.6546782804158472, "grad_norm": 0.3224712610244751, "learning_rate": 2.827067881254024e-05, "loss": 1.3275213241577148, "step": 1165 }, { "epoch": 0.657488058443383, "grad_norm": 0.2601047158241272, "learning_rate": 2.7861762042976088e-05, "loss": 1.2662556648254395, "step": 1170 }, { "epoch": 0.6602978364709188, "grad_norm": 0.247396320104599, "learning_rate": 2.745467884649559e-05, "loss": 1.2475319862365724, "step": 1175 }, { "epoch": 0.6631076144984546, "grad_norm": 0.29884234070777893, "learning_rate": 2.7049462939277714e-05, "loss": 1.2911073684692382, "step": 1180 }, { "epoch": 0.6659173925259905, "grad_norm": 0.25450336933135986, "learning_rate": 2.6646147882845352e-05, "loss": 1.3277381896972655, "step": 1185 }, { "epoch": 0.6687271705535263, "grad_norm": 0.25891590118408203, "learning_rate": 2.624476708128571e-05, "loss": 1.2731073379516602, "step": 1190 }, { "epoch": 0.671536948581062, "grad_norm": 0.2705190181732178, "learning_rate": 2.5845353778483706e-05, "loss": 1.319203758239746, "step": 1195 }, { "epoch": 0.674346726608598, "grad_norm": 0.2589894235134125, "learning_rate": 2.5447941055368463e-05, "loss": 1.2830557823181152, "step": 1200 }, { "epoch": 0.6771565046361337, "grad_norm": 0.26667284965515137, "learning_rate": 2.505256182717349e-05, "loss": 1.219803237915039, "step": 1205 }, { "epoch": 0.6799662826636695, "grad_norm": 0.3165528476238251, "learning_rate": 2.4659248840710565e-05, "loss": 1.2219919204711913, "step": 1210 }, { "epoch": 0.6827760606912054, "grad_norm": 0.28107449412345886, "learning_rate": 2.4268034671657413e-05, "loss": 1.2486148834228517, "step": 1215 }, { "epoch": 0.6855858387187412, "grad_norm": 0.26772573590278625, "learning_rate": 2.3878951721859715e-05, "loss": 1.2740370750427246, "step": 1220 }, { "epoch": 0.688395616746277, "grad_norm": 0.27105262875556946, "learning_rate": 2.349203221664752e-05, "loss": 1.2959449768066407, "step": 1225 }, { "epoch": 0.6912053947738128, "grad_norm": 0.2614283859729767, "learning_rate": 2.310730820216611e-05, "loss": 1.2672136306762696, "step": 1230 }, { "epoch": 0.6940151728013487, "grad_norm": 0.2921479642391205, "learning_rate": 2.272481154272188e-05, "loss": 1.2982084274291992, "step": 1235 }, { "epoch": 0.6968249508288845, "grad_norm": 0.3035147786140442, "learning_rate": 2.2344573918143263e-05, "loss": 1.2618439674377442, "step": 1240 }, { "epoch": 0.6996347288564203, "grad_norm": 0.2591157555580139, "learning_rate": 2.1966626821156733e-05, "loss": 1.3002023696899414, "step": 1245 }, { "epoch": 0.7024445068839562, "grad_norm": 0.24796362221240997, "learning_rate": 2.1591001554778652e-05, "loss": 1.3142871856689453, "step": 1250 }, { "epoch": 0.705254284911492, "grad_norm": 0.2760918140411377, "learning_rate": 2.1217729229722482e-05, "loss": 1.2769397735595702, "step": 1255 }, { "epoch": 0.7080640629390278, "grad_norm": 0.28339120745658875, "learning_rate": 2.084684076182214e-05, "loss": 1.3175119400024413, "step": 1260 }, { "epoch": 0.7108738409665636, "grad_norm": 0.24828463792800903, "learning_rate": 2.047836686947146e-05, "loss": 1.3253046035766602, "step": 1265 }, { "epoch": 0.7136836189940995, "grad_norm": 0.22130407392978668, "learning_rate": 2.0112338071079906e-05, "loss": 1.3292524337768554, "step": 1270 }, { "epoch": 0.7164933970216353, "grad_norm": 0.2423369139432907, "learning_rate": 1.9748784682544952e-05, "loss": 1.346501064300537, "step": 1275 }, { "epoch": 0.7193031750491711, "grad_norm": 0.31215769052505493, "learning_rate": 1.9387736814741265e-05, "loss": 1.2533220291137694, "step": 1280 }, { "epoch": 0.722112953076707, "grad_norm": 0.31818124651908875, "learning_rate": 1.90292243710267e-05, "loss": 1.2422703742980956, "step": 1285 }, { "epoch": 0.7249227311042428, "grad_norm": 0.29535409808158875, "learning_rate": 1.8673277044765647e-05, "loss": 1.2251718521118165, "step": 1290 }, { "epoch": 0.7277325091317786, "grad_norm": 0.270018607378006, "learning_rate": 1.8319924316869763e-05, "loss": 1.2688865661621094, "step": 1295 }, { "epoch": 0.7305422871593145, "grad_norm": 0.27247878909111023, "learning_rate": 1.796919545335614e-05, "loss": 1.2945980072021483, "step": 1300 }, { "epoch": 0.7333520651868503, "grad_norm": 0.2697427272796631, "learning_rate": 1.7621119502923446e-05, "loss": 1.2795835494995118, "step": 1305 }, { "epoch": 0.736161843214386, "grad_norm": 0.2619296610355377, "learning_rate": 1.7275725294546064e-05, "loss": 1.2763350486755372, "step": 1310 }, { "epoch": 0.7389716212419218, "grad_norm": 0.2582402229309082, "learning_rate": 1.693304143508618e-05, "loss": 1.2695822715759277, "step": 1315 }, { "epoch": 0.7417813992694577, "grad_norm": 0.25293993949890137, "learning_rate": 1.6593096306924666e-05, "loss": 1.2680401802062988, "step": 1320 }, { "epoch": 0.7445911772969935, "grad_norm": 0.2790253162384033, "learning_rate": 1.6255918065610265e-05, "loss": 1.3060011863708496, "step": 1325 }, { "epoch": 0.7474009553245293, "grad_norm": 0.262707382440567, "learning_rate": 1.5921534637527503e-05, "loss": 1.2574471473693847, "step": 1330 }, { "epoch": 0.7502107333520652, "grad_norm": 0.24735324084758759, "learning_rate": 1.5589973717583966e-05, "loss": 1.2912208557128906, "step": 1335 }, { "epoch": 0.753020511379601, "grad_norm": 0.259985089302063, "learning_rate": 1.526126276691636e-05, "loss": 1.2958283424377441, "step": 1340 }, { "epoch": 0.7558302894071368, "grad_norm": 0.26692306995391846, "learning_rate": 1.4935429010616015e-05, "loss": 1.296837043762207, "step": 1345 }, { "epoch": 0.7586400674346727, "grad_norm": 0.26619982719421387, "learning_rate": 1.4612499435474165e-05, "loss": 1.2909753799438477, "step": 1350 }, { "epoch": 0.7614498454622085, "grad_norm": 0.30181729793548584, "learning_rate": 1.4292500787746676e-05, "loss": 1.243568229675293, "step": 1355 }, { "epoch": 0.7642596234897443, "grad_norm": 0.276384174823761, "learning_rate": 1.3975459570938838e-05, "loss": 1.2312581062316894, "step": 1360 }, { "epoch": 0.7670694015172801, "grad_norm": 0.29950255155563354, "learning_rate": 1.3661402043610311e-05, "loss": 1.2767308235168457, "step": 1365 }, { "epoch": 0.769879179544816, "grad_norm": 0.25538370013237, "learning_rate": 1.3350354217200211e-05, "loss": 1.2776817321777343, "step": 1370 }, { "epoch": 0.7726889575723518, "grad_norm": 0.2514149844646454, "learning_rate": 1.3042341853872753e-05, "loss": 1.3385185241699218, "step": 1375 }, { "epoch": 0.7754987355998876, "grad_norm": 0.26831093430519104, "learning_rate": 1.2737390464383613e-05, "loss": 1.227066421508789, "step": 1380 }, { "epoch": 0.7783085136274235, "grad_norm": 0.2465086281299591, "learning_rate": 1.2435525305966916e-05, "loss": 1.3070301055908202, "step": 1385 }, { "epoch": 0.7811182916549593, "grad_norm": 0.23436810076236725, "learning_rate": 1.21367713802434e-05, "loss": 1.2262978553771973, "step": 1390 }, { "epoch": 0.7839280696824951, "grad_norm": 0.30117887258529663, "learning_rate": 1.1841153431149715e-05, "loss": 1.2419342041015624, "step": 1395 }, { "epoch": 0.7867378477100309, "grad_norm": 0.2514709532260895, "learning_rate": 1.1548695942888914e-05, "loss": 1.2513567924499511, "step": 1400 }, { "epoch": 0.7895476257375668, "grad_norm": 0.2476656585931778, "learning_rate": 1.1259423137902746e-05, "loss": 1.2520858764648437, "step": 1405 }, { "epoch": 0.7923574037651026, "grad_norm": 0.26847171783447266, "learning_rate": 1.0973358974865366e-05, "loss": 1.2342302322387695, "step": 1410 }, { "epoch": 0.7951671817926383, "grad_norm": 0.2882215082645416, "learning_rate": 1.0690527146698914e-05, "loss": 1.3000935554504394, "step": 1415 }, { "epoch": 0.7979769598201742, "grad_norm": 0.2424335777759552, "learning_rate": 1.0410951078611353e-05, "loss": 1.274312973022461, "step": 1420 }, { "epoch": 0.80078673784771, "grad_norm": 0.3096713423728943, "learning_rate": 1.0134653926156195e-05, "loss": 1.3291780471801757, "step": 1425 }, { "epoch": 0.8035965158752458, "grad_norm": 0.28623753786087036, "learning_rate": 9.86165857331463e-06, "loss": 1.3233673095703125, "step": 1430 }, { "epoch": 0.8064062939027817, "grad_norm": 0.2785836160182953, "learning_rate": 9.591987630600313e-06, "loss": 1.2693240165710449, "step": 1435 }, { "epoch": 0.8092160719303175, "grad_norm": 0.2621985971927643, "learning_rate": 9.32566343318656e-06, "loss": 1.2956453323364259, "step": 1440 }, { "epoch": 0.8120258499578533, "grad_norm": 0.2541707158088684, "learning_rate": 9.062708039056517e-06, "loss": 1.2893829345703125, "step": 1445 }, { "epoch": 0.8148356279853891, "grad_norm": 0.2711021900177002, "learning_rate": 8.803143227176252e-06, "loss": 1.3157413482666016, "step": 1450 }, { "epoch": 0.817645406012925, "grad_norm": 0.275565505027771, "learning_rate": 8.546990495690893e-06, "loss": 1.2888648986816407, "step": 1455 }, { "epoch": 0.8204551840404608, "grad_norm": 0.28350818157196045, "learning_rate": 8.294271060144076e-06, "loss": 1.2555255889892578, "step": 1460 }, { "epoch": 0.8232649620679966, "grad_norm": 0.3125888705253601, "learning_rate": 8.045005851720843e-06, "loss": 1.306340217590332, "step": 1465 }, { "epoch": 0.8260747400955325, "grad_norm": 0.27130141854286194, "learning_rate": 7.79921551551398e-06, "loss": 1.2710606575012207, "step": 1470 }, { "epoch": 0.8288845181230683, "grad_norm": 0.2524664103984833, "learning_rate": 7.556920408814133e-06, "loss": 1.2475395202636719, "step": 1475 }, { "epoch": 0.8316942961506041, "grad_norm": 0.2685166895389557, "learning_rate": 7.318140599423767e-06, "loss": 1.2027135848999024, "step": 1480 }, { "epoch": 0.8345040741781399, "grad_norm": 0.32713717222213745, "learning_rate": 7.082895863995032e-06, "loss": 1.2866425514221191, "step": 1485 }, { "epoch": 0.8373138522056758, "grad_norm": 0.24749763309955597, "learning_rate": 6.851205686391799e-06, "loss": 1.2808418273925781, "step": 1490 }, { "epoch": 0.8401236302332116, "grad_norm": 0.2623976469039917, "learning_rate": 6.6230892560759705e-06, "loss": 1.2696876525878906, "step": 1495 }, { "epoch": 0.8429334082607474, "grad_norm": 0.31625860929489136, "learning_rate": 6.398565466518075e-06, "loss": 1.280930519104004, "step": 1500 }, { "epoch": 0.8457431862882833, "grad_norm": 0.28187277913093567, "learning_rate": 6.177652913632476e-06, "loss": 1.2785576820373534, "step": 1505 }, { "epoch": 0.8485529643158191, "grad_norm": 0.2667565643787384, "learning_rate": 5.960369894237167e-06, "loss": 1.2934371948242187, "step": 1510 }, { "epoch": 0.8513627423433549, "grad_norm": 0.2629576027393341, "learning_rate": 5.74673440453839e-06, "loss": 1.2887065887451172, "step": 1515 }, { "epoch": 0.8541725203708908, "grad_norm": 0.28751328587532043, "learning_rate": 5.5367641386401e-06, "loss": 1.2288874626159667, "step": 1520 }, { "epoch": 0.8569822983984265, "grad_norm": 0.2510315179824829, "learning_rate": 5.3304764870784505e-06, "loss": 1.307783031463623, "step": 1525 }, { "epoch": 0.8597920764259623, "grad_norm": 0.32426729798316956, "learning_rate": 5.127888535381481e-06, "loss": 1.2589733123779296, "step": 1530 }, { "epoch": 0.8626018544534981, "grad_norm": 0.27217867970466614, "learning_rate": 4.92901706265404e-06, "loss": 1.2603012084960938, "step": 1535 }, { "epoch": 0.865411632481034, "grad_norm": 0.25051552057266235, "learning_rate": 4.7338785401880085e-06, "loss": 1.2598634719848634, "step": 1540 }, { "epoch": 0.8682214105085698, "grad_norm": 0.2964218854904175, "learning_rate": 4.5424891300981325e-06, "loss": 1.262913703918457, "step": 1545 }, { "epoch": 0.8710311885361056, "grad_norm": 0.2676181197166443, "learning_rate": 4.354864683983445e-06, "loss": 1.2766684532165526, "step": 1550 }, { "epoch": 0.8738409665636415, "grad_norm": 0.2766728401184082, "learning_rate": 4.1710207416143065e-06, "loss": 1.2717493057250977, "step": 1555 }, { "epoch": 0.8766507445911773, "grad_norm": 0.2938271760940552, "learning_rate": 3.990972529645371e-06, "loss": 1.2540876388549804, "step": 1560 }, { "epoch": 0.8794605226187131, "grad_norm": 0.28244903683662415, "learning_rate": 3.814734960354493e-06, "loss": 1.2864410400390625, "step": 1565 }, { "epoch": 0.8822703006462489, "grad_norm": 0.2865670919418335, "learning_rate": 3.6423226304075855e-06, "loss": 1.2283477783203125, "step": 1570 }, { "epoch": 0.8850800786737848, "grad_norm": 0.29519692063331604, "learning_rate": 3.4737498196496686e-06, "loss": 1.239719772338867, "step": 1575 }, { "epoch": 0.8878898567013206, "grad_norm": 0.28669726848602295, "learning_rate": 3.3090304899222215e-06, "loss": 1.2508049011230469, "step": 1580 }, { "epoch": 0.8906996347288564, "grad_norm": 0.3678744435310364, "learning_rate": 3.148178283906733e-06, "loss": 1.2658747673034667, "step": 1585 }, { "epoch": 0.8935094127563923, "grad_norm": 0.27260535955429077, "learning_rate": 2.991206523994805e-06, "loss": 1.267996597290039, "step": 1590 }, { "epoch": 0.8963191907839281, "grad_norm": 0.26227322220802307, "learning_rate": 2.8381282111847094e-06, "loss": 1.2717796325683595, "step": 1595 }, { "epoch": 0.8991289688114639, "grad_norm": 0.29462897777557373, "learning_rate": 2.6889560240046686e-06, "loss": 1.2797386169433593, "step": 1600 }, { "epoch": 0.9019387468389998, "grad_norm": 0.3033002018928528, "learning_rate": 2.5437023174626762e-06, "loss": 1.263514804840088, "step": 1605 }, { "epoch": 0.9047485248665356, "grad_norm": 0.25233593583106995, "learning_rate": 2.402379122023263e-06, "loss": 1.230501079559326, "step": 1610 }, { "epoch": 0.9075583028940714, "grad_norm": 0.2747349739074707, "learning_rate": 2.2649981426110967e-06, "loss": 1.2697263717651368, "step": 1615 }, { "epoch": 0.9103680809216071, "grad_norm": 0.30863797664642334, "learning_rate": 2.1315707576414934e-06, "loss": 1.298058032989502, "step": 1620 }, { "epoch": 0.913177858949143, "grad_norm": 0.2642074227333069, "learning_rate": 2.0021080180780417e-06, "loss": 1.2725077629089356, "step": 1625 }, { "epoch": 0.9159876369766788, "grad_norm": 0.2506329417228699, "learning_rate": 1.8766206465173352e-06, "loss": 1.2773086547851562, "step": 1630 }, { "epoch": 0.9187974150042146, "grad_norm": 0.2562831938266754, "learning_rate": 1.755119036300845e-06, "loss": 1.2906747817993165, "step": 1635 }, { "epoch": 0.9216071930317505, "grad_norm": 0.29017218947410583, "learning_rate": 1.6376132506541354e-06, "loss": 1.3145267486572265, "step": 1640 }, { "epoch": 0.9244169710592863, "grad_norm": 0.2922571003437042, "learning_rate": 1.5241130218533794e-06, "loss": 1.293178176879883, "step": 1645 }, { "epoch": 0.9272267490868221, "grad_norm": 0.2911592721939087, "learning_rate": 1.4146277504192951e-06, "loss": 1.262591552734375, "step": 1650 }, { "epoch": 0.9300365271143579, "grad_norm": 0.3456173241138458, "learning_rate": 1.3091665043385383e-06, "loss": 1.2702527046203613, "step": 1655 }, { "epoch": 0.9328463051418938, "grad_norm": 0.29181134700775146, "learning_rate": 1.2077380183127262e-06, "loss": 1.2759284973144531, "step": 1660 }, { "epoch": 0.9356560831694296, "grad_norm": 0.25466254353523254, "learning_rate": 1.110350693034884e-06, "loss": 1.2200567245483398, "step": 1665 }, { "epoch": 0.9384658611969654, "grad_norm": 0.32315805554389954, "learning_rate": 1.017012594493777e-06, "loss": 1.2686627388000489, "step": 1670 }, { "epoch": 0.9412756392245013, "grad_norm": 0.2786712646484375, "learning_rate": 9.277314533057913e-07, "loss": 1.2560710906982422, "step": 1675 }, { "epoch": 0.9440854172520371, "grad_norm": 0.32764026522636414, "learning_rate": 8.425146640746784e-07, "loss": 1.2417731285095215, "step": 1680 }, { "epoch": 0.9468951952795729, "grad_norm": 0.2823631763458252, "learning_rate": 7.613692847790899e-07, "loss": 1.2339458465576172, "step": 1685 }, { "epoch": 0.9497049733071088, "grad_norm": 0.2952862083911896, "learning_rate": 6.843020361880281e-07, "loss": 1.271276092529297, "step": 1690 }, { "epoch": 0.9525147513346446, "grad_norm": 0.2804461717605591, "learning_rate": 6.113193013041918e-07, "loss": 1.3072498321533204, "step": 1695 }, { "epoch": 0.9553245293621804, "grad_norm": 0.2772251069545746, "learning_rate": 5.424271248353207e-07, "loss": 1.2360713005065918, "step": 1700 }, { "epoch": 0.9581343073897162, "grad_norm": 0.2894945740699768, "learning_rate": 4.776312126935356e-07, "loss": 1.2895278930664062, "step": 1705 }, { "epoch": 0.9609440854172521, "grad_norm": 0.24990274012088776, "learning_rate": 4.169369315227711e-07, "loss": 1.2748977661132812, "step": 1710 }, { "epoch": 0.9637538634447879, "grad_norm": 0.2774486243724823, "learning_rate": 3.6034930825429305e-07, "loss": 1.293336772918701, "step": 1715 }, { "epoch": 0.9665636414723237, "grad_norm": 0.24710939824581146, "learning_rate": 3.078730296903087e-07, "loss": 1.2664811134338378, "step": 1720 }, { "epoch": 0.9693734194998596, "grad_norm": 0.2996719181537628, "learning_rate": 2.5951244211584456e-07, "loss": 1.286187744140625, "step": 1725 }, { "epoch": 0.9721831975273953, "grad_norm": 0.28394415974617004, "learning_rate": 2.152715509387282e-07, "loss": 1.2709294319152833, "step": 1730 }, { "epoch": 0.9749929755549311, "grad_norm": 0.3106130063533783, "learning_rate": 1.7515402035787055e-07, "loss": 1.2738256454467773, "step": 1735 }, { "epoch": 0.9778027535824669, "grad_norm": 0.24721162021160126, "learning_rate": 1.3916317305975312e-07, "loss": 1.318666934967041, "step": 1740 }, { "epoch": 0.9806125316100028, "grad_norm": 0.30419814586639404, "learning_rate": 1.0730198994327035e-07, "loss": 1.2712329864501952, "step": 1745 }, { "epoch": 0.9834223096375386, "grad_norm": 0.2756534814834595, "learning_rate": 7.957310987280475e-08, "loss": 1.268894577026367, "step": 1750 }, { "epoch": 0.9862320876650744, "grad_norm": 0.2969802916049957, "learning_rate": 5.5978829459696344e-08, "loss": 1.3021017074584962, "step": 1755 }, { "epoch": 0.9890418656926103, "grad_norm": 0.2974204421043396, "learning_rate": 3.652110287200028e-08, "loss": 1.2562143325805664, "step": 1760 }, { "epoch": 0.9918516437201461, "grad_norm": 0.2829109728336334, "learning_rate": 2.12015416726441e-08, "loss": 1.2331953048706055, "step": 1765 }, { "epoch": 0.9946614217476819, "grad_norm": 0.34386247396469116, "learning_rate": 1.0021414685973396e-08, "loss": 1.2777393341064454, "step": 1770 }, { "epoch": 0.9974711997752178, "grad_norm": 0.2781239449977875, "learning_rate": 2.981647892635886e-09, "loss": 1.2811437606811524, "step": 1775 }, { "epoch": 1.0, "grad_norm": 0.3863658905029297, "learning_rate": 8.282435288720081e-11, "loss": 1.261753463745117, "step": 1780 } ], "logging_steps": 5, "max_steps": 1780, "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": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2.4246623474496307e+17, "train_batch_size": 1, "trial_name": null, "trial_params": null }