{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 9864, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0010138710229324953, "grad_norm": 54.065914154052734, "learning_rate": 6.081081081081082e-07, "loss": 1.520133113861084, "step": 10 }, { "epoch": 0.0020277420458649905, "grad_norm": 24.033771514892578, "learning_rate": 1.2837837837837838e-06, "loss": 0.27851874828338624, "step": 20 }, { "epoch": 0.003041613068797486, "grad_norm": 16.095767974853516, "learning_rate": 1.9594594594594595e-06, "loss": 0.2259448528289795, "step": 30 }, { "epoch": 0.004055484091729981, "grad_norm": 17.86259651184082, "learning_rate": 2.6351351351351353e-06, "loss": 0.21848561763763427, "step": 40 }, { "epoch": 0.005069355114662476, "grad_norm": 15.440773963928223, "learning_rate": 3.310810810810811e-06, "loss": 0.22158634662628174, "step": 50 }, { "epoch": 0.006083226137594972, "grad_norm": 10.876513481140137, "learning_rate": 3.986486486486487e-06, "loss": 0.23932509422302245, "step": 60 }, { "epoch": 0.0070970971605274664, "grad_norm": 9.157422065734863, "learning_rate": 4.6621621621621625e-06, "loss": 0.21273837089538575, "step": 70 }, { "epoch": 0.008110968183459962, "grad_norm": 10.485193252563477, "learning_rate": 5.337837837837838e-06, "loss": 0.23638854026794434, "step": 80 }, { "epoch": 0.009124839206392456, "grad_norm": 8.743518829345703, "learning_rate": 6.013513513513514e-06, "loss": 0.22891027927398683, "step": 90 }, { "epoch": 0.010138710229324952, "grad_norm": 8.005756378173828, "learning_rate": 6.689189189189191e-06, "loss": 0.20653209686279297, "step": 100 }, { "epoch": 0.011152581252257448, "grad_norm": 8.85816478729248, "learning_rate": 7.3648648648648655e-06, "loss": 0.24246582984924317, "step": 110 }, { "epoch": 0.012166452275189943, "grad_norm": 14.67863941192627, "learning_rate": 8.040540540540541e-06, "loss": 0.2229517936706543, "step": 120 }, { "epoch": 0.013180323298122437, "grad_norm": 9.709903717041016, "learning_rate": 8.716216216216217e-06, "loss": 0.22794766426086427, "step": 130 }, { "epoch": 0.014194194321054933, "grad_norm": 10.03411865234375, "learning_rate": 9.391891891891893e-06, "loss": 0.2263890266418457, "step": 140 }, { "epoch": 0.015208065343987429, "grad_norm": 16.272846221923828, "learning_rate": 1.0067567567567569e-05, "loss": 0.2167212963104248, "step": 150 }, { "epoch": 0.016221936366919924, "grad_norm": 4.539907455444336, "learning_rate": 1.0743243243243244e-05, "loss": 0.1908333420753479, "step": 160 }, { "epoch": 0.01723580738985242, "grad_norm": 10.159111976623535, "learning_rate": 1.141891891891892e-05, "loss": 0.1988150954246521, "step": 170 }, { "epoch": 0.018249678412784912, "grad_norm": 8.252718925476074, "learning_rate": 1.2094594594594596e-05, "loss": 0.19948232173919678, "step": 180 }, { "epoch": 0.019263549435717408, "grad_norm": 8.020528793334961, "learning_rate": 1.2770270270270272e-05, "loss": 0.2007739305496216, "step": 190 }, { "epoch": 0.020277420458649904, "grad_norm": 14.875117301940918, "learning_rate": 1.3445945945945946e-05, "loss": 0.23172152042388916, "step": 200 }, { "epoch": 0.0212912914815824, "grad_norm": 5.547830581665039, "learning_rate": 1.4121621621621621e-05, "loss": 0.21770195960998534, "step": 210 }, { "epoch": 0.022305162504514895, "grad_norm": 14.017234802246094, "learning_rate": 1.4797297297297299e-05, "loss": 0.20420165061950685, "step": 220 }, { "epoch": 0.02331903352744739, "grad_norm": 6.951585292816162, "learning_rate": 1.5472972972972976e-05, "loss": 0.19893283843994142, "step": 230 }, { "epoch": 0.024332904550379886, "grad_norm": 3.905736207962036, "learning_rate": 1.614864864864865e-05, "loss": 0.19842545986175536, "step": 240 }, { "epoch": 0.02534677557331238, "grad_norm": 6.121711254119873, "learning_rate": 1.6824324324324324e-05, "loss": 0.20475029945373535, "step": 250 }, { "epoch": 0.026360646596244874, "grad_norm": 6.5915937423706055, "learning_rate": 1.7500000000000002e-05, "loss": 0.21211562156677247, "step": 260 }, { "epoch": 0.02737451761917737, "grad_norm": 7.251730918884277, "learning_rate": 1.8175675675675676e-05, "loss": 0.2100444555282593, "step": 270 }, { "epoch": 0.028388388642109866, "grad_norm": 9.88249397277832, "learning_rate": 1.8851351351351353e-05, "loss": 0.2181532859802246, "step": 280 }, { "epoch": 0.02940225966504236, "grad_norm": 4.603264808654785, "learning_rate": 1.9527027027027027e-05, "loss": 0.2107445478439331, "step": 290 }, { "epoch": 0.030416130687974857, "grad_norm": 4.215793132781982, "learning_rate": 1.999999514856865e-05, "loss": 0.18826016187667846, "step": 300 }, { "epoch": 0.03143000171090735, "grad_norm": 4.64166259765625, "learning_rate": 1.999990890103106e-05, "loss": 0.19252219200134277, "step": 310 }, { "epoch": 0.03244387273383985, "grad_norm": 4.882780075073242, "learning_rate": 1.999971484497808e-05, "loss": 0.19978002309799195, "step": 320 }, { "epoch": 0.033457743756772344, "grad_norm": 3.3688063621520996, "learning_rate": 1.9999412982501806e-05, "loss": 0.18030136823654175, "step": 330 }, { "epoch": 0.03447161477970484, "grad_norm": 6.338453769683838, "learning_rate": 1.9999003316856605e-05, "loss": 0.18263598680496215, "step": 340 }, { "epoch": 0.03548548580263733, "grad_norm": 6.052334785461426, "learning_rate": 1.9998485852459068e-05, "loss": 0.17920044660568238, "step": 350 }, { "epoch": 0.036499356825569824, "grad_norm": 4.058633327484131, "learning_rate": 1.9997860594887947e-05, "loss": 0.2006176471710205, "step": 360 }, { "epoch": 0.03751322784850232, "grad_norm": 10.05197525024414, "learning_rate": 1.9997127550884116e-05, "loss": 0.2089214563369751, "step": 370 }, { "epoch": 0.038527098871434816, "grad_norm": 4.922497749328613, "learning_rate": 1.9996286728350484e-05, "loss": 0.19474167823791505, "step": 380 }, { "epoch": 0.03954096989436731, "grad_norm": 5.406052112579346, "learning_rate": 1.9995338136351913e-05, "loss": 0.2053391933441162, "step": 390 }, { "epoch": 0.04055484091729981, "grad_norm": 5.817878246307373, "learning_rate": 1.9994281785115127e-05, "loss": 0.19281054735183717, "step": 400 }, { "epoch": 0.0415687119402323, "grad_norm": 4.665223121643066, "learning_rate": 1.9993117686028603e-05, "loss": 0.17888987064361572, "step": 410 }, { "epoch": 0.0425825829631648, "grad_norm": 9.750685691833496, "learning_rate": 1.9991845851642426e-05, "loss": 0.2079761505126953, "step": 420 }, { "epoch": 0.043596453986097294, "grad_norm": 5.4740986824035645, "learning_rate": 1.999046629566818e-05, "loss": 0.1942216396331787, "step": 430 }, { "epoch": 0.04461032500902979, "grad_norm": 5.590164661407471, "learning_rate": 1.998897903297879e-05, "loss": 0.2099510669708252, "step": 440 }, { "epoch": 0.045624196031962286, "grad_norm": 8.225191116333008, "learning_rate": 1.9987384079608362e-05, "loss": 0.1906811237335205, "step": 450 }, { "epoch": 0.04663806705489478, "grad_norm": 5.6593098640441895, "learning_rate": 1.998568145275201e-05, "loss": 0.2013000249862671, "step": 460 }, { "epoch": 0.04765193807782728, "grad_norm": 2.916322708129883, "learning_rate": 1.998387117076566e-05, "loss": 0.20088567733764648, "step": 470 }, { "epoch": 0.04866580910075977, "grad_norm": 4.850968837738037, "learning_rate": 1.998195325316588e-05, "loss": 0.19450520277023314, "step": 480 }, { "epoch": 0.04967968012369226, "grad_norm": 6.396564483642578, "learning_rate": 1.997992772062964e-05, "loss": 0.21461331844329834, "step": 490 }, { "epoch": 0.05069355114662476, "grad_norm": 9.471354484558105, "learning_rate": 1.9977794594994103e-05, "loss": 0.20871458053588868, "step": 500 }, { "epoch": 0.05170742216955725, "grad_norm": 2.8109402656555176, "learning_rate": 1.9975553899256388e-05, "loss": 0.19498629570007325, "step": 510 }, { "epoch": 0.05272129319248975, "grad_norm": 3.005371332168579, "learning_rate": 1.9973205657573328e-05, "loss": 0.19074337482452391, "step": 520 }, { "epoch": 0.053735164215422244, "grad_norm": 7.0671186447143555, "learning_rate": 1.99707498952612e-05, "loss": 0.1850874662399292, "step": 530 }, { "epoch": 0.05474903523835474, "grad_norm": 4.0884480476379395, "learning_rate": 1.9968186638795445e-05, "loss": 0.17661709785461427, "step": 540 }, { "epoch": 0.055762906261287236, "grad_norm": 6.148981094360352, "learning_rate": 1.9965515915810408e-05, "loss": 0.18472154140472413, "step": 550 }, { "epoch": 0.05677677728421973, "grad_norm": 4.966785430908203, "learning_rate": 1.9962737755099023e-05, "loss": 0.19710171222686768, "step": 560 }, { "epoch": 0.05779064830715223, "grad_norm": 4.06459379196167, "learning_rate": 1.9959852186612492e-05, "loss": 0.1921678066253662, "step": 570 }, { "epoch": 0.05880451933008472, "grad_norm": 5.011148929595947, "learning_rate": 1.995685924145999e-05, "loss": 0.1909174919128418, "step": 580 }, { "epoch": 0.05981839035301722, "grad_norm": 7.9923553466796875, "learning_rate": 1.9953758951908305e-05, "loss": 0.17002491950988768, "step": 590 }, { "epoch": 0.060832261375949714, "grad_norm": 4.800923824310303, "learning_rate": 1.995055135138151e-05, "loss": 0.18571338653564454, "step": 600 }, { "epoch": 0.06184613239888221, "grad_norm": 4.341009140014648, "learning_rate": 1.994723647446058e-05, "loss": 0.19407963752746582, "step": 610 }, { "epoch": 0.0628600034218147, "grad_norm": 2.858027458190918, "learning_rate": 1.994381435688303e-05, "loss": 0.1886829137802124, "step": 620 }, { "epoch": 0.0638738744447472, "grad_norm": 3.3556840419769287, "learning_rate": 1.994028503554255e-05, "loss": 0.1831519365310669, "step": 630 }, { "epoch": 0.0648877454676797, "grad_norm": 5.114283084869385, "learning_rate": 1.9936648548488568e-05, "loss": 0.19730255603790284, "step": 640 }, { "epoch": 0.06590161649061219, "grad_norm": 8.279708862304688, "learning_rate": 1.993290493492587e-05, "loss": 0.1874381422996521, "step": 650 }, { "epoch": 0.06691548751354469, "grad_norm": 7.098570823669434, "learning_rate": 1.9929054235214168e-05, "loss": 0.1768972396850586, "step": 660 }, { "epoch": 0.06792935853647718, "grad_norm": 6.150336265563965, "learning_rate": 1.992509649086766e-05, "loss": 0.15221590995788575, "step": 670 }, { "epoch": 0.06894322955940968, "grad_norm": 4.061022758483887, "learning_rate": 1.9921031744554588e-05, "loss": 0.21414330005645751, "step": 680 }, { "epoch": 0.06995710058234217, "grad_norm": 6.6819376945495605, "learning_rate": 1.991686004009678e-05, "loss": 0.1902976632118225, "step": 690 }, { "epoch": 0.07097097160527466, "grad_norm": 4.2416791915893555, "learning_rate": 1.991258142246917e-05, "loss": 0.19085474014282228, "step": 700 }, { "epoch": 0.07198484262820716, "grad_norm": 7.674250602722168, "learning_rate": 1.990819593779932e-05, "loss": 0.18513224124908448, "step": 710 }, { "epoch": 0.07299871365113965, "grad_norm": 5.179104328155518, "learning_rate": 1.9903703633366923e-05, "loss": 0.17377997636795045, "step": 720 }, { "epoch": 0.07401258467407215, "grad_norm": 8.237866401672363, "learning_rate": 1.9899104557603285e-05, "loss": 0.175753653049469, "step": 730 }, { "epoch": 0.07502645569700464, "grad_norm": 7.171549320220947, "learning_rate": 1.9894398760090807e-05, "loss": 0.21885242462158203, "step": 740 }, { "epoch": 0.07604032671993714, "grad_norm": 5.269348621368408, "learning_rate": 1.988958629156246e-05, "loss": 0.1912320375442505, "step": 750 }, { "epoch": 0.07705419774286963, "grad_norm": 2.7595841884613037, "learning_rate": 1.988466720390123e-05, "loss": 0.18940874338150024, "step": 760 }, { "epoch": 0.07806806876580213, "grad_norm": 5.689294815063477, "learning_rate": 1.9879641550139545e-05, "loss": 0.18036298751831054, "step": 770 }, { "epoch": 0.07908193978873462, "grad_norm": 5.79356575012207, "learning_rate": 1.9874509384458726e-05, "loss": 0.19173318147659302, "step": 780 }, { "epoch": 0.08009581081166713, "grad_norm": 3.286029577255249, "learning_rate": 1.9869270762188402e-05, "loss": 0.187531042098999, "step": 790 }, { "epoch": 0.08110968183459961, "grad_norm": 5.273270606994629, "learning_rate": 1.986392573980589e-05, "loss": 0.19191293716430663, "step": 800 }, { "epoch": 0.08212355285753212, "grad_norm": 4.944830894470215, "learning_rate": 1.9858474374935606e-05, "loss": 0.1794827938079834, "step": 810 }, { "epoch": 0.0831374238804646, "grad_norm": 2.850363254547119, "learning_rate": 1.9852916726348446e-05, "loss": 0.18593220710754393, "step": 820 }, { "epoch": 0.0841512949033971, "grad_norm": 2.694675922393799, "learning_rate": 1.9847252853961136e-05, "loss": 0.18177213668823242, "step": 830 }, { "epoch": 0.0851651659263296, "grad_norm": 5.168567180633545, "learning_rate": 1.98414828188356e-05, "loss": 0.18541338443756103, "step": 840 }, { "epoch": 0.08617903694926209, "grad_norm": 3.8705310821533203, "learning_rate": 1.98356066831783e-05, "loss": 0.18410418033599854, "step": 850 }, { "epoch": 0.08719290797219459, "grad_norm": 4.089294910430908, "learning_rate": 1.982962451033956e-05, "loss": 0.1832610011100769, "step": 860 }, { "epoch": 0.08820677899512708, "grad_norm": 3.4392645359039307, "learning_rate": 1.9823536364812875e-05, "loss": 0.17454156875610352, "step": 870 }, { "epoch": 0.08922065001805958, "grad_norm": 3.981369972229004, "learning_rate": 1.981734231223425e-05, "loss": 0.1648927688598633, "step": 880 }, { "epoch": 0.09023452104099207, "grad_norm": 6.308178424835205, "learning_rate": 1.9811042419381444e-05, "loss": 0.18655641078948976, "step": 890 }, { "epoch": 0.09124839206392457, "grad_norm": 4.906444549560547, "learning_rate": 1.980463675417329e-05, "loss": 0.17853434085845948, "step": 900 }, { "epoch": 0.09226226308685706, "grad_norm": 6.063106536865234, "learning_rate": 1.9798125385668942e-05, "loss": 0.1871834635734558, "step": 910 }, { "epoch": 0.09327613410978956, "grad_norm": 2.9892194271087646, "learning_rate": 1.9791508384067138e-05, "loss": 0.17658915519714355, "step": 920 }, { "epoch": 0.09429000513272205, "grad_norm": 4.633831977844238, "learning_rate": 1.9784785820705435e-05, "loss": 0.18573063611984253, "step": 930 }, { "epoch": 0.09530387615565455, "grad_norm": 5.638926982879639, "learning_rate": 1.9777957768059456e-05, "loss": 0.1791480302810669, "step": 940 }, { "epoch": 0.09631774717858704, "grad_norm": 7.189413070678711, "learning_rate": 1.977102429974209e-05, "loss": 0.18278396129608154, "step": 950 }, { "epoch": 0.09733161820151955, "grad_norm": 5.215597152709961, "learning_rate": 1.9763985490502714e-05, "loss": 0.1593470096588135, "step": 960 }, { "epoch": 0.09834548922445203, "grad_norm": 5.068212985992432, "learning_rate": 1.9756841416226372e-05, "loss": 0.19746614694595338, "step": 970 }, { "epoch": 0.09935936024738452, "grad_norm": 4.84002685546875, "learning_rate": 1.9749592153932974e-05, "loss": 0.18891273736953734, "step": 980 }, { "epoch": 0.10037323127031703, "grad_norm": 7.565490245819092, "learning_rate": 1.9742237781776455e-05, "loss": 0.1780113697052002, "step": 990 }, { "epoch": 0.10138710229324951, "grad_norm": 4.04754114151001, "learning_rate": 1.9734778379043923e-05, "loss": 0.19677281379699707, "step": 1000 }, { "epoch": 0.10240097331618202, "grad_norm": 3.9600181579589844, "learning_rate": 1.9727214026154827e-05, "loss": 0.17537347078323365, "step": 1010 }, { "epoch": 0.1034148443391145, "grad_norm": 5.7994232177734375, "learning_rate": 1.9719544804660084e-05, "loss": 0.19096342325210572, "step": 1020 }, { "epoch": 0.10442871536204701, "grad_norm": 9.362167358398438, "learning_rate": 1.9711770797241174e-05, "loss": 0.1922837734222412, "step": 1030 }, { "epoch": 0.1054425863849795, "grad_norm": 4.798088073730469, "learning_rate": 1.9703892087709287e-05, "loss": 0.15940141677856445, "step": 1040 }, { "epoch": 0.106456457407912, "grad_norm": 3.042177438735962, "learning_rate": 1.9695908761004392e-05, "loss": 0.1667789101600647, "step": 1050 }, { "epoch": 0.10747032843084449, "grad_norm": 3.674420118331909, "learning_rate": 1.9687820903194335e-05, "loss": 0.15515973567962646, "step": 1060 }, { "epoch": 0.10848419945377699, "grad_norm": 2.5263283252716064, "learning_rate": 1.9679628601473905e-05, "loss": 0.19042487144470216, "step": 1070 }, { "epoch": 0.10949807047670948, "grad_norm": 7.314944267272949, "learning_rate": 1.967133194416389e-05, "loss": 0.17966201305389404, "step": 1080 }, { "epoch": 0.11051194149964198, "grad_norm": 10.163249969482422, "learning_rate": 1.9662931020710138e-05, "loss": 0.19183292388916015, "step": 1090 }, { "epoch": 0.11152581252257447, "grad_norm": 2.9684982299804688, "learning_rate": 1.965442592168259e-05, "loss": 0.20674433708190917, "step": 1100 }, { "epoch": 0.11253968354550696, "grad_norm": 4.713918209075928, "learning_rate": 1.964581673877428e-05, "loss": 0.17251594066619874, "step": 1110 }, { "epoch": 0.11355355456843946, "grad_norm": 1.5363044738769531, "learning_rate": 1.9637103564800384e-05, "loss": 0.17438819408416747, "step": 1120 }, { "epoch": 0.11456742559137195, "grad_norm": 3.922895908355713, "learning_rate": 1.962828649369719e-05, "loss": 0.17682374715805055, "step": 1130 }, { "epoch": 0.11558129661430445, "grad_norm": 5.378303050994873, "learning_rate": 1.96193656205211e-05, "loss": 0.18028029203414916, "step": 1140 }, { "epoch": 0.11659516763723694, "grad_norm": 2.6935150623321533, "learning_rate": 1.9610341041447595e-05, "loss": 0.1798741936683655, "step": 1150 }, { "epoch": 0.11760903866016945, "grad_norm": 3.1230521202087402, "learning_rate": 1.9601212853770214e-05, "loss": 0.17196711301803588, "step": 1160 }, { "epoch": 0.11862290968310193, "grad_norm": 7.072906017303467, "learning_rate": 1.959198115589949e-05, "loss": 0.1969095826148987, "step": 1170 }, { "epoch": 0.11963678070603444, "grad_norm": 2.60880184173584, "learning_rate": 1.9582646047361888e-05, "loss": 0.16163069009780884, "step": 1180 }, { "epoch": 0.12065065172896693, "grad_norm": 1.5123794078826904, "learning_rate": 1.9573207628798747e-05, "loss": 0.17277970314025878, "step": 1190 }, { "epoch": 0.12166452275189943, "grad_norm": 2.2984704971313477, "learning_rate": 1.956366600196519e-05, "loss": 0.1937960147857666, "step": 1200 }, { "epoch": 0.12267839377483192, "grad_norm": 1.8616126775741577, "learning_rate": 1.9554021269729003e-05, "loss": 0.1671885848045349, "step": 1210 }, { "epoch": 0.12369226479776442, "grad_norm": 3.7106781005859375, "learning_rate": 1.9544273536069573e-05, "loss": 0.1698637366294861, "step": 1220 }, { "epoch": 0.12470613582069691, "grad_norm": 4.517592906951904, "learning_rate": 1.9534422906076714e-05, "loss": 0.18909647464752197, "step": 1230 }, { "epoch": 0.1257200068436294, "grad_norm": 2.5214335918426514, "learning_rate": 1.9524469485949586e-05, "loss": 0.18441424369812012, "step": 1240 }, { "epoch": 0.1267338778665619, "grad_norm": 5.038455486297607, "learning_rate": 1.9514413382995498e-05, "loss": 0.19644736051559447, "step": 1250 }, { "epoch": 0.1277477488894944, "grad_norm": 5.936961650848389, "learning_rate": 1.9504254705628806e-05, "loss": 0.17664324045181273, "step": 1260 }, { "epoch": 0.12876161991242688, "grad_norm": 2.198801279067993, "learning_rate": 1.9493993563369688e-05, "loss": 0.19271180629730225, "step": 1270 }, { "epoch": 0.1297754909353594, "grad_norm": 12.719691276550293, "learning_rate": 1.9483630066843005e-05, "loss": 0.1695432186126709, "step": 1280 }, { "epoch": 0.13078936195829188, "grad_norm": 2.3120219707489014, "learning_rate": 1.9473164327777095e-05, "loss": 0.16613447666168213, "step": 1290 }, { "epoch": 0.13180323298122437, "grad_norm": 5.115593433380127, "learning_rate": 1.9462596459002565e-05, "loss": 0.18397741317749022, "step": 1300 }, { "epoch": 0.13281710400415686, "grad_norm": 2.199949264526367, "learning_rate": 1.9451926574451074e-05, "loss": 0.16637964248657228, "step": 1310 }, { "epoch": 0.13383097502708938, "grad_norm": 2.485140085220337, "learning_rate": 1.944115478915412e-05, "loss": 0.1729670763015747, "step": 1320 }, { "epoch": 0.13484484605002187, "grad_norm": 4.5406365394592285, "learning_rate": 1.9430281219241767e-05, "loss": 0.17730602025985717, "step": 1330 }, { "epoch": 0.13585871707295435, "grad_norm": 2.678560972213745, "learning_rate": 1.9419305981941436e-05, "loss": 0.18363167047500611, "step": 1340 }, { "epoch": 0.13687258809588684, "grad_norm": 3.416365385055542, "learning_rate": 1.94082291955766e-05, "loss": 0.16623823642730712, "step": 1350 }, { "epoch": 0.13788645911881936, "grad_norm": 3.2021608352661133, "learning_rate": 1.939705097956554e-05, "loss": 0.1659439444541931, "step": 1360 }, { "epoch": 0.13890033014175185, "grad_norm": 3.1144473552703857, "learning_rate": 1.9385771454420048e-05, "loss": 0.17845301628112792, "step": 1370 }, { "epoch": 0.13991420116468434, "grad_norm": 5.1975274085998535, "learning_rate": 1.9374390741744107e-05, "loss": 0.17592031955718995, "step": 1380 }, { "epoch": 0.14092807218761683, "grad_norm": 7.63873815536499, "learning_rate": 1.9362908964232616e-05, "loss": 0.2012483596801758, "step": 1390 }, { "epoch": 0.14194194321054932, "grad_norm": 2.4830098152160645, "learning_rate": 1.9351326245670038e-05, "loss": 0.1835278034210205, "step": 1400 }, { "epoch": 0.14295581423348183, "grad_norm": 4.609010219573975, "learning_rate": 1.933964271092908e-05, "loss": 0.17810438871383666, "step": 1410 }, { "epoch": 0.14396968525641432, "grad_norm": 2.2308027744293213, "learning_rate": 1.932785848596934e-05, "loss": 0.1932157516479492, "step": 1420 }, { "epoch": 0.1449835562793468, "grad_norm": 3.1811892986297607, "learning_rate": 1.9315973697835966e-05, "loss": 0.17875434160232545, "step": 1430 }, { "epoch": 0.1459974273022793, "grad_norm": 2.3002524375915527, "learning_rate": 1.930398847465825e-05, "loss": 0.16362283229827881, "step": 1440 }, { "epoch": 0.14701129832521181, "grad_norm": 3.316676616668701, "learning_rate": 1.9291902945648283e-05, "loss": 0.16171934604644775, "step": 1450 }, { "epoch": 0.1480251693481443, "grad_norm": 2.781221628189087, "learning_rate": 1.9279717241099554e-05, "loss": 0.19271483421325683, "step": 1460 }, { "epoch": 0.1490390403710768, "grad_norm": 1.7318871021270752, "learning_rate": 1.9267431492385524e-05, "loss": 0.1767755389213562, "step": 1470 }, { "epoch": 0.15005291139400928, "grad_norm": 2.5098562240600586, "learning_rate": 1.925504583195823e-05, "loss": 0.16866325139999389, "step": 1480 }, { "epoch": 0.1510667824169418, "grad_norm": 2.1298861503601074, "learning_rate": 1.924256039334686e-05, "loss": 0.1762561321258545, "step": 1490 }, { "epoch": 0.15208065343987429, "grad_norm": 2.472111940383911, "learning_rate": 1.9229975311156305e-05, "loss": 0.1861296057701111, "step": 1500 }, { "epoch": 0.15309452446280677, "grad_norm": 2.915313482284546, "learning_rate": 1.9217290721065693e-05, "loss": 0.19158486127853394, "step": 1510 }, { "epoch": 0.15410839548573926, "grad_norm": 4.520017147064209, "learning_rate": 1.9204506759826957e-05, "loss": 0.17097247838974, "step": 1520 }, { "epoch": 0.15512226650867175, "grad_norm": 1.1512256860733032, "learning_rate": 1.9191623565263342e-05, "loss": 0.17486515045166015, "step": 1530 }, { "epoch": 0.15613613753160427, "grad_norm": 4.905345439910889, "learning_rate": 1.9178641276267922e-05, "loss": 0.17996604442596437, "step": 1540 }, { "epoch": 0.15715000855453676, "grad_norm": 1.692692518234253, "learning_rate": 1.91655600328021e-05, "loss": 0.17610858678817748, "step": 1550 }, { "epoch": 0.15816387957746925, "grad_norm": 5.815668106079102, "learning_rate": 1.91523799758941e-05, "loss": 0.16673849821090697, "step": 1560 }, { "epoch": 0.15917775060040174, "grad_norm": 5.642833232879639, "learning_rate": 1.9139101247637465e-05, "loss": 0.1701938271522522, "step": 1570 }, { "epoch": 0.16019162162333425, "grad_norm": 5.0546650886535645, "learning_rate": 1.912572399118949e-05, "loss": 0.1675083041191101, "step": 1580 }, { "epoch": 0.16120549264626674, "grad_norm": 3.982346296310425, "learning_rate": 1.9112248350769704e-05, "loss": 0.19020025730133056, "step": 1590 }, { "epoch": 0.16221936366919923, "grad_norm": 4.223562240600586, "learning_rate": 1.909867447165831e-05, "loss": 0.1673296093940735, "step": 1600 }, { "epoch": 0.16323323469213172, "grad_norm": 1.5704752206802368, "learning_rate": 1.908500250019462e-05, "loss": 0.16742819547653198, "step": 1610 }, { "epoch": 0.16424710571506423, "grad_norm": 6.003251552581787, "learning_rate": 1.9071232583775465e-05, "loss": 0.17273739576339722, "step": 1620 }, { "epoch": 0.16526097673799672, "grad_norm": 3.0065383911132812, "learning_rate": 1.9057364870853628e-05, "loss": 0.1541060209274292, "step": 1630 }, { "epoch": 0.1662748477609292, "grad_norm": 2.6820485591888428, "learning_rate": 1.904339951093622e-05, "loss": 0.1747200608253479, "step": 1640 }, { "epoch": 0.1672887187838617, "grad_norm": 4.330827713012695, "learning_rate": 1.902933665458309e-05, "loss": 0.17008296251296998, "step": 1650 }, { "epoch": 0.1683025898067942, "grad_norm": 3.6790735721588135, "learning_rate": 1.901517645340518e-05, "loss": 0.18094885349273682, "step": 1660 }, { "epoch": 0.1693164608297267, "grad_norm": 3.9152917861938477, "learning_rate": 1.900091906006291e-05, "loss": 0.18886241912841797, "step": 1670 }, { "epoch": 0.1703303318526592, "grad_norm": 2.6571097373962402, "learning_rate": 1.8986564628264527e-05, "loss": 0.18806593418121337, "step": 1680 }, { "epoch": 0.17134420287559168, "grad_norm": 2.1233229637145996, "learning_rate": 1.8972113312764432e-05, "loss": 0.16118054389953612, "step": 1690 }, { "epoch": 0.17235807389852417, "grad_norm": 3.058311939239502, "learning_rate": 1.895756526936153e-05, "loss": 0.1614047646522522, "step": 1700 }, { "epoch": 0.1733719449214567, "grad_norm": 2.524916172027588, "learning_rate": 1.8942920654897553e-05, "loss": 0.17712470293045043, "step": 1710 }, { "epoch": 0.17438581594438918, "grad_norm": 1.3714523315429688, "learning_rate": 1.8928179627255347e-05, "loss": 0.18684077262878418, "step": 1720 }, { "epoch": 0.17539968696732167, "grad_norm": 3.797271728515625, "learning_rate": 1.891334234535719e-05, "loss": 0.18001096248626708, "step": 1730 }, { "epoch": 0.17641355799025416, "grad_norm": 3.3112452030181885, "learning_rate": 1.8898408969163078e-05, "loss": 0.1629951000213623, "step": 1740 }, { "epoch": 0.17742742901318667, "grad_norm": 2.874302625656128, "learning_rate": 1.8883379659668987e-05, "loss": 0.18624918460845946, "step": 1750 }, { "epoch": 0.17844130003611916, "grad_norm": 4.887789249420166, "learning_rate": 1.8868254578905147e-05, "loss": 0.1874616861343384, "step": 1760 }, { "epoch": 0.17945517105905165, "grad_norm": 3.177999496459961, "learning_rate": 1.8853033889934293e-05, "loss": 0.15253348350524903, "step": 1770 }, { "epoch": 0.18046904208198414, "grad_norm": 2.826559543609619, "learning_rate": 1.883771775684991e-05, "loss": 0.15824637413024903, "step": 1780 }, { "epoch": 0.18148291310491665, "grad_norm": 4.109426021575928, "learning_rate": 1.882230634477446e-05, "loss": 0.17982494831085205, "step": 1790 }, { "epoch": 0.18249678412784914, "grad_norm": 5.088949203491211, "learning_rate": 1.8806799819857598e-05, "loss": 0.1891101598739624, "step": 1800 }, { "epoch": 0.18351065515078163, "grad_norm": 1.9347425699234009, "learning_rate": 1.8791198349274393e-05, "loss": 0.16663086414337158, "step": 1810 }, { "epoch": 0.18452452617371412, "grad_norm": 2.845951557159424, "learning_rate": 1.8775502101223516e-05, "loss": 0.1824922204017639, "step": 1820 }, { "epoch": 0.1855383971966466, "grad_norm": 3.4623749256134033, "learning_rate": 1.8759711244925424e-05, "loss": 0.16982486248016357, "step": 1830 }, { "epoch": 0.18655226821957913, "grad_norm": 1.8325976133346558, "learning_rate": 1.874382595062055e-05, "loss": 0.15325578451156616, "step": 1840 }, { "epoch": 0.18756613924251161, "grad_norm": 2.141446828842163, "learning_rate": 1.8727846389567457e-05, "loss": 0.17125388383865356, "step": 1850 }, { "epoch": 0.1885800102654441, "grad_norm": 4.792362689971924, "learning_rate": 1.871177273404098e-05, "loss": 0.18583623170852662, "step": 1860 }, { "epoch": 0.1895938812883766, "grad_norm": 2.8601365089416504, "learning_rate": 1.8695605157330398e-05, "loss": 0.15231878757476808, "step": 1870 }, { "epoch": 0.1906077523113091, "grad_norm": 2.5790035724639893, "learning_rate": 1.8679343833737546e-05, "loss": 0.1831616520881653, "step": 1880 }, { "epoch": 0.1916216233342416, "grad_norm": 3.038278341293335, "learning_rate": 1.8662988938574926e-05, "loss": 0.17072190046310426, "step": 1890 }, { "epoch": 0.1926354943571741, "grad_norm": 2.687863826751709, "learning_rate": 1.8646540648163853e-05, "loss": 0.16032761335372925, "step": 1900 }, { "epoch": 0.19364936538010658, "grad_norm": 3.4532766342163086, "learning_rate": 1.862999913983251e-05, "loss": 0.1771616220474243, "step": 1910 }, { "epoch": 0.1946632364030391, "grad_norm": 3.906498432159424, "learning_rate": 1.8613364591914073e-05, "loss": 0.16035499572753906, "step": 1920 }, { "epoch": 0.19567710742597158, "grad_norm": 3.620501756668091, "learning_rate": 1.8596637183744762e-05, "loss": 0.16395418643951415, "step": 1930 }, { "epoch": 0.19669097844890407, "grad_norm": 5.456326007843018, "learning_rate": 1.857981709566193e-05, "loss": 0.18343181610107423, "step": 1940 }, { "epoch": 0.19770484947183656, "grad_norm": 3.251154661178589, "learning_rate": 1.85629045090021e-05, "loss": 0.16939957141876222, "step": 1950 }, { "epoch": 0.19871872049476905, "grad_norm": 1.8900903463363647, "learning_rate": 1.854589960609902e-05, "loss": 0.1430753469467163, "step": 1960 }, { "epoch": 0.19973259151770156, "grad_norm": 4.313816070556641, "learning_rate": 1.8528802570281686e-05, "loss": 0.18892641067504884, "step": 1970 }, { "epoch": 0.20074646254063405, "grad_norm": 6.0279622077941895, "learning_rate": 1.851161358587239e-05, "loss": 0.16997485160827636, "step": 1980 }, { "epoch": 0.20176033356356654, "grad_norm": 4.766754150390625, "learning_rate": 1.8494332838184707e-05, "loss": 0.1887844681739807, "step": 1990 }, { "epoch": 0.20277420458649903, "grad_norm": 3.5042755603790283, "learning_rate": 1.847696051352151e-05, "loss": 0.16582064628601073, "step": 2000 }, { "epoch": 0.20378807560943155, "grad_norm": 2.0462892055511475, "learning_rate": 1.8459496799172957e-05, "loss": 0.16119011640548705, "step": 2010 }, { "epoch": 0.20480194663236403, "grad_norm": 8.056730270385742, "learning_rate": 1.8441941883414475e-05, "loss": 0.19488905668258666, "step": 2020 }, { "epoch": 0.20581581765529652, "grad_norm": 2.8844306468963623, "learning_rate": 1.8424295955504727e-05, "loss": 0.159842848777771, "step": 2030 }, { "epoch": 0.206829688678229, "grad_norm": 1.9913198947906494, "learning_rate": 1.840655920568358e-05, "loss": 0.17711122035980226, "step": 2040 }, { "epoch": 0.20784355970116153, "grad_norm": 3.0647897720336914, "learning_rate": 1.838873182517004e-05, "loss": 0.17203614711761475, "step": 2050 }, { "epoch": 0.20885743072409402, "grad_norm": 3.8819925785064697, "learning_rate": 1.83708140061602e-05, "loss": 0.17960208654403687, "step": 2060 }, { "epoch": 0.2098713017470265, "grad_norm": 4.275032997131348, "learning_rate": 1.835280594182517e-05, "loss": 0.1667160987854004, "step": 2070 }, { "epoch": 0.210885172769959, "grad_norm": 2.1576082706451416, "learning_rate": 1.833470782630898e-05, "loss": 0.1786700129508972, "step": 2080 }, { "epoch": 0.21189904379289148, "grad_norm": 4.163649082183838, "learning_rate": 1.831651985472651e-05, "loss": 0.16972904205322265, "step": 2090 }, { "epoch": 0.212912914815824, "grad_norm": 5.163391590118408, "learning_rate": 1.8298242223161362e-05, "loss": 0.18543204069137573, "step": 2100 }, { "epoch": 0.2139267858387565, "grad_norm": 2.9441566467285156, "learning_rate": 1.827987512866377e-05, "loss": 0.1635942578315735, "step": 2110 }, { "epoch": 0.21494065686168898, "grad_norm": 4.517545700073242, "learning_rate": 1.826141876924845e-05, "loss": 0.17161061763763427, "step": 2120 }, { "epoch": 0.21595452788462147, "grad_norm": 7.296326160430908, "learning_rate": 1.8242873343892494e-05, "loss": 0.1961526393890381, "step": 2130 }, { "epoch": 0.21696839890755398, "grad_norm": 2.4989607334136963, "learning_rate": 1.8224239052533194e-05, "loss": 0.17404482364654542, "step": 2140 }, { "epoch": 0.21798226993048647, "grad_norm": 3.246403217315674, "learning_rate": 1.820551609606591e-05, "loss": 0.17169376611709594, "step": 2150 }, { "epoch": 0.21899614095341896, "grad_norm": 1.8820948600769043, "learning_rate": 1.81867046763419e-05, "loss": 0.1829328179359436, "step": 2160 }, { "epoch": 0.22001001197635145, "grad_norm": 3.347292184829712, "learning_rate": 1.816780499616613e-05, "loss": 0.18234559297561645, "step": 2170 }, { "epoch": 0.22102388299928397, "grad_norm": 3.4207775592803955, "learning_rate": 1.81488172592951e-05, "loss": 0.16770377159118652, "step": 2180 }, { "epoch": 0.22203775402221645, "grad_norm": 2.304325819015503, "learning_rate": 1.812974167043465e-05, "loss": 0.17140578031539916, "step": 2190 }, { "epoch": 0.22305162504514894, "grad_norm": 2.789093494415283, "learning_rate": 1.8110578435237748e-05, "loss": 0.17390357255935668, "step": 2200 }, { "epoch": 0.22406549606808143, "grad_norm": 3.6614654064178467, "learning_rate": 1.8091327760302267e-05, "loss": 0.1794888496398926, "step": 2210 }, { "epoch": 0.22507936709101392, "grad_norm": 9.684952735900879, "learning_rate": 1.8071989853168765e-05, "loss": 0.21230728626251222, "step": 2220 }, { "epoch": 0.22609323811394644, "grad_norm": 1.4972645044326782, "learning_rate": 1.8052564922318247e-05, "loss": 0.174281108379364, "step": 2230 }, { "epoch": 0.22710710913687893, "grad_norm": 6.230835437774658, "learning_rate": 1.803305317716992e-05, "loss": 0.17702302932739258, "step": 2240 }, { "epoch": 0.22812098015981142, "grad_norm": 3.2745707035064697, "learning_rate": 1.8013454828078925e-05, "loss": 0.16210670471191407, "step": 2250 }, { "epoch": 0.2291348511827439, "grad_norm": 2.407383441925049, "learning_rate": 1.7993770086334082e-05, "loss": 0.15724389553070067, "step": 2260 }, { "epoch": 0.23014872220567642, "grad_norm": 4.97621488571167, "learning_rate": 1.7973999164155597e-05, "loss": 0.15707823038101196, "step": 2270 }, { "epoch": 0.2311625932286089, "grad_norm": 3.9608426094055176, "learning_rate": 1.795414227469279e-05, "loss": 0.15669410228729247, "step": 2280 }, { "epoch": 0.2321764642515414, "grad_norm": 3.1507160663604736, "learning_rate": 1.7934199632021795e-05, "loss": 0.17024825811386107, "step": 2290 }, { "epoch": 0.2331903352744739, "grad_norm": 2.3113698959350586, "learning_rate": 1.7914171451143235e-05, "loss": 0.17838795185089112, "step": 2300 }, { "epoch": 0.2342042062974064, "grad_norm": 1.854884386062622, "learning_rate": 1.7894057947979923e-05, "loss": 0.1628665328025818, "step": 2310 }, { "epoch": 0.2352180773203389, "grad_norm": 4.116936206817627, "learning_rate": 1.7873859339374528e-05, "loss": 0.1894883394241333, "step": 2320 }, { "epoch": 0.23623194834327138, "grad_norm": 5.746030330657959, "learning_rate": 1.7853575843087227e-05, "loss": 0.1636752486228943, "step": 2330 }, { "epoch": 0.23724581936620387, "grad_norm": 2.1242284774780273, "learning_rate": 1.7833207677793382e-05, "loss": 0.16240038871765136, "step": 2340 }, { "epoch": 0.23825969038913636, "grad_norm": 1.5818480253219604, "learning_rate": 1.7812755063081156e-05, "loss": 0.1619746446609497, "step": 2350 }, { "epoch": 0.23927356141206887, "grad_norm": 4.139419078826904, "learning_rate": 1.7792218219449165e-05, "loss": 0.16380761861801146, "step": 2360 }, { "epoch": 0.24028743243500136, "grad_norm": 3.958611011505127, "learning_rate": 1.777159736830408e-05, "loss": 0.16114625930786133, "step": 2370 }, { "epoch": 0.24130130345793385, "grad_norm": 3.458869695663452, "learning_rate": 1.7750892731958268e-05, "loss": 0.1632944703102112, "step": 2380 }, { "epoch": 0.24231517448086634, "grad_norm": 2.4994559288024902, "learning_rate": 1.773010453362737e-05, "loss": 0.1701113224029541, "step": 2390 }, { "epoch": 0.24332904550379886, "grad_norm": 3.1814823150634766, "learning_rate": 1.770923299742791e-05, "loss": 0.16020988225936889, "step": 2400 }, { "epoch": 0.24434291652673135, "grad_norm": 2.110896587371826, "learning_rate": 1.768827834837487e-05, "loss": 0.16348291635513307, "step": 2410 }, { "epoch": 0.24535678754966384, "grad_norm": 3.6030819416046143, "learning_rate": 1.7667240812379266e-05, "loss": 0.1471432328224182, "step": 2420 }, { "epoch": 0.24637065857259632, "grad_norm": 2.823291301727295, "learning_rate": 1.7646120616245724e-05, "loss": 0.17209304571151735, "step": 2430 }, { "epoch": 0.24738452959552884, "grad_norm": 2.164945363998413, "learning_rate": 1.7624917987670006e-05, "loss": 0.18536050319671632, "step": 2440 }, { "epoch": 0.24839840061846133, "grad_norm": 2.651195526123047, "learning_rate": 1.7603633155236595e-05, "loss": 0.16683683395385743, "step": 2450 }, { "epoch": 0.24941227164139382, "grad_norm": 2.8347835540771484, "learning_rate": 1.7582266348416194e-05, "loss": 0.17739517688751222, "step": 2460 }, { "epoch": 0.25042614266432633, "grad_norm": 1.9781173467636108, "learning_rate": 1.7560817797563275e-05, "loss": 0.1689896583557129, "step": 2470 }, { "epoch": 0.2514400136872588, "grad_norm": 2.88718843460083, "learning_rate": 1.7539287733913592e-05, "loss": 0.1780226469039917, "step": 2480 }, { "epoch": 0.2524538847101913, "grad_norm": 4.442538738250732, "learning_rate": 1.7517676389581675e-05, "loss": 0.17155239582061768, "step": 2490 }, { "epoch": 0.2534677557331238, "grad_norm": 3.9092788696289062, "learning_rate": 1.7495983997558342e-05, "loss": 0.16014407873153685, "step": 2500 }, { "epoch": 0.2544816267560563, "grad_norm": 3.4788639545440674, "learning_rate": 1.7474210791708177e-05, "loss": 0.1686904549598694, "step": 2510 }, { "epoch": 0.2554954977789888, "grad_norm": 4.453357696533203, "learning_rate": 1.7452357006767026e-05, "loss": 0.15930066108703614, "step": 2520 }, { "epoch": 0.25650936880192127, "grad_norm": 2.027261972427368, "learning_rate": 1.7430422878339443e-05, "loss": 0.1678618907928467, "step": 2530 }, { "epoch": 0.25752323982485376, "grad_norm": 2.2901926040649414, "learning_rate": 1.740840864289616e-05, "loss": 0.1627918839454651, "step": 2540 }, { "epoch": 0.2585371108477863, "grad_norm": 2.2386393547058105, "learning_rate": 1.7386314537771553e-05, "loss": 0.15760986804962157, "step": 2550 }, { "epoch": 0.2595509818707188, "grad_norm": 3.4129230976104736, "learning_rate": 1.736414080116105e-05, "loss": 0.17834205627441407, "step": 2560 }, { "epoch": 0.2605648528936513, "grad_norm": 3.053713321685791, "learning_rate": 1.7341887672118596e-05, "loss": 0.16621415615081786, "step": 2570 }, { "epoch": 0.26157872391658377, "grad_norm": 2.823934316635132, "learning_rate": 1.7319555390554054e-05, "loss": 0.18907192945480347, "step": 2580 }, { "epoch": 0.26259259493951626, "grad_norm": 2.9242324829101562, "learning_rate": 1.7297144197230637e-05, "loss": 0.17941267490386964, "step": 2590 }, { "epoch": 0.26360646596244874, "grad_norm": 2.356062889099121, "learning_rate": 1.7274654333762284e-05, "loss": 0.15956292152404786, "step": 2600 }, { "epoch": 0.26462033698538123, "grad_norm": 4.526851654052734, "learning_rate": 1.7252086042611086e-05, "loss": 0.1769614815711975, "step": 2610 }, { "epoch": 0.2656342080083137, "grad_norm": 2.1252825260162354, "learning_rate": 1.722943956708466e-05, "loss": 0.1581934690475464, "step": 2620 }, { "epoch": 0.2666480790312462, "grad_norm": 2.454115629196167, "learning_rate": 1.720671515133352e-05, "loss": 0.1702282428741455, "step": 2630 }, { "epoch": 0.26766195005417875, "grad_norm": 4.458924770355225, "learning_rate": 1.7183913040348447e-05, "loss": 0.16552886962890626, "step": 2640 }, { "epoch": 0.26867582107711124, "grad_norm": 2.543257474899292, "learning_rate": 1.716103347995785e-05, "loss": 0.16289067268371582, "step": 2650 }, { "epoch": 0.26968969210004373, "grad_norm": 2.5859835147857666, "learning_rate": 1.713807671682513e-05, "loss": 0.14557743072509766, "step": 2660 }, { "epoch": 0.2707035631229762, "grad_norm": 3.5959365367889404, "learning_rate": 1.711504299844599e-05, "loss": 0.16536003351211548, "step": 2670 }, { "epoch": 0.2717174341459087, "grad_norm": 1.9410333633422852, "learning_rate": 1.7091932573145798e-05, "loss": 0.175376558303833, "step": 2680 }, { "epoch": 0.2727313051688412, "grad_norm": 4.991951942443848, "learning_rate": 1.706874569007688e-05, "loss": 0.15580806732177735, "step": 2690 }, { "epoch": 0.2737451761917737, "grad_norm": 1.4936360120773315, "learning_rate": 1.7045482599215856e-05, "loss": 0.174545955657959, "step": 2700 }, { "epoch": 0.2747590472147062, "grad_norm": 3.0964057445526123, "learning_rate": 1.7022143551360947e-05, "loss": 0.15402806997299195, "step": 2710 }, { "epoch": 0.2757729182376387, "grad_norm": 3.385063409805298, "learning_rate": 1.699872879812925e-05, "loss": 0.18071091175079346, "step": 2720 }, { "epoch": 0.2767867892605712, "grad_norm": 4.071890354156494, "learning_rate": 1.6975238591954048e-05, "loss": 0.18014321327209473, "step": 2730 }, { "epoch": 0.2778006602835037, "grad_norm": 3.482182502746582, "learning_rate": 1.695167318608206e-05, "loss": 0.17079235315322877, "step": 2740 }, { "epoch": 0.2788145313064362, "grad_norm": 1.515297532081604, "learning_rate": 1.6928032834570767e-05, "loss": 0.16878323554992675, "step": 2750 }, { "epoch": 0.2798284023293687, "grad_norm": 3.255599021911621, "learning_rate": 1.690431779228559e-05, "loss": 0.16493769884109497, "step": 2760 }, { "epoch": 0.28084227335230116, "grad_norm": 4.405327796936035, "learning_rate": 1.6880528314897212e-05, "loss": 0.16831092834472655, "step": 2770 }, { "epoch": 0.28185614437523365, "grad_norm": 4.258333683013916, "learning_rate": 1.6856664658878797e-05, "loss": 0.1661960482597351, "step": 2780 }, { "epoch": 0.28287001539816614, "grad_norm": 2.4200406074523926, "learning_rate": 1.6832727081503227e-05, "loss": 0.1710052967071533, "step": 2790 }, { "epoch": 0.28388388642109863, "grad_norm": 2.5622406005859375, "learning_rate": 1.6808715840840308e-05, "loss": 0.1568651556968689, "step": 2800 }, { "epoch": 0.2848977574440312, "grad_norm": 4.719352722167969, "learning_rate": 1.6784631195754027e-05, "loss": 0.17858612537384033, "step": 2810 }, { "epoch": 0.28591162846696366, "grad_norm": 2.246222496032715, "learning_rate": 1.6760473405899733e-05, "loss": 0.1501971125602722, "step": 2820 }, { "epoch": 0.28692549948989615, "grad_norm": 4.396531581878662, "learning_rate": 1.673624273172134e-05, "loss": 0.16483056545257568, "step": 2830 }, { "epoch": 0.28793937051282864, "grad_norm": 1.5058412551879883, "learning_rate": 1.6711939434448537e-05, "loss": 0.1539397954940796, "step": 2840 }, { "epoch": 0.28895324153576113, "grad_norm": 4.910403251647949, "learning_rate": 1.6687563776093943e-05, "loss": 0.17588284015655517, "step": 2850 }, { "epoch": 0.2899671125586936, "grad_norm": 4.184820652008057, "learning_rate": 1.6663116019450306e-05, "loss": 0.16201233863830566, "step": 2860 }, { "epoch": 0.2909809835816261, "grad_norm": 2.3576252460479736, "learning_rate": 1.6638596428087662e-05, "loss": 0.179340398311615, "step": 2870 }, { "epoch": 0.2919948546045586, "grad_norm": 4.198968887329102, "learning_rate": 1.66140052663505e-05, "loss": 0.16696414947509766, "step": 2880 }, { "epoch": 0.29300872562749114, "grad_norm": 2.4338316917419434, "learning_rate": 1.6589342799354895e-05, "loss": 0.16598769426345825, "step": 2890 }, { "epoch": 0.29402259665042363, "grad_norm": 2.0648765563964844, "learning_rate": 1.6564609292985663e-05, "loss": 0.16421579122543334, "step": 2900 }, { "epoch": 0.2950364676733561, "grad_norm": 3.6903867721557617, "learning_rate": 1.6539805013893493e-05, "loss": 0.1708754777908325, "step": 2910 }, { "epoch": 0.2960503386962886, "grad_norm": 5.318367004394531, "learning_rate": 1.6514930229492073e-05, "loss": 0.1758953332901001, "step": 2920 }, { "epoch": 0.2970642097192211, "grad_norm": 3.420600414276123, "learning_rate": 1.6489985207955207e-05, "loss": 0.16568173170089723, "step": 2930 }, { "epoch": 0.2980780807421536, "grad_norm": 3.650148391723633, "learning_rate": 1.6464970218213912e-05, "loss": 0.17269517183303834, "step": 2940 }, { "epoch": 0.2990919517650861, "grad_norm": 3.1654107570648193, "learning_rate": 1.643988552995354e-05, "loss": 0.16831443309783936, "step": 2950 }, { "epoch": 0.30010582278801856, "grad_norm": 3.7565762996673584, "learning_rate": 1.6414731413610856e-05, "loss": 0.15644680261611937, "step": 2960 }, { "epoch": 0.30111969381095105, "grad_norm": 1.893249750137329, "learning_rate": 1.638950814037112e-05, "loss": 0.15852735042572022, "step": 2970 }, { "epoch": 0.3021335648338836, "grad_norm": 3.949559211730957, "learning_rate": 1.6364215982165178e-05, "loss": 0.16078976392745972, "step": 2980 }, { "epoch": 0.3031474358568161, "grad_norm": 1.9977219104766846, "learning_rate": 1.633885521166651e-05, "loss": 0.1558140277862549, "step": 2990 }, { "epoch": 0.30416130687974857, "grad_norm": 1.8379961252212524, "learning_rate": 1.6313426102288315e-05, "loss": 0.1643061637878418, "step": 3000 }, { "epoch": 0.30517517790268106, "grad_norm": 4.7477335929870605, "learning_rate": 1.6287928928180544e-05, "loss": 0.17171866893768312, "step": 3010 }, { "epoch": 0.30618904892561355, "grad_norm": 2.1639857292175293, "learning_rate": 1.6262363964226943e-05, "loss": 0.15198819637298583, "step": 3020 }, { "epoch": 0.30720291994854604, "grad_norm": 4.7467145919799805, "learning_rate": 1.623673148604211e-05, "loss": 0.14992291927337648, "step": 3030 }, { "epoch": 0.3082167909714785, "grad_norm": 3.1087965965270996, "learning_rate": 1.6211031769968503e-05, "loss": 0.16175444126129152, "step": 3040 }, { "epoch": 0.309230661994411, "grad_norm": 3.6399638652801514, "learning_rate": 1.6185265093073468e-05, "loss": 0.15413382053375244, "step": 3050 }, { "epoch": 0.3102445330173435, "grad_norm": 2.2595608234405518, "learning_rate": 1.6159431733146255e-05, "loss": 0.1687397241592407, "step": 3060 }, { "epoch": 0.31125840404027605, "grad_norm": 2.612565517425537, "learning_rate": 1.613353196869502e-05, "loss": 0.16854994297027587, "step": 3070 }, { "epoch": 0.31227227506320854, "grad_norm": 2.1001062393188477, "learning_rate": 1.6107566078943818e-05, "loss": 0.17416659593582154, "step": 3080 }, { "epoch": 0.313286146086141, "grad_norm": 2.4093902111053467, "learning_rate": 1.608153434382961e-05, "loss": 0.1679131031036377, "step": 3090 }, { "epoch": 0.3143000171090735, "grad_norm": 1.6475828886032104, "learning_rate": 1.6055437043999215e-05, "loss": 0.14217361211776733, "step": 3100 }, { "epoch": 0.315313888132006, "grad_norm": 1.8604295253753662, "learning_rate": 1.6029274460806318e-05, "loss": 0.16413625478744506, "step": 3110 }, { "epoch": 0.3163277591549385, "grad_norm": 2.3817739486694336, "learning_rate": 1.6003046876308413e-05, "loss": 0.1642291784286499, "step": 3120 }, { "epoch": 0.317341630177871, "grad_norm": 2.7766079902648926, "learning_rate": 1.5976754573263767e-05, "loss": 0.14706027507781982, "step": 3130 }, { "epoch": 0.31835550120080347, "grad_norm": 3.210603952407837, "learning_rate": 1.5950397835128378e-05, "loss": 0.16233630180358888, "step": 3140 }, { "epoch": 0.319369372223736, "grad_norm": 1.5461747646331787, "learning_rate": 1.5923976946052918e-05, "loss": 0.1350633382797241, "step": 3150 }, { "epoch": 0.3203832432466685, "grad_norm": 4.011674880981445, "learning_rate": 1.5897492190879667e-05, "loss": 0.16921379566192626, "step": 3160 }, { "epoch": 0.321397114269601, "grad_norm": 2.1632449626922607, "learning_rate": 1.5870943855139437e-05, "loss": 0.16487640142440796, "step": 3170 }, { "epoch": 0.3224109852925335, "grad_norm": 2.9155633449554443, "learning_rate": 1.5844332225048496e-05, "loss": 0.1492033362388611, "step": 3180 }, { "epoch": 0.32342485631546597, "grad_norm": 3.7048699855804443, "learning_rate": 1.5817657587505503e-05, "loss": 0.1628275752067566, "step": 3190 }, { "epoch": 0.32443872733839846, "grad_norm": 3.9063196182250977, "learning_rate": 1.5790920230088375e-05, "loss": 0.16420419216156007, "step": 3200 }, { "epoch": 0.32545259836133095, "grad_norm": 5.72119665145874, "learning_rate": 1.576412044105122e-05, "loss": 0.15580499172210693, "step": 3210 }, { "epoch": 0.32646646938426344, "grad_norm": 4.4666218757629395, "learning_rate": 1.5737258509321224e-05, "loss": 0.16530698537826538, "step": 3220 }, { "epoch": 0.3274803404071959, "grad_norm": 5.464004039764404, "learning_rate": 1.5710334724495514e-05, "loss": 0.16337277889251708, "step": 3230 }, { "epoch": 0.32849421143012847, "grad_norm": 1.7131398916244507, "learning_rate": 1.5683349376838067e-05, "loss": 0.15996296405792237, "step": 3240 }, { "epoch": 0.32950808245306096, "grad_norm": 2.6720709800720215, "learning_rate": 1.565630275727656e-05, "loss": 0.1547483444213867, "step": 3250 }, { "epoch": 0.33052195347599345, "grad_norm": 3.187878370285034, "learning_rate": 1.5629195157399236e-05, "loss": 0.1694662094116211, "step": 3260 }, { "epoch": 0.33153582449892594, "grad_norm": 4.198315620422363, "learning_rate": 1.5602026869451773e-05, "loss": 0.16123212575912477, "step": 3270 }, { "epoch": 0.3325496955218584, "grad_norm": 2.8000714778900146, "learning_rate": 1.5574798186334112e-05, "loss": 0.1490675687789917, "step": 3280 }, { "epoch": 0.3335635665447909, "grad_norm": 3.1955208778381348, "learning_rate": 1.5547509401597322e-05, "loss": 0.1639019727706909, "step": 3290 }, { "epoch": 0.3345774375677234, "grad_norm": 2.0572643280029297, "learning_rate": 1.552016080944042e-05, "loss": 0.15419870615005493, "step": 3300 }, { "epoch": 0.3355913085906559, "grad_norm": 1.8151379823684692, "learning_rate": 1.5492752704707198e-05, "loss": 0.15907851457595826, "step": 3310 }, { "epoch": 0.3366051796135884, "grad_norm": 4.217092514038086, "learning_rate": 1.5465285382883065e-05, "loss": 0.15967466831207275, "step": 3320 }, { "epoch": 0.3376190506365209, "grad_norm": 4.84382438659668, "learning_rate": 1.5437759140091827e-05, "loss": 0.17561089992523193, "step": 3330 }, { "epoch": 0.3386329216594534, "grad_norm": 2.546062707901001, "learning_rate": 1.541017427309254e-05, "loss": 0.16150405406951904, "step": 3340 }, { "epoch": 0.3396467926823859, "grad_norm": 3.613337993621826, "learning_rate": 1.538253107927625e-05, "loss": 0.15007296800613404, "step": 3350 }, { "epoch": 0.3406606637053184, "grad_norm": 3.2882962226867676, "learning_rate": 1.535482985666285e-05, "loss": 0.14795156717300414, "step": 3360 }, { "epoch": 0.3416745347282509, "grad_norm": 4.747004985809326, "learning_rate": 1.5327070903897832e-05, "loss": 0.16775504350662232, "step": 3370 }, { "epoch": 0.34268840575118337, "grad_norm": 5.055791854858398, "learning_rate": 1.529925452024907e-05, "loss": 0.1632939338684082, "step": 3380 }, { "epoch": 0.34370227677411586, "grad_norm": 4.071845531463623, "learning_rate": 1.5271381005603593e-05, "loss": 0.16516703367233276, "step": 3390 }, { "epoch": 0.34471614779704834, "grad_norm": 4.571382999420166, "learning_rate": 1.5243450660464368e-05, "loss": 0.1506056308746338, "step": 3400 }, { "epoch": 0.3457300188199809, "grad_norm": 2.996842384338379, "learning_rate": 1.5215463785947036e-05, "loss": 0.1650078296661377, "step": 3410 }, { "epoch": 0.3467438898429134, "grad_norm": 2.425377130508423, "learning_rate": 1.518742068377669e-05, "loss": 0.15442434549331666, "step": 3420 }, { "epoch": 0.34775776086584587, "grad_norm": 2.876756429672241, "learning_rate": 1.5159321656284602e-05, "loss": 0.15910015106201172, "step": 3430 }, { "epoch": 0.34877163188877836, "grad_norm": 2.910867691040039, "learning_rate": 1.5131167006404978e-05, "loss": 0.17237730026245118, "step": 3440 }, { "epoch": 0.34978550291171084, "grad_norm": 5.905397415161133, "learning_rate": 1.5102957037671689e-05, "loss": 0.15525999069213867, "step": 3450 }, { "epoch": 0.35079937393464333, "grad_norm": 2.616652250289917, "learning_rate": 1.5074692054214977e-05, "loss": 0.16004446744918824, "step": 3460 }, { "epoch": 0.3518132449575758, "grad_norm": 3.184831142425537, "learning_rate": 1.504637236075822e-05, "loss": 0.14448859691619872, "step": 3470 }, { "epoch": 0.3528271159805083, "grad_norm": 2.3364005088806152, "learning_rate": 1.5017998262614609e-05, "loss": 0.1622619152069092, "step": 3480 }, { "epoch": 0.3538409870034408, "grad_norm": 2.043290615081787, "learning_rate": 1.498957006568386e-05, "loss": 0.15845755338668824, "step": 3490 }, { "epoch": 0.35485485802637334, "grad_norm": 4.019158840179443, "learning_rate": 1.4961088076448947e-05, "loss": 0.14840054512023926, "step": 3500 }, { "epoch": 0.35586872904930583, "grad_norm": 2.3025240898132324, "learning_rate": 1.4932552601972763e-05, "loss": 0.1665415048599243, "step": 3510 }, { "epoch": 0.3568826000722383, "grad_norm": 5.027355670928955, "learning_rate": 1.490396394989482e-05, "loss": 0.16089267730712892, "step": 3520 }, { "epoch": 0.3578964710951708, "grad_norm": 2.2657501697540283, "learning_rate": 1.4875322428427943e-05, "loss": 0.15195436477661134, "step": 3530 }, { "epoch": 0.3589103421181033, "grad_norm": 2.1305277347564697, "learning_rate": 1.4846628346354934e-05, "loss": 0.1518019437789917, "step": 3540 }, { "epoch": 0.3599242131410358, "grad_norm": 4.663304805755615, "learning_rate": 1.4817882013025253e-05, "loss": 0.17168933153152466, "step": 3550 }, { "epoch": 0.3609380841639683, "grad_norm": 2.6213650703430176, "learning_rate": 1.478908373835167e-05, "loss": 0.15895335674285888, "step": 3560 }, { "epoch": 0.36195195518690076, "grad_norm": 3.248706340789795, "learning_rate": 1.476023383280694e-05, "loss": 0.15868529081344604, "step": 3570 }, { "epoch": 0.3629658262098333, "grad_norm": 2.8941662311553955, "learning_rate": 1.473133260742045e-05, "loss": 0.15786092281341552, "step": 3580 }, { "epoch": 0.3639796972327658, "grad_norm": 3.799415111541748, "learning_rate": 1.4702380373774852e-05, "loss": 0.16111060380935668, "step": 3590 }, { "epoch": 0.3649935682556983, "grad_norm": 5.1525654792785645, "learning_rate": 1.4673377444002724e-05, "loss": 0.13931698799133302, "step": 3600 }, { "epoch": 0.3660074392786308, "grad_norm": 5.300889492034912, "learning_rate": 1.4644324130783197e-05, "loss": 0.1509416937828064, "step": 3610 }, { "epoch": 0.36702131030156326, "grad_norm": 2.022728443145752, "learning_rate": 1.4615220747338574e-05, "loss": 0.16831804513931276, "step": 3620 }, { "epoch": 0.36803518132449575, "grad_norm": 3.0947630405426025, "learning_rate": 1.4586067607430976e-05, "loss": 0.15680031776428222, "step": 3630 }, { "epoch": 0.36904905234742824, "grad_norm": 3.896332025527954, "learning_rate": 1.4556865025358942e-05, "loss": 0.1758225679397583, "step": 3640 }, { "epoch": 0.37006292337036073, "grad_norm": 2.5771217346191406, "learning_rate": 1.4527613315954035e-05, "loss": 0.16474642753601074, "step": 3650 }, { "epoch": 0.3710767943932932, "grad_norm": 2.045078754425049, "learning_rate": 1.4498312794577465e-05, "loss": 0.14499516487121583, "step": 3660 }, { "epoch": 0.37209066541622576, "grad_norm": 2.8077468872070312, "learning_rate": 1.4468963777116686e-05, "loss": 0.17776894569396973, "step": 3670 }, { "epoch": 0.37310453643915825, "grad_norm": 3.979741096496582, "learning_rate": 1.4439566579981979e-05, "loss": 0.1638380765914917, "step": 3680 }, { "epoch": 0.37411840746209074, "grad_norm": 2.000814437866211, "learning_rate": 1.4410121520103045e-05, "loss": 0.15297305583953857, "step": 3690 }, { "epoch": 0.37513227848502323, "grad_norm": 1.5550616979599, "learning_rate": 1.4380628914925597e-05, "loss": 0.14360692501068115, "step": 3700 }, { "epoch": 0.3761461495079557, "grad_norm": 3.509068727493286, "learning_rate": 1.4351089082407929e-05, "loss": 0.15884438753128052, "step": 3710 }, { "epoch": 0.3771600205308882, "grad_norm": 4.330090522766113, "learning_rate": 1.4321502341017496e-05, "loss": 0.16337828636169432, "step": 3720 }, { "epoch": 0.3781738915538207, "grad_norm": 3.6429696083068848, "learning_rate": 1.4291869009727463e-05, "loss": 0.15418857336044312, "step": 3730 }, { "epoch": 0.3791877625767532, "grad_norm": 2.8036179542541504, "learning_rate": 1.4262189408013294e-05, "loss": 0.15133652687072754, "step": 3740 }, { "epoch": 0.3802016335996857, "grad_norm": 5.3105244636535645, "learning_rate": 1.4232463855849275e-05, "loss": 0.1656266212463379, "step": 3750 }, { "epoch": 0.3812155046226182, "grad_norm": 1.8165103197097778, "learning_rate": 1.4202692673705097e-05, "loss": 0.17142508029937745, "step": 3760 }, { "epoch": 0.3822293756455507, "grad_norm": 3.004964590072632, "learning_rate": 1.4172876182542372e-05, "loss": 0.1577453851699829, "step": 3770 }, { "epoch": 0.3832432466684832, "grad_norm": 3.505474090576172, "learning_rate": 1.41430147038112e-05, "loss": 0.15141154527664186, "step": 3780 }, { "epoch": 0.3842571176914157, "grad_norm": 2.2831735610961914, "learning_rate": 1.411310855944668e-05, "loss": 0.16570837497711183, "step": 3790 }, { "epoch": 0.3852709887143482, "grad_norm": 3.2854127883911133, "learning_rate": 1.4083158071865451e-05, "loss": 0.17151739597320556, "step": 3800 }, { "epoch": 0.38628485973728066, "grad_norm": 2.32826566696167, "learning_rate": 1.4053163563962215e-05, "loss": 0.15501291751861573, "step": 3810 }, { "epoch": 0.38729873076021315, "grad_norm": 4.709210395812988, "learning_rate": 1.4023125359106253e-05, "loss": 0.1587153673171997, "step": 3820 }, { "epoch": 0.38831260178314564, "grad_norm": 3.927186965942383, "learning_rate": 1.3993043781137945e-05, "loss": 0.15746581554412842, "step": 3830 }, { "epoch": 0.3893264728060782, "grad_norm": 2.101165533065796, "learning_rate": 1.3962919154365273e-05, "loss": 0.1655545711517334, "step": 3840 }, { "epoch": 0.39034034382901067, "grad_norm": 2.098872661590576, "learning_rate": 1.393275180356032e-05, "loss": 0.1636277198791504, "step": 3850 }, { "epoch": 0.39135421485194316, "grad_norm": 3.4658641815185547, "learning_rate": 1.3902542053955781e-05, "loss": 0.16852598190307616, "step": 3860 }, { "epoch": 0.39236808587487565, "grad_norm": 2.66860032081604, "learning_rate": 1.387229023124145e-05, "loss": 0.15629191398620607, "step": 3870 }, { "epoch": 0.39338195689780814, "grad_norm": 3.314290761947632, "learning_rate": 1.3841996661560706e-05, "loss": 0.15053828954696655, "step": 3880 }, { "epoch": 0.3943958279207406, "grad_norm": 3.186645030975342, "learning_rate": 1.3811661671507004e-05, "loss": 0.14788465499877929, "step": 3890 }, { "epoch": 0.3954096989436731, "grad_norm": 4.917973041534424, "learning_rate": 1.3781285588120343e-05, "loss": 0.1434534192085266, "step": 3900 }, { "epoch": 0.3964235699666056, "grad_norm": 1.8999214172363281, "learning_rate": 1.3750868738883755e-05, "loss": 0.1533747673034668, "step": 3910 }, { "epoch": 0.3974374409895381, "grad_norm": 5.419423580169678, "learning_rate": 1.3720411451719762e-05, "loss": 0.16501623392105103, "step": 3920 }, { "epoch": 0.39845131201247064, "grad_norm": 2.8895678520202637, "learning_rate": 1.3689914054986849e-05, "loss": 0.1607609510421753, "step": 3930 }, { "epoch": 0.3994651830354031, "grad_norm": 2.5226712226867676, "learning_rate": 1.3659376877475916e-05, "loss": 0.15650476217269899, "step": 3940 }, { "epoch": 0.4004790540583356, "grad_norm": 5.19219970703125, "learning_rate": 1.3628800248406738e-05, "loss": 0.15866252183914184, "step": 3950 }, { "epoch": 0.4014929250812681, "grad_norm": 4.662612438201904, "learning_rate": 1.3598184497424416e-05, "loss": 0.14897621870040895, "step": 3960 }, { "epoch": 0.4025067961042006, "grad_norm": 3.497056245803833, "learning_rate": 1.3567529954595826e-05, "loss": 0.15911462306976318, "step": 3970 }, { "epoch": 0.4035206671271331, "grad_norm": 2.9421417713165283, "learning_rate": 1.3536836950406057e-05, "loss": 0.14938981533050538, "step": 3980 }, { "epoch": 0.40453453815006557, "grad_norm": 2.4311370849609375, "learning_rate": 1.3506105815754836e-05, "loss": 0.15454344749450682, "step": 3990 }, { "epoch": 0.40554840917299806, "grad_norm": 4.494481563568115, "learning_rate": 1.3475336881952988e-05, "loss": 0.18586498498916626, "step": 4000 }, { "epoch": 0.40656228019593055, "grad_norm": 1.22752046585083, "learning_rate": 1.3444530480718838e-05, "loss": 0.1678995132446289, "step": 4010 }, { "epoch": 0.4075761512188631, "grad_norm": 1.8640897274017334, "learning_rate": 1.3413686944174655e-05, "loss": 0.1446659803390503, "step": 4020 }, { "epoch": 0.4085900222417956, "grad_norm": 3.3179891109466553, "learning_rate": 1.3382806604843053e-05, "loss": 0.1642834186553955, "step": 4030 }, { "epoch": 0.40960389326472807, "grad_norm": 2.2757351398468018, "learning_rate": 1.3351889795643423e-05, "loss": 0.14121344089508056, "step": 4040 }, { "epoch": 0.41061776428766056, "grad_norm": 4.184299945831299, "learning_rate": 1.3320936849888322e-05, "loss": 0.16399693489074707, "step": 4050 }, { "epoch": 0.41163163531059305, "grad_norm": 1.611425518989563, "learning_rate": 1.3289948101279912e-05, "loss": 0.16933578252792358, "step": 4060 }, { "epoch": 0.41264550633352554, "grad_norm": 3.600992441177368, "learning_rate": 1.3258923883906337e-05, "loss": 0.1600929856300354, "step": 4070 }, { "epoch": 0.413659377356458, "grad_norm": 1.5716931819915771, "learning_rate": 1.3227864532238113e-05, "loss": 0.16265861988067626, "step": 4080 }, { "epoch": 0.4146732483793905, "grad_norm": 1.3382700681686401, "learning_rate": 1.3196770381124557e-05, "loss": 0.15576196908950807, "step": 4090 }, { "epoch": 0.41568711940232306, "grad_norm": 3.0570852756500244, "learning_rate": 1.3165641765790153e-05, "loss": 0.13908689022064208, "step": 4100 }, { "epoch": 0.41670099042525555, "grad_norm": 1.2150094509124756, "learning_rate": 1.3134479021830938e-05, "loss": 0.15691429376602173, "step": 4110 }, { "epoch": 0.41771486144818804, "grad_norm": 4.518889904022217, "learning_rate": 1.3103282485210882e-05, "loss": 0.14011403322219848, "step": 4120 }, { "epoch": 0.4187287324711205, "grad_norm": 1.9061845541000366, "learning_rate": 1.3072052492258286e-05, "loss": 0.14194988012313842, "step": 4130 }, { "epoch": 0.419742603494053, "grad_norm": 3.961582899093628, "learning_rate": 1.3040789379662131e-05, "loss": 0.135078501701355, "step": 4140 }, { "epoch": 0.4207564745169855, "grad_norm": 2.2302379608154297, "learning_rate": 1.3009493484468464e-05, "loss": 0.1571796417236328, "step": 4150 }, { "epoch": 0.421770345539918, "grad_norm": 1.4528769254684448, "learning_rate": 1.2978165144076757e-05, "loss": 0.15472489595413208, "step": 4160 }, { "epoch": 0.4227842165628505, "grad_norm": 3.5666322708129883, "learning_rate": 1.2946804696236277e-05, "loss": 0.14508603811264037, "step": 4170 }, { "epoch": 0.42379808758578297, "grad_norm": 3.138543128967285, "learning_rate": 1.2915412479042436e-05, "loss": 0.14938297271728515, "step": 4180 }, { "epoch": 0.4248119586087155, "grad_norm": 1.3251638412475586, "learning_rate": 1.2883988830933148e-05, "loss": 0.15177901983261108, "step": 4190 }, { "epoch": 0.425825829631648, "grad_norm": 1.8907772302627563, "learning_rate": 1.2852534090685184e-05, "loss": 0.151725435256958, "step": 4200 }, { "epoch": 0.4268397006545805, "grad_norm": 1.725246787071228, "learning_rate": 1.282104859741052e-05, "loss": 0.15829064846038818, "step": 4210 }, { "epoch": 0.427853571677513, "grad_norm": 1.6737455129623413, "learning_rate": 1.2789532690552673e-05, "loss": 0.16137347221374512, "step": 4220 }, { "epoch": 0.42886744270044547, "grad_norm": 6.34685754776001, "learning_rate": 1.2757986709883059e-05, "loss": 0.14912045001983643, "step": 4230 }, { "epoch": 0.42988131372337796, "grad_norm": 4.3191237449646, "learning_rate": 1.2726410995497304e-05, "loss": 0.16066023111343383, "step": 4240 }, { "epoch": 0.43089518474631044, "grad_norm": 1.9942677021026611, "learning_rate": 1.2694805887811601e-05, "loss": 0.1254718065261841, "step": 4250 }, { "epoch": 0.43190905576924293, "grad_norm": 2.788224220275879, "learning_rate": 1.2663171727559025e-05, "loss": 0.15912203788757323, "step": 4260 }, { "epoch": 0.4329229267921755, "grad_norm": 2.0182583332061768, "learning_rate": 1.2631508855785877e-05, "loss": 0.1511770486831665, "step": 4270 }, { "epoch": 0.43393679781510797, "grad_norm": 3.362715005874634, "learning_rate": 1.2599817613847973e-05, "loss": 0.16213788986206054, "step": 4280 }, { "epoch": 0.43495066883804046, "grad_norm": 2.0848422050476074, "learning_rate": 1.2568098343407007e-05, "loss": 0.1483547329902649, "step": 4290 }, { "epoch": 0.43596453986097294, "grad_norm": 3.710782527923584, "learning_rate": 1.2536351386426844e-05, "loss": 0.1563962697982788, "step": 4300 }, { "epoch": 0.43697841088390543, "grad_norm": 3.29544997215271, "learning_rate": 1.2504577085169826e-05, "loss": 0.16600465774536133, "step": 4310 }, { "epoch": 0.4379922819068379, "grad_norm": 3.267214059829712, "learning_rate": 1.2472775782193099e-05, "loss": 0.1628407597541809, "step": 4320 }, { "epoch": 0.4390061529297704, "grad_norm": 2.6848013401031494, "learning_rate": 1.2440947820344916e-05, "loss": 0.15968276262283326, "step": 4330 }, { "epoch": 0.4400200239527029, "grad_norm": 3.150873899459839, "learning_rate": 1.2409093542760925e-05, "loss": 0.1444813847541809, "step": 4340 }, { "epoch": 0.4410338949756354, "grad_norm": 4.208096981048584, "learning_rate": 1.2377213292860506e-05, "loss": 0.18056418895721435, "step": 4350 }, { "epoch": 0.44204776599856793, "grad_norm": 5.456891059875488, "learning_rate": 1.2345307414343021e-05, "loss": 0.15256738662719727, "step": 4360 }, { "epoch": 0.4430616370215004, "grad_norm": 3.3352019786834717, "learning_rate": 1.2313376251184148e-05, "loss": 0.1520820140838623, "step": 4370 }, { "epoch": 0.4440755080444329, "grad_norm": 2.821455717086792, "learning_rate": 1.2281420147632148e-05, "loss": 0.14468976259231567, "step": 4380 }, { "epoch": 0.4450893790673654, "grad_norm": 5.016327381134033, "learning_rate": 1.2249439448204172e-05, "loss": 0.13628456592559815, "step": 4390 }, { "epoch": 0.4461032500902979, "grad_norm": 2.569862127304077, "learning_rate": 1.2217434497682537e-05, "loss": 0.1576918125152588, "step": 4400 }, { "epoch": 0.4471171211132304, "grad_norm": 4.193596839904785, "learning_rate": 1.2185405641110997e-05, "loss": 0.16109137535095214, "step": 4410 }, { "epoch": 0.44813099213616286, "grad_norm": 4.402929306030273, "learning_rate": 1.2153353223791049e-05, "loss": 0.1527587890625, "step": 4420 }, { "epoch": 0.44914486315909535, "grad_norm": 5.629524230957031, "learning_rate": 1.2121277591278197e-05, "loss": 0.16658217906951905, "step": 4430 }, { "epoch": 0.45015873418202784, "grad_norm": 4.673092842102051, "learning_rate": 1.2089179089378222e-05, "loss": 0.1516258716583252, "step": 4440 }, { "epoch": 0.4511726052049604, "grad_norm": 3.1489901542663574, "learning_rate": 1.2057058064143456e-05, "loss": 0.1482829213142395, "step": 4450 }, { "epoch": 0.4521864762278929, "grad_norm": 6.367969989776611, "learning_rate": 1.2024914861869064e-05, "loss": 0.15949922800064087, "step": 4460 }, { "epoch": 0.45320034725082536, "grad_norm": 2.3136024475097656, "learning_rate": 1.199274982908929e-05, "loss": 0.16110578775405884, "step": 4470 }, { "epoch": 0.45421421827375785, "grad_norm": 2.1072843074798584, "learning_rate": 1.196056331257374e-05, "loss": 0.14763277769088745, "step": 4480 }, { "epoch": 0.45522808929669034, "grad_norm": 3.2122669219970703, "learning_rate": 1.1928355659323627e-05, "loss": 0.14761734008789062, "step": 4490 }, { "epoch": 0.45624196031962283, "grad_norm": 2.7295751571655273, "learning_rate": 1.1896127216568047e-05, "loss": 0.15880320072174073, "step": 4500 }, { "epoch": 0.4572558313425553, "grad_norm": 2.840578317642212, "learning_rate": 1.1863878331760217e-05, "loss": 0.15693938732147217, "step": 4510 }, { "epoch": 0.4582697023654878, "grad_norm": 1.7341231107711792, "learning_rate": 1.183160935257375e-05, "loss": 0.15299410820007325, "step": 4520 }, { "epoch": 0.45928357338842035, "grad_norm": 2.5454583168029785, "learning_rate": 1.1799320626898883e-05, "loss": 0.1321274757385254, "step": 4530 }, { "epoch": 0.46029744441135284, "grad_norm": 2.3572998046875, "learning_rate": 1.1767012502838746e-05, "loss": 0.14898910522460937, "step": 4540 }, { "epoch": 0.46131131543428533, "grad_norm": 5.3571648597717285, "learning_rate": 1.1734685328705604e-05, "loss": 0.15999345779418944, "step": 4550 }, { "epoch": 0.4623251864572178, "grad_norm": 2.612882137298584, "learning_rate": 1.17023394530171e-05, "loss": 0.17403907775878907, "step": 4560 }, { "epoch": 0.4633390574801503, "grad_norm": 3.0967886447906494, "learning_rate": 1.1669975224492486e-05, "loss": 0.14922735691070557, "step": 4570 }, { "epoch": 0.4643529285030828, "grad_norm": 3.4149181842803955, "learning_rate": 1.1637592992048888e-05, "loss": 0.1409383773803711, "step": 4580 }, { "epoch": 0.4653667995260153, "grad_norm": 6.384353160858154, "learning_rate": 1.160519310479753e-05, "loss": 0.16888909339904784, "step": 4590 }, { "epoch": 0.4663806705489478, "grad_norm": 1.9173179864883423, "learning_rate": 1.157277591203996e-05, "loss": 0.14584288597106934, "step": 4600 }, { "epoch": 0.46739454157188026, "grad_norm": 3.680772066116333, "learning_rate": 1.1540341763264314e-05, "loss": 0.14248201847076417, "step": 4610 }, { "epoch": 0.4684084125948128, "grad_norm": 3.2434966564178467, "learning_rate": 1.1507891008141512e-05, "loss": 0.14000784158706664, "step": 4620 }, { "epoch": 0.4694222836177453, "grad_norm": 2.750932455062866, "learning_rate": 1.147542399652152e-05, "loss": 0.1525184392929077, "step": 4630 }, { "epoch": 0.4704361546406778, "grad_norm": 1.8439111709594727, "learning_rate": 1.1442941078429554e-05, "loss": 0.13528980016708375, "step": 4640 }, { "epoch": 0.4714500256636103, "grad_norm": 3.702160120010376, "learning_rate": 1.141044260406233e-05, "loss": 0.14878929853439332, "step": 4650 }, { "epoch": 0.47246389668654276, "grad_norm": 5.364548206329346, "learning_rate": 1.1377928923784261e-05, "loss": 0.14988694190979004, "step": 4660 }, { "epoch": 0.47347776770947525, "grad_norm": 2.7176766395568848, "learning_rate": 1.1345400388123698e-05, "loss": 0.14117112159729003, "step": 4670 }, { "epoch": 0.47449163873240774, "grad_norm": 2.172227144241333, "learning_rate": 1.1312857347769153e-05, "loss": 0.13937623500823976, "step": 4680 }, { "epoch": 0.4755055097553402, "grad_norm": 3.84472918510437, "learning_rate": 1.128030015356551e-05, "loss": 0.15010546445846557, "step": 4690 }, { "epoch": 0.4765193807782727, "grad_norm": 1.7800929546356201, "learning_rate": 1.1247729156510245e-05, "loss": 0.146453595161438, "step": 4700 }, { "epoch": 0.47753325180120526, "grad_norm": 2.0117807388305664, "learning_rate": 1.1215144707749635e-05, "loss": 0.1439850687980652, "step": 4710 }, { "epoch": 0.47854712282413775, "grad_norm": 3.817077875137329, "learning_rate": 1.1182547158574988e-05, "loss": 0.13343343734741211, "step": 4720 }, { "epoch": 0.47956099384707024, "grad_norm": 2.741931200027466, "learning_rate": 1.1149936860418846e-05, "loss": 0.15758879184722902, "step": 4730 }, { "epoch": 0.4805748648700027, "grad_norm": 1.59450364112854, "learning_rate": 1.1117314164851191e-05, "loss": 0.1505899429321289, "step": 4740 }, { "epoch": 0.4815887358929352, "grad_norm": 4.192437648773193, "learning_rate": 1.1084679423575666e-05, "loss": 0.14624897241592408, "step": 4750 }, { "epoch": 0.4826026069158677, "grad_norm": 2.459639549255371, "learning_rate": 1.1052032988425778e-05, "loss": 0.12390985488891601, "step": 4760 }, { "epoch": 0.4836164779388002, "grad_norm": 4.844198226928711, "learning_rate": 1.1019375211361104e-05, "loss": 0.13102657794952394, "step": 4770 }, { "epoch": 0.4846303489617327, "grad_norm": 1.806954264640808, "learning_rate": 1.0986706444463496e-05, "loss": 0.1502392053604126, "step": 4780 }, { "epoch": 0.4856442199846652, "grad_norm": 4.163661956787109, "learning_rate": 1.0954027039933288e-05, "loss": 0.13805919885635376, "step": 4790 }, { "epoch": 0.4866580910075977, "grad_norm": 5.7266082763671875, "learning_rate": 1.09213373500855e-05, "loss": 0.14625669717788697, "step": 4800 }, { "epoch": 0.4876719620305302, "grad_norm": 2.106107234954834, "learning_rate": 1.0888637727346032e-05, "loss": 0.159951651096344, "step": 4810 }, { "epoch": 0.4886858330534627, "grad_norm": 4.179742336273193, "learning_rate": 1.0855928524247884e-05, "loss": 0.15063775777816774, "step": 4820 }, { "epoch": 0.4896997040763952, "grad_norm": 2.0576350688934326, "learning_rate": 1.0823210093427318e-05, "loss": 0.1336990237236023, "step": 4830 }, { "epoch": 0.49071357509932767, "grad_norm": 2.030158281326294, "learning_rate": 1.07904827876201e-05, "loss": 0.1462249755859375, "step": 4840 }, { "epoch": 0.49172744612226016, "grad_norm": 2.844871997833252, "learning_rate": 1.0757746959657666e-05, "loss": 0.1475326418876648, "step": 4850 }, { "epoch": 0.49274131714519265, "grad_norm": 3.9303481578826904, "learning_rate": 1.072500296246334e-05, "loss": 0.13690648078918458, "step": 4860 }, { "epoch": 0.49375518816812514, "grad_norm": 5.64979887008667, "learning_rate": 1.06922511490485e-05, "loss": 0.13674840927124024, "step": 4870 }, { "epoch": 0.4947690591910577, "grad_norm": 1.9784489870071411, "learning_rate": 1.0659491872508807e-05, "loss": 0.150091814994812, "step": 4880 }, { "epoch": 0.49578293021399017, "grad_norm": 6.888116359710693, "learning_rate": 1.0626725486020374e-05, "loss": 0.13838388919830322, "step": 4890 }, { "epoch": 0.49679680123692266, "grad_norm": 3.678612470626831, "learning_rate": 1.059395234283597e-05, "loss": 0.14262590408325196, "step": 4900 }, { "epoch": 0.49781067225985515, "grad_norm": 3.1704108715057373, "learning_rate": 1.0561172796281196e-05, "loss": 0.15714406967163086, "step": 4910 }, { "epoch": 0.49882454328278764, "grad_norm": 2.4490365982055664, "learning_rate": 1.0528387199750706e-05, "loss": 0.1514257311820984, "step": 4920 }, { "epoch": 0.4998384143057201, "grad_norm": 2.0849621295928955, "learning_rate": 1.0495595906704365e-05, "loss": 0.13504106998443605, "step": 4930 }, { "epoch": 0.5008522853286527, "grad_norm": 2.786098003387451, "learning_rate": 1.0462799270663457e-05, "loss": 0.12540415525436402, "step": 4940 }, { "epoch": 0.5018661563515852, "grad_norm": 2.5414814949035645, "learning_rate": 1.0429997645206865e-05, "loss": 0.13944039344787598, "step": 4950 }, { "epoch": 0.5028800273745176, "grad_norm": 2.4179294109344482, "learning_rate": 1.0397191383967267e-05, "loss": 0.1368776798248291, "step": 4960 }, { "epoch": 0.5038938983974501, "grad_norm": 3.623608350753784, "learning_rate": 1.0364380840627315e-05, "loss": 0.1489039182662964, "step": 4970 }, { "epoch": 0.5049077694203826, "grad_norm": 3.5043811798095703, "learning_rate": 1.033156636891583e-05, "loss": 0.1536710739135742, "step": 4980 }, { "epoch": 0.5059216404433151, "grad_norm": 1.9873998165130615, "learning_rate": 1.0298748322603982e-05, "loss": 0.14229766130447388, "step": 4990 }, { "epoch": 0.5069355114662476, "grad_norm": 3.850745916366577, "learning_rate": 1.0265927055501476e-05, "loss": 0.162398624420166, "step": 5000 }, { "epoch": 0.5079493824891801, "grad_norm": 1.8369120359420776, "learning_rate": 1.023310292145275e-05, "loss": 0.13160550594329834, "step": 5010 }, { "epoch": 0.5089632535121126, "grad_norm": 4.752310752868652, "learning_rate": 1.020027627433314e-05, "loss": 0.1418124556541443, "step": 5020 }, { "epoch": 0.5099771245350451, "grad_norm": 3.276517152786255, "learning_rate": 1.0167447468045083e-05, "loss": 0.14100091457366942, "step": 5030 }, { "epoch": 0.5109909955579776, "grad_norm": 3.7310259342193604, "learning_rate": 1.0134616856514282e-05, "loss": 0.14823601245880128, "step": 5040 }, { "epoch": 0.51200486658091, "grad_norm": 3.8280911445617676, "learning_rate": 1.0101784793685914e-05, "loss": 0.15059430599212648, "step": 5050 }, { "epoch": 0.5130187376038425, "grad_norm": 4.311124801635742, "learning_rate": 1.0068951633520802e-05, "loss": 0.13678994178771972, "step": 5060 }, { "epoch": 0.514032608626775, "grad_norm": 2.4698967933654785, "learning_rate": 1.0036117729991595e-05, "loss": 0.1424540400505066, "step": 5070 }, { "epoch": 0.5150464796497075, "grad_norm": 4.44072961807251, "learning_rate": 1.0003283437078951e-05, "loss": 0.15592775344848633, "step": 5080 }, { "epoch": 0.5160603506726401, "grad_norm": 3.0974409580230713, "learning_rate": 9.970449108767742e-06, "loss": 0.14119877815246581, "step": 5090 }, { "epoch": 0.5170742216955726, "grad_norm": 3.0910537242889404, "learning_rate": 9.937615099043206e-06, "loss": 0.1322195291519165, "step": 5100 }, { "epoch": 0.5180880927185051, "grad_norm": 3.528085708618164, "learning_rate": 9.904781761887147e-06, "loss": 0.14898601770401002, "step": 5110 }, { "epoch": 0.5191019637414376, "grad_norm": 2.0305070877075195, "learning_rate": 9.871949451274137e-06, "loss": 0.14006927013397216, "step": 5120 }, { "epoch": 0.5201158347643701, "grad_norm": 1.3840585947036743, "learning_rate": 9.839118521167656e-06, "loss": 0.14380936622619628, "step": 5130 }, { "epoch": 0.5211297057873026, "grad_norm": 3.169626474380493, "learning_rate": 9.80628932551631e-06, "loss": 0.14864907264709473, "step": 5140 }, { "epoch": 0.522143576810235, "grad_norm": 3.6034061908721924, "learning_rate": 9.773462218250014e-06, "loss": 0.13397750854492188, "step": 5150 }, { "epoch": 0.5231574478331675, "grad_norm": 3.9890198707580566, "learning_rate": 9.740637553276162e-06, "loss": 0.1498684048652649, "step": 5160 }, { "epoch": 0.5241713188561, "grad_norm": 3.38358736038208, "learning_rate": 9.707815684475817e-06, "loss": 0.13838456869125365, "step": 5170 }, { "epoch": 0.5251851898790325, "grad_norm": 3.371189832687378, "learning_rate": 9.674996965699895e-06, "loss": 0.13287925720214844, "step": 5180 }, { "epoch": 0.526199060901965, "grad_norm": 2.7113873958587646, "learning_rate": 9.642181750765354e-06, "loss": 0.14616312980651855, "step": 5190 }, { "epoch": 0.5272129319248975, "grad_norm": 2.1429178714752197, "learning_rate": 9.60937039345138e-06, "loss": 0.15338377952575682, "step": 5200 }, { "epoch": 0.52822680294783, "grad_norm": 2.0431737899780273, "learning_rate": 9.576563247495566e-06, "loss": 0.13499071598052978, "step": 5210 }, { "epoch": 0.5292406739707625, "grad_norm": 2.9356353282928467, "learning_rate": 9.543760666590105e-06, "loss": 0.14146993160247803, "step": 5220 }, { "epoch": 0.530254544993695, "grad_norm": 2.717825412750244, "learning_rate": 9.510963004377974e-06, "loss": 0.1341123104095459, "step": 5230 }, { "epoch": 0.5312684160166274, "grad_norm": 3.1736528873443604, "learning_rate": 9.478170614449114e-06, "loss": 0.15088335275650025, "step": 5240 }, { "epoch": 0.5322822870395599, "grad_norm": 2.294435977935791, "learning_rate": 9.445383850336648e-06, "loss": 0.13496150970458984, "step": 5250 }, { "epoch": 0.5332961580624924, "grad_norm": 2.335131883621216, "learning_rate": 9.412603065513021e-06, "loss": 0.14189012050628663, "step": 5260 }, { "epoch": 0.534310029085425, "grad_norm": 2.9677584171295166, "learning_rate": 9.379828613386225e-06, "loss": 0.1508120059967041, "step": 5270 }, { "epoch": 0.5353239001083575, "grad_norm": 3.1078073978424072, "learning_rate": 9.347060847295991e-06, "loss": 0.14090564250946044, "step": 5280 }, { "epoch": 0.53633777113129, "grad_norm": 1.9318772554397583, "learning_rate": 9.314300120509952e-06, "loss": 0.14429980516433716, "step": 5290 }, { "epoch": 0.5373516421542225, "grad_norm": 1.7979222536087036, "learning_rate": 9.281546786219861e-06, "loss": 0.14580373764038085, "step": 5300 }, { "epoch": 0.538365513177155, "grad_norm": 3.196040391921997, "learning_rate": 9.24880119753777e-06, "loss": 0.14203424453735353, "step": 5310 }, { "epoch": 0.5393793842000875, "grad_norm": 5.6159186363220215, "learning_rate": 9.216063707492218e-06, "loss": 0.14082812070846557, "step": 5320 }, { "epoch": 0.54039325522302, "grad_norm": 3.4765636920928955, "learning_rate": 9.183334669024449e-06, "loss": 0.14653401374816893, "step": 5330 }, { "epoch": 0.5414071262459524, "grad_norm": 2.980239152908325, "learning_rate": 9.150614434984578e-06, "loss": 0.1461557626724243, "step": 5340 }, { "epoch": 0.5424209972688849, "grad_norm": 4.57841157913208, "learning_rate": 9.117903358127801e-06, "loss": 0.1403814435005188, "step": 5350 }, { "epoch": 0.5434348682918174, "grad_norm": 2.838510036468506, "learning_rate": 9.085201791110602e-06, "loss": 0.12382808923721314, "step": 5360 }, { "epoch": 0.5444487393147499, "grad_norm": 3.2383475303649902, "learning_rate": 9.052510086486922e-06, "loss": 0.13035615682601928, "step": 5370 }, { "epoch": 0.5454626103376824, "grad_norm": 2.0148308277130127, "learning_rate": 9.019828596704394e-06, "loss": 0.14036786556243896, "step": 5380 }, { "epoch": 0.5464764813606149, "grad_norm": 3.1799731254577637, "learning_rate": 8.987157674100519e-06, "loss": 0.1443201184272766, "step": 5390 }, { "epoch": 0.5474903523835474, "grad_norm": 3.0046825408935547, "learning_rate": 8.954497670898858e-06, "loss": 0.1291917085647583, "step": 5400 }, { "epoch": 0.5485042234064799, "grad_norm": 3.59100341796875, "learning_rate": 8.92184893920528e-06, "loss": 0.129168701171875, "step": 5410 }, { "epoch": 0.5495180944294124, "grad_norm": 2.70055890083313, "learning_rate": 8.889211831004112e-06, "loss": 0.14090925455093384, "step": 5420 }, { "epoch": 0.5505319654523448, "grad_norm": 4.645945072174072, "learning_rate": 8.856586698154382e-06, "loss": 0.14275412559509276, "step": 5430 }, { "epoch": 0.5515458364752774, "grad_norm": 3.4758381843566895, "learning_rate": 8.823973892386007e-06, "loss": 0.16266590356826782, "step": 5440 }, { "epoch": 0.5525597074982099, "grad_norm": 3.9717025756835938, "learning_rate": 8.791373765296006e-06, "loss": 0.1387179374694824, "step": 5450 }, { "epoch": 0.5535735785211424, "grad_norm": 2.4444327354431152, "learning_rate": 8.758786668344711e-06, "loss": 0.13958990573883057, "step": 5460 }, { "epoch": 0.5545874495440749, "grad_norm": 3.412431478500366, "learning_rate": 8.726212952851978e-06, "loss": 0.14743423461914062, "step": 5470 }, { "epoch": 0.5556013205670074, "grad_norm": 2.4237442016601562, "learning_rate": 8.693652969993396e-06, "loss": 0.13249880075454712, "step": 5480 }, { "epoch": 0.5566151915899399, "grad_norm": 2.113952875137329, "learning_rate": 8.661107070796504e-06, "loss": 0.1441777229309082, "step": 5490 }, { "epoch": 0.5576290626128724, "grad_norm": 3.2196567058563232, "learning_rate": 8.628575606137005e-06, "loss": 0.143310809135437, "step": 5500 }, { "epoch": 0.5586429336358049, "grad_norm": 3.3370327949523926, "learning_rate": 8.59605892673499e-06, "loss": 0.1518491268157959, "step": 5510 }, { "epoch": 0.5596568046587374, "grad_norm": 3.433121919631958, "learning_rate": 8.563557383151143e-06, "loss": 0.141062331199646, "step": 5520 }, { "epoch": 0.5606706756816698, "grad_norm": 2.838108777999878, "learning_rate": 8.531071325782965e-06, "loss": 0.1444779396057129, "step": 5530 }, { "epoch": 0.5616845467046023, "grad_norm": 2.428161382675171, "learning_rate": 8.49860110486102e-06, "loss": 0.12467169761657715, "step": 5540 }, { "epoch": 0.5626984177275348, "grad_norm": 2.7312076091766357, "learning_rate": 8.466147070445123e-06, "loss": 0.1401872992515564, "step": 5550 }, { "epoch": 0.5637122887504673, "grad_norm": 4.861104488372803, "learning_rate": 8.433709572420586e-06, "loss": 0.12339017391204835, "step": 5560 }, { "epoch": 0.5647261597733998, "grad_norm": 3.617304801940918, "learning_rate": 8.40128896049445e-06, "loss": 0.13500137329101564, "step": 5570 }, { "epoch": 0.5657400307963323, "grad_norm": 2.767732858657837, "learning_rate": 8.368885584191698e-06, "loss": 0.12970378398895263, "step": 5580 }, { "epoch": 0.5667539018192648, "grad_norm": 3.201475143432617, "learning_rate": 8.336499792851505e-06, "loss": 0.14100971221923828, "step": 5590 }, { "epoch": 0.5677677728421973, "grad_norm": 2.3301680088043213, "learning_rate": 8.304131935623461e-06, "loss": 0.14272778034210204, "step": 5600 }, { "epoch": 0.5687816438651299, "grad_norm": 2.6317920684814453, "learning_rate": 8.271782361463806e-06, "loss": 0.13399499654769897, "step": 5610 }, { "epoch": 0.5697955148880623, "grad_norm": 2.150559663772583, "learning_rate": 8.239451419131676e-06, "loss": 0.1290881633758545, "step": 5620 }, { "epoch": 0.5708093859109948, "grad_norm": 3.7837092876434326, "learning_rate": 8.207139457185328e-06, "loss": 0.13941054344177245, "step": 5630 }, { "epoch": 0.5718232569339273, "grad_norm": 5.6488518714904785, "learning_rate": 8.174846823978412e-06, "loss": 0.13704842329025269, "step": 5640 }, { "epoch": 0.5728371279568598, "grad_norm": 2.8089699745178223, "learning_rate": 8.142573867656182e-06, "loss": 0.12998459339141846, "step": 5650 }, { "epoch": 0.5738509989797923, "grad_norm": 3.4906744956970215, "learning_rate": 8.110320936151746e-06, "loss": 0.1258852481842041, "step": 5660 }, { "epoch": 0.5748648700027248, "grad_norm": 2.9150304794311523, "learning_rate": 8.078088377182352e-06, "loss": 0.11062123775482177, "step": 5670 }, { "epoch": 0.5758787410256573, "grad_norm": 2.087451696395874, "learning_rate": 8.045876538245595e-06, "loss": 0.13030285835266114, "step": 5680 }, { "epoch": 0.5768926120485898, "grad_norm": 2.1050169467926025, "learning_rate": 8.013685766615687e-06, "loss": 0.13732010126113892, "step": 5690 }, { "epoch": 0.5779064830715223, "grad_norm": 3.128848075866699, "learning_rate": 7.981516409339726e-06, "loss": 0.14144413471221923, "step": 5700 }, { "epoch": 0.5789203540944547, "grad_norm": 2.1837708950042725, "learning_rate": 7.94936881323393e-06, "loss": 0.12652392387390138, "step": 5710 }, { "epoch": 0.5799342251173872, "grad_norm": 3.496488332748413, "learning_rate": 7.917243324879924e-06, "loss": 0.14472917318344117, "step": 5720 }, { "epoch": 0.5809480961403197, "grad_norm": 2.698774814605713, "learning_rate": 7.88514029062098e-06, "loss": 0.13145649433135986, "step": 5730 }, { "epoch": 0.5819619671632522, "grad_norm": 2.4342129230499268, "learning_rate": 7.853060056558294e-06, "loss": 0.12895283699035645, "step": 5740 }, { "epoch": 0.5829758381861847, "grad_norm": 2.763894557952881, "learning_rate": 7.821002968547266e-06, "loss": 0.14454400539398193, "step": 5750 }, { "epoch": 0.5839897092091172, "grad_norm": 2.3635659217834473, "learning_rate": 7.788969372193744e-06, "loss": 0.13212335109710693, "step": 5760 }, { "epoch": 0.5850035802320497, "grad_norm": 2.5646743774414062, "learning_rate": 7.75695961285032e-06, "loss": 0.12348930835723877, "step": 5770 }, { "epoch": 0.5860174512549823, "grad_norm": 3.4153664112091064, "learning_rate": 7.724974035612611e-06, "loss": 0.1278630495071411, "step": 5780 }, { "epoch": 0.5870313222779148, "grad_norm": 2.6756341457366943, "learning_rate": 7.693012985315503e-06, "loss": 0.14954442977905275, "step": 5790 }, { "epoch": 0.5880451933008473, "grad_norm": 4.088594436645508, "learning_rate": 7.661076806529486e-06, "loss": 0.12447078227996826, "step": 5800 }, { "epoch": 0.5890590643237797, "grad_norm": 3.3953211307525635, "learning_rate": 7.629165843556896e-06, "loss": 0.13135871887207032, "step": 5810 }, { "epoch": 0.5900729353467122, "grad_norm": 2.8151490688323975, "learning_rate": 7.597280440428216e-06, "loss": 0.13550337553024291, "step": 5820 }, { "epoch": 0.5910868063696447, "grad_norm": 2.8101680278778076, "learning_rate": 7.565420940898381e-06, "loss": 0.11584151983261108, "step": 5830 }, { "epoch": 0.5921006773925772, "grad_norm": 3.9984376430511475, "learning_rate": 7.5335876884430495e-06, "loss": 0.143160879611969, "step": 5840 }, { "epoch": 0.5931145484155097, "grad_norm": 3.9961602687835693, "learning_rate": 7.501781026254922e-06, "loss": 0.13399825096130372, "step": 5850 }, { "epoch": 0.5941284194384422, "grad_norm": 3.1466002464294434, "learning_rate": 7.4700012972400224e-06, "loss": 0.13568265438079835, "step": 5860 }, { "epoch": 0.5951422904613747, "grad_norm": 2.4248788356781006, "learning_rate": 7.438248844014011e-06, "loss": 0.1347496509552002, "step": 5870 }, { "epoch": 0.5961561614843072, "grad_norm": 3.610424280166626, "learning_rate": 7.4065240088984944e-06, "loss": 0.12099912166595458, "step": 5880 }, { "epoch": 0.5971700325072397, "grad_norm": 3.9414684772491455, "learning_rate": 7.3748271339173224e-06, "loss": 0.13935841321945192, "step": 5890 }, { "epoch": 0.5981839035301721, "grad_norm": 3.182291269302368, "learning_rate": 7.34315856079291e-06, "loss": 0.15318042039871216, "step": 5900 }, { "epoch": 0.5991977745531046, "grad_norm": 3.877315044403076, "learning_rate": 7.311518630942562e-06, "loss": 0.13752840757369994, "step": 5910 }, { "epoch": 0.6002116455760371, "grad_norm": 3.5102782249450684, "learning_rate": 7.279907685474759e-06, "loss": 0.13885791301727296, "step": 5920 }, { "epoch": 0.6012255165989696, "grad_norm": 3.738729476928711, "learning_rate": 7.248326065185527e-06, "loss": 0.14312238693237306, "step": 5930 }, { "epoch": 0.6022393876219021, "grad_norm": 2.429018974304199, "learning_rate": 7.216774110554724e-06, "loss": 0.1282360315322876, "step": 5940 }, { "epoch": 0.6032532586448346, "grad_norm": 2.6033029556274414, "learning_rate": 7.185252161742385e-06, "loss": 0.13689571619033813, "step": 5950 }, { "epoch": 0.6042671296677672, "grad_norm": 2.5960543155670166, "learning_rate": 7.153760558585059e-06, "loss": 0.10911132097244262, "step": 5960 }, { "epoch": 0.6052810006906997, "grad_norm": 3.044832706451416, "learning_rate": 7.122299640592135e-06, "loss": 0.12476054430007935, "step": 5970 }, { "epoch": 0.6062948717136322, "grad_norm": 2.1960983276367188, "learning_rate": 7.090869746942191e-06, "loss": 0.12017645835876464, "step": 5980 }, { "epoch": 0.6073087427365647, "grad_norm": 2.766711950302124, "learning_rate": 7.05947121647933e-06, "loss": 0.13081536293029786, "step": 5990 }, { "epoch": 0.6083226137594971, "grad_norm": 4.043858051300049, "learning_rate": 7.028104387709531e-06, "loss": 0.1143458366394043, "step": 6000 }, { "epoch": 0.6093364847824296, "grad_norm": 2.789555549621582, "learning_rate": 6.996769598797001e-06, "loss": 0.12077580690383911, "step": 6010 }, { "epoch": 0.6103503558053621, "grad_norm": 3.8456947803497314, "learning_rate": 6.965467187560524e-06, "loss": 0.11407146453857422, "step": 6020 }, { "epoch": 0.6113642268282946, "grad_norm": 3.8791728019714355, "learning_rate": 6.934197491469818e-06, "loss": 0.11689395904541015, "step": 6030 }, { "epoch": 0.6123780978512271, "grad_norm": 4.246792316436768, "learning_rate": 6.902960847641915e-06, "loss": 0.12660518884658814, "step": 6040 }, { "epoch": 0.6133919688741596, "grad_norm": 3.2569217681884766, "learning_rate": 6.8717575928374915e-06, "loss": 0.13300209045410155, "step": 6050 }, { "epoch": 0.6144058398970921, "grad_norm": 2.673898935317993, "learning_rate": 6.840588063457278e-06, "loss": 0.12314605712890625, "step": 6060 }, { "epoch": 0.6154197109200246, "grad_norm": 2.243187665939331, "learning_rate": 6.809452595538403e-06, "loss": 0.12547509670257567, "step": 6070 }, { "epoch": 0.616433581942957, "grad_norm": 2.4731249809265137, "learning_rate": 6.778351524750777e-06, "loss": 0.11558983325958253, "step": 6080 }, { "epoch": 0.6174474529658895, "grad_norm": 3.2658729553222656, "learning_rate": 6.747285186393488e-06, "loss": 0.11421394348144531, "step": 6090 }, { "epoch": 0.618461323988822, "grad_norm": 6.561492919921875, "learning_rate": 6.716253915391167e-06, "loss": 0.1471024751663208, "step": 6100 }, { "epoch": 0.6194751950117545, "grad_norm": 2.6462771892547607, "learning_rate": 6.685258046290381e-06, "loss": 0.13123025894165039, "step": 6110 }, { "epoch": 0.620489066034687, "grad_norm": 3.8872733116149902, "learning_rate": 6.654297913256047e-06, "loss": 0.14837377071380614, "step": 6120 }, { "epoch": 0.6215029370576196, "grad_norm": 2.9958813190460205, "learning_rate": 6.623373850067794e-06, "loss": 0.13919970989227295, "step": 6130 }, { "epoch": 0.6225168080805521, "grad_norm": 4.286759376525879, "learning_rate": 6.592486190116405e-06, "loss": 0.13670952320098878, "step": 6140 }, { "epoch": 0.6235306791034846, "grad_norm": 4.1659722328186035, "learning_rate": 6.561635266400181e-06, "loss": 0.11511440277099609, "step": 6150 }, { "epoch": 0.6245445501264171, "grad_norm": 5.5972185134887695, "learning_rate": 6.5308214115213785e-06, "loss": 0.13189681768417358, "step": 6160 }, { "epoch": 0.6255584211493496, "grad_norm": 3.282991647720337, "learning_rate": 6.500044957682627e-06, "loss": 0.13416744470596315, "step": 6170 }, { "epoch": 0.626572292172282, "grad_norm": 2.657196521759033, "learning_rate": 6.469306236683324e-06, "loss": 0.1179344892501831, "step": 6180 }, { "epoch": 0.6275861631952145, "grad_norm": 2.3670475482940674, "learning_rate": 6.438605579916078e-06, "loss": 0.12788450717926025, "step": 6190 }, { "epoch": 0.628600034218147, "grad_norm": 4.298807144165039, "learning_rate": 6.4079433183631255e-06, "loss": 0.12354569435119629, "step": 6200 }, { "epoch": 0.6296139052410795, "grad_norm": 2.8651440143585205, "learning_rate": 6.377319782592767e-06, "loss": 0.11803597211837769, "step": 6210 }, { "epoch": 0.630627776264012, "grad_norm": 3.3387951850891113, "learning_rate": 6.346735302755805e-06, "loss": 0.13426779508590697, "step": 6220 }, { "epoch": 0.6316416472869445, "grad_norm": 4.438510417938232, "learning_rate": 6.316190208581979e-06, "loss": 0.11797069311141968, "step": 6230 }, { "epoch": 0.632655518309877, "grad_norm": 3.9048256874084473, "learning_rate": 6.285684829376413e-06, "loss": 0.1269956111907959, "step": 6240 }, { "epoch": 0.6336693893328095, "grad_norm": 3.142540693283081, "learning_rate": 6.25521949401607e-06, "loss": 0.12499717473983765, "step": 6250 }, { "epoch": 0.634683260355742, "grad_norm": 3.977365493774414, "learning_rate": 6.2247945309461955e-06, "loss": 0.12299294471740722, "step": 6260 }, { "epoch": 0.6356971313786745, "grad_norm": 6.368356227874756, "learning_rate": 6.194410268176796e-06, "loss": 0.12960805892944335, "step": 6270 }, { "epoch": 0.6367110024016069, "grad_norm": 2.8934123516082764, "learning_rate": 6.164067033279073e-06, "loss": 0.11912492513656617, "step": 6280 }, { "epoch": 0.6377248734245394, "grad_norm": 2.6129987239837646, "learning_rate": 6.133765153381918e-06, "loss": 0.13836591243743895, "step": 6290 }, { "epoch": 0.638738744447472, "grad_norm": 3.994199752807617, "learning_rate": 6.103504955168382e-06, "loss": 0.11374611854553222, "step": 6300 }, { "epoch": 0.6397526154704045, "grad_norm": 3.9663777351379395, "learning_rate": 6.07328676487214e-06, "loss": 0.13231489658355713, "step": 6310 }, { "epoch": 0.640766486493337, "grad_norm": 3.7638115882873535, "learning_rate": 6.043110908273973e-06, "loss": 0.12144235372543336, "step": 6320 }, { "epoch": 0.6417803575162695, "grad_norm": 5.096113681793213, "learning_rate": 6.012977710698288e-06, "loss": 0.1177056074142456, "step": 6330 }, { "epoch": 0.642794228539202, "grad_norm": 4.089726448059082, "learning_rate": 5.982887497009566e-06, "loss": 0.1231408953666687, "step": 6340 }, { "epoch": 0.6438080995621345, "grad_norm": 3.48398756980896, "learning_rate": 5.9528405916088926e-06, "loss": 0.11804372072219849, "step": 6350 }, { "epoch": 0.644821970585067, "grad_norm": 6.429157733917236, "learning_rate": 5.9228373184304455e-06, "loss": 0.12501397132873535, "step": 6360 }, { "epoch": 0.6458358416079995, "grad_norm": 3.9615743160247803, "learning_rate": 5.892878000938001e-06, "loss": 0.1122741460800171, "step": 6370 }, { "epoch": 0.6468497126309319, "grad_norm": 2.9247329235076904, "learning_rate": 5.86296296212146e-06, "loss": 0.11864700317382812, "step": 6380 }, { "epoch": 0.6478635836538644, "grad_norm": 3.1488847732543945, "learning_rate": 5.833092524493349e-06, "loss": 0.12161738872528076, "step": 6390 }, { "epoch": 0.6488774546767969, "grad_norm": 3.2587037086486816, "learning_rate": 5.80326701008536e-06, "loss": 0.12324670553207398, "step": 6400 }, { "epoch": 0.6498913256997294, "grad_norm": 3.0361568927764893, "learning_rate": 5.773486740444862e-06, "loss": 0.10644094944000244, "step": 6410 }, { "epoch": 0.6509051967226619, "grad_norm": 2.8860788345336914, "learning_rate": 5.743752036631443e-06, "loss": 0.12003660202026367, "step": 6420 }, { "epoch": 0.6519190677455944, "grad_norm": 4.643134593963623, "learning_rate": 5.714063219213456e-06, "loss": 0.10775902271270751, "step": 6430 }, { "epoch": 0.6529329387685269, "grad_norm": 3.666762113571167, "learning_rate": 5.684420608264549e-06, "loss": 0.1248089075088501, "step": 6440 }, { "epoch": 0.6539468097914594, "grad_norm": 4.293899059295654, "learning_rate": 5.654824523360219e-06, "loss": 0.11614160537719727, "step": 6450 }, { "epoch": 0.6549606808143918, "grad_norm": 3.281294107437134, "learning_rate": 5.625275283574372e-06, "loss": 0.11112592220306397, "step": 6460 }, { "epoch": 0.6559745518373244, "grad_norm": 4.045760154724121, "learning_rate": 5.595773207475872e-06, "loss": 0.11639583110809326, "step": 6470 }, { "epoch": 0.6569884228602569, "grad_norm": 3.5295188426971436, "learning_rate": 5.566318613125128e-06, "loss": 0.12205100059509277, "step": 6480 }, { "epoch": 0.6580022938831894, "grad_norm": 3.5641188621520996, "learning_rate": 5.536911818070636e-06, "loss": 0.12331666946411132, "step": 6490 }, { "epoch": 0.6590161649061219, "grad_norm": 2.518031597137451, "learning_rate": 5.507553139345574e-06, "loss": 0.11571700572967529, "step": 6500 }, { "epoch": 0.6600300359290544, "grad_norm": 3.3817460536956787, "learning_rate": 5.478242893464389e-06, "loss": 0.1088633418083191, "step": 6510 }, { "epoch": 0.6610439069519869, "grad_norm": 4.555419445037842, "learning_rate": 5.448981396419366e-06, "loss": 0.11526222229003906, "step": 6520 }, { "epoch": 0.6620577779749194, "grad_norm": 3.3834614753723145, "learning_rate": 5.419768963677233e-06, "loss": 0.12198832035064697, "step": 6530 }, { "epoch": 0.6630716489978519, "grad_norm": 3.2353672981262207, "learning_rate": 5.39060591017576e-06, "loss": 0.1264477252960205, "step": 6540 }, { "epoch": 0.6640855200207844, "grad_norm": 2.8107082843780518, "learning_rate": 5.3614925503203586e-06, "loss": 0.11802868843078614, "step": 6550 }, { "epoch": 0.6650993910437168, "grad_norm": 3.9780309200286865, "learning_rate": 5.332429197980706e-06, "loss": 0.11213116645812989, "step": 6560 }, { "epoch": 0.6661132620666493, "grad_norm": 3.374769449234009, "learning_rate": 5.303416166487337e-06, "loss": 0.12249652147293091, "step": 6570 }, { "epoch": 0.6671271330895818, "grad_norm": 5.364370822906494, "learning_rate": 5.274453768628289e-06, "loss": 0.12504377365112304, "step": 6580 }, { "epoch": 0.6681410041125143, "grad_norm": 2.7013041973114014, "learning_rate": 5.245542316645718e-06, "loss": 0.11207096576690674, "step": 6590 }, { "epoch": 0.6691548751354468, "grad_norm": 3.664395332336426, "learning_rate": 5.2166821222325306e-06, "loss": 0.10427594184875488, "step": 6600 }, { "epoch": 0.6701687461583793, "grad_norm": 3.045022487640381, "learning_rate": 5.187873496529041e-06, "loss": 0.10590007305145263, "step": 6610 }, { "epoch": 0.6711826171813118, "grad_norm": 4.204352855682373, "learning_rate": 5.15911675011959e-06, "loss": 0.12086846828460693, "step": 6620 }, { "epoch": 0.6721964882042443, "grad_norm": 3.351041793823242, "learning_rate": 5.130412193029213e-06, "loss": 0.10880508422851562, "step": 6630 }, { "epoch": 0.6732103592271768, "grad_norm": 4.411935329437256, "learning_rate": 5.101760134720306e-06, "loss": 0.11888020038604737, "step": 6640 }, { "epoch": 0.6742242302501094, "grad_norm": 3.230668783187866, "learning_rate": 5.073160884089263e-06, "loss": 0.1163447618484497, "step": 6650 }, { "epoch": 0.6752381012730418, "grad_norm": 3.1217072010040283, "learning_rate": 5.044614749463173e-06, "loss": 0.113627028465271, "step": 6660 }, { "epoch": 0.6762519722959743, "grad_norm": 3.3817808628082275, "learning_rate": 5.0161220385964745e-06, "loss": 0.10503088235855103, "step": 6670 }, { "epoch": 0.6772658433189068, "grad_norm": 2.949280261993408, "learning_rate": 4.987683058667651e-06, "loss": 0.10839029550552368, "step": 6680 }, { "epoch": 0.6782797143418393, "grad_norm": 4.389811038970947, "learning_rate": 4.9592981162759215e-06, "loss": 0.12042725086212158, "step": 6690 }, { "epoch": 0.6792935853647718, "grad_norm": 2.9715123176574707, "learning_rate": 4.930967517437922e-06, "loss": 0.10009410381317138, "step": 6700 }, { "epoch": 0.6803074563877043, "grad_norm": 5.6734395027160645, "learning_rate": 4.902691567584412e-06, "loss": 0.12113149166107177, "step": 6710 }, { "epoch": 0.6813213274106368, "grad_norm": 2.8880650997161865, "learning_rate": 4.87447057155699e-06, "loss": 0.10906096696853637, "step": 6720 }, { "epoch": 0.6823351984335693, "grad_norm": 3.5281851291656494, "learning_rate": 4.846304833604792e-06, "loss": 0.10669144392013549, "step": 6730 }, { "epoch": 0.6833490694565018, "grad_norm": 5.557509899139404, "learning_rate": 4.8181946573812236e-06, "loss": 0.11881542205810547, "step": 6740 }, { "epoch": 0.6843629404794342, "grad_norm": 2.780925750732422, "learning_rate": 4.790140345940688e-06, "loss": 0.10358659029006959, "step": 6750 }, { "epoch": 0.6853768115023667, "grad_norm": 5.345205783843994, "learning_rate": 4.762142201735299e-06, "loss": 0.10904659032821655, "step": 6760 }, { "epoch": 0.6863906825252992, "grad_norm": 4.777839660644531, "learning_rate": 4.734200526611652e-06, "loss": 0.11082270145416259, "step": 6770 }, { "epoch": 0.6874045535482317, "grad_norm": 3.4058797359466553, "learning_rate": 4.706315621807537e-06, "loss": 0.11506295204162598, "step": 6780 }, { "epoch": 0.6884184245711642, "grad_norm": 3.290076732635498, "learning_rate": 4.678487787948711e-06, "loss": 0.10878434181213378, "step": 6790 }, { "epoch": 0.6894322955940967, "grad_norm": 3.9169623851776123, "learning_rate": 4.650717325045655e-06, "loss": 0.10317412614822388, "step": 6800 }, { "epoch": 0.6904461666170292, "grad_norm": 3.4715471267700195, "learning_rate": 4.623004532490328e-06, "loss": 0.11187317371368408, "step": 6810 }, { "epoch": 0.6914600376399618, "grad_norm": 4.665056228637695, "learning_rate": 4.595349709052964e-06, "loss": 0.10187575817108155, "step": 6820 }, { "epoch": 0.6924739086628943, "grad_norm": 4.911711692810059, "learning_rate": 4.5677531528788196e-06, "loss": 0.10676844120025634, "step": 6830 }, { "epoch": 0.6934877796858268, "grad_norm": 3.3055756092071533, "learning_rate": 4.54021516148498e-06, "loss": 0.11442896127700805, "step": 6840 }, { "epoch": 0.6945016507087592, "grad_norm": 3.6695101261138916, "learning_rate": 4.5127360317571475e-06, "loss": 0.11646138429641724, "step": 6850 }, { "epoch": 0.6955155217316917, "grad_norm": 3.392028331756592, "learning_rate": 4.485316059946438e-06, "loss": 0.10400726795196533, "step": 6860 }, { "epoch": 0.6965293927546242, "grad_norm": 4.68748140335083, "learning_rate": 4.457955541666188e-06, "loss": 0.11553049087524414, "step": 6870 }, { "epoch": 0.6975432637775567, "grad_norm": 3.831617593765259, "learning_rate": 4.430654771888776e-06, "loss": 0.09710331559181214, "step": 6880 }, { "epoch": 0.6985571348004892, "grad_norm": 4.701811790466309, "learning_rate": 4.403414044942422e-06, "loss": 0.09877232313156128, "step": 6890 }, { "epoch": 0.6995710058234217, "grad_norm": 6.280004978179932, "learning_rate": 4.376233654508042e-06, "loss": 0.10592336654663086, "step": 6900 }, { "epoch": 0.7005848768463542, "grad_norm": 4.494864463806152, "learning_rate": 4.349113893616056e-06, "loss": 0.09691223502159119, "step": 6910 }, { "epoch": 0.7015987478692867, "grad_norm": 5.084499835968018, "learning_rate": 4.322055054643244e-06, "loss": 0.09130823016166686, "step": 6920 }, { "epoch": 0.7026126188922192, "grad_norm": 5.532580375671387, "learning_rate": 4.295057429309589e-06, "loss": 0.11197545528411865, "step": 6930 }, { "epoch": 0.7036264899151516, "grad_norm": 4.2722883224487305, "learning_rate": 4.268121308675132e-06, "loss": 0.09661771059036255, "step": 6940 }, { "epoch": 0.7046403609380841, "grad_norm": 3.6670138835906982, "learning_rate": 4.241246983136834e-06, "loss": 0.10773448944091797, "step": 6950 }, { "epoch": 0.7056542319610166, "grad_norm": 3.9619176387786865, "learning_rate": 4.214434742425455e-06, "loss": 0.10445289611816407, "step": 6960 }, { "epoch": 0.7066681029839491, "grad_norm": 4.094937801361084, "learning_rate": 4.1876848756024116e-06, "loss": 0.10450396537780762, "step": 6970 }, { "epoch": 0.7076819740068816, "grad_norm": 3.327224016189575, "learning_rate": 4.1609976710566735e-06, "loss": 0.12379430532455445, "step": 6980 }, { "epoch": 0.7086958450298142, "grad_norm": 2.4376614093780518, "learning_rate": 4.134373416501652e-06, "loss": 0.1025037407875061, "step": 6990 }, { "epoch": 0.7097097160527467, "grad_norm": 4.551001071929932, "learning_rate": 4.107812398972093e-06, "loss": 0.10924985408782958, "step": 7000 }, { "epoch": 0.7107235870756792, "grad_norm": 4.285798072814941, "learning_rate": 4.081314904821001e-06, "loss": 0.1042705774307251, "step": 7010 }, { "epoch": 0.7117374580986117, "grad_norm": 3.739426374435425, "learning_rate": 4.054881219716521e-06, "loss": 0.11083234548568725, "step": 7020 }, { "epoch": 0.7127513291215442, "grad_norm": 5.392399311065674, "learning_rate": 4.0285116286388914e-06, "loss": 0.09437822103500366, "step": 7030 }, { "epoch": 0.7137652001444766, "grad_norm": 5.547801971435547, "learning_rate": 4.0022064158773445e-06, "loss": 0.11346341371536255, "step": 7040 }, { "epoch": 0.7147790711674091, "grad_norm": 3.42329740524292, "learning_rate": 3.9759658650270575e-06, "loss": 0.11530917882919312, "step": 7050 }, { "epoch": 0.7157929421903416, "grad_norm": 4.710278511047363, "learning_rate": 3.94979025898609e-06, "loss": 0.09959907531738281, "step": 7060 }, { "epoch": 0.7168068132132741, "grad_norm": 4.031907081604004, "learning_rate": 3.9236798799523375e-06, "loss": 0.1069058895111084, "step": 7070 }, { "epoch": 0.7178206842362066, "grad_norm": 3.5457589626312256, "learning_rate": 3.89763500942048e-06, "loss": 0.12394685745239258, "step": 7080 }, { "epoch": 0.7188345552591391, "grad_norm": 3.1813182830810547, "learning_rate": 3.871655928178962e-06, "loss": 0.099777752161026, "step": 7090 }, { "epoch": 0.7198484262820716, "grad_norm": 3.182338237762451, "learning_rate": 3.8457429163069534e-06, "loss": 0.1162135124206543, "step": 7100 }, { "epoch": 0.7208622973050041, "grad_norm": 3.4698047637939453, "learning_rate": 3.819896253171332e-06, "loss": 0.10802671909332276, "step": 7110 }, { "epoch": 0.7218761683279366, "grad_norm": 3.1061136722564697, "learning_rate": 3.7941162174236745e-06, "loss": 0.09621543884277343, "step": 7120 }, { "epoch": 0.722890039350869, "grad_norm": 3.5138957500457764, "learning_rate": 3.7684030869972464e-06, "loss": 0.09229887723922729, "step": 7130 }, { "epoch": 0.7239039103738015, "grad_norm": 4.7144341468811035, "learning_rate": 3.742757139104023e-06, "loss": 0.11308226585388184, "step": 7140 }, { "epoch": 0.724917781396734, "grad_norm": 4.317986011505127, "learning_rate": 3.7171786502316767e-06, "loss": 0.11160567998886109, "step": 7150 }, { "epoch": 0.7259316524196666, "grad_norm": 2.0425009727478027, "learning_rate": 3.691667896140605e-06, "loss": 0.09653580188751221, "step": 7160 }, { "epoch": 0.7269455234425991, "grad_norm": 3.610509157180786, "learning_rate": 3.6662251518609747e-06, "loss": 0.09671356678009033, "step": 7170 }, { "epoch": 0.7279593944655316, "grad_norm": 4.128097057342529, "learning_rate": 3.64085069168973e-06, "loss": 0.10217103958129883, "step": 7180 }, { "epoch": 0.7289732654884641, "grad_norm": 3.6411795616149902, "learning_rate": 3.6155447891876518e-06, "loss": 0.09337497353553773, "step": 7190 }, { "epoch": 0.7299871365113966, "grad_norm": 2.675365686416626, "learning_rate": 3.590307717176401e-06, "loss": 0.08786216974258423, "step": 7200 }, { "epoch": 0.7310010075343291, "grad_norm": 5.324674606323242, "learning_rate": 3.565139747735581e-06, "loss": 0.09442671537399291, "step": 7210 }, { "epoch": 0.7320148785572616, "grad_norm": 4.08104133605957, "learning_rate": 3.5400411521998123e-06, "loss": 0.08278114795684814, "step": 7220 }, { "epoch": 0.733028749580194, "grad_norm": 3.8054587841033936, "learning_rate": 3.5150122011557888e-06, "loss": 0.10287892818450928, "step": 7230 }, { "epoch": 0.7340426206031265, "grad_norm": 2.9532997608184814, "learning_rate": 3.4900531644393744e-06, "loss": 0.10185174942016602, "step": 7240 }, { "epoch": 0.735056491626059, "grad_norm": 3.99540114402771, "learning_rate": 3.4651643111326895e-06, "loss": 0.10327275991439819, "step": 7250 }, { "epoch": 0.7360703626489915, "grad_norm": 3.0269970893859863, "learning_rate": 3.440345909561208e-06, "loss": 0.08695226907730103, "step": 7260 }, { "epoch": 0.737084233671924, "grad_norm": 2.1181936264038086, "learning_rate": 3.415598227290877e-06, "loss": 0.09071719050407409, "step": 7270 }, { "epoch": 0.7380981046948565, "grad_norm": 4.644097328186035, "learning_rate": 3.390921531125211e-06, "loss": 0.09553059339523315, "step": 7280 }, { "epoch": 0.739111975717789, "grad_norm": 4.543661117553711, "learning_rate": 3.366316087102429e-06, "loss": 0.085978102684021, "step": 7290 }, { "epoch": 0.7401258467407215, "grad_norm": 4.516087055206299, "learning_rate": 3.3417821604925937e-06, "loss": 0.09353564977645874, "step": 7300 }, { "epoch": 0.741139717763654, "grad_norm": 3.748011827468872, "learning_rate": 3.3173200157947315e-06, "loss": 0.10101165771484374, "step": 7310 }, { "epoch": 0.7421535887865864, "grad_norm": 5.307192325592041, "learning_rate": 3.2929299167339955e-06, "loss": 0.09637811779975891, "step": 7320 }, { "epoch": 0.7431674598095189, "grad_norm": 3.744358777999878, "learning_rate": 3.2686121262588165e-06, "loss": 0.0961669385433197, "step": 7330 }, { "epoch": 0.7441813308324515, "grad_norm": 3.384345531463623, "learning_rate": 3.244366906538071e-06, "loss": 0.08872188329696655, "step": 7340 }, { "epoch": 0.745195201855384, "grad_norm": 3.7088749408721924, "learning_rate": 3.2201945189582597e-06, "loss": 0.1021013617515564, "step": 7350 }, { "epoch": 0.7462090728783165, "grad_norm": 4.680863857269287, "learning_rate": 3.1960952241206745e-06, "loss": 0.09415909051895141, "step": 7360 }, { "epoch": 0.747222943901249, "grad_norm": 5.806873321533203, "learning_rate": 3.172069281838603e-06, "loss": 0.09493076801300049, "step": 7370 }, { "epoch": 0.7482368149241815, "grad_norm": 6.642421722412109, "learning_rate": 3.148116951134522e-06, "loss": 0.10065172910690308, "step": 7380 }, { "epoch": 0.749250685947114, "grad_norm": 3.039306879043579, "learning_rate": 3.1242384902373024e-06, "loss": 0.09891849756240845, "step": 7390 }, { "epoch": 0.7502645569700465, "grad_norm": 3.1179604530334473, "learning_rate": 3.1004341565794373e-06, "loss": 0.09977250099182129, "step": 7400 }, { "epoch": 0.751278427992979, "grad_norm": 4.6320481300354, "learning_rate": 3.0767042067942475e-06, "loss": 0.10301012992858886, "step": 7410 }, { "epoch": 0.7522922990159114, "grad_norm": 4.090950965881348, "learning_rate": 3.0530488967131265e-06, "loss": 0.08721206188201905, "step": 7420 }, { "epoch": 0.7533061700388439, "grad_norm": 3.967625617980957, "learning_rate": 3.0294684813627917e-06, "loss": 0.08050169944763183, "step": 7430 }, { "epoch": 0.7543200410617764, "grad_norm": 5.879483699798584, "learning_rate": 3.0059632149625118e-06, "loss": 0.08694952726364136, "step": 7440 }, { "epoch": 0.7553339120847089, "grad_norm": 5.112794399261475, "learning_rate": 2.982533350921383e-06, "loss": 0.10190410614013672, "step": 7450 }, { "epoch": 0.7563477831076414, "grad_norm": 2.9094502925872803, "learning_rate": 2.959179141835591e-06, "loss": 0.08646960854530335, "step": 7460 }, { "epoch": 0.7573616541305739, "grad_norm": 3.807849407196045, "learning_rate": 2.935900839485688e-06, "loss": 0.09832744598388672, "step": 7470 }, { "epoch": 0.7583755251535064, "grad_norm": 4.391474723815918, "learning_rate": 2.9126986948338898e-06, "loss": 0.07721090316772461, "step": 7480 }, { "epoch": 0.7593893961764389, "grad_norm": 2.9415550231933594, "learning_rate": 2.889572958021347e-06, "loss": 0.1011284589767456, "step": 7490 }, { "epoch": 0.7604032671993713, "grad_norm": 4.071854114532471, "learning_rate": 2.866523878365468e-06, "loss": 0.08446152210235595, "step": 7500 }, { "epoch": 0.761417138222304, "grad_norm": 3.845054864883423, "learning_rate": 2.8435517043572204e-06, "loss": 0.08134447932243347, "step": 7510 }, { "epoch": 0.7624310092452364, "grad_norm": 4.432512283325195, "learning_rate": 2.820656683658456e-06, "loss": 0.10365548133850097, "step": 7520 }, { "epoch": 0.7634448802681689, "grad_norm": 4.861483573913574, "learning_rate": 2.797839063099249e-06, "loss": 0.08921254873275757, "step": 7530 }, { "epoch": 0.7644587512911014, "grad_norm": 2.86967396736145, "learning_rate": 2.775099088675216e-06, "loss": 0.10833526849746704, "step": 7540 }, { "epoch": 0.7654726223140339, "grad_norm": 4.260794639587402, "learning_rate": 2.7524370055448755e-06, "loss": 0.09460173845291138, "step": 7550 }, { "epoch": 0.7664864933369664, "grad_norm": 4.089643955230713, "learning_rate": 2.7298530580270154e-06, "loss": 0.09052483439445495, "step": 7560 }, { "epoch": 0.7675003643598989, "grad_norm": 3.3847389221191406, "learning_rate": 2.7073474895980333e-06, "loss": 0.08220982551574707, "step": 7570 }, { "epoch": 0.7685142353828314, "grad_norm": 4.178006649017334, "learning_rate": 2.6849205428893334e-06, "loss": 0.08945072889328003, "step": 7580 }, { "epoch": 0.7695281064057639, "grad_norm": 3.503528118133545, "learning_rate": 2.662572459684699e-06, "loss": 0.07887412905693054, "step": 7590 }, { "epoch": 0.7705419774286963, "grad_norm": 3.36225962638855, "learning_rate": 2.640303480917693e-06, "loss": 0.08730457425117492, "step": 7600 }, { "epoch": 0.7715558484516288, "grad_norm": 3.8069510459899902, "learning_rate": 2.618113846669059e-06, "loss": 0.10038375854492188, "step": 7610 }, { "epoch": 0.7725697194745613, "grad_norm": 5.466742992401123, "learning_rate": 2.596003796164127e-06, "loss": 0.08764554262161255, "step": 7620 }, { "epoch": 0.7735835904974938, "grad_norm": 4.25375509262085, "learning_rate": 2.5739735677702416e-06, "loss": 0.08420928716659545, "step": 7630 }, { "epoch": 0.7745974615204263, "grad_norm": 4.978283405303955, "learning_rate": 2.552023398994188e-06, "loss": 0.0951771855354309, "step": 7640 }, { "epoch": 0.7756113325433588, "grad_norm": 4.714199542999268, "learning_rate": 2.5301535264796274e-06, "loss": 0.09793185591697692, "step": 7650 }, { "epoch": 0.7766252035662913, "grad_norm": 5.001359462738037, "learning_rate": 2.508364186004566e-06, "loss": 0.09349420070648193, "step": 7660 }, { "epoch": 0.7776390745892238, "grad_norm": 5.127260208129883, "learning_rate": 2.486655612478782e-06, "loss": 0.08190755844116211, "step": 7670 }, { "epoch": 0.7786529456121564, "grad_norm": 4.448234558105469, "learning_rate": 2.465028039941316e-06, "loss": 0.07557468414306641, "step": 7680 }, { "epoch": 0.7796668166350889, "grad_norm": 3.739670753479004, "learning_rate": 2.443481701557946e-06, "loss": 0.08373762369155884, "step": 7690 }, { "epoch": 0.7806806876580213, "grad_norm": 3.350729465484619, "learning_rate": 2.4220168296186587e-06, "loss": 0.07435531616210937, "step": 7700 }, { "epoch": 0.7816945586809538, "grad_norm": 4.598116397857666, "learning_rate": 2.4006336555351615e-06, "loss": 0.08306187391281128, "step": 7710 }, { "epoch": 0.7827084297038863, "grad_norm": 5.413626194000244, "learning_rate": 2.3793324098383796e-06, "loss": 0.08636783361434937, "step": 7720 }, { "epoch": 0.7837223007268188, "grad_norm": 6.688737392425537, "learning_rate": 2.35811332217597e-06, "loss": 0.0787513017654419, "step": 7730 }, { "epoch": 0.7847361717497513, "grad_norm": 4.248786449432373, "learning_rate": 2.3369766213098553e-06, "loss": 0.0846238374710083, "step": 7740 }, { "epoch": 0.7857500427726838, "grad_norm": 3.5470480918884277, "learning_rate": 2.315922535113743e-06, "loss": 0.07786616683006287, "step": 7750 }, { "epoch": 0.7867639137956163, "grad_norm": 3.7187185287475586, "learning_rate": 2.2949512905706793e-06, "loss": 0.07953379154205323, "step": 7760 }, { "epoch": 0.7877777848185488, "grad_norm": 4.862491130828857, "learning_rate": 2.274063113770597e-06, "loss": 0.08083931207656861, "step": 7770 }, { "epoch": 0.7887916558414813, "grad_norm": 3.936415433883667, "learning_rate": 2.2532582299078775e-06, "loss": 0.08985249996185303, "step": 7780 }, { "epoch": 0.7898055268644137, "grad_norm": 4.0176897048950195, "learning_rate": 2.2325368632789345e-06, "loss": 0.07969216108322144, "step": 7790 }, { "epoch": 0.7908193978873462, "grad_norm": 4.34112024307251, "learning_rate": 2.211899237279779e-06, "loss": 0.08184972405433655, "step": 7800 }, { "epoch": 0.7918332689102787, "grad_norm": 4.3150954246521, "learning_rate": 2.1913455744036138e-06, "loss": 0.11544616222381592, "step": 7810 }, { "epoch": 0.7928471399332112, "grad_norm": 4.310425281524658, "learning_rate": 2.1708760962384545e-06, "loss": 0.10025635957717896, "step": 7820 }, { "epoch": 0.7938610109561437, "grad_norm": 4.397526264190674, "learning_rate": 2.1504910234647112e-06, "loss": 0.0755455493927002, "step": 7830 }, { "epoch": 0.7948748819790762, "grad_norm": 4.314229965209961, "learning_rate": 2.130190575852832e-06, "loss": 0.07759835124015808, "step": 7840 }, { "epoch": 0.7958887530020088, "grad_norm": 4.460013389587402, "learning_rate": 2.109974972260921e-06, "loss": 0.07634187936782837, "step": 7850 }, { "epoch": 0.7969026240249413, "grad_norm": 5.871506214141846, "learning_rate": 2.0898444306323807e-06, "loss": 0.07669662833213806, "step": 7860 }, { "epoch": 0.7979164950478738, "grad_norm": 3.2089526653289795, "learning_rate": 2.069799167993577e-06, "loss": 0.08080112934112549, "step": 7870 }, { "epoch": 0.7989303660708063, "grad_norm": 6.266903877258301, "learning_rate": 2.0498394004514745e-06, "loss": 0.0819943130016327, "step": 7880 }, { "epoch": 0.7999442370937387, "grad_norm": 5.062894821166992, "learning_rate": 2.029965343191326e-06, "loss": 0.09518548846244812, "step": 7890 }, { "epoch": 0.8009581081166712, "grad_norm": 4.096579074859619, "learning_rate": 2.0101772104743422e-06, "loss": 0.0963358998298645, "step": 7900 }, { "epoch": 0.8019719791396037, "grad_norm": 4.74107551574707, "learning_rate": 1.990475215635388e-06, "loss": 0.07841432094573975, "step": 7910 }, { "epoch": 0.8029858501625362, "grad_norm": 4.707579135894775, "learning_rate": 1.9708595710806787e-06, "loss": 0.07325399518013001, "step": 7920 }, { "epoch": 0.8039997211854687, "grad_norm": 3.8024659156799316, "learning_rate": 1.9513304882854966e-06, "loss": 0.07709759473800659, "step": 7930 }, { "epoch": 0.8050135922084012, "grad_norm": 4.53713321685791, "learning_rate": 1.9318881777918973e-06, "loss": 0.07721680402755737, "step": 7940 }, { "epoch": 0.8060274632313337, "grad_norm": 5.014318943023682, "learning_rate": 1.9125328492064575e-06, "loss": 0.0747635841369629, "step": 7950 }, { "epoch": 0.8070413342542662, "grad_norm": 5.478145599365234, "learning_rate": 1.8932647111980007e-06, "loss": 0.08259361982345581, "step": 7960 }, { "epoch": 0.8080552052771987, "grad_norm": 3.9182040691375732, "learning_rate": 1.8740839714953552e-06, "loss": 0.08397890329360962, "step": 7970 }, { "epoch": 0.8090690763001311, "grad_norm": 5.009013652801514, "learning_rate": 1.8549908368851099e-06, "loss": 0.08296942114830017, "step": 7980 }, { "epoch": 0.8100829473230636, "grad_norm": 3.954822063446045, "learning_rate": 1.8359855132093884e-06, "loss": 0.06878174543380737, "step": 7990 }, { "epoch": 0.8110968183459961, "grad_norm": 3.499051332473755, "learning_rate": 1.8170682053636358e-06, "loss": 0.08207530975341797, "step": 8000 }, { "epoch": 0.8121106893689286, "grad_norm": 4.1905717849731445, "learning_rate": 1.7982391172943936e-06, "loss": 0.08103704452514648, "step": 8010 }, { "epoch": 0.8131245603918611, "grad_norm": 3.984403371810913, "learning_rate": 1.7794984519971126e-06, "loss": 0.08934596776962281, "step": 8020 }, { "epoch": 0.8141384314147937, "grad_norm": 3.595994234085083, "learning_rate": 1.7608464115139712e-06, "loss": 0.06675329208374023, "step": 8030 }, { "epoch": 0.8151523024377262, "grad_norm": 4.017212390899658, "learning_rate": 1.7422831969316724e-06, "loss": 0.09222353100776673, "step": 8040 }, { "epoch": 0.8161661734606587, "grad_norm": 4.98130464553833, "learning_rate": 1.7238090083793003e-06, "loss": 0.07695608139038086, "step": 8050 }, { "epoch": 0.8171800444835912, "grad_norm": 3.3680684566497803, "learning_rate": 1.7054240450261594e-06, "loss": 0.07082827091217041, "step": 8060 }, { "epoch": 0.8181939155065237, "grad_norm": 3.7254083156585693, "learning_rate": 1.6871285050796093e-06, "loss": 0.0816503643989563, "step": 8070 }, { "epoch": 0.8192077865294561, "grad_norm": 3.1577675342559814, "learning_rate": 1.6689225857829527e-06, "loss": 0.07042143344879151, "step": 8080 }, { "epoch": 0.8202216575523886, "grad_norm": 4.929267883300781, "learning_rate": 1.6508064834132875e-06, "loss": 0.08171738386154175, "step": 8090 }, { "epoch": 0.8212355285753211, "grad_norm": 5.634464740753174, "learning_rate": 1.632780393279404e-06, "loss": 0.0778117060661316, "step": 8100 }, { "epoch": 0.8222493995982536, "grad_norm": 4.225894927978516, "learning_rate": 1.614844509719674e-06, "loss": 0.07193443775177003, "step": 8110 }, { "epoch": 0.8232632706211861, "grad_norm": 4.133730411529541, "learning_rate": 1.5969990260999569e-06, "loss": 0.08700134754180908, "step": 8120 }, { "epoch": 0.8242771416441186, "grad_norm": 2.472679376602173, "learning_rate": 1.5792441348115116e-06, "loss": 0.07080814838409424, "step": 8130 }, { "epoch": 0.8252910126670511, "grad_norm": 5.520077705383301, "learning_rate": 1.5615800272689352e-06, "loss": 0.06262004375457764, "step": 8140 }, { "epoch": 0.8263048836899836, "grad_norm": 4.497348785400391, "learning_rate": 1.5440068939080776e-06, "loss": 0.061619114875793454, "step": 8150 }, { "epoch": 0.827318754712916, "grad_norm": 4.669376373291016, "learning_rate": 1.5265249241840153e-06, "loss": 0.07927069664001465, "step": 8160 }, { "epoch": 0.8283326257358485, "grad_norm": 3.9333269596099854, "learning_rate": 1.5091343065689756e-06, "loss": 0.07319241762161255, "step": 8170 }, { "epoch": 0.829346496758781, "grad_norm": 4.524895668029785, "learning_rate": 1.4918352285503357e-06, "loss": 0.06305734515190124, "step": 8180 }, { "epoch": 0.8303603677817135, "grad_norm": 6.22911262512207, "learning_rate": 1.4746278766285905e-06, "loss": 0.074430650472641, "step": 8190 }, { "epoch": 0.8313742388046461, "grad_norm": 5.820641994476318, "learning_rate": 1.4575124363153315e-06, "loss": 0.08897539973258972, "step": 8200 }, { "epoch": 0.8323881098275786, "grad_norm": 5.502511978149414, "learning_rate": 1.4404890921312654e-06, "loss": 0.08019034862518311, "step": 8210 }, { "epoch": 0.8334019808505111, "grad_norm": 5.393154621124268, "learning_rate": 1.4235580276042071e-06, "loss": 0.06975998878479003, "step": 8220 }, { "epoch": 0.8344158518734436, "grad_norm": 4.2266340255737305, "learning_rate": 1.4067194252671157e-06, "loss": 0.06685256958007812, "step": 8230 }, { "epoch": 0.8354297228963761, "grad_norm": 3.9326212406158447, "learning_rate": 1.3899734666561138e-06, "loss": 0.0801885187625885, "step": 8240 }, { "epoch": 0.8364435939193086, "grad_norm": 5.024439334869385, "learning_rate": 1.373320332308541e-06, "loss": 0.07832292914390564, "step": 8250 }, { "epoch": 0.837457464942241, "grad_norm": 4.076301574707031, "learning_rate": 1.3567602017609981e-06, "loss": 0.07212212681770325, "step": 8260 }, { "epoch": 0.8384713359651735, "grad_norm": 4.740481376647949, "learning_rate": 1.3402932535474277e-06, "loss": 0.07341089844703674, "step": 8270 }, { "epoch": 0.839485206988106, "grad_norm": 5.031551361083984, "learning_rate": 1.3239196651971654e-06, "loss": 0.08399744033813476, "step": 8280 }, { "epoch": 0.8404990780110385, "grad_norm": 4.480967998504639, "learning_rate": 1.3076396132330516e-06, "loss": 0.06394438743591309, "step": 8290 }, { "epoch": 0.841512949033971, "grad_norm": 3.5601699352264404, "learning_rate": 1.2914532731694996e-06, "loss": 0.06620277166366577, "step": 8300 }, { "epoch": 0.8425268200569035, "grad_norm": 3.412207841873169, "learning_rate": 1.2753608195106314e-06, "loss": 0.06621693372726441, "step": 8310 }, { "epoch": 0.843540691079836, "grad_norm": 4.974854946136475, "learning_rate": 1.2593624257483838e-06, "loss": 0.07002999782562255, "step": 8320 }, { "epoch": 0.8445545621027685, "grad_norm": 4.54547119140625, "learning_rate": 1.243458264360634e-06, "loss": 0.08087360262870788, "step": 8330 }, { "epoch": 0.845568433125701, "grad_norm": 4.400896072387695, "learning_rate": 1.2276485068093447e-06, "loss": 0.07250528931617736, "step": 8340 }, { "epoch": 0.8465823041486334, "grad_norm": 4.1981282234191895, "learning_rate": 1.2119333235387232e-06, "loss": 0.06795997619628906, "step": 8350 }, { "epoch": 0.8475961751715659, "grad_norm": 3.662405014038086, "learning_rate": 1.1963128839733674e-06, "loss": 0.06427962779998779, "step": 8360 }, { "epoch": 0.8486100461944985, "grad_norm": 3.233088493347168, "learning_rate": 1.1807873565164507e-06, "loss": 0.0699239730834961, "step": 8370 }, { "epoch": 0.849623917217431, "grad_norm": 3.92746639251709, "learning_rate": 1.1653569085479067e-06, "loss": 0.07274344563484192, "step": 8380 }, { "epoch": 0.8506377882403635, "grad_norm": 3.006166934967041, "learning_rate": 1.150021706422615e-06, "loss": 0.0755650281906128, "step": 8390 }, { "epoch": 0.851651659263296, "grad_norm": 3.4340386390686035, "learning_rate": 1.1347819154686246e-06, "loss": 0.07209963202476502, "step": 8400 }, { "epoch": 0.8526655302862285, "grad_norm": 4.451588153839111, "learning_rate": 1.1196376999853531e-06, "loss": 0.06728412508964539, "step": 8410 }, { "epoch": 0.853679401309161, "grad_norm": 4.490442752838135, "learning_rate": 1.104589223241831e-06, "loss": 0.07142931818962098, "step": 8420 }, { "epoch": 0.8546932723320935, "grad_norm": 3.746236562728882, "learning_rate": 1.089636647474923e-06, "loss": 0.075538170337677, "step": 8430 }, { "epoch": 0.855707143355026, "grad_norm": 3.562237024307251, "learning_rate": 1.0747801338876006e-06, "loss": 0.06418299674987793, "step": 8440 }, { "epoch": 0.8567210143779584, "grad_norm": 4.9907636642456055, "learning_rate": 1.0600198426471908e-06, "loss": 0.06817303895950318, "step": 8450 }, { "epoch": 0.8577348854008909, "grad_norm": 3.785386562347412, "learning_rate": 1.0453559328836517e-06, "loss": 0.06737231612205505, "step": 8460 }, { "epoch": 0.8587487564238234, "grad_norm": 5.019269943237305, "learning_rate": 1.0307885626878555e-06, "loss": 0.06148245334625244, "step": 8470 }, { "epoch": 0.8597626274467559, "grad_norm": 4.502647876739502, "learning_rate": 1.0163178891098912e-06, "loss": 0.05712827444076538, "step": 8480 }, { "epoch": 0.8607764984696884, "grad_norm": 4.038949966430664, "learning_rate": 1.0019440681573633e-06, "loss": 0.059738820791244505, "step": 8490 }, { "epoch": 0.8617903694926209, "grad_norm": 2.734306573867798, "learning_rate": 9.876672547937117e-07, "loss": 0.0639310598373413, "step": 8500 }, { "epoch": 0.8628042405155534, "grad_norm": 4.635761737823486, "learning_rate": 9.734876029365448e-07, "loss": 0.06481058597564697, "step": 8510 }, { "epoch": 0.8638181115384859, "grad_norm": 6.583827495574951, "learning_rate": 9.594052654559737e-07, "loss": 0.061745846271514894, "step": 8520 }, { "epoch": 0.8648319825614184, "grad_norm": 5.370331287384033, "learning_rate": 9.454203941729767e-07, "loss": 0.05885998010635376, "step": 8530 }, { "epoch": 0.865845853584351, "grad_norm": 4.717994213104248, "learning_rate": 9.315331398577454e-07, "loss": 0.0638877272605896, "step": 8540 }, { "epoch": 0.8668597246072834, "grad_norm": 4.465182781219482, "learning_rate": 9.177436522280714e-07, "loss": 0.0677159309387207, "step": 8550 }, { "epoch": 0.8678735956302159, "grad_norm": 4.8473005294799805, "learning_rate": 9.04052079947727e-07, "loss": 0.06505510807037354, "step": 8560 }, { "epoch": 0.8688874666531484, "grad_norm": 3.5970427989959717, "learning_rate": 8.904585706248637e-07, "loss": 0.05420362949371338, "step": 8570 }, { "epoch": 0.8699013376760809, "grad_norm": 4.625578880310059, "learning_rate": 8.76963270810427e-07, "loss": 0.07077721357345582, "step": 8580 }, { "epoch": 0.8709152086990134, "grad_norm": 3.1826629638671875, "learning_rate": 8.635663259965632e-07, "loss": 0.066590815782547, "step": 8590 }, { "epoch": 0.8719290797219459, "grad_norm": 3.3548531532287598, "learning_rate": 8.502678806150588e-07, "loss": 0.0568658173084259, "step": 8600 }, { "epoch": 0.8729429507448784, "grad_norm": 3.5711004734039307, "learning_rate": 8.370680780357909e-07, "loss": 0.060006892681121825, "step": 8610 }, { "epoch": 0.8739568217678109, "grad_norm": 4.197173118591309, "learning_rate": 8.23967060565164e-07, "loss": 0.06090829968452453, "step": 8620 }, { "epoch": 0.8749706927907434, "grad_norm": 4.141108512878418, "learning_rate": 8.109649694445898e-07, "loss": 0.0549757182598114, "step": 8630 }, { "epoch": 0.8759845638136758, "grad_norm": 5.119808673858643, "learning_rate": 7.980619448489601e-07, "loss": 0.06038324236869812, "step": 8640 }, { "epoch": 0.8769984348366083, "grad_norm": 3.1116316318511963, "learning_rate": 7.852581258851333e-07, "loss": 0.05664582252502441, "step": 8650 }, { "epoch": 0.8780123058595408, "grad_norm": 4.079880714416504, "learning_rate": 7.725536505904396e-07, "loss": 0.04802635312080383, "step": 8660 }, { "epoch": 0.8790261768824733, "grad_norm": 3.920452356338501, "learning_rate": 7.599486559311887e-07, "loss": 0.06333847045898437, "step": 8670 }, { "epoch": 0.8800400479054058, "grad_norm": 4.778507232666016, "learning_rate": 7.474432778011953e-07, "loss": 0.06032472848892212, "step": 8680 }, { "epoch": 0.8810539189283383, "grad_norm": 3.380859136581421, "learning_rate": 7.350376510203105e-07, "loss": 0.05426461100578308, "step": 8690 }, { "epoch": 0.8820677899512708, "grad_norm": 4.178164958953857, "learning_rate": 7.227319093329732e-07, "loss": 0.06017763614654541, "step": 8700 }, { "epoch": 0.8830816609742033, "grad_norm": 3.390024423599243, "learning_rate": 7.105261854067691e-07, "loss": 0.049314862489700316, "step": 8710 }, { "epoch": 0.8840955319971359, "grad_norm": 3.1753265857696533, "learning_rate": 6.984206108309932e-07, "loss": 0.05510423183441162, "step": 8720 }, { "epoch": 0.8851094030200684, "grad_norm": 2.5311012268066406, "learning_rate": 6.864153161152354e-07, "loss": 0.04235256016254425, "step": 8730 }, { "epoch": 0.8861232740430008, "grad_norm": 3.382197618484497, "learning_rate": 6.745104306879769e-07, "loss": 0.06675397157669068, "step": 8740 }, { "epoch": 0.8871371450659333, "grad_norm": 5.376062393188477, "learning_rate": 6.627060828951881e-07, "loss": 0.05724536776542664, "step": 8750 }, { "epoch": 0.8881510160888658, "grad_norm": 4.281327724456787, "learning_rate": 6.510023999989501e-07, "loss": 0.06705225706100464, "step": 8760 }, { "epoch": 0.8891648871117983, "grad_norm": 4.805238246917725, "learning_rate": 6.393995081760795e-07, "loss": 0.05440206527709961, "step": 8770 }, { "epoch": 0.8901787581347308, "grad_norm": 5.185061454772949, "learning_rate": 6.278975325167691e-07, "loss": 0.06307616233825683, "step": 8780 }, { "epoch": 0.8911926291576633, "grad_norm": 6.797262668609619, "learning_rate": 6.164965970232417e-07, "loss": 0.07533777952194214, "step": 8790 }, { "epoch": 0.8922065001805958, "grad_norm": 5.427569389343262, "learning_rate": 6.051968246084117e-07, "loss": 0.06420820951461792, "step": 8800 }, { "epoch": 0.8932203712035283, "grad_norm": 5.613475322723389, "learning_rate": 5.939983370945535e-07, "loss": 0.06973521709442139, "step": 8810 }, { "epoch": 0.8942342422264608, "grad_norm": 2.6717851161956787, "learning_rate": 5.829012552120039e-07, "loss": 0.06689927577972413, "step": 8820 }, { "epoch": 0.8952481132493932, "grad_norm": 4.0211501121521, "learning_rate": 5.719056985978388e-07, "loss": 0.05906909704208374, "step": 8830 }, { "epoch": 0.8962619842723257, "grad_norm": 4.845189094543457, "learning_rate": 5.610117857946062e-07, "loss": 0.05613366365432739, "step": 8840 }, { "epoch": 0.8972758552952582, "grad_norm": 3.2385857105255127, "learning_rate": 5.502196342490318e-07, "loss": 0.061687004566192624, "step": 8850 }, { "epoch": 0.8982897263181907, "grad_norm": 3.9595015048980713, "learning_rate": 5.395293603107566e-07, "loss": 0.052939456701278684, "step": 8860 }, { "epoch": 0.8993035973411232, "grad_norm": 5.3884358406066895, "learning_rate": 5.2894107923109e-07, "loss": 0.05630512237548828, "step": 8870 }, { "epoch": 0.9003174683640557, "grad_norm": 5.046842575073242, "learning_rate": 5.184549051617571e-07, "loss": 0.06632070541381836, "step": 8880 }, { "epoch": 0.9013313393869883, "grad_norm": 4.437988758087158, "learning_rate": 5.08070951153673e-07, "loss": 0.054532623291015624, "step": 8890 }, { "epoch": 0.9023452104099208, "grad_norm": 3.7529032230377197, "learning_rate": 4.977893291557256e-07, "loss": 0.05522922873497009, "step": 8900 }, { "epoch": 0.9033590814328533, "grad_norm": 3.7596545219421387, "learning_rate": 4.876101500135621e-07, "loss": 0.06529688835144043, "step": 8910 }, { "epoch": 0.9043729524557858, "grad_norm": 5.834425926208496, "learning_rate": 4.775335234684042e-07, "loss": 0.060373115539550784, "step": 8920 }, { "epoch": 0.9053868234787182, "grad_norm": 4.4926557540893555, "learning_rate": 4.675595581558556e-07, "loss": 0.05875662565231323, "step": 8930 }, { "epoch": 0.9064006945016507, "grad_norm": 4.942712306976318, "learning_rate": 4.576883616047345e-07, "loss": 0.07494141459465027, "step": 8940 }, { "epoch": 0.9074145655245832, "grad_norm": 4.083345890045166, "learning_rate": 4.479200402359174e-07, "loss": 0.05066593885421753, "step": 8950 }, { "epoch": 0.9084284365475157, "grad_norm": 4.691787242889404, "learning_rate": 4.382546993611836e-07, "loss": 0.057959342002868654, "step": 8960 }, { "epoch": 0.9094423075704482, "grad_norm": 4.717258453369141, "learning_rate": 4.28692443182086e-07, "loss": 0.06311525106430053, "step": 8970 }, { "epoch": 0.9104561785933807, "grad_norm": 2.916468620300293, "learning_rate": 4.192333747888311e-07, "loss": 0.052760225534439084, "step": 8980 }, { "epoch": 0.9114700496163132, "grad_norm": 3.7380032539367676, "learning_rate": 4.0987759615915837e-07, "loss": 0.06414093971252441, "step": 8990 }, { "epoch": 0.9124839206392457, "grad_norm": 5.164063930511475, "learning_rate": 4.0062520815724816e-07, "loss": 0.06258560419082641, "step": 9000 }, { "epoch": 0.9134977916621781, "grad_norm": 4.9328131675720215, "learning_rate": 3.9147631053263027e-07, "loss": 0.043292635679244997, "step": 9010 }, { "epoch": 0.9145116626851106, "grad_norm": 5.94814920425415, "learning_rate": 3.824310019191102e-07, "loss": 0.07332800030708313, "step": 9020 }, { "epoch": 0.9155255337080431, "grad_norm": 3.881322145462036, "learning_rate": 3.734893798337058e-07, "loss": 0.05666385293006897, "step": 9030 }, { "epoch": 0.9165394047309756, "grad_norm": 2.978464365005493, "learning_rate": 3.646515406755946e-07, "loss": 0.052304571866989134, "step": 9040 }, { "epoch": 0.9175532757539081, "grad_norm": 4.097742080688477, "learning_rate": 3.559175797250769e-07, "loss": 0.057740306854248045, "step": 9050 }, { "epoch": 0.9185671467768407, "grad_norm": 3.373631715774536, "learning_rate": 3.4728759114254774e-07, "loss": 0.05409005284309387, "step": 9060 }, { "epoch": 0.9195810177997732, "grad_norm": 4.709866046905518, "learning_rate": 3.3876166796747877e-07, "loss": 0.06425161957740784, "step": 9070 }, { "epoch": 0.9205948888227057, "grad_norm": 2.4981751441955566, "learning_rate": 3.303399021174214e-07, "loss": 0.05294398069381714, "step": 9080 }, { "epoch": 0.9216087598456382, "grad_norm": 5.848832607269287, "learning_rate": 3.220223843870096e-07, "loss": 0.054045021533966064, "step": 9090 }, { "epoch": 0.9226226308685707, "grad_norm": 6.420655250549316, "learning_rate": 3.1380920444698093e-07, "loss": 0.06235460638999939, "step": 9100 }, { "epoch": 0.9236365018915031, "grad_norm": 7.283418655395508, "learning_rate": 3.057004508432193e-07, "loss": 0.047946369647979735, "step": 9110 }, { "epoch": 0.9246503729144356, "grad_norm": 2.093045473098755, "learning_rate": 2.976962109957882e-07, "loss": 0.055082899332046506, "step": 9120 }, { "epoch": 0.9256642439373681, "grad_norm": 1.8001848459243774, "learning_rate": 2.8979657119799667e-07, "loss": 0.05065317749977112, "step": 9130 }, { "epoch": 0.9266781149603006, "grad_norm": 5.5529093742370605, "learning_rate": 2.8200161661546377e-07, "loss": 0.05185009837150574, "step": 9140 }, { "epoch": 0.9276919859832331, "grad_norm": 4.868887901306152, "learning_rate": 2.7431143128520243e-07, "loss": 0.05766525864601135, "step": 9150 }, { "epoch": 0.9287058570061656, "grad_norm": 5.964512348175049, "learning_rate": 2.667260981147157e-07, "loss": 0.04646897315979004, "step": 9160 }, { "epoch": 0.9297197280290981, "grad_norm": 4.1813130378723145, "learning_rate": 2.5924569888109654e-07, "loss": 0.06439193487167358, "step": 9170 }, { "epoch": 0.9307335990520306, "grad_norm": 4.660661697387695, "learning_rate": 2.5187031423015597e-07, "loss": 0.05011106729507446, "step": 9180 }, { "epoch": 0.9317474700749631, "grad_norm": 3.9895458221435547, "learning_rate": 2.4460002367554523e-07, "loss": 0.04276304841041565, "step": 9190 }, { "epoch": 0.9327613410978955, "grad_norm": 4.65911865234375, "learning_rate": 2.3743490559789973e-07, "loss": 0.06373164653778077, "step": 9200 }, { "epoch": 0.933775212120828, "grad_norm": 2.3696436882019043, "learning_rate": 2.3037503724399946e-07, "loss": 0.04235234260559082, "step": 9210 }, { "epoch": 0.9347890831437605, "grad_norm": 4.029906749725342, "learning_rate": 2.2342049472592996e-07, "loss": 0.04934808313846588, "step": 9220 }, { "epoch": 0.9358029541666931, "grad_norm": 4.859477996826172, "learning_rate": 2.1657135302026177e-07, "loss": 0.053115105628967284, "step": 9230 }, { "epoch": 0.9368168251896256, "grad_norm": 2.7897565364837646, "learning_rate": 2.09827685967251e-07, "loss": 0.04016329646110535, "step": 9240 }, { "epoch": 0.9378306962125581, "grad_norm": 3.242612600326538, "learning_rate": 2.0318956627003227e-07, "loss": 0.04065244495868683, "step": 9250 }, { "epoch": 0.9388445672354906, "grad_norm": 3.1238834857940674, "learning_rate": 1.9665706549384044e-07, "loss": 0.0584023118019104, "step": 9260 }, { "epoch": 0.9398584382584231, "grad_norm": 4.536071300506592, "learning_rate": 1.9023025406523787e-07, "loss": 0.05531284213066101, "step": 9270 }, { "epoch": 0.9408723092813556, "grad_norm": 4.454169750213623, "learning_rate": 1.8390920127135613e-07, "loss": 0.04691073298454285, "step": 9280 }, { "epoch": 0.9418861803042881, "grad_norm": 5.17441463470459, "learning_rate": 1.7769397525914668e-07, "loss": 0.04910039305686951, "step": 9290 }, { "epoch": 0.9429000513272205, "grad_norm": 3.9141156673431396, "learning_rate": 1.7158464303465017e-07, "loss": 0.05116288065910339, "step": 9300 }, { "epoch": 0.943913922350153, "grad_norm": 6.03090763092041, "learning_rate": 1.6558127046226945e-07, "loss": 0.051803863048553465, "step": 9310 }, { "epoch": 0.9449277933730855, "grad_norm": 4.5996599197387695, "learning_rate": 1.5968392226406337e-07, "loss": 0.05180568695068359, "step": 9320 }, { "epoch": 0.945941664396018, "grad_norm": 6.470058917999268, "learning_rate": 1.5389266201904506e-07, "loss": 0.04744907319545746, "step": 9330 }, { "epoch": 0.9469555354189505, "grad_norm": 3.7647764682769775, "learning_rate": 1.482075521625026e-07, "loss": 0.05007511377334595, "step": 9340 }, { "epoch": 0.947969406441883, "grad_norm": 4.587770938873291, "learning_rate": 1.4262865398531834e-07, "loss": 0.043714639544487, "step": 9350 }, { "epoch": 0.9489832774648155, "grad_norm": 3.2250001430511475, "learning_rate": 1.3715602763331172e-07, "loss": 0.05296366810798645, "step": 9360 }, { "epoch": 0.949997148487748, "grad_norm": 4.35186243057251, "learning_rate": 1.3178973210659528e-07, "loss": 0.054897016286849974, "step": 9370 }, { "epoch": 0.9510110195106805, "grad_norm": 3.6740312576293945, "learning_rate": 1.2652982525892975e-07, "loss": 0.05021127462387085, "step": 9380 }, { "epoch": 0.9520248905336129, "grad_norm": 7.6606950759887695, "learning_rate": 1.213763637971066e-07, "loss": 0.060488998889923096, "step": 9390 }, { "epoch": 0.9530387615565454, "grad_norm": 4.986937046051025, "learning_rate": 1.1632940328033526e-07, "loss": 0.053536272048950194, "step": 9400 }, { "epoch": 0.954052632579478, "grad_norm": 6.728878021240234, "learning_rate": 1.1138899811964477e-07, "loss": 0.049317938089370725, "step": 9410 }, { "epoch": 0.9550665036024105, "grad_norm": 5.28226900100708, "learning_rate": 1.0655520157729194e-07, "loss": 0.05695276260375977, "step": 9420 }, { "epoch": 0.956080374625343, "grad_norm": 1.942326545715332, "learning_rate": 1.0182806576619742e-07, "loss": 0.04686980247497559, "step": 9430 }, { "epoch": 0.9570942456482755, "grad_norm": 3.90641188621521, "learning_rate": 9.72076416493728e-08, "loss": 0.03852401971817017, "step": 9440 }, { "epoch": 0.958108116671208, "grad_norm": 4.3858723640441895, "learning_rate": 9.269397903937883e-08, "loss": 0.06053915619850159, "step": 9450 }, { "epoch": 0.9591219876941405, "grad_norm": 3.400742530822754, "learning_rate": 8.828712659778471e-08, "loss": 0.0480923593044281, "step": 9460 }, { "epoch": 0.960135858717073, "grad_norm": 5.6949381828308105, "learning_rate": 8.398713183464857e-08, "loss": 0.039135128259658813, "step": 9470 }, { "epoch": 0.9611497297400055, "grad_norm": 6.125531196594238, "learning_rate": 7.979404110799338e-08, "loss": 0.05814707279205322, "step": 9480 }, { "epoch": 0.9621636007629379, "grad_norm": 3.5888006687164307, "learning_rate": 7.570789962332181e-08, "loss": 0.04627379775047302, "step": 9490 }, { "epoch": 0.9631774717858704, "grad_norm": 5.20789909362793, "learning_rate": 7.172875143311996e-08, "loss": 0.04514391422271728, "step": 9500 }, { "epoch": 0.9641913428088029, "grad_norm": 6.425010681152344, "learning_rate": 6.785663943638333e-08, "loss": 0.04697279334068298, "step": 9510 }, { "epoch": 0.9652052138317354, "grad_norm": 3.31837797164917, "learning_rate": 6.409160537815818e-08, "loss": 0.04523685276508331, "step": 9520 }, { "epoch": 0.9662190848546679, "grad_norm": 5.204803943634033, "learning_rate": 6.043368984908759e-08, "loss": 0.05264185667037964, "step": 9530 }, { "epoch": 0.9672329558776004, "grad_norm": 3.0137898921966553, "learning_rate": 5.688293228497399e-08, "loss": 0.05294708013534546, "step": 9540 }, { "epoch": 0.9682468269005329, "grad_norm": 3.0698719024658203, "learning_rate": 5.34393709663561e-08, "loss": 0.045028692483901976, "step": 9550 }, { "epoch": 0.9692606979234654, "grad_norm": 4.220433235168457, "learning_rate": 5.0103043018097096e-08, "loss": 0.059280645847320554, "step": 9560 }, { "epoch": 0.9702745689463979, "grad_norm": 4.792850971221924, "learning_rate": 4.687398440897828e-08, "loss": 0.05210263133049011, "step": 9570 }, { "epoch": 0.9712884399693305, "grad_norm": 3.2461912631988525, "learning_rate": 4.3752229951321553e-08, "loss": 0.050822651386260985, "step": 9580 }, { "epoch": 0.9723023109922629, "grad_norm": 3.8159897327423096, "learning_rate": 4.0737813300602e-08, "loss": 0.05449565052986145, "step": 9590 }, { "epoch": 0.9733161820151954, "grad_norm": 3.7876107692718506, "learning_rate": 3.783076695509702e-08, "loss": 0.043861985206604004, "step": 9600 }, { "epoch": 0.9743300530381279, "grad_norm": 4.6393046379089355, "learning_rate": 3.5031122255524406e-08, "loss": 0.05593615770339966, "step": 9610 }, { "epoch": 0.9753439240610604, "grad_norm": 4.546372413635254, "learning_rate": 3.233890938471373e-08, "loss": 0.05778273344039917, "step": 9620 }, { "epoch": 0.9763577950839929, "grad_norm": 3.1537251472473145, "learning_rate": 2.9754157367277715e-08, "loss": 0.053619551658630374, "step": 9630 }, { "epoch": 0.9773716661069254, "grad_norm": 4.762555122375488, "learning_rate": 2.72768940692969e-08, "loss": 0.044208356738090517, "step": 9640 }, { "epoch": 0.9783855371298579, "grad_norm": 6.351545810699463, "learning_rate": 2.4907146198023256e-08, "loss": 0.05403401851654053, "step": 9650 }, { "epoch": 0.9793994081527904, "grad_norm": 5.689228057861328, "learning_rate": 2.2644939301588174e-08, "loss": 0.050417250394821166, "step": 9660 }, { "epoch": 0.9804132791757229, "grad_norm": 5.011280059814453, "learning_rate": 2.049029776873268e-08, "loss": 0.04172515571117401, "step": 9670 }, { "epoch": 0.9814271501986553, "grad_norm": 5.512657642364502, "learning_rate": 1.8443244828536544e-08, "loss": 0.0523757815361023, "step": 9680 }, { "epoch": 0.9824410212215878, "grad_norm": 4.782060623168945, "learning_rate": 1.650380255017625e-08, "loss": 0.05628424882888794, "step": 9690 }, { "epoch": 0.9834548922445203, "grad_norm": 4.764213562011719, "learning_rate": 1.4671991842680756e-08, "loss": 0.04698509573936462, "step": 9700 }, { "epoch": 0.9844687632674528, "grad_norm": 4.142301559448242, "learning_rate": 1.294783245470943e-08, "loss": 0.05380809307098389, "step": 9710 }, { "epoch": 0.9854826342903853, "grad_norm": 6.222425937652588, "learning_rate": 1.13313429743378e-08, "loss": 0.05272483825683594, "step": 9720 }, { "epoch": 0.9864965053133178, "grad_norm": 2.8459224700927734, "learning_rate": 9.822540828858807e-09, "loss": 0.050334584712982175, "step": 9730 }, { "epoch": 0.9875103763362503, "grad_norm": 4.190244674682617, "learning_rate": 8.421442284591852e-09, "loss": 0.055065488815307616, "step": 9740 }, { "epoch": 0.9885242473591829, "grad_norm": 4.796865463256836, "learning_rate": 7.128062446709605e-09, "loss": 0.047337579727172854, "step": 9750 }, { "epoch": 0.9895381183821154, "grad_norm": 6.157744884490967, "learning_rate": 5.942415259074796e-09, "loss": 0.043320870399475096, "step": 9760 }, { "epoch": 0.9905519894050479, "grad_norm": 4.291812419891357, "learning_rate": 4.86451350409145e-09, "loss": 0.04657539427280426, "step": 9770 }, { "epoch": 0.9915658604279803, "grad_norm": 3.2863917350769043, "learning_rate": 3.894368802563886e-09, "loss": 0.04203671813011169, "step": 9780 }, { "epoch": 0.9925797314509128, "grad_norm": 5.401935577392578, "learning_rate": 3.0319916135723713e-09, "loss": 0.05616902112960816, "step": 9790 }, { "epoch": 0.9935936024738453, "grad_norm": 4.4945244789123535, "learning_rate": 2.277391234363213e-09, "loss": 0.04296615719795227, "step": 9800 }, { "epoch": 0.9946074734967778, "grad_norm": 5.042281627655029, "learning_rate": 1.6305758002443939e-09, "loss": 0.04220306575298309, "step": 9810 }, { "epoch": 0.9956213445197103, "grad_norm": 4.125828742980957, "learning_rate": 1.091552284500086e-09, "loss": 0.051171612739562986, "step": 9820 }, { "epoch": 0.9966352155426428, "grad_norm": 6.362788677215576, "learning_rate": 6.603264983173762e-10, "loss": 0.060136258602142334, "step": 9830 }, { "epoch": 0.9976490865655753, "grad_norm": 3.391649007797241, "learning_rate": 3.3690309071965355e-10, "loss": 0.04673959910869598, "step": 9840 }, { "epoch": 0.9986629575885078, "grad_norm": 5.393172264099121, "learning_rate": 1.2128554851664754e-10, "loss": 0.04672195315361023, "step": 9850 }, { "epoch": 0.9996768286114402, "grad_norm": 4.951012134552002, "learning_rate": 1.3476196272232955e-11, "loss": 0.041605958342552186, "step": 9860 }, { "epoch": 1.0, "step": 9864, "total_flos": 5.070703459485876e+19, "train_loss": 0.13386325289201464, "train_runtime": 236399.4352, "train_samples_per_second": 2.67, "train_steps_per_second": 0.042 } ], "logging_steps": 10, "max_steps": 9864, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 1000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 5.070703459485876e+19, "train_batch_size": 1, "trial_name": null, "trial_params": null }