{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.4999858203495, "eval_steps": 500, "global_step": 11019, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00045374881599918323, "grad_norm": 1.9574953317642212, "learning_rate": 6.042296072507553e-07, "loss": 0.2873, "step": 10 }, { "epoch": 0.0009074976319983665, "grad_norm": 1.3956202268600464, "learning_rate": 1.2084592145015106e-06, "loss": 0.2568, "step": 20 }, { "epoch": 0.0013612464479975498, "grad_norm": 0.9479272961616516, "learning_rate": 1.8126888217522659e-06, "loss": 0.2176, "step": 30 }, { "epoch": 0.001814995263996733, "grad_norm": 0.8508697748184204, "learning_rate": 2.4169184290030213e-06, "loss": 0.1337, "step": 40 }, { "epoch": 0.002268744079995916, "grad_norm": 0.7933751344680786, "learning_rate": 3.0211480362537765e-06, "loss": 0.0958, "step": 50 }, { "epoch": 0.0027224928959950997, "grad_norm": 1.468451738357544, "learning_rate": 3.6253776435045317e-06, "loss": 0.0851, "step": 60 }, { "epoch": 0.0031762417119942828, "grad_norm": 0.6320226192474365, "learning_rate": 4.229607250755287e-06, "loss": 0.0818, "step": 70 }, { "epoch": 0.003629990527993466, "grad_norm": 0.9758052825927734, "learning_rate": 4.833836858006043e-06, "loss": 0.069, "step": 80 }, { "epoch": 0.004083739343992649, "grad_norm": 0.4698069393634796, "learning_rate": 5.438066465256799e-06, "loss": 0.0611, "step": 90 }, { "epoch": 0.004537488159991832, "grad_norm": 1.057978868484497, "learning_rate": 6.042296072507553e-06, "loss": 0.0536, "step": 100 }, { "epoch": 0.004991236975991016, "grad_norm": 1.5551972389221191, "learning_rate": 6.646525679758309e-06, "loss": 0.0675, "step": 110 }, { "epoch": 0.005444985791990199, "grad_norm": 0.5527336001396179, "learning_rate": 7.2507552870090635e-06, "loss": 0.0518, "step": 120 }, { "epoch": 0.005898734607989382, "grad_norm": 0.4519714117050171, "learning_rate": 7.85498489425982e-06, "loss": 0.0504, "step": 130 }, { "epoch": 0.0063524834239885655, "grad_norm": 0.43451157212257385, "learning_rate": 8.459214501510575e-06, "loss": 0.0581, "step": 140 }, { "epoch": 0.006806232239987749, "grad_norm": 0.437094509601593, "learning_rate": 9.06344410876133e-06, "loss": 0.047, "step": 150 }, { "epoch": 0.007259981055986932, "grad_norm": 0.42156246304512024, "learning_rate": 9.667673716012085e-06, "loss": 0.0478, "step": 160 }, { "epoch": 0.007713729871986115, "grad_norm": 0.4071364402770996, "learning_rate": 1.0271903323262842e-05, "loss": 0.0375, "step": 170 }, { "epoch": 0.008167478687985298, "grad_norm": 0.4608546793460846, "learning_rate": 1.0876132930513597e-05, "loss": 0.0408, "step": 180 }, { "epoch": 0.008621227503984481, "grad_norm": 0.4172491431236267, "learning_rate": 1.1480362537764351e-05, "loss": 0.049, "step": 190 }, { "epoch": 0.009074976319983665, "grad_norm": 0.27939194440841675, "learning_rate": 1.2084592145015106e-05, "loss": 0.0375, "step": 200 }, { "epoch": 0.009528725135982848, "grad_norm": 0.32932278513908386, "learning_rate": 1.2688821752265863e-05, "loss": 0.0378, "step": 210 }, { "epoch": 0.009982473951982032, "grad_norm": 0.4204069972038269, "learning_rate": 1.3293051359516618e-05, "loss": 0.035, "step": 220 }, { "epoch": 0.010436222767981215, "grad_norm": 0.34354570508003235, "learning_rate": 1.3897280966767372e-05, "loss": 0.0359, "step": 230 }, { "epoch": 0.010889971583980399, "grad_norm": 0.4892970025539398, "learning_rate": 1.4501510574018127e-05, "loss": 0.0381, "step": 240 }, { "epoch": 0.01134372039997958, "grad_norm": 0.33908453583717346, "learning_rate": 1.5105740181268884e-05, "loss": 0.0337, "step": 250 }, { "epoch": 0.011797469215978764, "grad_norm": 0.3221483826637268, "learning_rate": 1.570996978851964e-05, "loss": 0.043, "step": 260 }, { "epoch": 0.012251218031977948, "grad_norm": 0.8258805274963379, "learning_rate": 1.6314199395770393e-05, "loss": 0.0417, "step": 270 }, { "epoch": 0.012704966847977131, "grad_norm": 0.5601330995559692, "learning_rate": 1.691842900302115e-05, "loss": 0.0407, "step": 280 }, { "epoch": 0.013158715663976315, "grad_norm": 0.38478824496269226, "learning_rate": 1.7522658610271906e-05, "loss": 0.0406, "step": 290 }, { "epoch": 0.013612464479975498, "grad_norm": 0.5881060361862183, "learning_rate": 1.812688821752266e-05, "loss": 0.0334, "step": 300 }, { "epoch": 0.014066213295974682, "grad_norm": 0.4245070815086365, "learning_rate": 1.8731117824773413e-05, "loss": 0.0385, "step": 310 }, { "epoch": 0.014519962111973863, "grad_norm": 0.4297800660133362, "learning_rate": 1.933534743202417e-05, "loss": 0.0358, "step": 320 }, { "epoch": 0.014973710927973047, "grad_norm": 0.2811647653579712, "learning_rate": 1.9939577039274927e-05, "loss": 0.0335, "step": 330 }, { "epoch": 0.01542745974397223, "grad_norm": 0.57546466588974, "learning_rate": 1.9999965008575334e-05, "loss": 0.0361, "step": 340 }, { "epoch": 0.015881208559971414, "grad_norm": 0.3007296323776245, "learning_rate": 1.999984405087852e-05, "loss": 0.0339, "step": 350 }, { "epoch": 0.016334957375970596, "grad_norm": 0.3105521500110626, "learning_rate": 1.999963669596147e-05, "loss": 0.0292, "step": 360 }, { "epoch": 0.01678870619196978, "grad_norm": 0.290270060300827, "learning_rate": 1.9999342945615705e-05, "loss": 0.0346, "step": 370 }, { "epoch": 0.017242455007968963, "grad_norm": 0.2813795208930969, "learning_rate": 1.9998962802379185e-05, "loss": 0.0301, "step": 380 }, { "epoch": 0.017696203823968148, "grad_norm": 0.29500070214271545, "learning_rate": 1.9998496269536293e-05, "loss": 0.0318, "step": 390 }, { "epoch": 0.01814995263996733, "grad_norm": 0.2540959417819977, "learning_rate": 1.9997943351117804e-05, "loss": 0.0329, "step": 400 }, { "epoch": 0.018603701455966515, "grad_norm": 0.2642346918582916, "learning_rate": 1.9997304051900853e-05, "loss": 0.0304, "step": 410 }, { "epoch": 0.019057450271965697, "grad_norm": 0.22838017344474792, "learning_rate": 1.9996578377408897e-05, "loss": 0.0294, "step": 420 }, { "epoch": 0.01951119908796488, "grad_norm": 0.4193016290664673, "learning_rate": 1.9995766333911663e-05, "loss": 0.027, "step": 430 }, { "epoch": 0.019964947903964064, "grad_norm": 0.22686834633350372, "learning_rate": 1.999486792842508e-05, "loss": 0.0344, "step": 440 }, { "epoch": 0.020418696719963245, "grad_norm": 0.302196741104126, "learning_rate": 1.999388316871125e-05, "loss": 0.0334, "step": 450 }, { "epoch": 0.02087244553596243, "grad_norm": 0.3537577986717224, "learning_rate": 1.9992812063278354e-05, "loss": 0.0306, "step": 460 }, { "epoch": 0.021326194351961612, "grad_norm": 0.22693808376789093, "learning_rate": 1.9991654621380593e-05, "loss": 0.0226, "step": 470 }, { "epoch": 0.021779943167960798, "grad_norm": 0.24681711196899414, "learning_rate": 1.9990410853018094e-05, "loss": 0.0321, "step": 480 }, { "epoch": 0.02223369198395998, "grad_norm": 0.2591070234775543, "learning_rate": 1.998908076893684e-05, "loss": 0.0261, "step": 490 }, { "epoch": 0.02268744079995916, "grad_norm": 0.20605862140655518, "learning_rate": 1.9987664380628566e-05, "loss": 0.0327, "step": 500 }, { "epoch": 0.023141189615958346, "grad_norm": 0.20583385229110718, "learning_rate": 1.9986161700330668e-05, "loss": 0.026, "step": 510 }, { "epoch": 0.023594938431957528, "grad_norm": 0.19202348589897156, "learning_rate": 1.998457274102608e-05, "loss": 0.0292, "step": 520 }, { "epoch": 0.024048687247956713, "grad_norm": 0.21124207973480225, "learning_rate": 1.9982897516443194e-05, "loss": 0.0301, "step": 530 }, { "epoch": 0.024502436063955895, "grad_norm": 0.30822429060935974, "learning_rate": 1.9981136041055703e-05, "loss": 0.0315, "step": 540 }, { "epoch": 0.02495618487995508, "grad_norm": 0.19352686405181885, "learning_rate": 1.99792883300825e-05, "loss": 0.0315, "step": 550 }, { "epoch": 0.025409933695954262, "grad_norm": 0.30772942304611206, "learning_rate": 1.997735439948755e-05, "loss": 0.0306, "step": 560 }, { "epoch": 0.025863682511953444, "grad_norm": 0.19108739495277405, "learning_rate": 1.997533426597973e-05, "loss": 0.0289, "step": 570 }, { "epoch": 0.02631743132795263, "grad_norm": 0.33317863941192627, "learning_rate": 1.9973227947012713e-05, "loss": 0.0248, "step": 580 }, { "epoch": 0.02677118014395181, "grad_norm": 0.2728899419307709, "learning_rate": 1.9971035460784783e-05, "loss": 0.0309, "step": 590 }, { "epoch": 0.027224928959950996, "grad_norm": 0.1626482903957367, "learning_rate": 1.9968756826238713e-05, "loss": 0.03, "step": 600 }, { "epoch": 0.027678677775950178, "grad_norm": 0.21190127730369568, "learning_rate": 1.9966392063061573e-05, "loss": 0.0319, "step": 610 }, { "epoch": 0.028132426591949363, "grad_norm": 0.19617785513401031, "learning_rate": 1.9963941191684585e-05, "loss": 0.0255, "step": 620 }, { "epoch": 0.028586175407948545, "grad_norm": 0.1841568648815155, "learning_rate": 1.9961404233282926e-05, "loss": 0.0249, "step": 630 }, { "epoch": 0.029039924223947727, "grad_norm": 0.32211410999298096, "learning_rate": 1.995878120977555e-05, "loss": 0.0277, "step": 640 }, { "epoch": 0.029493673039946912, "grad_norm": 0.21315304934978485, "learning_rate": 1.9956072143825006e-05, "loss": 0.0271, "step": 650 }, { "epoch": 0.029947421855946094, "grad_norm": 0.21525444090366364, "learning_rate": 1.9953277058837237e-05, "loss": 0.0268, "step": 660 }, { "epoch": 0.03040117067194528, "grad_norm": 0.29101940989494324, "learning_rate": 1.9950395978961376e-05, "loss": 0.0303, "step": 670 }, { "epoch": 0.03085491948794446, "grad_norm": 0.21139028668403625, "learning_rate": 1.9947428929089536e-05, "loss": 0.0256, "step": 680 }, { "epoch": 0.031308668303943646, "grad_norm": 0.1668698489665985, "learning_rate": 1.9944375934856606e-05, "loss": 0.0228, "step": 690 }, { "epoch": 0.03176241711994283, "grad_norm": 0.18084610998630524, "learning_rate": 1.9941237022640024e-05, "loss": 0.0235, "step": 700 }, { "epoch": 0.03221616593594201, "grad_norm": 0.19767268002033234, "learning_rate": 1.9938012219559536e-05, "loss": 0.0222, "step": 710 }, { "epoch": 0.03266991475194119, "grad_norm": 0.16482102870941162, "learning_rate": 1.9934701553476983e-05, "loss": 0.0288, "step": 720 }, { "epoch": 0.03312366356794038, "grad_norm": 0.20850975811481476, "learning_rate": 1.993130505299604e-05, "loss": 0.0267, "step": 730 }, { "epoch": 0.03357741238393956, "grad_norm": 0.21490812301635742, "learning_rate": 1.9927822747461987e-05, "loss": 0.0235, "step": 740 }, { "epoch": 0.03403116119993874, "grad_norm": 0.19654904305934906, "learning_rate": 1.9924254666961446e-05, "loss": 0.0227, "step": 750 }, { "epoch": 0.034484910015937925, "grad_norm": 0.21930888295173645, "learning_rate": 1.9920600842322123e-05, "loss": 0.0193, "step": 760 }, { "epoch": 0.034938658831937114, "grad_norm": 0.1902710646390915, "learning_rate": 1.9916861305112536e-05, "loss": 0.025, "step": 770 }, { "epoch": 0.035392407647936296, "grad_norm": 0.22808505594730377, "learning_rate": 1.9913036087641756e-05, "loss": 0.0248, "step": 780 }, { "epoch": 0.03584615646393548, "grad_norm": 0.20141534507274628, "learning_rate": 1.9909125222959106e-05, "loss": 0.023, "step": 790 }, { "epoch": 0.03629990527993466, "grad_norm": 0.28839483857154846, "learning_rate": 1.9905128744853903e-05, "loss": 0.0239, "step": 800 }, { "epoch": 0.03675365409593384, "grad_norm": 0.20758938789367676, "learning_rate": 1.9901046687855142e-05, "loss": 0.0297, "step": 810 }, { "epoch": 0.03720740291193303, "grad_norm": 0.18895308673381805, "learning_rate": 1.9896879087231212e-05, "loss": 0.0285, "step": 820 }, { "epoch": 0.03766115172793221, "grad_norm": 0.1894659548997879, "learning_rate": 1.989262597898959e-05, "loss": 0.0221, "step": 830 }, { "epoch": 0.03811490054393139, "grad_norm": 0.1809016764163971, "learning_rate": 1.9888287399876514e-05, "loss": 0.0229, "step": 840 }, { "epoch": 0.038568649359930575, "grad_norm": 0.2581351399421692, "learning_rate": 1.9883863387376688e-05, "loss": 0.0227, "step": 850 }, { "epoch": 0.03902239817592976, "grad_norm": 0.17807897925376892, "learning_rate": 1.9879353979712953e-05, "loss": 0.0261, "step": 860 }, { "epoch": 0.039476146991928945, "grad_norm": 0.11872007697820663, "learning_rate": 1.987475921584594e-05, "loss": 0.0189, "step": 870 }, { "epoch": 0.03992989580792813, "grad_norm": 0.25756973028182983, "learning_rate": 1.987007913547375e-05, "loss": 0.0256, "step": 880 }, { "epoch": 0.04038364462392731, "grad_norm": 0.20726580917835236, "learning_rate": 1.9865313779031607e-05, "loss": 0.026, "step": 890 }, { "epoch": 0.04083739343992649, "grad_norm": 0.22280997037887573, "learning_rate": 1.986046318769151e-05, "loss": 0.0269, "step": 900 }, { "epoch": 0.04129114225592568, "grad_norm": 0.18491756916046143, "learning_rate": 1.9855527403361874e-05, "loss": 0.0254, "step": 910 }, { "epoch": 0.04174489107192486, "grad_norm": 0.20171596109867096, "learning_rate": 1.9850506468687164e-05, "loss": 0.0241, "step": 920 }, { "epoch": 0.04219863988792404, "grad_norm": 0.15816384553909302, "learning_rate": 1.9845400427047542e-05, "loss": 0.0197, "step": 930 }, { "epoch": 0.042652388703923225, "grad_norm": 0.230795219540596, "learning_rate": 1.9840209322558476e-05, "loss": 0.0259, "step": 940 }, { "epoch": 0.043106137519922406, "grad_norm": 0.19824784994125366, "learning_rate": 1.983493320007036e-05, "loss": 0.0211, "step": 950 }, { "epoch": 0.043559886335921595, "grad_norm": 0.3211159110069275, "learning_rate": 1.9829572105168137e-05, "loss": 0.0277, "step": 960 }, { "epoch": 0.04401363515192078, "grad_norm": 0.25476697087287903, "learning_rate": 1.9824126084170907e-05, "loss": 0.0243, "step": 970 }, { "epoch": 0.04446738396791996, "grad_norm": 0.14560280740261078, "learning_rate": 1.9818595184131505e-05, "loss": 0.0263, "step": 980 }, { "epoch": 0.04492113278391914, "grad_norm": 0.23038356006145477, "learning_rate": 1.9812979452836117e-05, "loss": 0.0254, "step": 990 }, { "epoch": 0.04537488159991832, "grad_norm": 0.2329760491847992, "learning_rate": 1.9807278938803853e-05, "loss": 0.025, "step": 1000 }, { "epoch": 0.04582863041591751, "grad_norm": 0.14942364394664764, "learning_rate": 1.980149369128634e-05, "loss": 0.0204, "step": 1010 }, { "epoch": 0.04628237923191669, "grad_norm": 0.25177106261253357, "learning_rate": 1.9795623760267294e-05, "loss": 0.0219, "step": 1020 }, { "epoch": 0.046736128047915874, "grad_norm": 0.13777080178260803, "learning_rate": 1.9789669196462072e-05, "loss": 0.0232, "step": 1030 }, { "epoch": 0.047189876863915056, "grad_norm": 0.29775476455688477, "learning_rate": 1.978363005131725e-05, "loss": 0.0232, "step": 1040 }, { "epoch": 0.047643625679914245, "grad_norm": 0.11764035373926163, "learning_rate": 1.9777506377010182e-05, "loss": 0.0216, "step": 1050 }, { "epoch": 0.04809737449591343, "grad_norm": 0.14460919797420502, "learning_rate": 1.9771298226448535e-05, "loss": 0.0196, "step": 1060 }, { "epoch": 0.04855112331191261, "grad_norm": 0.2370244413614273, "learning_rate": 1.9765005653269842e-05, "loss": 0.0186, "step": 1070 }, { "epoch": 0.04900487212791179, "grad_norm": 0.22975899279117584, "learning_rate": 1.9758628711841035e-05, "loss": 0.0255, "step": 1080 }, { "epoch": 0.04945862094391097, "grad_norm": 0.15732918679714203, "learning_rate": 1.975216745725797e-05, "loss": 0.0236, "step": 1090 }, { "epoch": 0.04991236975991016, "grad_norm": 0.22892169654369354, "learning_rate": 1.974562194534496e-05, "loss": 0.0221, "step": 1100 }, { "epoch": 0.05036611857590934, "grad_norm": 0.23350407183170319, "learning_rate": 1.9738992232654296e-05, "loss": 0.0214, "step": 1110 }, { "epoch": 0.050819867391908524, "grad_norm": 0.16440296173095703, "learning_rate": 1.9732278376465746e-05, "loss": 0.0229, "step": 1120 }, { "epoch": 0.051273616207907706, "grad_norm": 0.24186445772647858, "learning_rate": 1.9725480434786065e-05, "loss": 0.0173, "step": 1130 }, { "epoch": 0.05172736502390689, "grad_norm": 0.26814499497413635, "learning_rate": 1.971859846634849e-05, "loss": 0.0239, "step": 1140 }, { "epoch": 0.052181113839906076, "grad_norm": 0.18819460272789001, "learning_rate": 1.9711632530612247e-05, "loss": 0.0242, "step": 1150 }, { "epoch": 0.05263486265590526, "grad_norm": 0.24237270653247833, "learning_rate": 1.970458268776202e-05, "loss": 0.021, "step": 1160 }, { "epoch": 0.05308861147190444, "grad_norm": 0.12217427045106888, "learning_rate": 1.9697448998707448e-05, "loss": 0.0211, "step": 1170 }, { "epoch": 0.05354236028790362, "grad_norm": 0.1240953803062439, "learning_rate": 1.9690231525082576e-05, "loss": 0.0217, "step": 1180 }, { "epoch": 0.05399610910390281, "grad_norm": 0.20499229431152344, "learning_rate": 1.968293032924535e-05, "loss": 0.0181, "step": 1190 }, { "epoch": 0.05444985791990199, "grad_norm": 0.18976397812366486, "learning_rate": 1.9675545474277045e-05, "loss": 0.0227, "step": 1200 }, { "epoch": 0.054903606735901174, "grad_norm": 0.20261284708976746, "learning_rate": 1.966807702398176e-05, "loss": 0.0189, "step": 1210 }, { "epoch": 0.055357355551900356, "grad_norm": 0.2102660983800888, "learning_rate": 1.9660525042885828e-05, "loss": 0.0201, "step": 1220 }, { "epoch": 0.05581110436789954, "grad_norm": 0.14674915373325348, "learning_rate": 1.965288959623729e-05, "loss": 0.0219, "step": 1230 }, { "epoch": 0.056264853183898726, "grad_norm": 0.1795043647289276, "learning_rate": 1.964517075000531e-05, "loss": 0.0235, "step": 1240 }, { "epoch": 0.05671860199989791, "grad_norm": 0.17725716531276703, "learning_rate": 1.9637368570879612e-05, "loss": 0.0196, "step": 1250 }, { "epoch": 0.05717235081589709, "grad_norm": 0.257306307554245, "learning_rate": 1.9629483126269904e-05, "loss": 0.0267, "step": 1260 }, { "epoch": 0.05762609963189627, "grad_norm": 0.1503366380929947, "learning_rate": 1.9621514484305308e-05, "loss": 0.0235, "step": 1270 }, { "epoch": 0.05807984844789545, "grad_norm": 0.18728020787239075, "learning_rate": 1.9613462713833734e-05, "loss": 0.0224, "step": 1280 }, { "epoch": 0.05853359726389464, "grad_norm": 0.14319869875907898, "learning_rate": 1.9605327884421338e-05, "loss": 0.0226, "step": 1290 }, { "epoch": 0.058987346079893824, "grad_norm": 0.19164982438087463, "learning_rate": 1.9597110066351875e-05, "loss": 0.0214, "step": 1300 }, { "epoch": 0.059441094895893005, "grad_norm": 0.16897734999656677, "learning_rate": 1.958880933062612e-05, "loss": 0.0191, "step": 1310 }, { "epoch": 0.05989484371189219, "grad_norm": 0.17611093819141388, "learning_rate": 1.958042574896124e-05, "loss": 0.0191, "step": 1320 }, { "epoch": 0.060348592527891376, "grad_norm": 0.2144123613834381, "learning_rate": 1.9571959393790174e-05, "loss": 0.0199, "step": 1330 }, { "epoch": 0.06080234134389056, "grad_norm": 0.14778178930282593, "learning_rate": 1.9563410338261022e-05, "loss": 0.0211, "step": 1340 }, { "epoch": 0.06125609015988974, "grad_norm": 0.17958305776119232, "learning_rate": 1.9554778656236402e-05, "loss": 0.0219, "step": 1350 }, { "epoch": 0.06170983897588892, "grad_norm": 0.13452428579330444, "learning_rate": 1.9546064422292806e-05, "loss": 0.0195, "step": 1360 }, { "epoch": 0.0621635877918881, "grad_norm": 0.3412012755870819, "learning_rate": 1.9537267711719966e-05, "loss": 0.0255, "step": 1370 }, { "epoch": 0.06261733660788729, "grad_norm": 0.15667815506458282, "learning_rate": 1.9528388600520208e-05, "loss": 0.0205, "step": 1380 }, { "epoch": 0.06307108542388647, "grad_norm": 0.17193084955215454, "learning_rate": 1.9519427165407773e-05, "loss": 0.0184, "step": 1390 }, { "epoch": 0.06352483423988566, "grad_norm": 0.4006859362125397, "learning_rate": 1.9510383483808183e-05, "loss": 0.0205, "step": 1400 }, { "epoch": 0.06397858305588484, "grad_norm": 0.16710975766181946, "learning_rate": 1.950125763385755e-05, "loss": 0.0163, "step": 1410 }, { "epoch": 0.06443233187188402, "grad_norm": 0.10505062341690063, "learning_rate": 1.949204969440191e-05, "loss": 0.0218, "step": 1420 }, { "epoch": 0.06488608068788321, "grad_norm": 0.21609047055244446, "learning_rate": 1.9482759744996537e-05, "loss": 0.0229, "step": 1430 }, { "epoch": 0.06533982950388238, "grad_norm": 0.20407827198505402, "learning_rate": 1.9473387865905268e-05, "loss": 0.024, "step": 1440 }, { "epoch": 0.06579357831988157, "grad_norm": 0.23411345481872559, "learning_rate": 1.9463934138099796e-05, "loss": 0.0219, "step": 1450 }, { "epoch": 0.06624732713588076, "grad_norm": 0.12452846765518188, "learning_rate": 1.945439864325897e-05, "loss": 0.0193, "step": 1460 }, { "epoch": 0.06670107595187993, "grad_norm": 0.18108753859996796, "learning_rate": 1.944478146376811e-05, "loss": 0.0215, "step": 1470 }, { "epoch": 0.06715482476787912, "grad_norm": 0.26348456740379333, "learning_rate": 1.943508268271826e-05, "loss": 0.0237, "step": 1480 }, { "epoch": 0.0676085735838783, "grad_norm": 0.2291336953639984, "learning_rate": 1.9425302383905497e-05, "loss": 0.0253, "step": 1490 }, { "epoch": 0.06806232239987749, "grad_norm": 0.16427820920944214, "learning_rate": 1.941544065183021e-05, "loss": 0.0204, "step": 1500 }, { "epoch": 0.06851607121587668, "grad_norm": 0.1851368248462677, "learning_rate": 1.9405497571696347e-05, "loss": 0.0205, "step": 1510 }, { "epoch": 0.06896982003187585, "grad_norm": 0.14838038384914398, "learning_rate": 1.93954732294107e-05, "loss": 0.0215, "step": 1520 }, { "epoch": 0.06942356884787504, "grad_norm": 0.21539480984210968, "learning_rate": 1.9385367711582142e-05, "loss": 0.0188, "step": 1530 }, { "epoch": 0.06987731766387423, "grad_norm": 0.1814572513103485, "learning_rate": 1.9375181105520907e-05, "loss": 0.017, "step": 1540 }, { "epoch": 0.0703310664798734, "grad_norm": 0.15002450346946716, "learning_rate": 1.9364913499237814e-05, "loss": 0.0153, "step": 1550 }, { "epoch": 0.07078481529587259, "grad_norm": 0.1734616905450821, "learning_rate": 1.93545649814435e-05, "loss": 0.0175, "step": 1560 }, { "epoch": 0.07123856411187177, "grad_norm": 0.19587118923664093, "learning_rate": 1.934413564154769e-05, "loss": 0.0163, "step": 1570 }, { "epoch": 0.07169231292787095, "grad_norm": 0.3268190622329712, "learning_rate": 1.9333625569658377e-05, "loss": 0.0271, "step": 1580 }, { "epoch": 0.07214606174387014, "grad_norm": 0.13944011926651, "learning_rate": 1.9323034856581083e-05, "loss": 0.0192, "step": 1590 }, { "epoch": 0.07259981055986932, "grad_norm": 0.19798707962036133, "learning_rate": 1.9312363593818045e-05, "loss": 0.0218, "step": 1600 }, { "epoch": 0.07305355937586851, "grad_norm": 0.23335348069667816, "learning_rate": 1.930161187356745e-05, "loss": 0.0182, "step": 1610 }, { "epoch": 0.07350730819186768, "grad_norm": 0.22754572331905365, "learning_rate": 1.929077978872262e-05, "loss": 0.02, "step": 1620 }, { "epoch": 0.07396105700786687, "grad_norm": 0.204678013920784, "learning_rate": 1.9279867432871215e-05, "loss": 0.0183, "step": 1630 }, { "epoch": 0.07441480582386606, "grad_norm": 0.178049698472023, "learning_rate": 1.9268874900294426e-05, "loss": 0.0209, "step": 1640 }, { "epoch": 0.07486855463986523, "grad_norm": 0.15484187006950378, "learning_rate": 1.9257802285966166e-05, "loss": 0.0195, "step": 1650 }, { "epoch": 0.07532230345586442, "grad_norm": 0.24483802914619446, "learning_rate": 1.924664968555223e-05, "loss": 0.0209, "step": 1660 }, { "epoch": 0.0757760522718636, "grad_norm": 0.19685238599777222, "learning_rate": 1.9235417195409487e-05, "loss": 0.0185, "step": 1670 }, { "epoch": 0.07622980108786279, "grad_norm": 0.19824953377246857, "learning_rate": 1.922410491258505e-05, "loss": 0.0205, "step": 1680 }, { "epoch": 0.07668354990386198, "grad_norm": 0.22647970914840698, "learning_rate": 1.9212712934815413e-05, "loss": 0.0228, "step": 1690 }, { "epoch": 0.07713729871986115, "grad_norm": 0.17476406693458557, "learning_rate": 1.9201241360525643e-05, "loss": 0.0187, "step": 1700 }, { "epoch": 0.07759104753586034, "grad_norm": 0.16340398788452148, "learning_rate": 1.9189690288828487e-05, "loss": 0.0222, "step": 1710 }, { "epoch": 0.07804479635185951, "grad_norm": 0.18391962349414825, "learning_rate": 1.9178059819523563e-05, "loss": 0.0186, "step": 1720 }, { "epoch": 0.0784985451678587, "grad_norm": 0.2142099142074585, "learning_rate": 1.9166350053096453e-05, "loss": 0.0195, "step": 1730 }, { "epoch": 0.07895229398385789, "grad_norm": 0.1180528923869133, "learning_rate": 1.9154561090717857e-05, "loss": 0.0189, "step": 1740 }, { "epoch": 0.07940604279985707, "grad_norm": 0.5472745895385742, "learning_rate": 1.9142693034242726e-05, "loss": 0.0157, "step": 1750 }, { "epoch": 0.07985979161585625, "grad_norm": 0.22652597725391388, "learning_rate": 1.913074598620937e-05, "loss": 0.0209, "step": 1760 }, { "epoch": 0.08031354043185543, "grad_norm": 0.15762144327163696, "learning_rate": 1.9118720049838567e-05, "loss": 0.0185, "step": 1770 }, { "epoch": 0.08076728924785462, "grad_norm": 0.13876491785049438, "learning_rate": 1.9106615329032695e-05, "loss": 0.0199, "step": 1780 }, { "epoch": 0.0812210380638538, "grad_norm": 0.122488833963871, "learning_rate": 1.9094431928374798e-05, "loss": 0.0171, "step": 1790 }, { "epoch": 0.08167478687985298, "grad_norm": 0.180863156914711, "learning_rate": 1.9082169953127714e-05, "loss": 0.0188, "step": 1800 }, { "epoch": 0.08212853569585217, "grad_norm": 0.12064477801322937, "learning_rate": 1.9069829509233156e-05, "loss": 0.0167, "step": 1810 }, { "epoch": 0.08258228451185136, "grad_norm": 0.14084497094154358, "learning_rate": 1.9057410703310788e-05, "loss": 0.0171, "step": 1820 }, { "epoch": 0.08303603332785053, "grad_norm": 0.14194680750370026, "learning_rate": 1.9044913642657318e-05, "loss": 0.0181, "step": 1830 }, { "epoch": 0.08348978214384972, "grad_norm": 0.1599424034357071, "learning_rate": 1.9032338435245557e-05, "loss": 0.0182, "step": 1840 }, { "epoch": 0.0839435309598489, "grad_norm": 0.19771797955036163, "learning_rate": 1.9019685189723497e-05, "loss": 0.0206, "step": 1850 }, { "epoch": 0.08439727977584809, "grad_norm": 0.18152743577957153, "learning_rate": 1.900695401541337e-05, "loss": 0.0173, "step": 1860 }, { "epoch": 0.08485102859184727, "grad_norm": 0.2753470540046692, "learning_rate": 1.8994145022310693e-05, "loss": 0.0166, "step": 1870 }, { "epoch": 0.08530477740784645, "grad_norm": 0.15675047039985657, "learning_rate": 1.8981258321083335e-05, "loss": 0.0175, "step": 1880 }, { "epoch": 0.08575852622384564, "grad_norm": 0.17321479320526123, "learning_rate": 1.8968294023070548e-05, "loss": 0.0183, "step": 1890 }, { "epoch": 0.08621227503984481, "grad_norm": 0.17072314023971558, "learning_rate": 1.895525224028201e-05, "loss": 0.019, "step": 1900 }, { "epoch": 0.086666023855844, "grad_norm": 0.14354068040847778, "learning_rate": 1.8942133085396855e-05, "loss": 0.0156, "step": 1910 }, { "epoch": 0.08711977267184319, "grad_norm": 0.1175990179181099, "learning_rate": 1.8928936671762704e-05, "loss": 0.0185, "step": 1920 }, { "epoch": 0.08757352148784237, "grad_norm": 0.16355715692043304, "learning_rate": 1.8915663113394677e-05, "loss": 0.022, "step": 1930 }, { "epoch": 0.08802727030384155, "grad_norm": 0.17260967195034027, "learning_rate": 1.890231252497442e-05, "loss": 0.0173, "step": 1940 }, { "epoch": 0.08848101911984073, "grad_norm": 0.11865406483411789, "learning_rate": 1.8888885021849103e-05, "loss": 0.0178, "step": 1950 }, { "epoch": 0.08893476793583992, "grad_norm": 0.21612539887428284, "learning_rate": 1.8875380720030434e-05, "loss": 0.0182, "step": 1960 }, { "epoch": 0.0893885167518391, "grad_norm": 0.16676916182041168, "learning_rate": 1.886179973619364e-05, "loss": 0.0196, "step": 1970 }, { "epoch": 0.08984226556783828, "grad_norm": 0.19464704394340515, "learning_rate": 1.8848142187676485e-05, "loss": 0.0181, "step": 1980 }, { "epoch": 0.09029601438383747, "grad_norm": 0.132132887840271, "learning_rate": 1.883440819247822e-05, "loss": 0.0202, "step": 1990 }, { "epoch": 0.09074976319983664, "grad_norm": 0.06793658435344696, "learning_rate": 1.8820597869258606e-05, "loss": 0.0186, "step": 2000 }, { "epoch": 0.09120351201583583, "grad_norm": 0.12745976448059082, "learning_rate": 1.8806711337336852e-05, "loss": 0.0147, "step": 2010 }, { "epoch": 0.09165726083183502, "grad_norm": 0.1296985149383545, "learning_rate": 1.8792748716690608e-05, "loss": 0.0204, "step": 2020 }, { "epoch": 0.0921110096478342, "grad_norm": 0.13504616916179657, "learning_rate": 1.8778710127954912e-05, "loss": 0.0202, "step": 2030 }, { "epoch": 0.09256475846383339, "grad_norm": 0.16446679830551147, "learning_rate": 1.8764595692421163e-05, "loss": 0.0174, "step": 2040 }, { "epoch": 0.09301850727983256, "grad_norm": 0.16824571788311005, "learning_rate": 1.8750405532036064e-05, "loss": 0.0181, "step": 2050 }, { "epoch": 0.09347225609583175, "grad_norm": 0.16484525799751282, "learning_rate": 1.8736139769400567e-05, "loss": 0.019, "step": 2060 }, { "epoch": 0.09392600491183094, "grad_norm": 0.10692662000656128, "learning_rate": 1.8721798527768813e-05, "loss": 0.0173, "step": 2070 }, { "epoch": 0.09437975372783011, "grad_norm": 0.11817700415849686, "learning_rate": 1.870738193104708e-05, "loss": 0.0166, "step": 2080 }, { "epoch": 0.0948335025438293, "grad_norm": 0.08484214544296265, "learning_rate": 1.86928901037927e-05, "loss": 0.0162, "step": 2090 }, { "epoch": 0.09528725135982849, "grad_norm": 0.15628601610660553, "learning_rate": 1.8678323171212982e-05, "loss": 0.023, "step": 2100 }, { "epoch": 0.09574100017582766, "grad_norm": 0.1476244032382965, "learning_rate": 1.866368125916414e-05, "loss": 0.0165, "step": 2110 }, { "epoch": 0.09619474899182685, "grad_norm": 0.1540534645318985, "learning_rate": 1.864896449415019e-05, "loss": 0.0153, "step": 2120 }, { "epoch": 0.09664849780782603, "grad_norm": 0.16797024011611938, "learning_rate": 1.863417300332188e-05, "loss": 0.0174, "step": 2130 }, { "epoch": 0.09710224662382522, "grad_norm": 0.2063974291086197, "learning_rate": 1.8619306914475573e-05, "loss": 0.0179, "step": 2140 }, { "epoch": 0.0975559954398244, "grad_norm": 0.09223387390375137, "learning_rate": 1.860436635605214e-05, "loss": 0.0195, "step": 2150 }, { "epoch": 0.09800974425582358, "grad_norm": 0.13801980018615723, "learning_rate": 1.8589351457135873e-05, "loss": 0.0148, "step": 2160 }, { "epoch": 0.09846349307182277, "grad_norm": 0.1553402692079544, "learning_rate": 1.8574262347453344e-05, "loss": 0.0206, "step": 2170 }, { "epoch": 0.09891724188782194, "grad_norm": 0.15037605166435242, "learning_rate": 1.85590991573723e-05, "loss": 0.0184, "step": 2180 }, { "epoch": 0.09937099070382113, "grad_norm": 0.15879248082637787, "learning_rate": 1.854386201790053e-05, "loss": 0.0154, "step": 2190 }, { "epoch": 0.09982473951982032, "grad_norm": 0.1976829469203949, "learning_rate": 1.8528551060684744e-05, "loss": 0.0182, "step": 2200 }, { "epoch": 0.1002784883358195, "grad_norm": 0.13963422179222107, "learning_rate": 1.851316641800941e-05, "loss": 0.0177, "step": 2210 }, { "epoch": 0.10073223715181868, "grad_norm": 0.137124165892601, "learning_rate": 1.8497708222795638e-05, "loss": 0.0169, "step": 2220 }, { "epoch": 0.10118598596781786, "grad_norm": 0.12080398201942444, "learning_rate": 1.8482176608600025e-05, "loss": 0.0179, "step": 2230 }, { "epoch": 0.10163973478381705, "grad_norm": 0.15364421904087067, "learning_rate": 1.846657170961349e-05, "loss": 0.0213, "step": 2240 }, { "epoch": 0.10209348359981624, "grad_norm": 0.14096081256866455, "learning_rate": 1.8450893660660126e-05, "loss": 0.0192, "step": 2250 }, { "epoch": 0.10254723241581541, "grad_norm": 0.1408587396144867, "learning_rate": 1.8435142597196033e-05, "loss": 0.0175, "step": 2260 }, { "epoch": 0.1030009812318146, "grad_norm": 0.20252038538455963, "learning_rate": 1.8419318655308135e-05, "loss": 0.0184, "step": 2270 }, { "epoch": 0.10345473004781378, "grad_norm": 0.18738800287246704, "learning_rate": 1.8403421971713034e-05, "loss": 0.022, "step": 2280 }, { "epoch": 0.10390847886381296, "grad_norm": 0.12882310152053833, "learning_rate": 1.838745268375579e-05, "loss": 0.0162, "step": 2290 }, { "epoch": 0.10436222767981215, "grad_norm": 0.27208372950553894, "learning_rate": 1.8371410929408767e-05, "loss": 0.018, "step": 2300 }, { "epoch": 0.10481597649581133, "grad_norm": 0.17671839892864227, "learning_rate": 1.835529684727043e-05, "loss": 0.0153, "step": 2310 }, { "epoch": 0.10526972531181052, "grad_norm": 0.14073553681373596, "learning_rate": 1.8339110576564132e-05, "loss": 0.0129, "step": 2320 }, { "epoch": 0.10572347412780969, "grad_norm": 0.21200872957706451, "learning_rate": 1.8322852257136935e-05, "loss": 0.0149, "step": 2330 }, { "epoch": 0.10617722294380888, "grad_norm": 0.1357947438955307, "learning_rate": 1.8306522029458395e-05, "loss": 0.0152, "step": 2340 }, { "epoch": 0.10663097175980807, "grad_norm": 0.16543570160865784, "learning_rate": 1.8290120034619335e-05, "loss": 0.0174, "step": 2350 }, { "epoch": 0.10708472057580724, "grad_norm": 0.14833608269691467, "learning_rate": 1.8273646414330645e-05, "loss": 0.0188, "step": 2360 }, { "epoch": 0.10753846939180643, "grad_norm": 0.18101650476455688, "learning_rate": 1.8257101310922042e-05, "loss": 0.0209, "step": 2370 }, { "epoch": 0.10799221820780562, "grad_norm": 0.16748115420341492, "learning_rate": 1.8240484867340852e-05, "loss": 0.0139, "step": 2380 }, { "epoch": 0.1084459670238048, "grad_norm": 0.11527730524539948, "learning_rate": 1.8223797227150762e-05, "loss": 0.017, "step": 2390 }, { "epoch": 0.10889971583980398, "grad_norm": 0.11009083688259125, "learning_rate": 1.8207038534530598e-05, "loss": 0.0156, "step": 2400 }, { "epoch": 0.10935346465580316, "grad_norm": 0.13898172974586487, "learning_rate": 1.819020893427306e-05, "loss": 0.0139, "step": 2410 }, { "epoch": 0.10980721347180235, "grad_norm": 0.16770926117897034, "learning_rate": 1.817330857178349e-05, "loss": 0.0191, "step": 2420 }, { "epoch": 0.11026096228780154, "grad_norm": 0.18160074949264526, "learning_rate": 1.8156337593078594e-05, "loss": 0.0157, "step": 2430 }, { "epoch": 0.11071471110380071, "grad_norm": 0.3015523850917816, "learning_rate": 1.81392961447852e-05, "loss": 0.0164, "step": 2440 }, { "epoch": 0.1111684599197999, "grad_norm": 0.15210019052028656, "learning_rate": 1.8122184374138973e-05, "loss": 0.0163, "step": 2450 }, { "epoch": 0.11162220873579907, "grad_norm": 0.20538808405399323, "learning_rate": 1.810500242898317e-05, "loss": 0.017, "step": 2460 }, { "epoch": 0.11207595755179826, "grad_norm": 0.11042232811450958, "learning_rate": 1.808775045776733e-05, "loss": 0.0181, "step": 2470 }, { "epoch": 0.11252970636779745, "grad_norm": 0.17539720237255096, "learning_rate": 1.8070428609546012e-05, "loss": 0.0192, "step": 2480 }, { "epoch": 0.11298345518379663, "grad_norm": 0.12473191320896149, "learning_rate": 1.8053037033977513e-05, "loss": 0.0145, "step": 2490 }, { "epoch": 0.11343720399979582, "grad_norm": 0.18241970241069794, "learning_rate": 1.803557588132254e-05, "loss": 0.0152, "step": 2500 }, { "epoch": 0.11389095281579499, "grad_norm": 0.18567833304405212, "learning_rate": 1.8018045302442966e-05, "loss": 0.0191, "step": 2510 }, { "epoch": 0.11434470163179418, "grad_norm": 0.14060088992118835, "learning_rate": 1.8000445448800473e-05, "loss": 0.0149, "step": 2520 }, { "epoch": 0.11479845044779337, "grad_norm": 0.13550737500190735, "learning_rate": 1.7982776472455274e-05, "loss": 0.0162, "step": 2530 }, { "epoch": 0.11525219926379254, "grad_norm": 0.19916965067386627, "learning_rate": 1.7965038526064796e-05, "loss": 0.0223, "step": 2540 }, { "epoch": 0.11570594807979173, "grad_norm": 0.12130658328533173, "learning_rate": 1.794723176288236e-05, "loss": 0.0174, "step": 2550 }, { "epoch": 0.1161596968957909, "grad_norm": 0.1917196363210678, "learning_rate": 1.7929356336755842e-05, "loss": 0.0163, "step": 2560 }, { "epoch": 0.1166134457117901, "grad_norm": 0.17202790081501007, "learning_rate": 1.7911412402126366e-05, "loss": 0.0186, "step": 2570 }, { "epoch": 0.11706719452778928, "grad_norm": 0.14728401601314545, "learning_rate": 1.789340011402696e-05, "loss": 0.0183, "step": 2580 }, { "epoch": 0.11752094334378846, "grad_norm": 0.14162848889827728, "learning_rate": 1.7875319628081205e-05, "loss": 0.0169, "step": 2590 }, { "epoch": 0.11797469215978765, "grad_norm": 0.21042858064174652, "learning_rate": 1.785717110050192e-05, "loss": 0.0175, "step": 2600 }, { "epoch": 0.11842844097578682, "grad_norm": 0.19633285701274872, "learning_rate": 1.7838954688089777e-05, "loss": 0.0177, "step": 2610 }, { "epoch": 0.11888218979178601, "grad_norm": 0.17580154538154602, "learning_rate": 1.782067054823197e-05, "loss": 0.0173, "step": 2620 }, { "epoch": 0.1193359386077852, "grad_norm": 0.19531863927841187, "learning_rate": 1.7802318838900855e-05, "loss": 0.017, "step": 2630 }, { "epoch": 0.11978968742378437, "grad_norm": 0.18159744143486023, "learning_rate": 1.7783899718652563e-05, "loss": 0.0156, "step": 2640 }, { "epoch": 0.12024343623978356, "grad_norm": 0.1459454447031021, "learning_rate": 1.776541334662566e-05, "loss": 0.0186, "step": 2650 }, { "epoch": 0.12069718505578275, "grad_norm": 0.1914101392030716, "learning_rate": 1.7746859882539747e-05, "loss": 0.0187, "step": 2660 }, { "epoch": 0.12115093387178193, "grad_norm": 0.1784563958644867, "learning_rate": 1.7728239486694104e-05, "loss": 0.0196, "step": 2670 }, { "epoch": 0.12160468268778112, "grad_norm": 0.08064709603786469, "learning_rate": 1.7709552319966275e-05, "loss": 0.0176, "step": 2680 }, { "epoch": 0.12205843150378029, "grad_norm": 0.14399228990077972, "learning_rate": 1.7690798543810715e-05, "loss": 0.0183, "step": 2690 }, { "epoch": 0.12251218031977948, "grad_norm": 0.17591546475887299, "learning_rate": 1.7671978320257356e-05, "loss": 0.0175, "step": 2700 }, { "epoch": 0.12296592913577867, "grad_norm": 0.13131193816661835, "learning_rate": 1.7653091811910236e-05, "loss": 0.016, "step": 2710 }, { "epoch": 0.12341967795177784, "grad_norm": 0.1686732918024063, "learning_rate": 1.763413918194608e-05, "loss": 0.018, "step": 2720 }, { "epoch": 0.12387342676777703, "grad_norm": 0.11113517731428146, "learning_rate": 1.7615120594112895e-05, "loss": 0.0116, "step": 2730 }, { "epoch": 0.1243271755837762, "grad_norm": 0.1889534294605255, "learning_rate": 1.7596036212728558e-05, "loss": 0.0134, "step": 2740 }, { "epoch": 0.1247809243997754, "grad_norm": 0.11649326980113983, "learning_rate": 1.757688620267939e-05, "loss": 0.0166, "step": 2750 }, { "epoch": 0.12523467321577458, "grad_norm": 0.10533057898283005, "learning_rate": 1.755767072941874e-05, "loss": 0.0168, "step": 2760 }, { "epoch": 0.12568842203177377, "grad_norm": 0.12259650975465775, "learning_rate": 1.7538389958965537e-05, "loss": 0.019, "step": 2770 }, { "epoch": 0.12614217084777293, "grad_norm": 0.12395651638507843, "learning_rate": 1.7519044057902877e-05, "loss": 0.0173, "step": 2780 }, { "epoch": 0.12659591966377212, "grad_norm": 0.1267583966255188, "learning_rate": 1.749963319337658e-05, "loss": 0.0193, "step": 2790 }, { "epoch": 0.1270496684797713, "grad_norm": 0.13603775203227997, "learning_rate": 1.748015753309373e-05, "loss": 0.0129, "step": 2800 }, { "epoch": 0.1275034172957705, "grad_norm": 0.13848282396793365, "learning_rate": 1.746061724532124e-05, "loss": 0.0174, "step": 2810 }, { "epoch": 0.1279571661117697, "grad_norm": 0.12324777990579605, "learning_rate": 1.7441012498884402e-05, "loss": 0.0154, "step": 2820 }, { "epoch": 0.12841091492776885, "grad_norm": 0.11400323361158371, "learning_rate": 1.7421343463165415e-05, "loss": 0.0228, "step": 2830 }, { "epoch": 0.12886466374376804, "grad_norm": 0.15013644099235535, "learning_rate": 1.7401610308101933e-05, "loss": 0.0186, "step": 2840 }, { "epoch": 0.12931841255976723, "grad_norm": 0.09237401932477951, "learning_rate": 1.7381813204185585e-05, "loss": 0.013, "step": 2850 }, { "epoch": 0.12977216137576641, "grad_norm": 0.10135433822870255, "learning_rate": 1.7361952322460513e-05, "loss": 0.0155, "step": 2860 }, { "epoch": 0.1302259101917656, "grad_norm": 0.14442168176174164, "learning_rate": 1.7342027834521896e-05, "loss": 0.0152, "step": 2870 }, { "epoch": 0.13067965900776476, "grad_norm": 0.18447421491146088, "learning_rate": 1.7322039912514453e-05, "loss": 0.0132, "step": 2880 }, { "epoch": 0.13113340782376395, "grad_norm": 0.12967820465564728, "learning_rate": 1.7301988729130964e-05, "loss": 0.016, "step": 2890 }, { "epoch": 0.13158715663976314, "grad_norm": 0.12769745290279388, "learning_rate": 1.7281874457610787e-05, "loss": 0.0153, "step": 2900 }, { "epoch": 0.13204090545576233, "grad_norm": 0.15218707919120789, "learning_rate": 1.7261697271738337e-05, "loss": 0.0183, "step": 2910 }, { "epoch": 0.13249465427176152, "grad_norm": 0.16455717384815216, "learning_rate": 1.724145734584162e-05, "loss": 0.0143, "step": 2920 }, { "epoch": 0.13294840308776068, "grad_norm": 0.10103851556777954, "learning_rate": 1.7221154854790696e-05, "loss": 0.0147, "step": 2930 }, { "epoch": 0.13340215190375987, "grad_norm": 0.14905039966106415, "learning_rate": 1.7200789973996172e-05, "loss": 0.016, "step": 2940 }, { "epoch": 0.13385590071975906, "grad_norm": 0.12322589010000229, "learning_rate": 1.7180362879407707e-05, "loss": 0.0157, "step": 2950 }, { "epoch": 0.13430964953575825, "grad_norm": 0.11649531126022339, "learning_rate": 1.7159873747512472e-05, "loss": 0.0163, "step": 2960 }, { "epoch": 0.13476339835175744, "grad_norm": 0.14495816826820374, "learning_rate": 1.713932275533363e-05, "loss": 0.0166, "step": 2970 }, { "epoch": 0.1352171471677566, "grad_norm": 0.15184004604816437, "learning_rate": 1.7118710080428807e-05, "loss": 0.0166, "step": 2980 }, { "epoch": 0.13567089598375578, "grad_norm": 0.12919002771377563, "learning_rate": 1.7098035900888566e-05, "loss": 0.0152, "step": 2990 }, { "epoch": 0.13612464479975497, "grad_norm": 0.11966107785701752, "learning_rate": 1.7077300395334857e-05, "loss": 0.0195, "step": 3000 }, { "epoch": 0.13657839361575416, "grad_norm": 0.17783291637897491, "learning_rate": 1.7056503742919476e-05, "loss": 0.0167, "step": 3010 }, { "epoch": 0.13703214243175335, "grad_norm": 0.12602168321609497, "learning_rate": 1.703564612332252e-05, "loss": 0.0151, "step": 3020 }, { "epoch": 0.1374858912477525, "grad_norm": 0.09736641496419907, "learning_rate": 1.7014727716750842e-05, "loss": 0.0158, "step": 3030 }, { "epoch": 0.1379396400637517, "grad_norm": 0.1253587156534195, "learning_rate": 1.699374870393647e-05, "loss": 0.0156, "step": 3040 }, { "epoch": 0.1383933888797509, "grad_norm": 0.09786481410264969, "learning_rate": 1.697270926613507e-05, "loss": 0.0149, "step": 3050 }, { "epoch": 0.13884713769575008, "grad_norm": 0.21456241607666016, "learning_rate": 1.6951609585124377e-05, "loss": 0.0181, "step": 3060 }, { "epoch": 0.13930088651174927, "grad_norm": 0.11838903278112411, "learning_rate": 1.6930449843202607e-05, "loss": 0.0159, "step": 3070 }, { "epoch": 0.13975463532774846, "grad_norm": 0.11284634470939636, "learning_rate": 1.69092302231869e-05, "loss": 0.0175, "step": 3080 }, { "epoch": 0.14020838414374762, "grad_norm": 0.11104199290275574, "learning_rate": 1.688795090841173e-05, "loss": 0.0146, "step": 3090 }, { "epoch": 0.1406621329597468, "grad_norm": 0.12857995927333832, "learning_rate": 1.686661208272734e-05, "loss": 0.0152, "step": 3100 }, { "epoch": 0.141115881775746, "grad_norm": 0.11044860631227493, "learning_rate": 1.6845213930498122e-05, "loss": 0.0168, "step": 3110 }, { "epoch": 0.14156963059174518, "grad_norm": 0.10590340197086334, "learning_rate": 1.682375663660104e-05, "loss": 0.0137, "step": 3120 }, { "epoch": 0.14202337940774437, "grad_norm": 0.11977773904800415, "learning_rate": 1.680224038642405e-05, "loss": 0.0137, "step": 3130 }, { "epoch": 0.14247712822374353, "grad_norm": 0.14470188319683075, "learning_rate": 1.6780665365864465e-05, "loss": 0.0173, "step": 3140 }, { "epoch": 0.14293087703974272, "grad_norm": 0.1370120346546173, "learning_rate": 1.675903176132737e-05, "loss": 0.0145, "step": 3150 }, { "epoch": 0.1433846258557419, "grad_norm": 0.11182472109794617, "learning_rate": 1.6737339759724016e-05, "loss": 0.0155, "step": 3160 }, { "epoch": 0.1438383746717411, "grad_norm": 0.14719906449317932, "learning_rate": 1.6715589548470187e-05, "loss": 0.015, "step": 3170 }, { "epoch": 0.1442921234877403, "grad_norm": 0.12168306112289429, "learning_rate": 1.669378131548459e-05, "loss": 0.0147, "step": 3180 }, { "epoch": 0.14474587230373945, "grad_norm": 0.25270065665245056, "learning_rate": 1.6671915249187237e-05, "loss": 0.0134, "step": 3190 }, { "epoch": 0.14519962111973864, "grad_norm": 0.09988359361886978, "learning_rate": 1.6649991538497808e-05, "loss": 0.0165, "step": 3200 }, { "epoch": 0.14565336993573783, "grad_norm": 0.15102815628051758, "learning_rate": 1.6628010372834028e-05, "loss": 0.0176, "step": 3210 }, { "epoch": 0.14610711875173701, "grad_norm": 0.12083399295806885, "learning_rate": 1.660597194211001e-05, "loss": 0.016, "step": 3220 }, { "epoch": 0.1465608675677362, "grad_norm": 0.11156380921602249, "learning_rate": 1.6583876436734646e-05, "loss": 0.0157, "step": 3230 }, { "epoch": 0.14701461638373536, "grad_norm": 0.14670194685459137, "learning_rate": 1.6561724047609936e-05, "loss": 0.0151, "step": 3240 }, { "epoch": 0.14746836519973455, "grad_norm": 0.1251230537891388, "learning_rate": 1.653951496612935e-05, "loss": 0.0142, "step": 3250 }, { "epoch": 0.14792211401573374, "grad_norm": 0.1488153636455536, "learning_rate": 1.6517249384176163e-05, "loss": 0.0124, "step": 3260 }, { "epoch": 0.14837586283173293, "grad_norm": 0.13089244067668915, "learning_rate": 1.6494927494121827e-05, "loss": 0.0136, "step": 3270 }, { "epoch": 0.14882961164773212, "grad_norm": 0.10569626837968826, "learning_rate": 1.647254948882426e-05, "loss": 0.0144, "step": 3280 }, { "epoch": 0.14928336046373128, "grad_norm": 0.172092467546463, "learning_rate": 1.6450115561626237e-05, "loss": 0.0182, "step": 3290 }, { "epoch": 0.14973710927973047, "grad_norm": 0.11375053972005844, "learning_rate": 1.6427625906353667e-05, "loss": 0.015, "step": 3300 }, { "epoch": 0.15019085809572966, "grad_norm": 0.11546178162097931, "learning_rate": 1.640508071731395e-05, "loss": 0.0178, "step": 3310 }, { "epoch": 0.15064460691172885, "grad_norm": 0.12166525423526764, "learning_rate": 1.6382480189294293e-05, "loss": 0.0112, "step": 3320 }, { "epoch": 0.15109835572772803, "grad_norm": 0.18551099300384521, "learning_rate": 1.635982451756002e-05, "loss": 0.0161, "step": 3330 }, { "epoch": 0.1515521045437272, "grad_norm": 0.11153236776590347, "learning_rate": 1.6337113897852887e-05, "loss": 0.0132, "step": 3340 }, { "epoch": 0.15200585335972638, "grad_norm": 0.17926083505153656, "learning_rate": 1.6314348526389396e-05, "loss": 0.0137, "step": 3350 }, { "epoch": 0.15245960217572557, "grad_norm": 0.13617047667503357, "learning_rate": 1.6291528599859102e-05, "loss": 0.0139, "step": 3360 }, { "epoch": 0.15291335099172476, "grad_norm": 0.13956233859062195, "learning_rate": 1.6268654315422892e-05, "loss": 0.0167, "step": 3370 }, { "epoch": 0.15336709980772395, "grad_norm": 0.16784027218818665, "learning_rate": 1.6245725870711314e-05, "loss": 0.0147, "step": 3380 }, { "epoch": 0.1538208486237231, "grad_norm": 0.114019475877285, "learning_rate": 1.6222743463822842e-05, "loss": 0.0143, "step": 3390 }, { "epoch": 0.1542745974397223, "grad_norm": 0.09962613880634308, "learning_rate": 1.6199707293322183e-05, "loss": 0.0146, "step": 3400 }, { "epoch": 0.1547283462557215, "grad_norm": 0.1009678766131401, "learning_rate": 1.6176617558238548e-05, "loss": 0.0185, "step": 3410 }, { "epoch": 0.15518209507172068, "grad_norm": 0.1502830982208252, "learning_rate": 1.615347445806394e-05, "loss": 0.0176, "step": 3420 }, { "epoch": 0.15563584388771987, "grad_norm": 0.12032261490821838, "learning_rate": 1.613027819275143e-05, "loss": 0.0159, "step": 3430 }, { "epoch": 0.15608959270371903, "grad_norm": 0.0938112884759903, "learning_rate": 1.6107028962713433e-05, "loss": 0.0151, "step": 3440 }, { "epoch": 0.15654334151971822, "grad_norm": 0.12551243603229523, "learning_rate": 1.608372696881996e-05, "loss": 0.0152, "step": 3450 }, { "epoch": 0.1569970903357174, "grad_norm": 0.14302802085876465, "learning_rate": 1.60603724123969e-05, "loss": 0.014, "step": 3460 }, { "epoch": 0.1574508391517166, "grad_norm": 0.10727311670780182, "learning_rate": 1.603696549522428e-05, "loss": 0.0147, "step": 3470 }, { "epoch": 0.15790458796771578, "grad_norm": 0.12573154270648956, "learning_rate": 1.6013506419534505e-05, "loss": 0.0178, "step": 3480 }, { "epoch": 0.15835833678371494, "grad_norm": 0.1385488659143448, "learning_rate": 1.598999538801064e-05, "loss": 0.0136, "step": 3490 }, { "epoch": 0.15881208559971413, "grad_norm": 0.1109369620680809, "learning_rate": 1.5966432603784615e-05, "loss": 0.0127, "step": 3500 }, { "epoch": 0.15926583441571332, "grad_norm": 0.10793564468622208, "learning_rate": 1.594281827043552e-05, "loss": 0.0137, "step": 3510 }, { "epoch": 0.1597195832317125, "grad_norm": 0.2065846174955368, "learning_rate": 1.5919152591987814e-05, "loss": 0.0139, "step": 3520 }, { "epoch": 0.1601733320477117, "grad_norm": 0.1269092559814453, "learning_rate": 1.5895435772909564e-05, "loss": 0.014, "step": 3530 }, { "epoch": 0.16062708086371086, "grad_norm": 0.11606848984956741, "learning_rate": 1.5871668018110694e-05, "loss": 0.0179, "step": 3540 }, { "epoch": 0.16108082967971005, "grad_norm": 0.11414334177970886, "learning_rate": 1.5847849532941196e-05, "loss": 0.0148, "step": 3550 }, { "epoch": 0.16153457849570924, "grad_norm": 0.16407953202724457, "learning_rate": 1.5823980523189373e-05, "loss": 0.0121, "step": 3560 }, { "epoch": 0.16198832731170842, "grad_norm": 0.12298201024532318, "learning_rate": 1.580006119508005e-05, "loss": 0.0144, "step": 3570 }, { "epoch": 0.1624420761277076, "grad_norm": 0.21627740561962128, "learning_rate": 1.5776091755272792e-05, "loss": 0.0128, "step": 3580 }, { "epoch": 0.16289582494370677, "grad_norm": 0.1419907957315445, "learning_rate": 1.5752072410860132e-05, "loss": 0.0183, "step": 3590 }, { "epoch": 0.16334957375970596, "grad_norm": 0.12556162476539612, "learning_rate": 1.5728003369365763e-05, "loss": 0.0146, "step": 3600 }, { "epoch": 0.16380332257570515, "grad_norm": 0.14906148612499237, "learning_rate": 1.5703884838742755e-05, "loss": 0.0148, "step": 3610 }, { "epoch": 0.16425707139170434, "grad_norm": 0.1575646996498108, "learning_rate": 1.5679717027371756e-05, "loss": 0.0165, "step": 3620 }, { "epoch": 0.16471082020770353, "grad_norm": 0.1563308835029602, "learning_rate": 1.5655500144059202e-05, "loss": 0.0131, "step": 3630 }, { "epoch": 0.16516456902370272, "grad_norm": 0.11647270619869232, "learning_rate": 1.5631234398035483e-05, "loss": 0.0143, "step": 3640 }, { "epoch": 0.16561831783970188, "grad_norm": 0.12990880012512207, "learning_rate": 1.5606919998953182e-05, "loss": 0.0155, "step": 3650 }, { "epoch": 0.16607206665570107, "grad_norm": 0.16923795640468597, "learning_rate": 1.5582557156885218e-05, "loss": 0.0154, "step": 3660 }, { "epoch": 0.16652581547170026, "grad_norm": 0.11621172726154327, "learning_rate": 1.5558146082323056e-05, "loss": 0.0157, "step": 3670 }, { "epoch": 0.16697956428769944, "grad_norm": 0.15920764207839966, "learning_rate": 1.5533686986174885e-05, "loss": 0.0134, "step": 3680 }, { "epoch": 0.16743331310369863, "grad_norm": 0.10490966588258743, "learning_rate": 1.5509180079763794e-05, "loss": 0.0178, "step": 3690 }, { "epoch": 0.1678870619196978, "grad_norm": 0.10213067382574081, "learning_rate": 1.548462557482594e-05, "loss": 0.0148, "step": 3700 }, { "epoch": 0.16834081073569698, "grad_norm": 0.11328372359275818, "learning_rate": 1.546002368350873e-05, "loss": 0.0132, "step": 3710 }, { "epoch": 0.16879455955169617, "grad_norm": 0.1595434993505478, "learning_rate": 1.5435374618368987e-05, "loss": 0.0153, "step": 3720 }, { "epoch": 0.16924830836769536, "grad_norm": 0.18421152234077454, "learning_rate": 1.5410678592371097e-05, "loss": 0.0167, "step": 3730 }, { "epoch": 0.16970205718369455, "grad_norm": 0.11394022405147552, "learning_rate": 1.5385935818885185e-05, "loss": 0.0133, "step": 3740 }, { "epoch": 0.1701558059996937, "grad_norm": 0.09311575442552567, "learning_rate": 1.5361146511685275e-05, "loss": 0.0123, "step": 3750 }, { "epoch": 0.1706095548156929, "grad_norm": 0.08096790313720703, "learning_rate": 1.5336310884947424e-05, "loss": 0.0125, "step": 3760 }, { "epoch": 0.1710633036316921, "grad_norm": 0.15707452595233917, "learning_rate": 1.5311429153247898e-05, "loss": 0.0119, "step": 3770 }, { "epoch": 0.17151705244769128, "grad_norm": 0.12189309298992157, "learning_rate": 1.5286501531561292e-05, "loss": 0.0134, "step": 3780 }, { "epoch": 0.17197080126369046, "grad_norm": 0.15345165133476257, "learning_rate": 1.526152823525868e-05, "loss": 0.0147, "step": 3790 }, { "epoch": 0.17242455007968963, "grad_norm": 0.12922775745391846, "learning_rate": 1.5236509480105781e-05, "loss": 0.0164, "step": 3800 }, { "epoch": 0.17287829889568881, "grad_norm": 0.19504646956920624, "learning_rate": 1.5211445482261039e-05, "loss": 0.0181, "step": 3810 }, { "epoch": 0.173332047711688, "grad_norm": 0.1409461349248886, "learning_rate": 1.5186336458273809e-05, "loss": 0.0157, "step": 3820 }, { "epoch": 0.1737857965276872, "grad_norm": 0.1698140949010849, "learning_rate": 1.5161182625082469e-05, "loss": 0.0147, "step": 3830 }, { "epoch": 0.17423954534368638, "grad_norm": 0.1612328290939331, "learning_rate": 1.5135984200012526e-05, "loss": 0.0168, "step": 3840 }, { "epoch": 0.17469329415968554, "grad_norm": 0.10053840279579163, "learning_rate": 1.511074140077477e-05, "loss": 0.0138, "step": 3850 }, { "epoch": 0.17514704297568473, "grad_norm": 0.13965512812137604, "learning_rate": 1.5085454445463367e-05, "loss": 0.0159, "step": 3860 }, { "epoch": 0.17560079179168392, "grad_norm": 0.1308697760105133, "learning_rate": 1.506012355255399e-05, "loss": 0.0123, "step": 3870 }, { "epoch": 0.1760545406076831, "grad_norm": 0.15388274192810059, "learning_rate": 1.503474894090193e-05, "loss": 0.0132, "step": 3880 }, { "epoch": 0.1765082894236823, "grad_norm": 0.13517123460769653, "learning_rate": 1.5009330829740183e-05, "loss": 0.0126, "step": 3890 }, { "epoch": 0.17696203823968146, "grad_norm": 0.1223309189081192, "learning_rate": 1.4983869438677605e-05, "loss": 0.0148, "step": 3900 }, { "epoch": 0.17741578705568065, "grad_norm": 0.1638365089893341, "learning_rate": 1.4958364987696956e-05, "loss": 0.0117, "step": 3910 }, { "epoch": 0.17786953587167983, "grad_norm": 0.12717320024967194, "learning_rate": 1.4932817697153046e-05, "loss": 0.0129, "step": 3920 }, { "epoch": 0.17832328468767902, "grad_norm": 0.1357133835554123, "learning_rate": 1.4907227787770805e-05, "loss": 0.0159, "step": 3930 }, { "epoch": 0.1787770335036782, "grad_norm": 0.12038825452327728, "learning_rate": 1.4881595480643379e-05, "loss": 0.0147, "step": 3940 }, { "epoch": 0.17923078231967737, "grad_norm": 0.1027536392211914, "learning_rate": 1.4855920997230238e-05, "loss": 0.0141, "step": 3950 }, { "epoch": 0.17968453113567656, "grad_norm": 0.12810742855072021, "learning_rate": 1.4830204559355234e-05, "loss": 0.0147, "step": 3960 }, { "epoch": 0.18013827995167575, "grad_norm": 0.11282184720039368, "learning_rate": 1.4804446389204715e-05, "loss": 0.0132, "step": 3970 }, { "epoch": 0.18059202876767494, "grad_norm": 0.15203283727169037, "learning_rate": 1.4778646709325573e-05, "loss": 0.0142, "step": 3980 }, { "epoch": 0.18104577758367413, "grad_norm": 0.10177380591630936, "learning_rate": 1.4752805742623349e-05, "loss": 0.015, "step": 3990 }, { "epoch": 0.1814995263996733, "grad_norm": 0.42804914712905884, "learning_rate": 1.47269237123603e-05, "loss": 0.0166, "step": 4000 }, { "epoch": 0.18195327521567248, "grad_norm": 0.07249004393815994, "learning_rate": 1.470100084215345e-05, "loss": 0.0131, "step": 4010 }, { "epoch": 0.18240702403167167, "grad_norm": 0.5060725808143616, "learning_rate": 1.4675037355972693e-05, "loss": 0.0177, "step": 4020 }, { "epoch": 0.18286077284767085, "grad_norm": 0.1497131884098053, "learning_rate": 1.4649033478138825e-05, "loss": 0.0141, "step": 4030 }, { "epoch": 0.18331452166367004, "grad_norm": 0.11946047097444534, "learning_rate": 1.4622989433321627e-05, "loss": 0.0196, "step": 4040 }, { "epoch": 0.1837682704796692, "grad_norm": 0.149189293384552, "learning_rate": 1.459690544653792e-05, "loss": 0.0162, "step": 4050 }, { "epoch": 0.1842220192956684, "grad_norm": 0.13301686942577362, "learning_rate": 1.457078174314961e-05, "loss": 0.0139, "step": 4060 }, { "epoch": 0.18467576811166758, "grad_norm": 0.11232901364564896, "learning_rate": 1.4544618548861753e-05, "loss": 0.014, "step": 4070 }, { "epoch": 0.18512951692766677, "grad_norm": 0.10592498630285263, "learning_rate": 1.45184160897206e-05, "loss": 0.0118, "step": 4080 }, { "epoch": 0.18558326574366596, "grad_norm": 0.12410669773817062, "learning_rate": 1.4492174592111642e-05, "loss": 0.0164, "step": 4090 }, { "epoch": 0.18603701455966512, "grad_norm": 0.1423037350177765, "learning_rate": 1.4465894282757662e-05, "loss": 0.0141, "step": 4100 }, { "epoch": 0.1864907633756643, "grad_norm": 0.12676963210105896, "learning_rate": 1.4439575388716768e-05, "loss": 0.0142, "step": 4110 }, { "epoch": 0.1869445121916635, "grad_norm": 0.14317011833190918, "learning_rate": 1.441321813738044e-05, "loss": 0.0137, "step": 4120 }, { "epoch": 0.1873982610076627, "grad_norm": 0.14456255733966827, "learning_rate": 1.4386822756471545e-05, "loss": 0.0153, "step": 4130 }, { "epoch": 0.18785200982366188, "grad_norm": 0.0736534371972084, "learning_rate": 1.43603894740424e-05, "loss": 0.0138, "step": 4140 }, { "epoch": 0.18830575863966104, "grad_norm": 0.13916346430778503, "learning_rate": 1.4333918518472773e-05, "loss": 0.0147, "step": 4150 }, { "epoch": 0.18875950745566022, "grad_norm": 0.10532277077436447, "learning_rate": 1.4307410118467932e-05, "loss": 0.0115, "step": 4160 }, { "epoch": 0.1892132562716594, "grad_norm": 0.07763885706663132, "learning_rate": 1.428086450305666e-05, "loss": 0.0138, "step": 4170 }, { "epoch": 0.1896670050876586, "grad_norm": 0.15108561515808105, "learning_rate": 1.4254281901589263e-05, "loss": 0.0137, "step": 4180 }, { "epoch": 0.1901207539036578, "grad_norm": 0.10432786494493484, "learning_rate": 1.4227662543735618e-05, "loss": 0.0137, "step": 4190 }, { "epoch": 0.19057450271965698, "grad_norm": 0.12716031074523926, "learning_rate": 1.4201006659483156e-05, "loss": 0.0133, "step": 4200 }, { "epoch": 0.19102825153565614, "grad_norm": 0.16272354125976562, "learning_rate": 1.4174314479134909e-05, "loss": 0.0127, "step": 4210 }, { "epoch": 0.19148200035165533, "grad_norm": 0.15649910271167755, "learning_rate": 1.4147586233307485e-05, "loss": 0.0152, "step": 4220 }, { "epoch": 0.19193574916765452, "grad_norm": 0.13929864764213562, "learning_rate": 1.4120822152929099e-05, "loss": 0.0139, "step": 4230 }, { "epoch": 0.1923894979836537, "grad_norm": 0.14396138489246368, "learning_rate": 1.4094022469237577e-05, "loss": 0.0153, "step": 4240 }, { "epoch": 0.1928432467996529, "grad_norm": 0.08763469755649567, "learning_rate": 1.4067187413778338e-05, "loss": 0.0113, "step": 4250 }, { "epoch": 0.19329699561565206, "grad_norm": 0.1224103793501854, "learning_rate": 1.4040317218402426e-05, "loss": 0.0128, "step": 4260 }, { "epoch": 0.19375074443165125, "grad_norm": 0.13453181087970734, "learning_rate": 1.4013412115264477e-05, "loss": 0.0162, "step": 4270 }, { "epoch": 0.19420449324765043, "grad_norm": 0.12611383199691772, "learning_rate": 1.398647233682073e-05, "loss": 0.014, "step": 4280 }, { "epoch": 0.19465824206364962, "grad_norm": 0.11181385815143585, "learning_rate": 1.3959498115827007e-05, "loss": 0.0111, "step": 4290 }, { "epoch": 0.1951119908796488, "grad_norm": 0.11242038756608963, "learning_rate": 1.3932489685336722e-05, "loss": 0.0138, "step": 4300 }, { "epoch": 0.19556573969564797, "grad_norm": 0.13714377582073212, "learning_rate": 1.3905447278698838e-05, "loss": 0.0138, "step": 4310 }, { "epoch": 0.19601948851164716, "grad_norm": 0.16913384199142456, "learning_rate": 1.3878371129555874e-05, "loss": 0.0122, "step": 4320 }, { "epoch": 0.19647323732764635, "grad_norm": 0.10871516913175583, "learning_rate": 1.3851261471841891e-05, "loss": 0.0126, "step": 4330 }, { "epoch": 0.19692698614364554, "grad_norm": 0.11557555198669434, "learning_rate": 1.382411853978044e-05, "loss": 0.0122, "step": 4340 }, { "epoch": 0.19738073495964473, "grad_norm": 0.1095661148428917, "learning_rate": 1.3796942567882565e-05, "loss": 0.0117, "step": 4350 }, { "epoch": 0.1978344837756439, "grad_norm": 0.1236121654510498, "learning_rate": 1.3769733790944777e-05, "loss": 0.0129, "step": 4360 }, { "epoch": 0.19828823259164308, "grad_norm": 0.11015874892473221, "learning_rate": 1.3742492444047e-05, "loss": 0.0129, "step": 4370 }, { "epoch": 0.19874198140764227, "grad_norm": 0.15501569211483002, "learning_rate": 1.3715218762550584e-05, "loss": 0.0122, "step": 4380 }, { "epoch": 0.19919573022364145, "grad_norm": 0.11920386552810669, "learning_rate": 1.368791298209622e-05, "loss": 0.0135, "step": 4390 }, { "epoch": 0.19964947903964064, "grad_norm": 0.13255856931209564, "learning_rate": 1.3660575338601945e-05, "loss": 0.0119, "step": 4400 }, { "epoch": 0.2001032278556398, "grad_norm": 0.1280907243490219, "learning_rate": 1.363320606826108e-05, "loss": 0.0134, "step": 4410 }, { "epoch": 0.200556976671639, "grad_norm": 0.09508081525564194, "learning_rate": 1.36058054075402e-05, "loss": 0.012, "step": 4420 }, { "epoch": 0.20101072548763818, "grad_norm": 0.12136292457580566, "learning_rate": 1.3578373593177091e-05, "loss": 0.011, "step": 4430 }, { "epoch": 0.20146447430363737, "grad_norm": 0.1445646733045578, "learning_rate": 1.35509108621787e-05, "loss": 0.0139, "step": 4440 }, { "epoch": 0.20191822311963656, "grad_norm": 0.1297726035118103, "learning_rate": 1.3523417451819087e-05, "loss": 0.0131, "step": 4450 }, { "epoch": 0.20237197193563572, "grad_norm": 0.16649243235588074, "learning_rate": 1.3495893599637385e-05, "loss": 0.0129, "step": 4460 }, { "epoch": 0.2028257207516349, "grad_norm": 0.11745346337556839, "learning_rate": 1.3468339543435725e-05, "loss": 0.0134, "step": 4470 }, { "epoch": 0.2032794695676341, "grad_norm": 0.11485689133405685, "learning_rate": 1.3440755521277209e-05, "loss": 0.0145, "step": 4480 }, { "epoch": 0.20373321838363329, "grad_norm": 0.1094205230474472, "learning_rate": 1.3413141771483842e-05, "loss": 0.0129, "step": 4490 }, { "epoch": 0.20418696719963247, "grad_norm": 0.12220988422632217, "learning_rate": 1.3385498532634465e-05, "loss": 0.0134, "step": 4500 }, { "epoch": 0.20464071601563164, "grad_norm": 0.12510019540786743, "learning_rate": 1.3357826043562698e-05, "loss": 0.0152, "step": 4510 }, { "epoch": 0.20509446483163082, "grad_norm": 0.08057999610900879, "learning_rate": 1.3330124543354888e-05, "loss": 0.0138, "step": 4520 }, { "epoch": 0.20554821364763, "grad_norm": 0.15725575387477875, "learning_rate": 1.3302394271348026e-05, "loss": 0.0148, "step": 4530 }, { "epoch": 0.2060019624636292, "grad_norm": 0.4353750944137573, "learning_rate": 1.3274635467127688e-05, "loss": 0.0115, "step": 4540 }, { "epoch": 0.2064557112796284, "grad_norm": 0.09682906419038773, "learning_rate": 1.3246848370525973e-05, "loss": 0.0139, "step": 4550 }, { "epoch": 0.20690946009562755, "grad_norm": 0.09269677847623825, "learning_rate": 1.3219033221619408e-05, "loss": 0.0127, "step": 4560 }, { "epoch": 0.20736320891162674, "grad_norm": 0.12921477854251862, "learning_rate": 1.3191190260726903e-05, "loss": 0.0126, "step": 4570 }, { "epoch": 0.20781695772762593, "grad_norm": 0.1492907702922821, "learning_rate": 1.3163319728407645e-05, "loss": 0.0137, "step": 4580 }, { "epoch": 0.20827070654362512, "grad_norm": 0.20090225338935852, "learning_rate": 1.3135421865459042e-05, "loss": 0.0159, "step": 4590 }, { "epoch": 0.2087244553596243, "grad_norm": 0.09534034132957458, "learning_rate": 1.3107496912914636e-05, "loss": 0.0109, "step": 4600 }, { "epoch": 0.20917820417562347, "grad_norm": 0.09393394738435745, "learning_rate": 1.307954511204202e-05, "loss": 0.0147, "step": 4610 }, { "epoch": 0.20963195299162266, "grad_norm": 0.10880058258771896, "learning_rate": 1.3051566704340746e-05, "loss": 0.0121, "step": 4620 }, { "epoch": 0.21008570180762184, "grad_norm": 0.10969436913728714, "learning_rate": 1.3023561931540247e-05, "loss": 0.0127, "step": 4630 }, { "epoch": 0.21053945062362103, "grad_norm": 0.10579615086317062, "learning_rate": 1.2995531035597753e-05, "loss": 0.012, "step": 4640 }, { "epoch": 0.21099319943962022, "grad_norm": 0.14967896044254303, "learning_rate": 1.2967474258696186e-05, "loss": 0.012, "step": 4650 }, { "epoch": 0.21144694825561938, "grad_norm": 0.10502340644598007, "learning_rate": 1.2939391843242082e-05, "loss": 0.0158, "step": 4660 }, { "epoch": 0.21190069707161857, "grad_norm": 0.07245222479104996, "learning_rate": 1.291128403186349e-05, "loss": 0.0107, "step": 4670 }, { "epoch": 0.21235444588761776, "grad_norm": 0.1306321620941162, "learning_rate": 1.2883151067407866e-05, "loss": 0.0127, "step": 4680 }, { "epoch": 0.21280819470361695, "grad_norm": 0.08145710080862045, "learning_rate": 1.2854993192940005e-05, "loss": 0.0133, "step": 4690 }, { "epoch": 0.21326194351961614, "grad_norm": 0.10710037499666214, "learning_rate": 1.2826810651739899e-05, "loss": 0.0153, "step": 4700 }, { "epoch": 0.2137156923356153, "grad_norm": 0.08956768363714218, "learning_rate": 1.279860368730067e-05, "loss": 0.0132, "step": 4710 }, { "epoch": 0.2141694411516145, "grad_norm": 0.09983127564191818, "learning_rate": 1.2770372543326454e-05, "loss": 0.0159, "step": 4720 }, { "epoch": 0.21462318996761368, "grad_norm": 0.09682271629571915, "learning_rate": 1.2742117463730289e-05, "loss": 0.0098, "step": 4730 }, { "epoch": 0.21507693878361286, "grad_norm": 0.1017518863081932, "learning_rate": 1.2713838692632015e-05, "loss": 0.0144, "step": 4740 }, { "epoch": 0.21553068759961205, "grad_norm": 0.10464289039373398, "learning_rate": 1.2685536474356161e-05, "loss": 0.0144, "step": 4750 }, { "epoch": 0.21598443641561124, "grad_norm": 0.10350547730922699, "learning_rate": 1.2657211053429844e-05, "loss": 0.0128, "step": 4760 }, { "epoch": 0.2164381852316104, "grad_norm": 0.12434636801481247, "learning_rate": 1.2628862674580642e-05, "loss": 0.0135, "step": 4770 }, { "epoch": 0.2168919340476096, "grad_norm": 0.1342182159423828, "learning_rate": 1.2600491582734484e-05, "loss": 0.0139, "step": 4780 }, { "epoch": 0.21734568286360878, "grad_norm": 0.12550152838230133, "learning_rate": 1.2572098023013544e-05, "loss": 0.015, "step": 4790 }, { "epoch": 0.21779943167960797, "grad_norm": 0.1396545171737671, "learning_rate": 1.254368224073411e-05, "loss": 0.0137, "step": 4800 }, { "epoch": 0.21825318049560716, "grad_norm": 0.1077975407242775, "learning_rate": 1.251524448140447e-05, "loss": 0.0157, "step": 4810 }, { "epoch": 0.21870692931160632, "grad_norm": 0.13596457242965698, "learning_rate": 1.2486784990722791e-05, "loss": 0.0156, "step": 4820 }, { "epoch": 0.2191606781276055, "grad_norm": 0.07514549791812897, "learning_rate": 1.2458304014574996e-05, "loss": 0.0122, "step": 4830 }, { "epoch": 0.2196144269436047, "grad_norm": 0.15136843919754028, "learning_rate": 1.242980179903264e-05, "loss": 0.0155, "step": 4840 }, { "epoch": 0.22006817575960388, "grad_norm": 0.11219659447669983, "learning_rate": 1.2401278590350782e-05, "loss": 0.0154, "step": 4850 }, { "epoch": 0.22052192457560307, "grad_norm": 0.10784641653299332, "learning_rate": 1.2372734634965861e-05, "loss": 0.0142, "step": 4860 }, { "epoch": 0.22097567339160223, "grad_norm": 0.12322937697172165, "learning_rate": 1.234417017949356e-05, "loss": 0.0133, "step": 4870 }, { "epoch": 0.22142942220760142, "grad_norm": 0.12015904486179352, "learning_rate": 1.2315585470726685e-05, "loss": 0.0151, "step": 4880 }, { "epoch": 0.2218831710236006, "grad_norm": 0.12124694138765335, "learning_rate": 1.2286980755633027e-05, "loss": 0.0133, "step": 4890 }, { "epoch": 0.2223369198395998, "grad_norm": 0.13471055030822754, "learning_rate": 1.225835628135322e-05, "loss": 0.013, "step": 4900 }, { "epoch": 0.222790668655599, "grad_norm": 0.13785183429718018, "learning_rate": 1.2229712295198633e-05, "loss": 0.0131, "step": 4910 }, { "epoch": 0.22324441747159815, "grad_norm": 0.13422000408172607, "learning_rate": 1.2201049044649192e-05, "loss": 0.0151, "step": 4920 }, { "epoch": 0.22369816628759734, "grad_norm": 0.1454576998949051, "learning_rate": 1.217236677735128e-05, "loss": 0.0116, "step": 4930 }, { "epoch": 0.22415191510359653, "grad_norm": 0.08958277851343155, "learning_rate": 1.2143665741115581e-05, "loss": 0.0108, "step": 4940 }, { "epoch": 0.22460566391959572, "grad_norm": 0.10231640189886093, "learning_rate": 1.2114946183914935e-05, "loss": 0.0114, "step": 4950 }, { "epoch": 0.2250594127355949, "grad_norm": 0.16529706120491028, "learning_rate": 1.2086208353882203e-05, "loss": 0.0156, "step": 4960 }, { "epoch": 0.22551316155159407, "grad_norm": 0.11818477511405945, "learning_rate": 1.2057452499308117e-05, "loss": 0.0144, "step": 4970 }, { "epoch": 0.22596691036759325, "grad_norm": 0.1120464950799942, "learning_rate": 1.2028678868639147e-05, "loss": 0.0119, "step": 4980 }, { "epoch": 0.22642065918359244, "grad_norm": 0.11998723447322845, "learning_rate": 1.1999887710475337e-05, "loss": 0.013, "step": 4990 }, { "epoch": 0.22687440799959163, "grad_norm": 0.1197367012500763, "learning_rate": 1.197107927356817e-05, "loss": 0.0119, "step": 5000 }, { "epoch": 0.22732815681559082, "grad_norm": 0.13285987079143524, "learning_rate": 1.1942253806818414e-05, "loss": 0.0142, "step": 5010 }, { "epoch": 0.22778190563158998, "grad_norm": 0.13335882127285004, "learning_rate": 1.1913411559273973e-05, "loss": 0.0113, "step": 5020 }, { "epoch": 0.22823565444758917, "grad_norm": 0.2546532452106476, "learning_rate": 1.1884552780127736e-05, "loss": 0.0137, "step": 5030 }, { "epoch": 0.22868940326358836, "grad_norm": 0.1003192663192749, "learning_rate": 1.1855677718715417e-05, "loss": 0.0116, "step": 5040 }, { "epoch": 0.22914315207958755, "grad_norm": 0.09578375518321991, "learning_rate": 1.1826786624513416e-05, "loss": 0.0143, "step": 5050 }, { "epoch": 0.22959690089558674, "grad_norm": 0.15513285994529724, "learning_rate": 1.1797879747136645e-05, "loss": 0.0108, "step": 5060 }, { "epoch": 0.2300506497115859, "grad_norm": 0.12582165002822876, "learning_rate": 1.1768957336336384e-05, "loss": 0.0111, "step": 5070 }, { "epoch": 0.23050439852758509, "grad_norm": 0.09985069930553436, "learning_rate": 1.1740019641998124e-05, "loss": 0.0135, "step": 5080 }, { "epoch": 0.23095814734358427, "grad_norm": 0.1115417554974556, "learning_rate": 1.171106691413939e-05, "loss": 0.0122, "step": 5090 }, { "epoch": 0.23141189615958346, "grad_norm": 0.0902300626039505, "learning_rate": 1.1682099402907612e-05, "loss": 0.0137, "step": 5100 }, { "epoch": 0.23186564497558265, "grad_norm": 0.13599762320518494, "learning_rate": 1.1653117358577937e-05, "loss": 0.0125, "step": 5110 }, { "epoch": 0.2323193937915818, "grad_norm": 0.14796219766139984, "learning_rate": 1.1624121031551073e-05, "loss": 0.0132, "step": 5120 }, { "epoch": 0.232773142607581, "grad_norm": 0.11207287758588791, "learning_rate": 1.1595110672351132e-05, "loss": 0.0088, "step": 5130 }, { "epoch": 0.2332268914235802, "grad_norm": 0.14406666159629822, "learning_rate": 1.1566086531623464e-05, "loss": 0.0136, "step": 5140 }, { "epoch": 0.23368064023957938, "grad_norm": 0.13029412925243378, "learning_rate": 1.1537048860132487e-05, "loss": 0.0126, "step": 5150 }, { "epoch": 0.23413438905557857, "grad_norm": 0.10569052398204803, "learning_rate": 1.1507997908759525e-05, "loss": 0.0129, "step": 5160 }, { "epoch": 0.23458813787157773, "grad_norm": 0.09842711687088013, "learning_rate": 1.1478933928500635e-05, "loss": 0.0109, "step": 5170 }, { "epoch": 0.23504188668757692, "grad_norm": 0.14181552827358246, "learning_rate": 1.1449857170464445e-05, "loss": 0.0119, "step": 5180 }, { "epoch": 0.2354956355035761, "grad_norm": 0.15493468940258026, "learning_rate": 1.1420767885869974e-05, "loss": 0.0153, "step": 5190 }, { "epoch": 0.2359493843195753, "grad_norm": 0.08616474270820618, "learning_rate": 1.1391666326044484e-05, "loss": 0.0114, "step": 5200 }, { "epoch": 0.23640313313557448, "grad_norm": 0.10491077601909637, "learning_rate": 1.1362552742421269e-05, "loss": 0.0136, "step": 5210 }, { "epoch": 0.23685688195157364, "grad_norm": 0.1455802321434021, "learning_rate": 1.1333427386537537e-05, "loss": 0.0139, "step": 5220 }, { "epoch": 0.23731063076757283, "grad_norm": 0.12788164615631104, "learning_rate": 1.1304290510032184e-05, "loss": 0.0112, "step": 5230 }, { "epoch": 0.23776437958357202, "grad_norm": 0.17252400517463684, "learning_rate": 1.1275142364643645e-05, "loss": 0.0115, "step": 5240 }, { "epoch": 0.2382181283995712, "grad_norm": 0.1328468769788742, "learning_rate": 1.1245983202207729e-05, "loss": 0.013, "step": 5250 }, { "epoch": 0.2386718772155704, "grad_norm": 0.09754417091608047, "learning_rate": 1.1216813274655417e-05, "loss": 0.0099, "step": 5260 }, { "epoch": 0.23912562603156956, "grad_norm": 0.1304081678390503, "learning_rate": 1.1187632834010707e-05, "loss": 0.0104, "step": 5270 }, { "epoch": 0.23957937484756875, "grad_norm": 0.10372321307659149, "learning_rate": 1.1158442132388427e-05, "loss": 0.012, "step": 5280 }, { "epoch": 0.24003312366356794, "grad_norm": 0.20873187482357025, "learning_rate": 1.1129241421992059e-05, "loss": 0.0142, "step": 5290 }, { "epoch": 0.24048687247956713, "grad_norm": 0.1094968393445015, "learning_rate": 1.1100030955111554e-05, "loss": 0.0106, "step": 5300 }, { "epoch": 0.24094062129556632, "grad_norm": 0.1218864843249321, "learning_rate": 1.1070810984121164e-05, "loss": 0.012, "step": 5310 }, { "epoch": 0.2413943701115655, "grad_norm": 0.1277485489845276, "learning_rate": 1.1041581761477252e-05, "loss": 0.0153, "step": 5320 }, { "epoch": 0.24184811892756466, "grad_norm": 0.1440143883228302, "learning_rate": 1.1012343539716115e-05, "loss": 0.0161, "step": 5330 }, { "epoch": 0.24230186774356385, "grad_norm": 0.13456301391124725, "learning_rate": 1.0983096571451805e-05, "loss": 0.0136, "step": 5340 }, { "epoch": 0.24275561655956304, "grad_norm": 0.1500135064125061, "learning_rate": 1.0953841109373935e-05, "loss": 0.0147, "step": 5350 }, { "epoch": 0.24320936537556223, "grad_norm": 0.08728645741939545, "learning_rate": 1.0924577406245507e-05, "loss": 0.0103, "step": 5360 }, { "epoch": 0.24366311419156142, "grad_norm": 0.07684322446584702, "learning_rate": 1.0895305714900721e-05, "loss": 0.0096, "step": 5370 }, { "epoch": 0.24411686300756058, "grad_norm": 0.09726769477128983, "learning_rate": 1.0866026288242803e-05, "loss": 0.0107, "step": 5380 }, { "epoch": 0.24457061182355977, "grad_norm": 0.16744130849838257, "learning_rate": 1.0836739379241805e-05, "loss": 0.0134, "step": 5390 }, { "epoch": 0.24502436063955896, "grad_norm": 0.1598443239927292, "learning_rate": 1.0807445240932422e-05, "loss": 0.0169, "step": 5400 }, { "epoch": 0.24547810945555815, "grad_norm": 0.09486149996519089, "learning_rate": 1.0778144126411815e-05, "loss": 0.0106, "step": 5410 }, { "epoch": 0.24593185827155734, "grad_norm": 0.12555833160877228, "learning_rate": 1.0748836288837418e-05, "loss": 0.0133, "step": 5420 }, { "epoch": 0.2463856070875565, "grad_norm": 0.10856787860393524, "learning_rate": 1.0719521981424745e-05, "loss": 0.0122, "step": 5430 }, { "epoch": 0.24683935590355569, "grad_norm": 0.15390191972255707, "learning_rate": 1.0690201457445218e-05, "loss": 0.0108, "step": 5440 }, { "epoch": 0.24729310471955487, "grad_norm": 0.10890336334705353, "learning_rate": 1.0660874970223963e-05, "loss": 0.0124, "step": 5450 }, { "epoch": 0.24774685353555406, "grad_norm": 0.11292314529418945, "learning_rate": 1.0631542773137627e-05, "loss": 0.0099, "step": 5460 }, { "epoch": 0.24820060235155325, "grad_norm": 0.1451224535703659, "learning_rate": 1.060220511961219e-05, "loss": 0.0113, "step": 5470 }, { "epoch": 0.2486543511675524, "grad_norm": 0.10389512777328491, "learning_rate": 1.0572862263120784e-05, "loss": 0.0123, "step": 5480 }, { "epoch": 0.2491080999835516, "grad_norm": 0.05811413750052452, "learning_rate": 1.0543514457181476e-05, "loss": 0.0118, "step": 5490 }, { "epoch": 0.2495618487995508, "grad_norm": 0.07917970418930054, "learning_rate": 1.051416195535511e-05, "loss": 0.012, "step": 5500 }, { "epoch": 0.25001559761555, "grad_norm": 0.07790730893611908, "learning_rate": 1.0484805011243102e-05, "loss": 0.0107, "step": 5510 }, { "epoch": 0.25046934643154917, "grad_norm": 0.14826864004135132, "learning_rate": 1.0455443878485238e-05, "loss": 0.0117, "step": 5520 }, { "epoch": 0.25092309524754836, "grad_norm": 0.11600346863269806, "learning_rate": 1.0426078810757502e-05, "loss": 0.0123, "step": 5530 }, { "epoch": 0.25137684406354754, "grad_norm": 0.11259524524211884, "learning_rate": 1.039671006176987e-05, "loss": 0.012, "step": 5540 }, { "epoch": 0.2518305928795467, "grad_norm": 0.12264496088027954, "learning_rate": 1.0367337885264128e-05, "loss": 0.0122, "step": 5550 }, { "epoch": 0.25228434169554587, "grad_norm": 0.11145228892564774, "learning_rate": 1.0337962535011679e-05, "loss": 0.0113, "step": 5560 }, { "epoch": 0.25273809051154505, "grad_norm": 0.05592544004321098, "learning_rate": 1.0308584264811332e-05, "loss": 0.0099, "step": 5570 }, { "epoch": 0.25319183932754424, "grad_norm": 0.08989985287189484, "learning_rate": 1.0279203328487142e-05, "loss": 0.0094, "step": 5580 }, { "epoch": 0.25364558814354343, "grad_norm": 0.07590541988611221, "learning_rate": 1.0249819979886184e-05, "loss": 0.0093, "step": 5590 }, { "epoch": 0.2540993369595426, "grad_norm": 0.08524557948112488, "learning_rate": 1.0220434472876384e-05, "loss": 0.0077, "step": 5600 }, { "epoch": 0.2545530857755418, "grad_norm": 0.09717737883329391, "learning_rate": 1.0191047061344315e-05, "loss": 0.0112, "step": 5610 }, { "epoch": 0.255006834591541, "grad_norm": 0.08177042007446289, "learning_rate": 1.0161657999192998e-05, "loss": 0.0112, "step": 5620 }, { "epoch": 0.2554605834075402, "grad_norm": 0.08801747113466263, "learning_rate": 1.0132267540339726e-05, "loss": 0.0094, "step": 5630 }, { "epoch": 0.2559143322235394, "grad_norm": 0.10516278445720673, "learning_rate": 1.010287593871385e-05, "loss": 0.0107, "step": 5640 }, { "epoch": 0.25636808103953856, "grad_norm": 0.09306921809911728, "learning_rate": 1.0073483448254599e-05, "loss": 0.0108, "step": 5650 }, { "epoch": 0.2568218298555377, "grad_norm": 0.13333863019943237, "learning_rate": 1.0044090322908884e-05, "loss": 0.0096, "step": 5660 }, { "epoch": 0.2572755786715369, "grad_norm": 0.11567696183919907, "learning_rate": 1.0014696816629093e-05, "loss": 0.0115, "step": 5670 }, { "epoch": 0.2577293274875361, "grad_norm": 0.1339040994644165, "learning_rate": 9.985303183370909e-06, "loss": 0.0138, "step": 5680 }, { "epoch": 0.25818307630353526, "grad_norm": 0.0859203189611435, "learning_rate": 9.95590967709112e-06, "loss": 0.0104, "step": 5690 }, { "epoch": 0.25863682511953445, "grad_norm": 0.12810003757476807, "learning_rate": 9.926516551745401e-06, "loss": 0.0104, "step": 5700 }, { "epoch": 0.25909057393553364, "grad_norm": 0.09984268993139267, "learning_rate": 9.897124061286152e-06, "loss": 0.009, "step": 5710 }, { "epoch": 0.25954432275153283, "grad_norm": 0.11395058035850525, "learning_rate": 9.867732459660277e-06, "loss": 0.01, "step": 5720 }, { "epoch": 0.259998071567532, "grad_norm": 0.13486523926258087, "learning_rate": 9.838342000807006e-06, "loss": 0.0119, "step": 5730 }, { "epoch": 0.2604518203835312, "grad_norm": 0.13149206340312958, "learning_rate": 9.808952938655689e-06, "loss": 0.0132, "step": 5740 }, { "epoch": 0.2609055691995304, "grad_norm": 0.14824911952018738, "learning_rate": 9.77956552712362e-06, "loss": 0.0139, "step": 5750 }, { "epoch": 0.26135931801552953, "grad_norm": 0.08595529198646545, "learning_rate": 9.75018002011382e-06, "loss": 0.0086, "step": 5760 }, { "epoch": 0.2618130668315287, "grad_norm": 0.19259941577911377, "learning_rate": 9.720796671512863e-06, "loss": 0.0125, "step": 5770 }, { "epoch": 0.2622668156475279, "grad_norm": 0.09172676503658295, "learning_rate": 9.69141573518867e-06, "loss": 0.0116, "step": 5780 }, { "epoch": 0.2627205644635271, "grad_norm": 0.0886547639966011, "learning_rate": 9.662037464988323e-06, "loss": 0.0105, "step": 5790 }, { "epoch": 0.2631743132795263, "grad_norm": 0.09387862682342529, "learning_rate": 9.63266211473587e-06, "loss": 0.0113, "step": 5800 }, { "epoch": 0.2636280620955255, "grad_norm": 0.1309051811695099, "learning_rate": 9.603289938230132e-06, "loss": 0.0114, "step": 5810 }, { "epoch": 0.26408181091152466, "grad_norm": 0.1166449636220932, "learning_rate": 9.573921189242501e-06, "loss": 0.0116, "step": 5820 }, { "epoch": 0.26453555972752385, "grad_norm": 0.2173297256231308, "learning_rate": 9.544556121514765e-06, "loss": 0.0124, "step": 5830 }, { "epoch": 0.26498930854352304, "grad_norm": 0.1184614896774292, "learning_rate": 9.5151949887569e-06, "loss": 0.012, "step": 5840 }, { "epoch": 0.2654430573595222, "grad_norm": 0.11791530251502991, "learning_rate": 9.485838044644891e-06, "loss": 0.0115, "step": 5850 }, { "epoch": 0.26589680617552136, "grad_norm": 0.10721667110919952, "learning_rate": 9.456485542818527e-06, "loss": 0.013, "step": 5860 }, { "epoch": 0.26635055499152055, "grad_norm": 0.12556636333465576, "learning_rate": 9.427137736879222e-06, "loss": 0.0099, "step": 5870 }, { "epoch": 0.26680430380751974, "grad_norm": 0.11269138753414154, "learning_rate": 9.397794880387812e-06, "loss": 0.0119, "step": 5880 }, { "epoch": 0.2672580526235189, "grad_norm": 0.10264328122138977, "learning_rate": 9.368457226862378e-06, "loss": 0.0105, "step": 5890 }, { "epoch": 0.2677118014395181, "grad_norm": 0.12940654158592224, "learning_rate": 9.339125029776039e-06, "loss": 0.0136, "step": 5900 }, { "epoch": 0.2681655502555173, "grad_norm": 0.13572752475738525, "learning_rate": 9.309798542554782e-06, "loss": 0.01, "step": 5910 }, { "epoch": 0.2686192990715165, "grad_norm": 0.137733593583107, "learning_rate": 9.280478018575257e-06, "loss": 0.0109, "step": 5920 }, { "epoch": 0.2690730478875157, "grad_norm": 0.1549292504787445, "learning_rate": 9.251163711162584e-06, "loss": 0.0114, "step": 5930 }, { "epoch": 0.26952679670351487, "grad_norm": 0.09104438126087189, "learning_rate": 9.221855873588187e-06, "loss": 0.0112, "step": 5940 }, { "epoch": 0.26998054551951406, "grad_norm": 0.11055117845535278, "learning_rate": 9.192554759067581e-06, "loss": 0.0134, "step": 5950 }, { "epoch": 0.2704342943355132, "grad_norm": 0.08758547902107239, "learning_rate": 9.163260620758197e-06, "loss": 0.0085, "step": 5960 }, { "epoch": 0.2708880431515124, "grad_norm": 0.0683690756559372, "learning_rate": 9.133973711757198e-06, "loss": 0.0105, "step": 5970 }, { "epoch": 0.27134179196751157, "grad_norm": 0.1375247836112976, "learning_rate": 9.10469428509928e-06, "loss": 0.012, "step": 5980 }, { "epoch": 0.27179554078351076, "grad_norm": 0.10550401359796524, "learning_rate": 9.075422593754498e-06, "loss": 0.01, "step": 5990 }, { "epoch": 0.27224928959950995, "grad_norm": 0.1643981784582138, "learning_rate": 9.046158890626069e-06, "loss": 0.0144, "step": 6000 }, { "epoch": 0.27270303841550914, "grad_norm": 0.1455339938402176, "learning_rate": 9.016903428548195e-06, "loss": 0.0123, "step": 6010 }, { "epoch": 0.2731567872315083, "grad_norm": 0.145781472325325, "learning_rate": 8.987656460283885e-06, "loss": 0.0105, "step": 6020 }, { "epoch": 0.2736105360475075, "grad_norm": 0.11122782528400421, "learning_rate": 8.958418238522748e-06, "loss": 0.0129, "step": 6030 }, { "epoch": 0.2740642848635067, "grad_norm": 0.1163267269730568, "learning_rate": 8.929189015878838e-06, "loss": 0.0113, "step": 6040 }, { "epoch": 0.2745180336795059, "grad_norm": 0.19611865282058716, "learning_rate": 8.899969044888448e-06, "loss": 0.0107, "step": 6050 }, { "epoch": 0.274971782495505, "grad_norm": 0.13644863665103912, "learning_rate": 8.870758578007944e-06, "loss": 0.0109, "step": 6060 }, { "epoch": 0.2754255313115042, "grad_norm": 0.12602873146533966, "learning_rate": 8.841557867611576e-06, "loss": 0.0119, "step": 6070 }, { "epoch": 0.2758792801275034, "grad_norm": 0.13512378931045532, "learning_rate": 8.812367165989295e-06, "loss": 0.0114, "step": 6080 }, { "epoch": 0.2763330289435026, "grad_norm": 0.09388775378465652, "learning_rate": 8.783186725344588e-06, "loss": 0.0106, "step": 6090 }, { "epoch": 0.2767867777595018, "grad_norm": 0.12592685222625732, "learning_rate": 8.754016797792276e-06, "loss": 0.0129, "step": 6100 }, { "epoch": 0.27724052657550097, "grad_norm": 0.0980309247970581, "learning_rate": 8.72485763535636e-06, "loss": 0.0104, "step": 6110 }, { "epoch": 0.27769427539150016, "grad_norm": 0.11767059564590454, "learning_rate": 8.695709489967821e-06, "loss": 0.0111, "step": 6120 }, { "epoch": 0.27814802420749934, "grad_norm": 0.12724921107292175, "learning_rate": 8.666572613462465e-06, "loss": 0.0131, "step": 6130 }, { "epoch": 0.27860177302349853, "grad_norm": 0.11023367941379547, "learning_rate": 8.63744725757873e-06, "loss": 0.0106, "step": 6140 }, { "epoch": 0.2790555218394977, "grad_norm": 0.07530383765697479, "learning_rate": 8.60833367395552e-06, "loss": 0.0102, "step": 6150 }, { "epoch": 0.2795092706554969, "grad_norm": 0.10836543887853622, "learning_rate": 8.579232114130027e-06, "loss": 0.0127, "step": 6160 }, { "epoch": 0.27996301947149604, "grad_norm": 0.09886719286441803, "learning_rate": 8.550142829535559e-06, "loss": 0.0079, "step": 6170 }, { "epoch": 0.28041676828749523, "grad_norm": 0.1724623739719391, "learning_rate": 8.521066071499368e-06, "loss": 0.0109, "step": 6180 }, { "epoch": 0.2808705171034944, "grad_norm": 0.08696513622999191, "learning_rate": 8.492002091240478e-06, "loss": 0.0115, "step": 6190 }, { "epoch": 0.2813242659194936, "grad_norm": 0.07495306432247162, "learning_rate": 8.462951139867514e-06, "loss": 0.0117, "step": 6200 }, { "epoch": 0.2817780147354928, "grad_norm": 0.09909680485725403, "learning_rate": 8.43391346837654e-06, "loss": 0.0106, "step": 6210 }, { "epoch": 0.282231763551492, "grad_norm": 0.10531170666217804, "learning_rate": 8.404889327648873e-06, "loss": 0.0107, "step": 6220 }, { "epoch": 0.2826855123674912, "grad_norm": 0.1318645477294922, "learning_rate": 8.375878968448934e-06, "loss": 0.0113, "step": 6230 }, { "epoch": 0.28313926118349036, "grad_norm": 0.08889100700616837, "learning_rate": 8.346882641422066e-06, "loss": 0.0104, "step": 6240 }, { "epoch": 0.28359300999948955, "grad_norm": 0.15128177404403687, "learning_rate": 8.317900597092388e-06, "loss": 0.0122, "step": 6250 }, { "epoch": 0.28404675881548874, "grad_norm": 0.094027578830719, "learning_rate": 8.288933085860611e-06, "loss": 0.0104, "step": 6260 }, { "epoch": 0.2845005076314879, "grad_norm": 0.08185138553380966, "learning_rate": 8.25998035800188e-06, "loss": 0.0113, "step": 6270 }, { "epoch": 0.28495425644748706, "grad_norm": 0.07670748233795166, "learning_rate": 8.231042663663619e-06, "loss": 0.0127, "step": 6280 }, { "epoch": 0.28540800526348625, "grad_norm": 0.12662577629089355, "learning_rate": 8.202120252863359e-06, "loss": 0.0098, "step": 6290 }, { "epoch": 0.28586175407948544, "grad_norm": 0.07162360846996307, "learning_rate": 8.173213375486589e-06, "loss": 0.0123, "step": 6300 }, { "epoch": 0.28631550289548463, "grad_norm": 0.0815914049744606, "learning_rate": 8.144322281284586e-06, "loss": 0.0131, "step": 6310 }, { "epoch": 0.2867692517114838, "grad_norm": 0.12353387475013733, "learning_rate": 8.11544721987227e-06, "loss": 0.012, "step": 6320 }, { "epoch": 0.287223000527483, "grad_norm": 0.16967299580574036, "learning_rate": 8.086588440726034e-06, "loss": 0.0109, "step": 6330 }, { "epoch": 0.2876767493434822, "grad_norm": 0.12848824262619019, "learning_rate": 8.057746193181591e-06, "loss": 0.0105, "step": 6340 }, { "epoch": 0.2881304981594814, "grad_norm": 0.15796878933906555, "learning_rate": 8.028920726431832e-06, "loss": 0.0106, "step": 6350 }, { "epoch": 0.2885842469754806, "grad_norm": 0.12131201475858688, "learning_rate": 8.000112289524666e-06, "loss": 0.0094, "step": 6360 }, { "epoch": 0.2890379957914797, "grad_norm": 0.154999241232872, "learning_rate": 7.971321131360855e-06, "loss": 0.0106, "step": 6370 }, { "epoch": 0.2894917446074789, "grad_norm": 0.08240187913179398, "learning_rate": 7.942547500691884e-06, "loss": 0.0124, "step": 6380 }, { "epoch": 0.2899454934234781, "grad_norm": 0.08584964275360107, "learning_rate": 7.913791646117798e-06, "loss": 0.0117, "step": 6390 }, { "epoch": 0.2903992422394773, "grad_norm": 0.08594949543476105, "learning_rate": 7.885053816085067e-06, "loss": 0.0134, "step": 6400 }, { "epoch": 0.29085299105547646, "grad_norm": 0.09068033844232559, "learning_rate": 7.85633425888442e-06, "loss": 0.0104, "step": 6410 }, { "epoch": 0.29130673987147565, "grad_norm": 0.08089166134595871, "learning_rate": 7.827633222648722e-06, "loss": 0.0115, "step": 6420 }, { "epoch": 0.29176048868747484, "grad_norm": 0.11609190702438354, "learning_rate": 7.798950955350812e-06, "loss": 0.0116, "step": 6430 }, { "epoch": 0.29221423750347403, "grad_norm": 0.13425108790397644, "learning_rate": 7.770287704801374e-06, "loss": 0.0117, "step": 6440 }, { "epoch": 0.2926679863194732, "grad_norm": 0.12515288591384888, "learning_rate": 7.741643718646783e-06, "loss": 0.0109, "step": 6450 }, { "epoch": 0.2931217351354724, "grad_norm": 0.08237916976213455, "learning_rate": 7.713019244366977e-06, "loss": 0.0108, "step": 6460 }, { "epoch": 0.29357548395147154, "grad_norm": 0.11018085479736328, "learning_rate": 7.684414529273315e-06, "loss": 0.0105, "step": 6470 }, { "epoch": 0.2940292327674707, "grad_norm": 0.08896933495998383, "learning_rate": 7.655829820506442e-06, "loss": 0.0099, "step": 6480 }, { "epoch": 0.2944829815834699, "grad_norm": 0.13289591670036316, "learning_rate": 7.627265365034141e-06, "loss": 0.0083, "step": 6490 }, { "epoch": 0.2949367303994691, "grad_norm": 0.08486663550138474, "learning_rate": 7.59872140964922e-06, "loss": 0.0119, "step": 6500 }, { "epoch": 0.2953904792154683, "grad_norm": 0.11567846685647964, "learning_rate": 7.570198200967363e-06, "loss": 0.0091, "step": 6510 }, { "epoch": 0.2958442280314675, "grad_norm": 0.1008777767419815, "learning_rate": 7.5416959854250076e-06, "loss": 0.0094, "step": 6520 }, { "epoch": 0.29629797684746667, "grad_norm": 0.15154337882995605, "learning_rate": 7.513215009277212e-06, "loss": 0.0118, "step": 6530 }, { "epoch": 0.29675172566346586, "grad_norm": 0.15152202546596527, "learning_rate": 7.484755518595534e-06, "loss": 0.0128, "step": 6540 }, { "epoch": 0.29720547447946505, "grad_norm": 0.09559983760118484, "learning_rate": 7.456317759265893e-06, "loss": 0.0098, "step": 6550 }, { "epoch": 0.29765922329546424, "grad_norm": 0.12080786377191544, "learning_rate": 7.4279019769864605e-06, "loss": 0.0113, "step": 6560 }, { "epoch": 0.29811297211146337, "grad_norm": 0.12270969897508621, "learning_rate": 7.399508417265517e-06, "loss": 0.0118, "step": 6570 }, { "epoch": 0.29856672092746256, "grad_norm": 0.12189963459968567, "learning_rate": 7.3711373254193595e-06, "loss": 0.0104, "step": 6580 }, { "epoch": 0.29902046974346175, "grad_norm": 0.10878108441829681, "learning_rate": 7.342788946570159e-06, "loss": 0.0108, "step": 6590 }, { "epoch": 0.29947421855946094, "grad_norm": 0.11416057497262955, "learning_rate": 7.314463525643842e-06, "loss": 0.0107, "step": 6600 }, { "epoch": 0.2999279673754601, "grad_norm": 0.11088518053293228, "learning_rate": 7.286161307367989e-06, "loss": 0.0113, "step": 6610 }, { "epoch": 0.3003817161914593, "grad_norm": 0.09079835563898087, "learning_rate": 7.257882536269716e-06, "loss": 0.0091, "step": 6620 }, { "epoch": 0.3008354650074585, "grad_norm": 0.13540850579738617, "learning_rate": 7.2296274566735494e-06, "loss": 0.0103, "step": 6630 }, { "epoch": 0.3012892138234577, "grad_norm": 0.11761265248060226, "learning_rate": 7.201396312699334e-06, "loss": 0.0081, "step": 6640 }, { "epoch": 0.3017429626394569, "grad_norm": 0.11518513411283493, "learning_rate": 7.173189348260105e-06, "loss": 0.0093, "step": 6650 }, { "epoch": 0.30219671145545607, "grad_norm": 0.07760702073574066, "learning_rate": 7.145006807060002e-06, "loss": 0.0102, "step": 6660 }, { "epoch": 0.3026504602714552, "grad_norm": 0.1049085259437561, "learning_rate": 7.116848932592136e-06, "loss": 0.0117, "step": 6670 }, { "epoch": 0.3031042090874544, "grad_norm": 0.07651153951883316, "learning_rate": 7.088715968136513e-06, "loss": 0.0124, "step": 6680 }, { "epoch": 0.3035579579034536, "grad_norm": 0.1406790018081665, "learning_rate": 7.06060815675792e-06, "loss": 0.0104, "step": 6690 }, { "epoch": 0.30401170671945277, "grad_norm": 0.12033837288618088, "learning_rate": 7.032525741303815e-06, "loss": 0.0125, "step": 6700 }, { "epoch": 0.30446545553545196, "grad_norm": 0.0917229875922203, "learning_rate": 7.00446896440225e-06, "loss": 0.0115, "step": 6710 }, { "epoch": 0.30491920435145115, "grad_norm": 0.09652969986200333, "learning_rate": 6.976438068459756e-06, "loss": 0.0094, "step": 6720 }, { "epoch": 0.30537295316745033, "grad_norm": 0.11267021298408508, "learning_rate": 6.948433295659258e-06, "loss": 0.0111, "step": 6730 }, { "epoch": 0.3058267019834495, "grad_norm": 0.11834914237260818, "learning_rate": 6.920454887957984e-06, "loss": 0.0127, "step": 6740 }, { "epoch": 0.3062804507994487, "grad_norm": 0.18919065594673157, "learning_rate": 6.892503087085365e-06, "loss": 0.0119, "step": 6750 }, { "epoch": 0.3067341996154479, "grad_norm": 0.10613425076007843, "learning_rate": 6.864578134540961e-06, "loss": 0.0109, "step": 6760 }, { "epoch": 0.3071879484314471, "grad_norm": 0.08858054131269455, "learning_rate": 6.83668027159236e-06, "loss": 0.0102, "step": 6770 }, { "epoch": 0.3076416972474462, "grad_norm": 0.15926940739154816, "learning_rate": 6.8088097392731035e-06, "loss": 0.0124, "step": 6780 }, { "epoch": 0.3080954460634454, "grad_norm": 0.17257630825042725, "learning_rate": 6.7809667783805934e-06, "loss": 0.0115, "step": 6790 }, { "epoch": 0.3085491948794446, "grad_norm": 0.08885093778371811, "learning_rate": 6.753151629474028e-06, "loss": 0.0101, "step": 6800 }, { "epoch": 0.3090029436954438, "grad_norm": 0.13596957921981812, "learning_rate": 6.725364532872312e-06, "loss": 0.0109, "step": 6810 }, { "epoch": 0.309456692511443, "grad_norm": 0.1258602887392044, "learning_rate": 6.697605728651977e-06, "loss": 0.0111, "step": 6820 }, { "epoch": 0.30991044132744217, "grad_norm": 0.12389425188302994, "learning_rate": 6.669875456645115e-06, "loss": 0.0116, "step": 6830 }, { "epoch": 0.31036419014344135, "grad_norm": 0.14142358303070068, "learning_rate": 6.642173956437306e-06, "loss": 0.0092, "step": 6840 }, { "epoch": 0.31081793895944054, "grad_norm": 0.10134940594434738, "learning_rate": 6.614501467365539e-06, "loss": 0.0099, "step": 6850 }, { "epoch": 0.31127168777543973, "grad_norm": 0.10126183182001114, "learning_rate": 6.586858228516162e-06, "loss": 0.0099, "step": 6860 }, { "epoch": 0.3117254365914389, "grad_norm": 0.13878075778484344, "learning_rate": 6.559244478722792e-06, "loss": 0.0102, "step": 6870 }, { "epoch": 0.31217918540743805, "grad_norm": 0.11945836246013641, "learning_rate": 6.531660456564282e-06, "loss": 0.0152, "step": 6880 }, { "epoch": 0.31263293422343724, "grad_norm": 0.09034676849842072, "learning_rate": 6.504106400362621e-06, "loss": 0.0093, "step": 6890 }, { "epoch": 0.31308668303943643, "grad_norm": 0.10739793628454208, "learning_rate": 6.476582548180912e-06, "loss": 0.0095, "step": 6900 }, { "epoch": 0.3135404318554356, "grad_norm": 0.07027256488800049, "learning_rate": 6.449089137821301e-06, "loss": 0.0124, "step": 6910 }, { "epoch": 0.3139941806714348, "grad_norm": 0.120933897793293, "learning_rate": 6.421626406822909e-06, "loss": 0.0094, "step": 6920 }, { "epoch": 0.314447929487434, "grad_norm": 0.13272157311439514, "learning_rate": 6.394194592459801e-06, "loss": 0.013, "step": 6930 }, { "epoch": 0.3149016783034332, "grad_norm": 0.12841524183750153, "learning_rate": 6.366793931738922e-06, "loss": 0.0123, "step": 6940 }, { "epoch": 0.3153554271194324, "grad_norm": 0.0611589141190052, "learning_rate": 6.339424661398058e-06, "loss": 0.0101, "step": 6950 }, { "epoch": 0.31580917593543156, "grad_norm": 0.09901798516511917, "learning_rate": 6.312087017903783e-06, "loss": 0.0133, "step": 6960 }, { "epoch": 0.31626292475143075, "grad_norm": 0.16483049094676971, "learning_rate": 6.284781237449419e-06, "loss": 0.0111, "step": 6970 }, { "epoch": 0.3167166735674299, "grad_norm": 0.09773898124694824, "learning_rate": 6.257507555953002e-06, "loss": 0.0101, "step": 6980 }, { "epoch": 0.3171704223834291, "grad_norm": 0.11541863530874252, "learning_rate": 6.230266209055229e-06, "loss": 0.0088, "step": 6990 }, { "epoch": 0.31762417119942826, "grad_norm": 0.2190392166376114, "learning_rate": 6.20305743211744e-06, "loss": 0.011, "step": 7000 }, { "epoch": 0.31807792001542745, "grad_norm": 0.10859877616167068, "learning_rate": 6.175881460219565e-06, "loss": 0.0088, "step": 7010 }, { "epoch": 0.31853166883142664, "grad_norm": 0.11000591516494751, "learning_rate": 6.148738528158109e-06, "loss": 0.0096, "step": 7020 }, { "epoch": 0.31898541764742583, "grad_norm": 0.10755246132612228, "learning_rate": 6.1216288704441255e-06, "loss": 0.0089, "step": 7030 }, { "epoch": 0.319439166463425, "grad_norm": 0.07993614673614502, "learning_rate": 6.094552721301164e-06, "loss": 0.0089, "step": 7040 }, { "epoch": 0.3198929152794242, "grad_norm": 0.10610359907150269, "learning_rate": 6.067510314663283e-06, "loss": 0.008, "step": 7050 }, { "epoch": 0.3203466640954234, "grad_norm": 0.09651736915111542, "learning_rate": 6.0405018841729934e-06, "loss": 0.0091, "step": 7060 }, { "epoch": 0.3208004129114226, "grad_norm": 0.09271356463432312, "learning_rate": 6.013527663179275e-06, "loss": 0.0111, "step": 7070 }, { "epoch": 0.3212541617274217, "grad_norm": 0.12792983651161194, "learning_rate": 5.986587884735526e-06, "loss": 0.0134, "step": 7080 }, { "epoch": 0.3217079105434209, "grad_norm": 0.14052970707416534, "learning_rate": 5.9596827815975775e-06, "loss": 0.0112, "step": 7090 }, { "epoch": 0.3221616593594201, "grad_norm": 0.12076126039028168, "learning_rate": 5.9328125862216676e-06, "loss": 0.0108, "step": 7100 }, { "epoch": 0.3226154081754193, "grad_norm": 0.09900324791669846, "learning_rate": 5.90597753076243e-06, "loss": 0.0103, "step": 7110 }, { "epoch": 0.32306915699141847, "grad_norm": 0.11894827336072922, "learning_rate": 5.879177847070906e-06, "loss": 0.0103, "step": 7120 }, { "epoch": 0.32352290580741766, "grad_norm": 0.12155749648809433, "learning_rate": 5.8524137666925174e-06, "loss": 0.0091, "step": 7130 }, { "epoch": 0.32397665462341685, "grad_norm": 0.10398049652576447, "learning_rate": 5.825685520865092e-06, "loss": 0.0102, "step": 7140 }, { "epoch": 0.32443040343941604, "grad_norm": 0.10042271018028259, "learning_rate": 5.798993340516843e-06, "loss": 0.0102, "step": 7150 }, { "epoch": 0.3248841522554152, "grad_norm": 0.16334493458271027, "learning_rate": 5.772337456264386e-06, "loss": 0.0117, "step": 7160 }, { "epoch": 0.3253379010714144, "grad_norm": 0.11000385135412216, "learning_rate": 5.745718098410737e-06, "loss": 0.0113, "step": 7170 }, { "epoch": 0.32579164988741355, "grad_norm": 0.08863677084445953, "learning_rate": 5.719135496943343e-06, "loss": 0.0087, "step": 7180 }, { "epoch": 0.32624539870341274, "grad_norm": 0.14652566611766815, "learning_rate": 5.69258988153207e-06, "loss": 0.0105, "step": 7190 }, { "epoch": 0.3266991475194119, "grad_norm": 0.13419567048549652, "learning_rate": 5.666081481527232e-06, "loss": 0.0106, "step": 7200 }, { "epoch": 0.3271528963354111, "grad_norm": 0.1367209255695343, "learning_rate": 5.639610525957604e-06, "loss": 0.0102, "step": 7210 }, { "epoch": 0.3276066451514103, "grad_norm": 0.07173440605401993, "learning_rate": 5.613177243528458e-06, "loss": 0.0102, "step": 7220 }, { "epoch": 0.3280603939674095, "grad_norm": 0.11279363185167313, "learning_rate": 5.586781862619566e-06, "loss": 0.0098, "step": 7230 }, { "epoch": 0.3285141427834087, "grad_norm": 0.10586146265268326, "learning_rate": 5.560424611283231e-06, "loss": 0.0101, "step": 7240 }, { "epoch": 0.32896789159940787, "grad_norm": 0.12423428148031235, "learning_rate": 5.53410571724234e-06, "loss": 0.0101, "step": 7250 }, { "epoch": 0.32942164041540706, "grad_norm": 0.12010184675455093, "learning_rate": 5.507825407888362e-06, "loss": 0.0112, "step": 7260 }, { "epoch": 0.32987538923140625, "grad_norm": 0.10193236917257309, "learning_rate": 5.481583910279402e-06, "loss": 0.0115, "step": 7270 }, { "epoch": 0.33032913804740544, "grad_norm": 0.10638996958732605, "learning_rate": 5.4553814511382485e-06, "loss": 0.0091, "step": 7280 }, { "epoch": 0.33078288686340457, "grad_norm": 0.1172296553850174, "learning_rate": 5.429218256850393e-06, "loss": 0.0097, "step": 7290 }, { "epoch": 0.33123663567940376, "grad_norm": 0.11387880146503448, "learning_rate": 5.403094553462083e-06, "loss": 0.0112, "step": 7300 }, { "epoch": 0.33169038449540295, "grad_norm": 0.05639580264687538, "learning_rate": 5.377010566678371e-06, "loss": 0.0116, "step": 7310 }, { "epoch": 0.33214413331140213, "grad_norm": 0.09289851784706116, "learning_rate": 5.350966521861178e-06, "loss": 0.0089, "step": 7320 }, { "epoch": 0.3325978821274013, "grad_norm": 0.06516078114509583, "learning_rate": 5.324962644027312e-06, "loss": 0.013, "step": 7330 }, { "epoch": 0.3330516309434005, "grad_norm": 0.06923472136259079, "learning_rate": 5.298999157846555e-06, "loss": 0.0101, "step": 7340 }, { "epoch": 0.3335053797593997, "grad_norm": 0.08838687837123871, "learning_rate": 5.273076287639704e-06, "loss": 0.0106, "step": 7350 }, { "epoch": 0.3339591285753989, "grad_norm": 0.11485370993614197, "learning_rate": 5.247194257376653e-06, "loss": 0.0102, "step": 7360 }, { "epoch": 0.3344128773913981, "grad_norm": 0.08668481558561325, "learning_rate": 5.221353290674429e-06, "loss": 0.0097, "step": 7370 }, { "epoch": 0.33486662620739727, "grad_norm": 0.11812061816453934, "learning_rate": 5.1955536107952885e-06, "loss": 0.009, "step": 7380 }, { "epoch": 0.3353203750233964, "grad_norm": 0.07998587191104889, "learning_rate": 5.169795440644767e-06, "loss": 0.0098, "step": 7390 }, { "epoch": 0.3357741238393956, "grad_norm": 0.09531218558549881, "learning_rate": 5.144079002769766e-06, "loss": 0.0093, "step": 7400 }, { "epoch": 0.3362278726553948, "grad_norm": 0.08729390054941177, "learning_rate": 5.118404519356621e-06, "loss": 0.0092, "step": 7410 }, { "epoch": 0.33668162147139397, "grad_norm": 0.14389918744564056, "learning_rate": 5.0927722122292e-06, "loss": 0.0099, "step": 7420 }, { "epoch": 0.33713537028739315, "grad_norm": 0.11253806948661804, "learning_rate": 5.067182302846958e-06, "loss": 0.0096, "step": 7430 }, { "epoch": 0.33758911910339234, "grad_norm": 0.12042675167322159, "learning_rate": 5.041635012303048e-06, "loss": 0.0107, "step": 7440 }, { "epoch": 0.33804286791939153, "grad_norm": 0.09659507870674133, "learning_rate": 5.016130561322399e-06, "loss": 0.008, "step": 7450 }, { "epoch": 0.3384966167353907, "grad_norm": 0.08049003034830093, "learning_rate": 4.990669170259816e-06, "loss": 0.0105, "step": 7460 }, { "epoch": 0.3389503655513899, "grad_norm": 0.06659390032291412, "learning_rate": 4.965251059098074e-06, "loss": 0.0084, "step": 7470 }, { "epoch": 0.3394041143673891, "grad_norm": 0.10237156599760056, "learning_rate": 4.93987644744601e-06, "loss": 0.0103, "step": 7480 }, { "epoch": 0.33985786318338823, "grad_norm": 0.1182708591222763, "learning_rate": 4.9145455545366335e-06, "loss": 0.0086, "step": 7490 }, { "epoch": 0.3403116119993874, "grad_norm": 0.16461972892284393, "learning_rate": 4.889258599225233e-06, "loss": 0.012, "step": 7500 }, { "epoch": 0.3407653608153866, "grad_norm": 0.10249344259500504, "learning_rate": 4.864015799987474e-06, "loss": 0.0094, "step": 7510 }, { "epoch": 0.3412191096313858, "grad_norm": 0.10704388469457626, "learning_rate": 4.838817374917534e-06, "loss": 0.0132, "step": 7520 }, { "epoch": 0.341672858447385, "grad_norm": 0.1271437555551529, "learning_rate": 4.8136635417261935e-06, "loss": 0.0109, "step": 7530 }, { "epoch": 0.3421266072633842, "grad_norm": 0.07319293916225433, "learning_rate": 4.788554517738967e-06, "loss": 0.01, "step": 7540 }, { "epoch": 0.34258035607938336, "grad_norm": 0.1651199907064438, "learning_rate": 4.763490519894223e-06, "loss": 0.0088, "step": 7550 }, { "epoch": 0.34303410489538255, "grad_norm": 0.10440236330032349, "learning_rate": 4.738471764741319e-06, "loss": 0.0096, "step": 7560 }, { "epoch": 0.34348785371138174, "grad_norm": 0.07382295280694962, "learning_rate": 4.713498468438709e-06, "loss": 0.0118, "step": 7570 }, { "epoch": 0.34394160252738093, "grad_norm": 0.2104538232088089, "learning_rate": 4.6885708467521015e-06, "loss": 0.0129, "step": 7580 }, { "epoch": 0.34439535134338006, "grad_norm": 0.10214325785636902, "learning_rate": 4.6636891150525765e-06, "loss": 0.0096, "step": 7590 }, { "epoch": 0.34484910015937925, "grad_norm": 0.07409387826919556, "learning_rate": 4.638853488314727e-06, "loss": 0.0093, "step": 7600 }, { "epoch": 0.34530284897537844, "grad_norm": 0.11444170027971268, "learning_rate": 4.614064181114817e-06, "loss": 0.0086, "step": 7610 }, { "epoch": 0.34575659779137763, "grad_norm": 0.1845962554216385, "learning_rate": 4.589321407628907e-06, "loss": 0.0085, "step": 7620 }, { "epoch": 0.3462103466073768, "grad_norm": 0.0720563679933548, "learning_rate": 4.5646253816310175e-06, "loss": 0.0094, "step": 7630 }, { "epoch": 0.346664095423376, "grad_norm": 0.1298360973596573, "learning_rate": 4.539976316491272e-06, "loss": 0.0106, "step": 7640 }, { "epoch": 0.3471178442393752, "grad_norm": 0.10576549172401428, "learning_rate": 4.515374425174062e-06, "loss": 0.009, "step": 7650 }, { "epoch": 0.3475715930553744, "grad_norm": 0.1128876656293869, "learning_rate": 4.49081992023621e-06, "loss": 0.0078, "step": 7660 }, { "epoch": 0.3480253418713736, "grad_norm": 0.1043437197804451, "learning_rate": 4.466313013825119e-06, "loss": 0.009, "step": 7670 }, { "epoch": 0.34847909068737276, "grad_norm": 0.13101355731487274, "learning_rate": 4.4418539176769456e-06, "loss": 0.0098, "step": 7680 }, { "epoch": 0.3489328395033719, "grad_norm": 0.10214662551879883, "learning_rate": 4.417442843114786e-06, "loss": 0.0095, "step": 7690 }, { "epoch": 0.3493865883193711, "grad_norm": 0.1061006635427475, "learning_rate": 4.393080001046818e-06, "loss": 0.0098, "step": 7700 }, { "epoch": 0.34984033713537027, "grad_norm": 0.12027274072170258, "learning_rate": 4.368765601964516e-06, "loss": 0.0117, "step": 7710 }, { "epoch": 0.35029408595136946, "grad_norm": 0.09386374801397324, "learning_rate": 4.3444998559408025e-06, "loss": 0.0083, "step": 7720 }, { "epoch": 0.35074783476736865, "grad_norm": 0.10114315152168274, "learning_rate": 4.320282972628246e-06, "loss": 0.01, "step": 7730 }, { "epoch": 0.35120158358336784, "grad_norm": 0.11737121641635895, "learning_rate": 4.2961151612572495e-06, "loss": 0.011, "step": 7740 }, { "epoch": 0.351655332399367, "grad_norm": 0.0842217281460762, "learning_rate": 4.2719966306342386e-06, "loss": 0.0109, "step": 7750 }, { "epoch": 0.3521090812153662, "grad_norm": 0.09865950047969818, "learning_rate": 4.247927589139869e-06, "loss": 0.0088, "step": 7760 }, { "epoch": 0.3525628300313654, "grad_norm": 0.0670391395688057, "learning_rate": 4.223908244727211e-06, "loss": 0.0093, "step": 7770 }, { "epoch": 0.3530165788473646, "grad_norm": 0.08110418170690536, "learning_rate": 4.199938804919957e-06, "loss": 0.0081, "step": 7780 }, { "epoch": 0.3534703276633637, "grad_norm": 0.11343499273061752, "learning_rate": 4.176019476810631e-06, "loss": 0.0123, "step": 7790 }, { "epoch": 0.3539240764793629, "grad_norm": 0.10193148255348206, "learning_rate": 4.152150467058805e-06, "loss": 0.0113, "step": 7800 }, { "epoch": 0.3543778252953621, "grad_norm": 0.09715145081281662, "learning_rate": 4.128331981889309e-06, "loss": 0.0092, "step": 7810 }, { "epoch": 0.3548315741113613, "grad_norm": 0.07923878729343414, "learning_rate": 4.104564227090437e-06, "loss": 0.0116, "step": 7820 }, { "epoch": 0.3552853229273605, "grad_norm": 0.11488189548254013, "learning_rate": 4.080847408012189e-06, "loss": 0.0097, "step": 7830 }, { "epoch": 0.35573907174335967, "grad_norm": 0.09501442313194275, "learning_rate": 4.057181729564478e-06, "loss": 0.0083, "step": 7840 }, { "epoch": 0.35619282055935886, "grad_norm": 0.1033216342329979, "learning_rate": 4.033567396215387e-06, "loss": 0.0079, "step": 7850 }, { "epoch": 0.35664656937535805, "grad_norm": 0.13176698982715607, "learning_rate": 4.0100046119893654e-06, "loss": 0.0129, "step": 7860 }, { "epoch": 0.35710031819135724, "grad_norm": 0.10394264757633209, "learning_rate": 3.986493580465498e-06, "loss": 0.0087, "step": 7870 }, { "epoch": 0.3575540670073564, "grad_norm": 0.13478738069534302, "learning_rate": 3.963034504775727e-06, "loss": 0.0105, "step": 7880 }, { "epoch": 0.3580078158233556, "grad_norm": 0.12828779220581055, "learning_rate": 3.939627587603103e-06, "loss": 0.0127, "step": 7890 }, { "epoch": 0.35846156463935475, "grad_norm": 0.1657111644744873, "learning_rate": 3.9162730311800455e-06, "loss": 0.0109, "step": 7900 }, { "epoch": 0.35891531345535393, "grad_norm": 0.09156011044979095, "learning_rate": 3.8929710372865696e-06, "loss": 0.0093, "step": 7910 }, { "epoch": 0.3593690622713531, "grad_norm": 0.15309078991413116, "learning_rate": 3.869721807248571e-06, "loss": 0.0095, "step": 7920 }, { "epoch": 0.3598228110873523, "grad_norm": 0.08134149760007858, "learning_rate": 3.8465255419360635e-06, "loss": 0.0102, "step": 7930 }, { "epoch": 0.3602765599033515, "grad_norm": 0.07899979501962662, "learning_rate": 3.823382441761454e-06, "loss": 0.0085, "step": 7940 }, { "epoch": 0.3607303087193507, "grad_norm": 0.055894799530506134, "learning_rate": 3.8002927066778193e-06, "loss": 0.0114, "step": 7950 }, { "epoch": 0.3611840575353499, "grad_norm": 0.07259116321802139, "learning_rate": 3.7772565361771596e-06, "loss": 0.012, "step": 7960 }, { "epoch": 0.36163780635134907, "grad_norm": 0.10204251855611801, "learning_rate": 3.75427412928869e-06, "loss": 0.0123, "step": 7970 }, { "epoch": 0.36209155516734826, "grad_norm": 0.12866093218326569, "learning_rate": 3.731345684577109e-06, "loss": 0.0109, "step": 7980 }, { "epoch": 0.36254530398334744, "grad_norm": 0.16702964901924133, "learning_rate": 3.7084714001409016e-06, "loss": 0.0111, "step": 7990 }, { "epoch": 0.3629990527993466, "grad_norm": 0.07304515689611435, "learning_rate": 3.6856514736106063e-06, "loss": 0.009, "step": 8000 }, { "epoch": 0.36345280161534577, "grad_norm": 0.07702866941690445, "learning_rate": 3.6628861021471185e-06, "loss": 0.011, "step": 8010 }, { "epoch": 0.36390655043134496, "grad_norm": 0.07464990019798279, "learning_rate": 3.6401754824399837e-06, "loss": 0.0098, "step": 8020 }, { "epoch": 0.36436029924734414, "grad_norm": 0.07167572528123856, "learning_rate": 3.6175198107057107e-06, "loss": 0.0097, "step": 8030 }, { "epoch": 0.36481404806334333, "grad_norm": 0.12362537533044815, "learning_rate": 3.5949192826860513e-06, "loss": 0.0077, "step": 8040 }, { "epoch": 0.3652677968793425, "grad_norm": 0.07578972727060318, "learning_rate": 3.572374093646336e-06, "loss": 0.0096, "step": 8050 }, { "epoch": 0.3657215456953417, "grad_norm": 0.12454843521118164, "learning_rate": 3.5498844383737653e-06, "loss": 0.0099, "step": 8060 }, { "epoch": 0.3661752945113409, "grad_norm": 0.1021660566329956, "learning_rate": 3.5274505111757405e-06, "loss": 0.009, "step": 8070 }, { "epoch": 0.3666290433273401, "grad_norm": 0.11132406443357468, "learning_rate": 3.5050725058781765e-06, "loss": 0.0115, "step": 8080 }, { "epoch": 0.3670827921433393, "grad_norm": 0.1043797954916954, "learning_rate": 3.482750615823838e-06, "loss": 0.0086, "step": 8090 }, { "epoch": 0.3675365409593384, "grad_norm": 0.1179547980427742, "learning_rate": 3.4604850338706554e-06, "loss": 0.0096, "step": 8100 }, { "epoch": 0.3679902897753376, "grad_norm": 0.07106457650661469, "learning_rate": 3.4382759523900678e-06, "loss": 0.0089, "step": 8110 }, { "epoch": 0.3684440385913368, "grad_norm": 0.10606525093317032, "learning_rate": 3.4161235632653587e-06, "loss": 0.0093, "step": 8120 }, { "epoch": 0.368897787407336, "grad_norm": 0.0955435037612915, "learning_rate": 3.394028057889992e-06, "loss": 0.0091, "step": 8130 }, { "epoch": 0.36935153622333516, "grad_norm": 0.12934014201164246, "learning_rate": 3.3719896271659734e-06, "loss": 0.0099, "step": 8140 }, { "epoch": 0.36980528503933435, "grad_norm": 0.12838302552700043, "learning_rate": 3.3500084615021912e-06, "loss": 0.0092, "step": 8150 }, { "epoch": 0.37025903385533354, "grad_norm": 0.090861476957798, "learning_rate": 3.3280847508127644e-06, "loss": 0.0081, "step": 8160 }, { "epoch": 0.37071278267133273, "grad_norm": 0.09278837591409683, "learning_rate": 3.306218684515413e-06, "loss": 0.0078, "step": 8170 }, { "epoch": 0.3711665314873319, "grad_norm": 0.10649178177118301, "learning_rate": 3.284410451529816e-06, "loss": 0.0079, "step": 8180 }, { "epoch": 0.3716202803033311, "grad_norm": 0.10113388299942017, "learning_rate": 3.2626602402759865e-06, "loss": 0.0083, "step": 8190 }, { "epoch": 0.37207402911933024, "grad_norm": 0.11916524171829224, "learning_rate": 3.240968238672633e-06, "loss": 0.0084, "step": 8200 }, { "epoch": 0.37252777793532943, "grad_norm": 0.10443044453859329, "learning_rate": 3.2193346341355413e-06, "loss": 0.0106, "step": 8210 }, { "epoch": 0.3729815267513286, "grad_norm": 0.10287365317344666, "learning_rate": 3.1977596135759524e-06, "loss": 0.0079, "step": 8220 }, { "epoch": 0.3734352755673278, "grad_norm": 0.13503587245941162, "learning_rate": 3.176243363398961e-06, "loss": 0.0111, "step": 8230 }, { "epoch": 0.373889024383327, "grad_norm": 0.22208702564239502, "learning_rate": 3.1547860695018793e-06, "loss": 0.0106, "step": 8240 }, { "epoch": 0.3743427731993262, "grad_norm": 0.16151806712150574, "learning_rate": 3.13338791727266e-06, "loss": 0.0102, "step": 8250 }, { "epoch": 0.3747965220153254, "grad_norm": 0.09824798256158829, "learning_rate": 3.1120490915882694e-06, "loss": 0.0113, "step": 8260 }, { "epoch": 0.37525027083132456, "grad_norm": 0.06923127919435501, "learning_rate": 3.090769776813106e-06, "loss": 0.0081, "step": 8270 }, { "epoch": 0.37570401964732375, "grad_norm": 0.1138189509510994, "learning_rate": 3.0695501567973983e-06, "loss": 0.0074, "step": 8280 }, { "epoch": 0.37615776846332294, "grad_norm": 0.12380145490169525, "learning_rate": 3.0483904148756284e-06, "loss": 0.0111, "step": 8290 }, { "epoch": 0.37661151727932207, "grad_norm": 0.11057600378990173, "learning_rate": 3.0272907338649337e-06, "loss": 0.0115, "step": 8300 }, { "epoch": 0.37706526609532126, "grad_norm": 0.0969073548913002, "learning_rate": 3.006251296063536e-06, "loss": 0.0091, "step": 8310 }, { "epoch": 0.37751901491132045, "grad_norm": 0.08020509779453278, "learning_rate": 2.985272283249161e-06, "loss": 0.0099, "step": 8320 }, { "epoch": 0.37797276372731964, "grad_norm": 0.09954225271940231, "learning_rate": 2.9643538766774793e-06, "loss": 0.0089, "step": 8330 }, { "epoch": 0.3784265125433188, "grad_norm": 0.06478285789489746, "learning_rate": 2.943496257080527e-06, "loss": 0.0081, "step": 8340 }, { "epoch": 0.378880261359318, "grad_norm": 0.07575979828834534, "learning_rate": 2.9226996046651435e-06, "loss": 0.0111, "step": 8350 }, { "epoch": 0.3793340101753172, "grad_norm": 0.0934787318110466, "learning_rate": 2.901964099111435e-06, "loss": 0.0093, "step": 8360 }, { "epoch": 0.3797877589913164, "grad_norm": 0.08123017102479935, "learning_rate": 2.881289919571193e-06, "loss": 0.0109, "step": 8370 }, { "epoch": 0.3802415078073156, "grad_norm": 0.08231671899557114, "learning_rate": 2.860677244666373e-06, "loss": 0.0084, "step": 8380 }, { "epoch": 0.38069525662331477, "grad_norm": 0.10701660811901093, "learning_rate": 2.840126252487532e-06, "loss": 0.011, "step": 8390 }, { "epoch": 0.38114900543931396, "grad_norm": 0.11005216836929321, "learning_rate": 2.8196371205922955e-06, "loss": 0.0083, "step": 8400 }, { "epoch": 0.3816027542553131, "grad_norm": 0.07783106714487076, "learning_rate": 2.799210026003831e-06, "loss": 0.0088, "step": 8410 }, { "epoch": 0.3820565030713123, "grad_norm": 0.13532501459121704, "learning_rate": 2.7788451452093067e-06, "loss": 0.0117, "step": 8420 }, { "epoch": 0.38251025188731147, "grad_norm": 0.08362141996622086, "learning_rate": 2.75854265415838e-06, "loss": 0.0078, "step": 8430 }, { "epoch": 0.38296400070331066, "grad_norm": 0.1013425663113594, "learning_rate": 2.738302728261665e-06, "loss": 0.011, "step": 8440 }, { "epoch": 0.38341774951930985, "grad_norm": 0.08031856268644333, "learning_rate": 2.7181255423892192e-06, "loss": 0.0093, "step": 8450 }, { "epoch": 0.38387149833530904, "grad_norm": 0.09519562125205994, "learning_rate": 2.6980112708690374e-06, "loss": 0.0094, "step": 8460 }, { "epoch": 0.3843252471513082, "grad_norm": 0.11562605947256088, "learning_rate": 2.677960087485547e-06, "loss": 0.0086, "step": 8470 }, { "epoch": 0.3847789959673074, "grad_norm": 0.09193369001150131, "learning_rate": 2.657972165478103e-06, "loss": 0.0079, "step": 8480 }, { "epoch": 0.3852327447833066, "grad_norm": 0.11255563050508499, "learning_rate": 2.638047677539487e-06, "loss": 0.0098, "step": 8490 }, { "epoch": 0.3856864935993058, "grad_norm": 0.07042751461267471, "learning_rate": 2.618186795814418e-06, "loss": 0.0075, "step": 8500 }, { "epoch": 0.3861402424153049, "grad_norm": 0.10573995858430862, "learning_rate": 2.598389691898072e-06, "loss": 0.0112, "step": 8510 }, { "epoch": 0.3865939912313041, "grad_norm": 0.11931172758340836, "learning_rate": 2.578656536834586e-06, "loss": 0.0115, "step": 8520 }, { "epoch": 0.3870477400473033, "grad_norm": 0.1774836629629135, "learning_rate": 2.5589875011156008e-06, "loss": 0.0118, "step": 8530 }, { "epoch": 0.3875014888633025, "grad_norm": 0.08653493970632553, "learning_rate": 2.539382754678764e-06, "loss": 0.0108, "step": 8540 }, { "epoch": 0.3879552376793017, "grad_norm": 0.12400869280099869, "learning_rate": 2.519842466906276e-06, "loss": 0.0074, "step": 8550 }, { "epoch": 0.38840898649530087, "grad_norm": 0.11967054009437561, "learning_rate": 2.5003668066234233e-06, "loss": 0.008, "step": 8560 }, { "epoch": 0.38886273531130006, "grad_norm": 0.07257911562919617, "learning_rate": 2.480955942097121e-06, "loss": 0.0099, "step": 8570 }, { "epoch": 0.38931648412729924, "grad_norm": 0.08073431998491287, "learning_rate": 2.4616100410344634e-06, "loss": 0.0096, "step": 8580 }, { "epoch": 0.38977023294329843, "grad_norm": 0.10386104136705399, "learning_rate": 2.442329270581262e-06, "loss": 0.0118, "step": 8590 }, { "epoch": 0.3902239817592976, "grad_norm": 0.09636528789997101, "learning_rate": 2.4231137973206097e-06, "loss": 0.0125, "step": 8600 }, { "epoch": 0.39067773057529676, "grad_norm": 0.11959709972143173, "learning_rate": 2.4039637872714417e-06, "loss": 0.0083, "step": 8610 }, { "epoch": 0.39113147939129594, "grad_norm": 0.1058986634016037, "learning_rate": 2.3848794058871073e-06, "loss": 0.0084, "step": 8620 }, { "epoch": 0.39158522820729513, "grad_norm": 0.07962191849946976, "learning_rate": 2.3658608180539243e-06, "loss": 0.0104, "step": 8630 }, { "epoch": 0.3920389770232943, "grad_norm": 0.0981462225317955, "learning_rate": 2.3469081880897694e-06, "loss": 0.0095, "step": 8640 }, { "epoch": 0.3924927258392935, "grad_norm": 0.09810712933540344, "learning_rate": 2.328021679742648e-06, "loss": 0.0078, "step": 8650 }, { "epoch": 0.3929464746552927, "grad_norm": 0.08801249414682388, "learning_rate": 2.309201456189286e-06, "loss": 0.0091, "step": 8660 }, { "epoch": 0.3934002234712919, "grad_norm": 0.09836827218532562, "learning_rate": 2.290447680033725e-06, "loss": 0.0098, "step": 8670 }, { "epoch": 0.3938539722872911, "grad_norm": 0.1063736230134964, "learning_rate": 2.2717605133059007e-06, "loss": 0.0102, "step": 8680 }, { "epoch": 0.39430772110329027, "grad_norm": 0.10163119435310364, "learning_rate": 2.253140117460255e-06, "loss": 0.0086, "step": 8690 }, { "epoch": 0.39476146991928945, "grad_norm": 0.09455427527427673, "learning_rate": 2.2345866533743453e-06, "loss": 0.0087, "step": 8700 }, { "epoch": 0.3952152187352886, "grad_norm": 0.09013013541698456, "learning_rate": 2.2161002813474397e-06, "loss": 0.0082, "step": 8710 }, { "epoch": 0.3956689675512878, "grad_norm": 0.08666102588176727, "learning_rate": 2.197681161099149e-06, "loss": 0.0065, "step": 8720 }, { "epoch": 0.39612271636728696, "grad_norm": 0.09802000224590302, "learning_rate": 2.179329451768031e-06, "loss": 0.0082, "step": 8730 }, { "epoch": 0.39657646518328615, "grad_norm": 0.09157402068376541, "learning_rate": 2.161045311910227e-06, "loss": 0.0102, "step": 8740 }, { "epoch": 0.39703021399928534, "grad_norm": 0.1105928048491478, "learning_rate": 2.1428288994980816e-06, "loss": 0.0096, "step": 8750 }, { "epoch": 0.39748396281528453, "grad_norm": 0.13131096959114075, "learning_rate": 2.124680371918796e-06, "loss": 0.0105, "step": 8760 }, { "epoch": 0.3979377116312837, "grad_norm": 0.10070949047803879, "learning_rate": 2.106599885973044e-06, "loss": 0.0101, "step": 8770 }, { "epoch": 0.3983914604472829, "grad_norm": 0.09249789267778397, "learning_rate": 2.088587597873637e-06, "loss": 0.0079, "step": 8780 }, { "epoch": 0.3988452092632821, "grad_norm": 0.12309060245752335, "learning_rate": 2.070643663244163e-06, "loss": 0.0102, "step": 8790 }, { "epoch": 0.3992989580792813, "grad_norm": 0.11004301905632019, "learning_rate": 2.052768237117644e-06, "loss": 0.011, "step": 8800 }, { "epoch": 0.3997527068952804, "grad_norm": 0.11117362976074219, "learning_rate": 2.034961473935203e-06, "loss": 0.0071, "step": 8810 }, { "epoch": 0.4002064557112796, "grad_norm": 0.06948977708816528, "learning_rate": 2.0172235275447284e-06, "loss": 0.0079, "step": 8820 }, { "epoch": 0.4006602045272788, "grad_norm": 0.11114662140607834, "learning_rate": 1.9995545511995316e-06, "loss": 0.0084, "step": 8830 }, { "epoch": 0.401113953343278, "grad_norm": 0.08284008502960205, "learning_rate": 1.9819546975570382e-06, "loss": 0.0082, "step": 8840 }, { "epoch": 0.4015677021592772, "grad_norm": 0.10737113654613495, "learning_rate": 1.9644241186774593e-06, "loss": 0.0096, "step": 8850 }, { "epoch": 0.40202145097527636, "grad_norm": 0.07035491615533829, "learning_rate": 1.9469629660224907e-06, "loss": 0.0093, "step": 8860 }, { "epoch": 0.40247519979127555, "grad_norm": 0.10407382249832153, "learning_rate": 1.9295713904539892e-06, "loss": 0.0064, "step": 8870 }, { "epoch": 0.40292894860727474, "grad_norm": 0.09794197976589203, "learning_rate": 1.912249542232675e-06, "loss": 0.0103, "step": 8880 }, { "epoch": 0.40338269742327393, "grad_norm": 0.10132595896720886, "learning_rate": 1.8949975710168357e-06, "loss": 0.0099, "step": 8890 }, { "epoch": 0.4038364462392731, "grad_norm": 0.08574865758419037, "learning_rate": 1.8778156258610292e-06, "loss": 0.011, "step": 8900 }, { "epoch": 0.40429019505527225, "grad_norm": 0.09225784242153168, "learning_rate": 1.8607038552148039e-06, "loss": 0.0091, "step": 8910 }, { "epoch": 0.40474394387127144, "grad_norm": 0.08739297091960907, "learning_rate": 1.8436624069214071e-06, "loss": 0.0068, "step": 8920 }, { "epoch": 0.4051976926872706, "grad_norm": 0.1604710966348648, "learning_rate": 1.8266914282165116e-06, "loss": 0.0085, "step": 8930 }, { "epoch": 0.4056514415032698, "grad_norm": 0.07389248162508011, "learning_rate": 1.80979106572694e-06, "loss": 0.0081, "step": 8940 }, { "epoch": 0.406105190319269, "grad_norm": 0.10426627844572067, "learning_rate": 1.792961465469404e-06, "loss": 0.0091, "step": 8950 }, { "epoch": 0.4065589391352682, "grad_norm": 0.15305018424987793, "learning_rate": 1.7762027728492405e-06, "loss": 0.0113, "step": 8960 }, { "epoch": 0.4070126879512674, "grad_norm": 0.09772137552499771, "learning_rate": 1.759515132659153e-06, "loss": 0.0094, "step": 8970 }, { "epoch": 0.40746643676726657, "grad_norm": 0.09502757340669632, "learning_rate": 1.742898689077961e-06, "loss": 0.0095, "step": 8980 }, { "epoch": 0.40792018558326576, "grad_norm": 0.05672432482242584, "learning_rate": 1.726353585669356e-06, "loss": 0.0078, "step": 8990 }, { "epoch": 0.40837393439926495, "grad_norm": 0.08652110397815704, "learning_rate": 1.7098799653806663e-06, "loss": 0.0084, "step": 9000 }, { "epoch": 0.40882768321526414, "grad_norm": 0.10222375392913818, "learning_rate": 1.6934779705416082e-06, "loss": 0.0081, "step": 9010 }, { "epoch": 0.40928143203126327, "grad_norm": 0.12190228700637817, "learning_rate": 1.6771477428630656e-06, "loss": 0.0097, "step": 9020 }, { "epoch": 0.40973518084726246, "grad_norm": 0.14294026792049408, "learning_rate": 1.6608894234358708e-06, "loss": 0.0091, "step": 9030 }, { "epoch": 0.41018892966326165, "grad_norm": 0.10034189373254776, "learning_rate": 1.6447031527295744e-06, "loss": 0.0106, "step": 9040 }, { "epoch": 0.41064267847926084, "grad_norm": 0.10880102217197418, "learning_rate": 1.628589070591232e-06, "loss": 0.0098, "step": 9050 }, { "epoch": 0.41109642729526, "grad_norm": 0.0908391922712326, "learning_rate": 1.6125473162442107e-06, "loss": 0.0087, "step": 9060 }, { "epoch": 0.4115501761112592, "grad_norm": 0.13722823560237885, "learning_rate": 1.5965780282869693e-06, "loss": 0.0088, "step": 9070 }, { "epoch": 0.4120039249272584, "grad_norm": 0.17580917477607727, "learning_rate": 1.5806813446918657e-06, "loss": 0.0071, "step": 9080 }, { "epoch": 0.4124576737432576, "grad_norm": 0.10480867326259613, "learning_rate": 1.56485740280397e-06, "loss": 0.0094, "step": 9090 }, { "epoch": 0.4129114225592568, "grad_norm": 0.08441663533449173, "learning_rate": 1.5491063393398742e-06, "loss": 0.0099, "step": 9100 }, { "epoch": 0.41336517137525597, "grad_norm": 0.11388783901929855, "learning_rate": 1.5334282903865116e-06, "loss": 0.0095, "step": 9110 }, { "epoch": 0.4138189201912551, "grad_norm": 0.06890968978404999, "learning_rate": 1.5178233913999784e-06, "loss": 0.0088, "step": 9120 }, { "epoch": 0.4142726690072543, "grad_norm": 0.10206199437379837, "learning_rate": 1.5022917772043633e-06, "loss": 0.0087, "step": 9130 }, { "epoch": 0.4147264178232535, "grad_norm": 0.10712311416864395, "learning_rate": 1.4868335819905922e-06, "loss": 0.0082, "step": 9140 }, { "epoch": 0.41518016663925267, "grad_norm": 0.09817501902580261, "learning_rate": 1.4714489393152586e-06, "loss": 0.0088, "step": 9150 }, { "epoch": 0.41563391545525186, "grad_norm": 0.09176748991012573, "learning_rate": 1.4561379820994692e-06, "loss": 0.0081, "step": 9160 }, { "epoch": 0.41608766427125105, "grad_norm": 0.05821143090724945, "learning_rate": 1.4409008426277028e-06, "loss": 0.009, "step": 9170 }, { "epoch": 0.41654141308725023, "grad_norm": 0.12857897579669952, "learning_rate": 1.4257376525466594e-06, "loss": 0.0103, "step": 9180 }, { "epoch": 0.4169951619032494, "grad_norm": 0.07830528914928436, "learning_rate": 1.4106485428641292e-06, "loss": 0.0078, "step": 9190 }, { "epoch": 0.4174489107192486, "grad_norm": 0.1507706642150879, "learning_rate": 1.3956336439478612e-06, "loss": 0.0082, "step": 9200 }, { "epoch": 0.4179026595352478, "grad_norm": 0.08604637533426285, "learning_rate": 1.3806930855244315e-06, "loss": 0.0082, "step": 9210 }, { "epoch": 0.41835640835124693, "grad_norm": 0.08302732557058334, "learning_rate": 1.3658269966781223e-06, "loss": 0.0091, "step": 9220 }, { "epoch": 0.4188101571672461, "grad_norm": 0.08082342147827148, "learning_rate": 1.3510355058498114e-06, "loss": 0.0073, "step": 9230 }, { "epoch": 0.4192639059832453, "grad_norm": 0.06795746833086014, "learning_rate": 1.3363187408358612e-06, "loss": 0.0084, "step": 9240 }, { "epoch": 0.4197176547992445, "grad_norm": 0.09119124710559845, "learning_rate": 1.3216768287870185e-06, "loss": 0.0085, "step": 9250 }, { "epoch": 0.4201714036152437, "grad_norm": 0.1154276505112648, "learning_rate": 1.3071098962073004e-06, "loss": 0.0066, "step": 9260 }, { "epoch": 0.4206251524312429, "grad_norm": 0.07161936908960342, "learning_rate": 1.292618068952921e-06, "loss": 0.0093, "step": 9270 }, { "epoch": 0.42107890124724207, "grad_norm": 0.0967567190527916, "learning_rate": 1.2782014722311897e-06, "loss": 0.0076, "step": 9280 }, { "epoch": 0.42153265006324125, "grad_norm": 0.06425561755895615, "learning_rate": 1.2638602305994364e-06, "loss": 0.0093, "step": 9290 }, { "epoch": 0.42198639887924044, "grad_norm": 0.08820091187953949, "learning_rate": 1.2495944679639383e-06, "loss": 0.0097, "step": 9300 }, { "epoch": 0.42244014769523963, "grad_norm": 0.06562600284814835, "learning_rate": 1.2354043075788391e-06, "loss": 0.0091, "step": 9310 }, { "epoch": 0.42289389651123876, "grad_norm": 0.09714815020561218, "learning_rate": 1.2212898720450915e-06, "loss": 0.0097, "step": 9320 }, { "epoch": 0.42334764532723795, "grad_norm": 0.08260037004947662, "learning_rate": 1.2072512833093964e-06, "loss": 0.0091, "step": 9330 }, { "epoch": 0.42380139414323714, "grad_norm": 0.12126976251602173, "learning_rate": 1.1932886626631512e-06, "loss": 0.0106, "step": 9340 }, { "epoch": 0.42425514295923633, "grad_norm": 0.1290188729763031, "learning_rate": 1.179402130741396e-06, "loss": 0.0072, "step": 9350 }, { "epoch": 0.4247088917752355, "grad_norm": 0.1192982941865921, "learning_rate": 1.165591807521781e-06, "loss": 0.0102, "step": 9360 }, { "epoch": 0.4251626405912347, "grad_norm": 0.1461435705423355, "learning_rate": 1.1518578123235191e-06, "loss": 0.0078, "step": 9370 }, { "epoch": 0.4256163894072339, "grad_norm": 0.12295739352703094, "learning_rate": 1.1382002638063584e-06, "loss": 0.0092, "step": 9380 }, { "epoch": 0.4260701382232331, "grad_norm": 0.1849353313446045, "learning_rate": 1.1246192799695666e-06, "loss": 0.009, "step": 9390 }, { "epoch": 0.4265238870392323, "grad_norm": 0.1251634955406189, "learning_rate": 1.1111149781508968e-06, "loss": 0.0093, "step": 9400 }, { "epoch": 0.42697763585523146, "grad_norm": 0.1156451553106308, "learning_rate": 1.0976874750255828e-06, "loss": 0.0081, "step": 9410 }, { "epoch": 0.4274313846712306, "grad_norm": 0.09500299394130707, "learning_rate": 1.0843368866053271e-06, "loss": 0.0089, "step": 9420 }, { "epoch": 0.4278851334872298, "grad_norm": 0.10757829248905182, "learning_rate": 1.0710633282372996e-06, "loss": 0.0093, "step": 9430 }, { "epoch": 0.428338882303229, "grad_norm": 0.09244924038648605, "learning_rate": 1.0578669146031484e-06, "loss": 0.009, "step": 9440 }, { "epoch": 0.42879263111922816, "grad_norm": 0.1415679007768631, "learning_rate": 1.0447477597179945e-06, "loss": 0.0094, "step": 9450 }, { "epoch": 0.42924637993522735, "grad_norm": 0.09767192602157593, "learning_rate": 1.0317059769294557e-06, "loss": 0.0092, "step": 9460 }, { "epoch": 0.42970012875122654, "grad_norm": 0.104937344789505, "learning_rate": 1.0187416789166672e-06, "loss": 0.0087, "step": 9470 }, { "epoch": 0.43015387756722573, "grad_norm": 0.07533662766218185, "learning_rate": 1.0058549776893068e-06, "loss": 0.0105, "step": 9480 }, { "epoch": 0.4306076263832249, "grad_norm": 0.12171541154384613, "learning_rate": 9.930459845866313e-07, "loss": 0.0081, "step": 9490 }, { "epoch": 0.4310613751992241, "grad_norm": 0.10602816939353943, "learning_rate": 9.803148102765026e-07, "loss": 0.0081, "step": 9500 }, { "epoch": 0.4315151240152233, "grad_norm": 0.1023092046380043, "learning_rate": 9.676615647544452e-07, "loss": 0.0074, "step": 9510 }, { "epoch": 0.4319688728312225, "grad_norm": 0.19016389548778534, "learning_rate": 9.550863573426838e-07, "loss": 0.0095, "step": 9520 }, { "epoch": 0.4324226216472216, "grad_norm": 0.11293892562389374, "learning_rate": 9.425892966892136e-07, "loss": 0.0099, "step": 9530 }, { "epoch": 0.4328763704632208, "grad_norm": 0.1257106065750122, "learning_rate": 9.301704907668474e-07, "loss": 0.0088, "step": 9540 }, { "epoch": 0.43333011927922, "grad_norm": 0.0924149602651596, "learning_rate": 9.178300468722901e-07, "loss": 0.0087, "step": 9550 }, { "epoch": 0.4337838680952192, "grad_norm": 0.10932919383049011, "learning_rate": 9.055680716252068e-07, "loss": 0.0087, "step": 9560 }, { "epoch": 0.43423761691121837, "grad_norm": 0.12126089632511139, "learning_rate": 8.933846709673078e-07, "loss": 0.0089, "step": 9570 }, { "epoch": 0.43469136572721756, "grad_norm": 0.12364113330841064, "learning_rate": 8.812799501614311e-07, "loss": 0.0079, "step": 9580 }, { "epoch": 0.43514511454321675, "grad_norm": 0.057740189135074615, "learning_rate": 8.692540137906314e-07, "loss": 0.0085, "step": 9590 }, { "epoch": 0.43559886335921594, "grad_norm": 0.1810929924249649, "learning_rate": 8.573069657572752e-07, "loss": 0.009, "step": 9600 }, { "epoch": 0.4360526121752151, "grad_norm": 0.08297877013683319, "learning_rate": 8.454389092821458e-07, "loss": 0.0092, "step": 9610 }, { "epoch": 0.4365063609912143, "grad_norm": 0.0796361193060875, "learning_rate": 8.336499469035509e-07, "loss": 0.01, "step": 9620 }, { "epoch": 0.43696010980721345, "grad_norm": 0.08780820667743683, "learning_rate": 8.219401804764382e-07, "loss": 0.0091, "step": 9630 }, { "epoch": 0.43741385862321264, "grad_norm": 0.11457058042287827, "learning_rate": 8.10309711171512e-07, "loss": 0.0099, "step": 9640 }, { "epoch": 0.4378676074392118, "grad_norm": 0.10212496668100357, "learning_rate": 7.987586394743608e-07, "loss": 0.0088, "step": 9650 }, { "epoch": 0.438321356255211, "grad_norm": 0.1155591532588005, "learning_rate": 7.872870651845888e-07, "loss": 0.0099, "step": 9660 }, { "epoch": 0.4387751050712102, "grad_norm": 0.1185288056731224, "learning_rate": 7.758950874149541e-07, "loss": 0.0104, "step": 9670 }, { "epoch": 0.4392288538872094, "grad_norm": 0.14770649373531342, "learning_rate": 7.645828045905157e-07, "loss": 0.01, "step": 9680 }, { "epoch": 0.4396826027032086, "grad_norm": 0.08911648392677307, "learning_rate": 7.533503144477738e-07, "loss": 0.0087, "step": 9690 }, { "epoch": 0.44013635151920777, "grad_norm": 0.1284065544605255, "learning_rate": 7.421977140338376e-07, "loss": 0.0097, "step": 9700 }, { "epoch": 0.44059010033520696, "grad_norm": 0.1027558371424675, "learning_rate": 7.311250997055752e-07, "loss": 0.0093, "step": 9710 }, { "epoch": 0.44104384915120615, "grad_norm": 0.0774318277835846, "learning_rate": 7.201325671287862e-07, "loss": 0.0095, "step": 9720 }, { "epoch": 0.4414975979672053, "grad_norm": 0.08871971070766449, "learning_rate": 7.092202112773817e-07, "loss": 0.0084, "step": 9730 }, { "epoch": 0.44195134678320447, "grad_norm": 0.06491197645664215, "learning_rate": 6.983881264325521e-07, "loss": 0.0065, "step": 9740 }, { "epoch": 0.44240509559920366, "grad_norm": 0.0722510889172554, "learning_rate": 6.876364061819574e-07, "loss": 0.009, "step": 9750 }, { "epoch": 0.44285884441520285, "grad_norm": 0.11284934729337692, "learning_rate": 6.769651434189195e-07, "loss": 0.0075, "step": 9760 }, { "epoch": 0.44331259323120203, "grad_norm": 0.12994599342346191, "learning_rate": 6.663744303416231e-07, "loss": 0.0081, "step": 9770 }, { "epoch": 0.4437663420472012, "grad_norm": 0.08878470212221146, "learning_rate": 6.558643584523117e-07, "loss": 0.0085, "step": 9780 }, { "epoch": 0.4442200908632004, "grad_norm": 0.10006320476531982, "learning_rate": 6.454350185564994e-07, "loss": 0.0078, "step": 9790 }, { "epoch": 0.4446738396791996, "grad_norm": 0.11309023201465607, "learning_rate": 6.350865007621887e-07, "loss": 0.0094, "step": 9800 }, { "epoch": 0.4451275884951988, "grad_norm": 0.0747079998254776, "learning_rate": 6.248188944790933e-07, "loss": 0.0064, "step": 9810 }, { "epoch": 0.445581337311198, "grad_norm": 0.05021276697516441, "learning_rate": 6.146322884178591e-07, "loss": 0.0076, "step": 9820 }, { "epoch": 0.4460350861271971, "grad_norm": 0.1390632688999176, "learning_rate": 6.045267705893043e-07, "loss": 0.0081, "step": 9830 }, { "epoch": 0.4464888349431963, "grad_norm": 0.08714640885591507, "learning_rate": 5.945024283036549e-07, "loss": 0.0074, "step": 9840 }, { "epoch": 0.4469425837591955, "grad_norm": 0.07252706587314606, "learning_rate": 5.845593481697931e-07, "loss": 0.0078, "step": 9850 }, { "epoch": 0.4473963325751947, "grad_norm": 0.10125784575939178, "learning_rate": 5.746976160945051e-07, "loss": 0.0083, "step": 9860 }, { "epoch": 0.44785008139119387, "grad_norm": 0.16219675540924072, "learning_rate": 5.649173172817457e-07, "loss": 0.0105, "step": 9870 }, { "epoch": 0.44830383020719305, "grad_norm": 0.12300454825162888, "learning_rate": 5.55218536231894e-07, "loss": 0.011, "step": 9880 }, { "epoch": 0.44875757902319224, "grad_norm": 0.07039348036050797, "learning_rate": 5.456013567410312e-07, "loss": 0.0079, "step": 9890 }, { "epoch": 0.44921132783919143, "grad_norm": 0.10232234746217728, "learning_rate": 5.360658619002068e-07, "loss": 0.0105, "step": 9900 }, { "epoch": 0.4496650766551906, "grad_norm": 0.0777553990483284, "learning_rate": 5.266121340947327e-07, "loss": 0.0081, "step": 9910 }, { "epoch": 0.4501188254711898, "grad_norm": 0.08132746815681458, "learning_rate": 5.172402550034639e-07, "loss": 0.0097, "step": 9920 }, { "epoch": 0.45057257428718894, "grad_norm": 0.04767317324876785, "learning_rate": 5.079503055980939e-07, "loss": 0.0076, "step": 9930 }, { "epoch": 0.45102632310318813, "grad_norm": 0.07064193487167358, "learning_rate": 4.987423661424517e-07, "loss": 0.009, "step": 9940 }, { "epoch": 0.4514800719191873, "grad_norm": 0.07851279526948929, "learning_rate": 4.896165161918176e-07, "loss": 0.0088, "step": 9950 }, { "epoch": 0.4519338207351865, "grad_norm": 0.12864693999290466, "learning_rate": 4.805728345922267e-07, "loss": 0.0082, "step": 9960 }, { "epoch": 0.4523875695511857, "grad_norm": 0.11067596822977066, "learning_rate": 4.716113994797944e-07, "loss": 0.0119, "step": 9970 }, { "epoch": 0.4528413183671849, "grad_norm": 0.08597382158041, "learning_rate": 4.627322882800345e-07, "loss": 0.0102, "step": 9980 }, { "epoch": 0.4532950671831841, "grad_norm": 0.10068463534116745, "learning_rate": 4.5393557770719744e-07, "loss": 0.0099, "step": 9990 }, { "epoch": 0.45374881599918326, "grad_norm": 0.14817091822624207, "learning_rate": 4.4522134376359995e-07, "loss": 0.0094, "step": 10000 }, { "epoch": 0.45420256481518245, "grad_norm": 0.10317414999008179, "learning_rate": 4.3658966173897866e-07, "loss": 0.0087, "step": 10010 }, { "epoch": 0.45465631363118164, "grad_norm": 0.1607348471879959, "learning_rate": 4.2804060620982747e-07, "loss": 0.0073, "step": 10020 }, { "epoch": 0.4551100624471808, "grad_norm": 0.09899001568555832, "learning_rate": 4.1957425103876235e-07, "loss": 0.0094, "step": 10030 }, { "epoch": 0.45556381126317996, "grad_norm": 0.07764271646738052, "learning_rate": 4.111906693738799e-07, "loss": 0.0068, "step": 10040 }, { "epoch": 0.45601756007917915, "grad_norm": 0.09743394702672958, "learning_rate": 4.02889933648124e-07, "loss": 0.0088, "step": 10050 }, { "epoch": 0.45647130889517834, "grad_norm": 0.07267738878726959, "learning_rate": 3.946721155786615e-07, "loss": 0.0063, "step": 10060 }, { "epoch": 0.45692505771117753, "grad_norm": 0.1014907956123352, "learning_rate": 3.865372861662664e-07, "loss": 0.0084, "step": 10070 }, { "epoch": 0.4573788065271767, "grad_norm": 0.1163657158613205, "learning_rate": 3.784855156946965e-07, "loss": 0.0085, "step": 10080 }, { "epoch": 0.4578325553431759, "grad_norm": 0.10800126194953918, "learning_rate": 3.705168737300968e-07, "loss": 0.0115, "step": 10090 }, { "epoch": 0.4582863041591751, "grad_norm": 0.0844917818903923, "learning_rate": 3.626314291203914e-07, "loss": 0.0096, "step": 10100 }, { "epoch": 0.4587400529751743, "grad_norm": 0.11503920704126358, "learning_rate": 3.548292499946937e-07, "loss": 0.0091, "step": 10110 }, { "epoch": 0.4591938017911735, "grad_norm": 0.08369031548500061, "learning_rate": 3.4711040376271264e-07, "loss": 0.0082, "step": 10120 }, { "epoch": 0.45964755060717266, "grad_norm": 0.08376123011112213, "learning_rate": 3.394749571141731e-07, "loss": 0.0089, "step": 10130 }, { "epoch": 0.4601012994231718, "grad_norm": 0.15638533234596252, "learning_rate": 3.319229760182441e-07, "loss": 0.0099, "step": 10140 }, { "epoch": 0.460555048239171, "grad_norm": 0.1118149682879448, "learning_rate": 3.244545257229559e-07, "loss": 0.0113, "step": 10150 }, { "epoch": 0.46100879705517017, "grad_norm": 0.12428905069828033, "learning_rate": 3.170696707546539e-07, "loss": 0.0076, "step": 10160 }, { "epoch": 0.46146254587116936, "grad_norm": 0.11655561625957489, "learning_rate": 3.0976847491742347e-07, "loss": 0.0095, "step": 10170 }, { "epoch": 0.46191629468716855, "grad_norm": 0.0856955498456955, "learning_rate": 3.0255100129255364e-07, "loss": 0.0085, "step": 10180 }, { "epoch": 0.46237004350316774, "grad_norm": 0.13790924847126007, "learning_rate": 2.9541731223797997e-07, "loss": 0.0089, "step": 10190 }, { "epoch": 0.4628237923191669, "grad_norm": 0.07870922982692719, "learning_rate": 2.883674693877558e-07, "loss": 0.0084, "step": 10200 }, { "epoch": 0.4632775411351661, "grad_norm": 0.04750875383615494, "learning_rate": 2.8140153365151304e-07, "loss": 0.0109, "step": 10210 }, { "epoch": 0.4637312899511653, "grad_norm": 0.0392727330327034, "learning_rate": 2.7451956521393983e-07, "loss": 0.0086, "step": 10220 }, { "epoch": 0.4641850387671645, "grad_norm": 0.09652996808290482, "learning_rate": 2.677216235342561e-07, "loss": 0.0086, "step": 10230 }, { "epoch": 0.4646387875831636, "grad_norm": 0.10550557076931, "learning_rate": 2.6100776734570345e-07, "loss": 0.0103, "step": 10240 }, { "epoch": 0.4650925363991628, "grad_norm": 0.0862097516655922, "learning_rate": 2.543780546550401e-07, "loss": 0.0089, "step": 10250 }, { "epoch": 0.465546285215162, "grad_norm": 0.15287438035011292, "learning_rate": 2.478325427420336e-07, "loss": 0.0092, "step": 10260 }, { "epoch": 0.4660000340311612, "grad_norm": 0.07247801125049591, "learning_rate": 2.4137128815896803e-07, "loss": 0.0098, "step": 10270 }, { "epoch": 0.4664537828471604, "grad_norm": 0.11457608640193939, "learning_rate": 2.3499434673015852e-07, "loss": 0.0088, "step": 10280 }, { "epoch": 0.46690753166315957, "grad_norm": 0.06932705640792847, "learning_rate": 2.2870177355146406e-07, "loss": 0.0087, "step": 10290 }, { "epoch": 0.46736128047915876, "grad_norm": 0.0982157438993454, "learning_rate": 2.2249362298981892e-07, "loss": 0.0112, "step": 10300 }, { "epoch": 0.46781502929515795, "grad_norm": 0.09763089567422867, "learning_rate": 2.1636994868275085e-07, "loss": 0.0071, "step": 10310 }, { "epoch": 0.46826877811115714, "grad_norm": 0.09539797157049179, "learning_rate": 2.1033080353793144e-07, "loss": 0.0081, "step": 10320 }, { "epoch": 0.4687225269271563, "grad_norm": 0.08834879100322723, "learning_rate": 2.043762397327087e-07, "loss": 0.0084, "step": 10330 }, { "epoch": 0.46917627574315546, "grad_norm": 0.13164784014225006, "learning_rate": 1.985063087136596e-07, "loss": 0.0075, "step": 10340 }, { "epoch": 0.46963002455915465, "grad_norm": 0.07892737537622452, "learning_rate": 1.927210611961494e-07, "loss": 0.0086, "step": 10350 }, { "epoch": 0.47008377337515383, "grad_norm": 0.10719600319862366, "learning_rate": 1.870205471638864e-07, "loss": 0.0077, "step": 10360 }, { "epoch": 0.470537522191153, "grad_norm": 0.09440305829048157, "learning_rate": 1.814048158684978e-07, "loss": 0.0081, "step": 10370 }, { "epoch": 0.4709912710071522, "grad_norm": 0.12040349096059799, "learning_rate": 1.7587391582909452e-07, "loss": 0.0086, "step": 10380 }, { "epoch": 0.4714450198231514, "grad_norm": 0.08868300169706345, "learning_rate": 1.7042789483186273e-07, "loss": 0.0091, "step": 10390 }, { "epoch": 0.4718987686391506, "grad_norm": 0.08641085773706436, "learning_rate": 1.6506679992964292e-07, "loss": 0.0077, "step": 10400 }, { "epoch": 0.4723525174551498, "grad_norm": 0.11269844323396683, "learning_rate": 1.597906774415281e-07, "loss": 0.0082, "step": 10410 }, { "epoch": 0.47280626627114897, "grad_norm": 0.09324368089437485, "learning_rate": 1.5459957295245965e-07, "loss": 0.0087, "step": 10420 }, { "epoch": 0.47326001508714816, "grad_norm": 0.1024489626288414, "learning_rate": 1.494935313128376e-07, "loss": 0.008, "step": 10430 }, { "epoch": 0.4737137639031473, "grad_norm": 0.11675508320331573, "learning_rate": 1.4447259663812886e-07, "loss": 0.0085, "step": 10440 }, { "epoch": 0.4741675127191465, "grad_norm": 0.09133914858102798, "learning_rate": 1.395368123084917e-07, "loss": 0.0064, "step": 10450 }, { "epoch": 0.47462126153514567, "grad_norm": 0.11341153830289841, "learning_rate": 1.3468622096839524e-07, "loss": 0.0099, "step": 10460 }, { "epoch": 0.47507501035114486, "grad_norm": 0.07918799668550491, "learning_rate": 1.2992086452625175e-07, "loss": 0.0072, "step": 10470 }, { "epoch": 0.47552875916714404, "grad_norm": 0.10346852988004684, "learning_rate": 1.252407841540626e-07, "loss": 0.009, "step": 10480 }, { "epoch": 0.47598250798314323, "grad_norm": 0.09207387268543243, "learning_rate": 1.2064602028704742e-07, "loss": 0.0082, "step": 10490 }, { "epoch": 0.4764362567991424, "grad_norm": 0.08007527887821198, "learning_rate": 1.1613661262331099e-07, "loss": 0.0082, "step": 10500 }, { "epoch": 0.4768900056151416, "grad_norm": 0.1142473816871643, "learning_rate": 1.1171260012348805e-07, "loss": 0.0093, "step": 10510 }, { "epoch": 0.4773437544311408, "grad_norm": 0.07748722285032272, "learning_rate": 1.0737402101041349e-07, "loss": 0.0081, "step": 10520 }, { "epoch": 0.47779750324714, "grad_norm": 0.07912327349185944, "learning_rate": 1.0312091276878821e-07, "loss": 0.0085, "step": 10530 }, { "epoch": 0.4782512520631391, "grad_norm": 0.08111916482448578, "learning_rate": 9.895331214485937e-08, "loss": 0.0082, "step": 10540 }, { "epoch": 0.4787050008791383, "grad_norm": 0.0999038890004158, "learning_rate": 9.487125514610063e-08, "loss": 0.0082, "step": 10550 }, { "epoch": 0.4791587496951375, "grad_norm": 0.12247255444526672, "learning_rate": 9.087477704089686e-08, "loss": 0.0083, "step": 10560 }, { "epoch": 0.4796124985111367, "grad_norm": 0.1112070307135582, "learning_rate": 8.696391235824886e-08, "loss": 0.0092, "step": 10570 }, { "epoch": 0.4800662473271359, "grad_norm": 0.14070284366607666, "learning_rate": 8.313869488746574e-08, "loss": 0.0077, "step": 10580 }, { "epoch": 0.48051999614313506, "grad_norm": 0.38136252760887146, "learning_rate": 7.939915767787853e-08, "loss": 0.0063, "step": 10590 }, { "epoch": 0.48097374495913425, "grad_norm": 0.09036213904619217, "learning_rate": 7.574533303855491e-08, "loss": 0.0094, "step": 10600 }, { "epoch": 0.48142749377513344, "grad_norm": 0.10419604927301407, "learning_rate": 7.217725253801488e-08, "loss": 0.0091, "step": 10610 }, { "epoch": 0.48188124259113263, "grad_norm": 0.0749603733420372, "learning_rate": 6.869494700396328e-08, "loss": 0.0085, "step": 10620 }, { "epoch": 0.4823349914071318, "grad_norm": 0.0869176909327507, "learning_rate": 6.529844652301997e-08, "loss": 0.0104, "step": 10630 }, { "epoch": 0.482788740223131, "grad_norm": 0.09356246143579483, "learning_rate": 6.19877804404645e-08, "loss": 0.0066, "step": 10640 }, { "epoch": 0.48324248903913014, "grad_norm": 0.10017301142215729, "learning_rate": 5.876297735997738e-08, "loss": 0.0088, "step": 10650 }, { "epoch": 0.48369623785512933, "grad_norm": 0.11077237874269485, "learning_rate": 5.562406514339369e-08, "loss": 0.0081, "step": 10660 }, { "epoch": 0.4841499866711285, "grad_norm": 0.08762015402317047, "learning_rate": 5.257107091046654e-08, "loss": 0.0075, "step": 10670 }, { "epoch": 0.4846037354871277, "grad_norm": 0.0814470574259758, "learning_rate": 4.9604021038628384e-08, "loss": 0.0079, "step": 10680 }, { "epoch": 0.4850574843031269, "grad_norm": 0.13533402979373932, "learning_rate": 4.6722941162764546e-08, "loss": 0.0082, "step": 10690 }, { "epoch": 0.4855112331191261, "grad_norm": 0.2084999531507492, "learning_rate": 4.392785617499451e-08, "loss": 0.0084, "step": 10700 }, { "epoch": 0.4859649819351253, "grad_norm": 0.11600790172815323, "learning_rate": 4.1218790224450965e-08, "loss": 0.0099, "step": 10710 }, { "epoch": 0.48641873075112446, "grad_norm": 0.09649141132831573, "learning_rate": 3.859576671707554e-08, "loss": 0.0083, "step": 10720 }, { "epoch": 0.48687247956712365, "grad_norm": 0.10055869072675705, "learning_rate": 3.605880831541564e-08, "loss": 0.0107, "step": 10730 }, { "epoch": 0.48732622838312284, "grad_norm": 0.09977150708436966, "learning_rate": 3.36079369384279e-08, "loss": 0.0106, "step": 10740 }, { "epoch": 0.487779977199122, "grad_norm": 0.0789194107055664, "learning_rate": 3.124317376129171e-08, "loss": 0.0059, "step": 10750 }, { "epoch": 0.48823372601512116, "grad_norm": 0.11875753104686737, "learning_rate": 2.8964539215220468e-08, "loss": 0.0087, "step": 10760 }, { "epoch": 0.48868747483112035, "grad_norm": 0.1011434942483902, "learning_rate": 2.6772052987290575e-08, "loss": 0.0078, "step": 10770 }, { "epoch": 0.48914122364711954, "grad_norm": 0.045645855367183685, "learning_rate": 2.4665734020270503e-08, "loss": 0.0077, "step": 10780 }, { "epoch": 0.4895949724631187, "grad_norm": 0.07065833359956741, "learning_rate": 2.2645600512452016e-08, "loss": 0.009, "step": 10790 }, { "epoch": 0.4900487212791179, "grad_norm": 0.09284251928329468, "learning_rate": 2.0711669917501398e-08, "loss": 0.0069, "step": 10800 }, { "epoch": 0.4905024700951171, "grad_norm": 0.11340663582086563, "learning_rate": 1.8863958944300708e-08, "loss": 0.0091, "step": 10810 }, { "epoch": 0.4909562189111163, "grad_norm": 0.10025469958782196, "learning_rate": 1.710248355680788e-08, "loss": 0.0099, "step": 10820 }, { "epoch": 0.4914099677271155, "grad_norm": 0.0889265239238739, "learning_rate": 1.5427258973919058e-08, "loss": 0.0079, "step": 10830 }, { "epoch": 0.49186371654311467, "grad_norm": 0.09795159846544266, "learning_rate": 1.3838299669334255e-08, "loss": 0.0075, "step": 10840 }, { "epoch": 0.4923174653591138, "grad_norm": 0.07020303606987, "learning_rate": 1.2335619371434126e-08, "loss": 0.0073, "step": 10850 }, { "epoch": 0.492771214175113, "grad_norm": 0.07398790121078491, "learning_rate": 1.0919231063161173e-08, "loss": 0.0081, "step": 10860 }, { "epoch": 0.4932249629911122, "grad_norm": 0.09775375574827194, "learning_rate": 9.589146981907604e-09, "loss": 0.0077, "step": 10870 }, { "epoch": 0.49367871180711137, "grad_norm": 0.08531615883111954, "learning_rate": 8.345378619408762e-09, "loss": 0.0062, "step": 10880 }, { "epoch": 0.49413246062311056, "grad_norm": 0.10347537696361542, "learning_rate": 7.187936721646527e-09, "loss": 0.0089, "step": 10890 }, { "epoch": 0.49458620943910975, "grad_norm": 0.05376635491847992, "learning_rate": 6.116831288751624e-09, "loss": 0.009, "step": 10900 }, { "epoch": 0.49503995825510894, "grad_norm": 0.09046763926744461, "learning_rate": 5.13207157492257e-09, "loss": 0.0085, "step": 10910 }, { "epoch": 0.4954937070711081, "grad_norm": 0.1002441793680191, "learning_rate": 4.233666088341304e-09, "loss": 0.009, "step": 10920 }, { "epoch": 0.4959474558871073, "grad_norm": 0.14297433197498322, "learning_rate": 3.4216225911032354e-09, "loss": 0.0086, "step": 10930 }, { "epoch": 0.4964012047031065, "grad_norm": 0.09768819063901901, "learning_rate": 2.6959480991484157e-09, "loss": 0.0071, "step": 10940 }, { "epoch": 0.49685495351910564, "grad_norm": 0.12937182188034058, "learning_rate": 2.0566488821993635e-09, "loss": 0.0107, "step": 10950 }, { "epoch": 0.4973087023351048, "grad_norm": 0.1157827377319336, "learning_rate": 1.503730463709996e-09, "loss": 0.0068, "step": 10960 }, { "epoch": 0.497762451151104, "grad_norm": 0.13335159420967102, "learning_rate": 1.0371976208167766e-09, "loss": 0.0105, "step": 10970 }, { "epoch": 0.4982161999671032, "grad_norm": 0.0776859000325203, "learning_rate": 6.570543842965293e-10, "loss": 0.0088, "step": 10980 }, { "epoch": 0.4986699487831024, "grad_norm": 0.06962829828262329, "learning_rate": 3.6330403853201966e-10, "loss": 0.0066, "step": 10990 }, { "epoch": 0.4991236975991016, "grad_norm": 0.08173432946205139, "learning_rate": 1.5594912148420017e-10, "loss": 0.0093, "step": 11000 }, { "epoch": 0.49957744641510077, "grad_norm": 0.10342676937580109, "learning_rate": 3.49914246700056e-11, "loss": 0.0117, "step": 11010 }, { "epoch": 0.4999858203495, "step": 11019, "total_flos": 1.202267044973432e+19, "train_loss": 0.0151625880448374, "train_runtime": 117219.5601, "train_samples_per_second": 0.752, "train_steps_per_second": 0.094 } ], "logging_steps": 10, "max_steps": 11019, "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": 1.202267044973432e+19, "train_batch_size": 1, "trial_name": null, "trial_params": null }