{ "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": 52.689231872558594, "learning_rate": 6.081081081081082e-07, "loss": 1.4980816841125488, "step": 10 }, { "epoch": 0.0020277420458649905, "grad_norm": 22.100852966308594, "learning_rate": 1.2837837837837838e-06, "loss": 0.2816293239593506, "step": 20 }, { "epoch": 0.003041613068797486, "grad_norm": 16.77118492126465, "learning_rate": 1.9594594594594595e-06, "loss": 0.23066120147705077, "step": 30 }, { "epoch": 0.004055484091729981, "grad_norm": 17.746564865112305, "learning_rate": 2.6351351351351353e-06, "loss": 0.22449901103973388, "step": 40 }, { "epoch": 0.005069355114662476, "grad_norm": 13.657648086547852, "learning_rate": 3.310810810810811e-06, "loss": 0.22790637016296386, "step": 50 }, { "epoch": 0.006083226137594972, "grad_norm": 10.902705192565918, "learning_rate": 3.986486486486487e-06, "loss": 0.241322660446167, "step": 60 }, { "epoch": 0.0070970971605274664, "grad_norm": 13.005699157714844, "learning_rate": 4.6621621621621625e-06, "loss": 0.21494731903076172, "step": 70 }, { "epoch": 0.008110968183459962, "grad_norm": 12.961997985839844, "learning_rate": 5.337837837837838e-06, "loss": 0.23946185111999513, "step": 80 }, { "epoch": 0.009124839206392456, "grad_norm": 10.44554328918457, "learning_rate": 6.013513513513514e-06, "loss": 0.2320335865020752, "step": 90 }, { "epoch": 0.010138710229324952, "grad_norm": 9.492626190185547, "learning_rate": 6.689189189189191e-06, "loss": 0.21137080192565919, "step": 100 }, { "epoch": 0.011152581252257448, "grad_norm": 9.455656051635742, "learning_rate": 7.3648648648648655e-06, "loss": 0.23038852214813232, "step": 110 }, { "epoch": 0.012166452275189943, "grad_norm": 12.293399810791016, "learning_rate": 8.040540540540541e-06, "loss": 0.21167030334472656, "step": 120 }, { "epoch": 0.013180323298122437, "grad_norm": 5.026958465576172, "learning_rate": 8.716216216216217e-06, "loss": 0.2199310302734375, "step": 130 }, { "epoch": 0.014194194321054933, "grad_norm": 9.424009323120117, "learning_rate": 9.391891891891893e-06, "loss": 0.22490355968475342, "step": 140 }, { "epoch": 0.015208065343987429, "grad_norm": 12.879389762878418, "learning_rate": 1.0067567567567569e-05, "loss": 0.21257667541503905, "step": 150 }, { "epoch": 0.016221936366919924, "grad_norm": 5.9943342208862305, "learning_rate": 1.0743243243243244e-05, "loss": 0.1918721079826355, "step": 160 }, { "epoch": 0.01723580738985242, "grad_norm": 12.070473670959473, "learning_rate": 1.141891891891892e-05, "loss": 0.2071847915649414, "step": 170 }, { "epoch": 0.018249678412784912, "grad_norm": 11.52049446105957, "learning_rate": 1.2094594594594596e-05, "loss": 0.20331075191497802, "step": 180 }, { "epoch": 0.019263549435717408, "grad_norm": 12.033429145812988, "learning_rate": 1.2770270270270272e-05, "loss": 0.20076513290405273, "step": 190 }, { "epoch": 0.020277420458649904, "grad_norm": 13.895552635192871, "learning_rate": 1.3445945945945946e-05, "loss": 0.23635175228118896, "step": 200 }, { "epoch": 0.0212912914815824, "grad_norm": 6.417858123779297, "learning_rate": 1.4121621621621621e-05, "loss": 0.22982029914855956, "step": 210 }, { "epoch": 0.022305162504514895, "grad_norm": 9.04538631439209, "learning_rate": 1.4797297297297299e-05, "loss": 0.19581854343414307, "step": 220 }, { "epoch": 0.02331903352744739, "grad_norm": 6.283764839172363, "learning_rate": 1.5472972972972976e-05, "loss": 0.19752784967422485, "step": 230 }, { "epoch": 0.024332904550379886, "grad_norm": 3.9176976680755615, "learning_rate": 1.614864864864865e-05, "loss": 0.19479107856750488, "step": 240 }, { "epoch": 0.02534677557331238, "grad_norm": 6.0841450691223145, "learning_rate": 1.6824324324324324e-05, "loss": 0.20966198444366455, "step": 250 }, { "epoch": 0.026360646596244874, "grad_norm": 8.524599075317383, "learning_rate": 1.7500000000000002e-05, "loss": 0.21590545177459716, "step": 260 }, { "epoch": 0.02737451761917737, "grad_norm": 6.365138053894043, "learning_rate": 1.8175675675675676e-05, "loss": 0.2057650089263916, "step": 270 }, { "epoch": 0.028388388642109866, "grad_norm": 10.899138450622559, "learning_rate": 1.8851351351351353e-05, "loss": 0.21586356163024903, "step": 280 }, { "epoch": 0.02940225966504236, "grad_norm": 5.89202356338501, "learning_rate": 1.9527027027027027e-05, "loss": 0.20730252265930177, "step": 290 }, { "epoch": 0.030416130687974857, "grad_norm": 3.415865182876587, "learning_rate": 1.999999514856865e-05, "loss": 0.1861214280128479, "step": 300 }, { "epoch": 0.03143000171090735, "grad_norm": 5.143789768218994, "learning_rate": 1.999990890103106e-05, "loss": 0.19422532320022584, "step": 310 }, { "epoch": 0.03244387273383985, "grad_norm": 5.944070339202881, "learning_rate": 1.999971484497808e-05, "loss": 0.2016402006149292, "step": 320 }, { "epoch": 0.033457743756772344, "grad_norm": 4.4252028465271, "learning_rate": 1.9999412982501806e-05, "loss": 0.17550069093704224, "step": 330 }, { "epoch": 0.03447161477970484, "grad_norm": 6.227522850036621, "learning_rate": 1.9999003316856605e-05, "loss": 0.18854129314422607, "step": 340 }, { "epoch": 0.03548548580263733, "grad_norm": 6.471921920776367, "learning_rate": 1.9998485852459068e-05, "loss": 0.1759865999221802, "step": 350 }, { "epoch": 0.036499356825569824, "grad_norm": 3.8785336017608643, "learning_rate": 1.9997860594887947e-05, "loss": 0.2020045757293701, "step": 360 }, { "epoch": 0.03751322784850232, "grad_norm": 9.225075721740723, "learning_rate": 1.9997127550884116e-05, "loss": 0.208371901512146, "step": 370 }, { "epoch": 0.038527098871434816, "grad_norm": 4.19935941696167, "learning_rate": 1.9996286728350484e-05, "loss": 0.19521741867065429, "step": 380 }, { "epoch": 0.03954096989436731, "grad_norm": 6.2732367515563965, "learning_rate": 1.9995338136351913e-05, "loss": 0.2028432607650757, "step": 390 }, { "epoch": 0.04055484091729981, "grad_norm": 6.310310363769531, "learning_rate": 1.9994281785115127e-05, "loss": 0.1940312623977661, "step": 400 }, { "epoch": 0.0415687119402323, "grad_norm": 3.4868595600128174, "learning_rate": 1.9993117686028603e-05, "loss": 0.18066799640655518, "step": 410 }, { "epoch": 0.0425825829631648, "grad_norm": 9.23317813873291, "learning_rate": 1.9991845851642426e-05, "loss": 0.21005780696868898, "step": 420 }, { "epoch": 0.043596453986097294, "grad_norm": 5.31777811050415, "learning_rate": 1.999046629566818e-05, "loss": 0.19448843002319335, "step": 430 }, { "epoch": 0.04461032500902979, "grad_norm": 5.099650859832764, "learning_rate": 1.998897903297879e-05, "loss": 0.20186882019042968, "step": 440 }, { "epoch": 0.045624196031962286, "grad_norm": 9.136218070983887, "learning_rate": 1.9987384079608362e-05, "loss": 0.19529831409454346, "step": 450 }, { "epoch": 0.04663806705489478, "grad_norm": 5.015270709991455, "learning_rate": 1.998568145275201e-05, "loss": 0.20977776050567626, "step": 460 }, { "epoch": 0.04765193807782728, "grad_norm": 2.030641794204712, "learning_rate": 1.998387117076566e-05, "loss": 0.20386183261871338, "step": 470 }, { "epoch": 0.04866580910075977, "grad_norm": 4.366196632385254, "learning_rate": 1.998195325316588e-05, "loss": 0.1892482280731201, "step": 480 }, { "epoch": 0.04967968012369226, "grad_norm": 6.147183895111084, "learning_rate": 1.997992772062964e-05, "loss": 0.21510298252105714, "step": 490 }, { "epoch": 0.05069355114662476, "grad_norm": 9.439059257507324, "learning_rate": 1.9977794594994103e-05, "loss": 0.20907835960388182, "step": 500 }, { "epoch": 0.05170742216955725, "grad_norm": 4.398396015167236, "learning_rate": 1.9975553899256388e-05, "loss": 0.1916116952896118, "step": 510 }, { "epoch": 0.05272129319248975, "grad_norm": 3.9749207496643066, "learning_rate": 1.9973205657573328e-05, "loss": 0.19319522380828857, "step": 520 }, { "epoch": 0.053735164215422244, "grad_norm": 6.249217987060547, "learning_rate": 1.99707498952612e-05, "loss": 0.18762538433074952, "step": 530 }, { "epoch": 0.05474903523835474, "grad_norm": 5.271851539611816, "learning_rate": 1.9968186638795445e-05, "loss": 0.17093262672424317, "step": 540 }, { "epoch": 0.055762906261287236, "grad_norm": 4.920900821685791, "learning_rate": 1.9965515915810408e-05, "loss": 0.179451584815979, "step": 550 }, { "epoch": 0.05677677728421973, "grad_norm": 5.468657970428467, "learning_rate": 1.9962737755099023e-05, "loss": 0.1971689224243164, "step": 560 }, { "epoch": 0.05779064830715223, "grad_norm": 4.106780529022217, "learning_rate": 1.9959852186612492e-05, "loss": 0.19028024673461913, "step": 570 }, { "epoch": 0.05880451933008472, "grad_norm": 6.448229789733887, "learning_rate": 1.995685924145999e-05, "loss": 0.1879900097846985, "step": 580 }, { "epoch": 0.05981839035301722, "grad_norm": 6.7330241203308105, "learning_rate": 1.9953758951908305e-05, "loss": 0.1773219347000122, "step": 590 }, { "epoch": 0.060832261375949714, "grad_norm": 4.556361675262451, "learning_rate": 1.995055135138151e-05, "loss": 0.1945796012878418, "step": 600 }, { "epoch": 0.06184613239888221, "grad_norm": 5.205209255218506, "learning_rate": 1.994723647446058e-05, "loss": 0.20014376640319825, "step": 610 }, { "epoch": 0.0628600034218147, "grad_norm": 3.866236686706543, "learning_rate": 1.994381435688303e-05, "loss": 0.19155645370483398, "step": 620 }, { "epoch": 0.0638738744447472, "grad_norm": 4.289843559265137, "learning_rate": 1.994028503554255e-05, "loss": 0.18145978450775146, "step": 630 }, { "epoch": 0.0648877454676797, "grad_norm": 5.502810001373291, "learning_rate": 1.9936648548488568e-05, "loss": 0.1958376407623291, "step": 640 }, { "epoch": 0.06590161649061219, "grad_norm": 8.166403770446777, "learning_rate": 1.993290493492587e-05, "loss": 0.1857082486152649, "step": 650 }, { "epoch": 0.06691548751354469, "grad_norm": 6.59149694442749, "learning_rate": 1.9929054235214168e-05, "loss": 0.18010231256484985, "step": 660 }, { "epoch": 0.06792935853647718, "grad_norm": 6.2142720222473145, "learning_rate": 1.992509649086766e-05, "loss": 0.15861959457397462, "step": 670 }, { "epoch": 0.06894322955940968, "grad_norm": 3.789039373397827, "learning_rate": 1.9921031744554588e-05, "loss": 0.20805740356445312, "step": 680 }, { "epoch": 0.06995710058234217, "grad_norm": 6.444082736968994, "learning_rate": 1.991686004009678e-05, "loss": 0.18405556678771973, "step": 690 }, { "epoch": 0.07097097160527466, "grad_norm": 5.020689487457275, "learning_rate": 1.991258142246917e-05, "loss": 0.19572935104370118, "step": 700 }, { "epoch": 0.07198484262820716, "grad_norm": 6.295537948608398, "learning_rate": 1.990819593779932e-05, "loss": 0.19444732666015624, "step": 710 }, { "epoch": 0.07299871365113965, "grad_norm": 5.7630295753479, "learning_rate": 1.9903703633366923e-05, "loss": 0.1895642638206482, "step": 720 }, { "epoch": 0.07401258467407215, "grad_norm": 7.437016010284424, "learning_rate": 1.9899104557603285e-05, "loss": 0.17509762048721314, "step": 730 }, { "epoch": 0.07502645569700464, "grad_norm": 6.682457447052002, "learning_rate": 1.9894398760090807e-05, "loss": 0.21540846824645996, "step": 740 }, { "epoch": 0.07604032671993714, "grad_norm": 6.031078815460205, "learning_rate": 1.988958629156246e-05, "loss": 0.1921164870262146, "step": 750 }, { "epoch": 0.07705419774286963, "grad_norm": 2.6413254737854004, "learning_rate": 1.988466720390123e-05, "loss": 0.19180084466934205, "step": 760 }, { "epoch": 0.07806806876580213, "grad_norm": 5.105860233306885, "learning_rate": 1.9879641550139545e-05, "loss": 0.1862693428993225, "step": 770 }, { "epoch": 0.07908193978873462, "grad_norm": 5.992903709411621, "learning_rate": 1.9874509384458726e-05, "loss": 0.18619463443756104, "step": 780 }, { "epoch": 0.08009581081166713, "grad_norm": 2.4909920692443848, "learning_rate": 1.9869270762188402e-05, "loss": 0.18455719947814941, "step": 790 }, { "epoch": 0.08110968183459961, "grad_norm": 5.992520809173584, "learning_rate": 1.986392573980589e-05, "loss": 0.19353729486465454, "step": 800 }, { "epoch": 0.08212355285753212, "grad_norm": 3.7040157318115234, "learning_rate": 1.9858474374935606e-05, "loss": 0.18126453161239625, "step": 810 }, { "epoch": 0.0831374238804646, "grad_norm": 3.0903444290161133, "learning_rate": 1.9852916726348446e-05, "loss": 0.18586604595184325, "step": 820 }, { "epoch": 0.0841512949033971, "grad_norm": 3.2024335861206055, "learning_rate": 1.9847252853961136e-05, "loss": 0.17958736419677734, "step": 830 }, { "epoch": 0.0851651659263296, "grad_norm": 5.868228435516357, "learning_rate": 1.98414828188356e-05, "loss": 0.19275975227355957, "step": 840 }, { "epoch": 0.08617903694926209, "grad_norm": 3.6876020431518555, "learning_rate": 1.98356066831783e-05, "loss": 0.1866382598876953, "step": 850 }, { "epoch": 0.08719290797219459, "grad_norm": 3.578542709350586, "learning_rate": 1.982962451033956e-05, "loss": 0.1862724781036377, "step": 860 }, { "epoch": 0.08820677899512708, "grad_norm": 4.297239303588867, "learning_rate": 1.9823536364812875e-05, "loss": 0.17467619180679322, "step": 870 }, { "epoch": 0.08922065001805958, "grad_norm": 5.030392169952393, "learning_rate": 1.981734231223425e-05, "loss": 0.160123074054718, "step": 880 }, { "epoch": 0.09023452104099207, "grad_norm": 6.9222893714904785, "learning_rate": 1.9811042419381444e-05, "loss": 0.1841423273086548, "step": 890 }, { "epoch": 0.09124839206392457, "grad_norm": 5.505918025970459, "learning_rate": 1.980463675417329e-05, "loss": 0.17647252082824708, "step": 900 }, { "epoch": 0.09226226308685706, "grad_norm": 6.575755596160889, "learning_rate": 1.9798125385668942e-05, "loss": 0.18753652572631835, "step": 910 }, { "epoch": 0.09327613410978956, "grad_norm": 3.614300012588501, "learning_rate": 1.9791508384067138e-05, "loss": 0.17921411991119385, "step": 920 }, { "epoch": 0.09429000513272205, "grad_norm": 3.4898571968078613, "learning_rate": 1.9784785820705435e-05, "loss": 0.19246543645858766, "step": 930 }, { "epoch": 0.09530387615565455, "grad_norm": 5.355691432952881, "learning_rate": 1.9777957768059456e-05, "loss": 0.17592918872833252, "step": 940 }, { "epoch": 0.09631774717858704, "grad_norm": 8.686025619506836, "learning_rate": 1.977102429974209e-05, "loss": 0.18732056617736817, "step": 950 }, { "epoch": 0.09733161820151955, "grad_norm": 4.657790660858154, "learning_rate": 1.9763985490502714e-05, "loss": 0.16074410676956177, "step": 960 }, { "epoch": 0.09834548922445203, "grad_norm": 4.540040493011475, "learning_rate": 1.9756841416226372e-05, "loss": 0.18997480869293212, "step": 970 }, { "epoch": 0.09935936024738452, "grad_norm": 4.154084205627441, "learning_rate": 1.9749592153932974e-05, "loss": 0.18438781499862672, "step": 980 }, { "epoch": 0.10037323127031703, "grad_norm": 7.1951904296875, "learning_rate": 1.9742237781776455e-05, "loss": 0.17535382509231567, "step": 990 }, { "epoch": 0.10138710229324951, "grad_norm": 3.8317081928253174, "learning_rate": 1.9734778379043923e-05, "loss": 0.19298963546752929, "step": 1000 }, { "epoch": 0.10240097331618202, "grad_norm": 3.5647923946380615, "learning_rate": 1.9727214026154827e-05, "loss": 0.17747700214385986, "step": 1010 }, { "epoch": 0.1034148443391145, "grad_norm": 4.633984088897705, "learning_rate": 1.9719544804660084e-05, "loss": 0.19532750844955443, "step": 1020 }, { "epoch": 0.10442871536204701, "grad_norm": 9.078704833984375, "learning_rate": 1.9711770797241174e-05, "loss": 0.19000301361083985, "step": 1030 }, { "epoch": 0.1054425863849795, "grad_norm": 3.2882885932922363, "learning_rate": 1.9703892087709287e-05, "loss": 0.15756874084472655, "step": 1040 }, { "epoch": 0.106456457407912, "grad_norm": 1.8342398405075073, "learning_rate": 1.9695908761004392e-05, "loss": 0.16608941555023193, "step": 1050 }, { "epoch": 0.10747032843084449, "grad_norm": 2.8276236057281494, "learning_rate": 1.9687820903194335e-05, "loss": 0.15690202713012696, "step": 1060 }, { "epoch": 0.10848419945377699, "grad_norm": 2.8573203086853027, "learning_rate": 1.9679628601473905e-05, "loss": 0.20310654640197753, "step": 1070 }, { "epoch": 0.10949807047670948, "grad_norm": 6.750394821166992, "learning_rate": 1.967133194416389e-05, "loss": 0.17568986415863036, "step": 1080 }, { "epoch": 0.11051194149964198, "grad_norm": 6.260215759277344, "learning_rate": 1.9662931020710138e-05, "loss": 0.18261537551879883, "step": 1090 }, { "epoch": 0.11152581252257447, "grad_norm": 2.0599117279052734, "learning_rate": 1.965442592168259e-05, "loss": 0.19706878662109376, "step": 1100 }, { "epoch": 0.11253968354550696, "grad_norm": 4.966343402862549, "learning_rate": 1.964581673877428e-05, "loss": 0.16898794174194337, "step": 1110 }, { "epoch": 0.11355355456843946, "grad_norm": 1.5340001583099365, "learning_rate": 1.9637103564800384e-05, "loss": 0.1704729199409485, "step": 1120 }, { "epoch": 0.11456742559137195, "grad_norm": 4.358741760253906, "learning_rate": 1.962828649369719e-05, "loss": 0.1887378215789795, "step": 1130 }, { "epoch": 0.11558129661430445, "grad_norm": 6.004284381866455, "learning_rate": 1.96193656205211e-05, "loss": 0.17892675399780272, "step": 1140 }, { "epoch": 0.11659516763723694, "grad_norm": 3.316324472427368, "learning_rate": 1.9610341041447595e-05, "loss": 0.17767565250396727, "step": 1150 }, { "epoch": 0.11760903866016945, "grad_norm": 2.7632627487182617, "learning_rate": 1.9601212853770214e-05, "loss": 0.16793251037597656, "step": 1160 }, { "epoch": 0.11862290968310193, "grad_norm": 6.902182102203369, "learning_rate": 1.959198115589949e-05, "loss": 0.20009450912475585, "step": 1170 }, { "epoch": 0.11963678070603444, "grad_norm": 2.7308056354522705, "learning_rate": 1.9582646047361888e-05, "loss": 0.16866352558135986, "step": 1180 }, { "epoch": 0.12065065172896693, "grad_norm": 1.8271749019622803, "learning_rate": 1.9573207628798747e-05, "loss": 0.1748752474784851, "step": 1190 }, { "epoch": 0.12166452275189943, "grad_norm": 2.7246882915496826, "learning_rate": 1.956366600196519e-05, "loss": 0.1915472388267517, "step": 1200 }, { "epoch": 0.12267839377483192, "grad_norm": 1.7913086414337158, "learning_rate": 1.9554021269729003e-05, "loss": 0.1706780433654785, "step": 1210 }, { "epoch": 0.12369226479776442, "grad_norm": 3.201045513153076, "learning_rate": 1.9544273536069573e-05, "loss": 0.1776430368423462, "step": 1220 }, { "epoch": 0.12470613582069691, "grad_norm": 4.728579998016357, "learning_rate": 1.9534422906076714e-05, "loss": 0.18694002628326417, "step": 1230 }, { "epoch": 0.1257200068436294, "grad_norm": 1.909864068031311, "learning_rate": 1.9524469485949586e-05, "loss": 0.18598721027374268, "step": 1240 }, { "epoch": 0.1267338778665619, "grad_norm": 4.389528274536133, "learning_rate": 1.9514413382995498e-05, "loss": 0.19729926586151122, "step": 1250 }, { "epoch": 0.1277477488894944, "grad_norm": 5.753577709197998, "learning_rate": 1.9504254705628806e-05, "loss": 0.17821987867355346, "step": 1260 }, { "epoch": 0.12876161991242688, "grad_norm": 1.9967716932296753, "learning_rate": 1.9493993563369688e-05, "loss": 0.19371373653411866, "step": 1270 }, { "epoch": 0.1297754909353594, "grad_norm": 5.902470111846924, "learning_rate": 1.9483630066843005e-05, "loss": 0.17197438478469848, "step": 1280 }, { "epoch": 0.13078936195829188, "grad_norm": 2.695117473602295, "learning_rate": 1.9473164327777095e-05, "loss": 0.16276512145996094, "step": 1290 }, { "epoch": 0.13180323298122437, "grad_norm": 5.101327896118164, "learning_rate": 1.9462596459002565e-05, "loss": 0.18303682804107665, "step": 1300 }, { "epoch": 0.13281710400415686, "grad_norm": 1.7452325820922852, "learning_rate": 1.9451926574451074e-05, "loss": 0.16458845138549805, "step": 1310 }, { "epoch": 0.13383097502708938, "grad_norm": 2.226696491241455, "learning_rate": 1.944115478915412e-05, "loss": 0.16971166133880616, "step": 1320 }, { "epoch": 0.13484484605002187, "grad_norm": 5.213453769683838, "learning_rate": 1.9430281219241767e-05, "loss": 0.1727039098739624, "step": 1330 }, { "epoch": 0.13585871707295435, "grad_norm": 4.113743305206299, "learning_rate": 1.9419305981941436e-05, "loss": 0.18202898502349854, "step": 1340 }, { "epoch": 0.13687258809588684, "grad_norm": 3.9898152351379395, "learning_rate": 1.94082291955766e-05, "loss": 0.16357381343841554, "step": 1350 }, { "epoch": 0.13788645911881936, "grad_norm": 3.9995291233062744, "learning_rate": 1.939705097956554e-05, "loss": 0.16889476776123047, "step": 1360 }, { "epoch": 0.13890033014175185, "grad_norm": 2.8031697273254395, "learning_rate": 1.9385771454420048e-05, "loss": 0.17951802015304566, "step": 1370 }, { "epoch": 0.13991420116468434, "grad_norm": 4.656792640686035, "learning_rate": 1.9374390741744107e-05, "loss": 0.16987377405166626, "step": 1380 }, { "epoch": 0.14092807218761683, "grad_norm": 6.78140926361084, "learning_rate": 1.9362908964232616e-05, "loss": 0.19569728374481202, "step": 1390 }, { "epoch": 0.14194194321054932, "grad_norm": 2.7739100456237793, "learning_rate": 1.9351326245670038e-05, "loss": 0.18415477275848388, "step": 1400 }, { "epoch": 0.14295581423348183, "grad_norm": 4.088301658630371, "learning_rate": 1.933964271092908e-05, "loss": 0.1691323161125183, "step": 1410 }, { "epoch": 0.14396968525641432, "grad_norm": 2.388636827468872, "learning_rate": 1.932785848596934e-05, "loss": 0.19616374969482422, "step": 1420 }, { "epoch": 0.1449835562793468, "grad_norm": 3.312066078186035, "learning_rate": 1.9315973697835966e-05, "loss": 0.18437666893005372, "step": 1430 }, { "epoch": 0.1459974273022793, "grad_norm": 2.916862964630127, "learning_rate": 1.930398847465825e-05, "loss": 0.17030618190765381, "step": 1440 }, { "epoch": 0.14701129832521181, "grad_norm": 2.9020636081695557, "learning_rate": 1.9291902945648283e-05, "loss": 0.16182222366333007, "step": 1450 }, { "epoch": 0.1480251693481443, "grad_norm": 3.546509265899658, "learning_rate": 1.9279717241099554e-05, "loss": 0.1899935007095337, "step": 1460 }, { "epoch": 0.1490390403710768, "grad_norm": 1.826587200164795, "learning_rate": 1.9267431492385524e-05, "loss": 0.18424396514892577, "step": 1470 }, { "epoch": 0.15005291139400928, "grad_norm": 2.6257100105285645, "learning_rate": 1.925504583195823e-05, "loss": 0.17404019832611084, "step": 1480 }, { "epoch": 0.1510667824169418, "grad_norm": 2.132905960083008, "learning_rate": 1.924256039334686e-05, "loss": 0.18383276462554932, "step": 1490 }, { "epoch": 0.15208065343987429, "grad_norm": 2.7494001388549805, "learning_rate": 1.9229975311156305e-05, "loss": 0.18311716318130494, "step": 1500 }, { "epoch": 0.15309452446280677, "grad_norm": 3.04227614402771, "learning_rate": 1.9217290721065693e-05, "loss": 0.18842153549194335, "step": 1510 }, { "epoch": 0.15410839548573926, "grad_norm": 8.316437721252441, "learning_rate": 1.9204506759826957e-05, "loss": 0.17729623317718507, "step": 1520 }, { "epoch": 0.15512226650867175, "grad_norm": 2.3050310611724854, "learning_rate": 1.9191623565263342e-05, "loss": 0.17257111072540282, "step": 1530 }, { "epoch": 0.15613613753160427, "grad_norm": 2.3211262226104736, "learning_rate": 1.9178641276267922e-05, "loss": 0.1822495937347412, "step": 1540 }, { "epoch": 0.15715000855453676, "grad_norm": 1.7850751876831055, "learning_rate": 1.91655600328021e-05, "loss": 0.1808951497077942, "step": 1550 }, { "epoch": 0.15816387957746925, "grad_norm": 5.168383598327637, "learning_rate": 1.91523799758941e-05, "loss": 0.1696903944015503, "step": 1560 }, { "epoch": 0.15917775060040174, "grad_norm": 5.179516315460205, "learning_rate": 1.9139101247637465e-05, "loss": 0.16992257833480834, "step": 1570 }, { "epoch": 0.16019162162333425, "grad_norm": 4.750335216522217, "learning_rate": 1.912572399118949e-05, "loss": 0.17295485734939575, "step": 1580 }, { "epoch": 0.16120549264626674, "grad_norm": 5.075170516967773, "learning_rate": 1.9112248350769704e-05, "loss": 0.1901534914970398, "step": 1590 }, { "epoch": 0.16221936366919923, "grad_norm": 4.062738418579102, "learning_rate": 1.909867447165831e-05, "loss": 0.16737675666809082, "step": 1600 }, { "epoch": 0.16323323469213172, "grad_norm": 1.6387624740600586, "learning_rate": 1.908500250019462e-05, "loss": 0.17448633909225464, "step": 1610 }, { "epoch": 0.16424710571506423, "grad_norm": 4.930589199066162, "learning_rate": 1.9071232583775465e-05, "loss": 0.16891195774078369, "step": 1620 }, { "epoch": 0.16526097673799672, "grad_norm": 2.7544565200805664, "learning_rate": 1.9057364870853628e-05, "loss": 0.15351226329803466, "step": 1630 }, { "epoch": 0.1662748477609292, "grad_norm": 3.460505962371826, "learning_rate": 1.904339951093622e-05, "loss": 0.17251522541046144, "step": 1640 }, { "epoch": 0.1672887187838617, "grad_norm": 2.8821370601654053, "learning_rate": 1.902933665458309e-05, "loss": 0.17019891738891602, "step": 1650 }, { "epoch": 0.1683025898067942, "grad_norm": 3.277745485305786, "learning_rate": 1.901517645340518e-05, "loss": 0.18318748474121094, "step": 1660 }, { "epoch": 0.1693164608297267, "grad_norm": 5.395684242248535, "learning_rate": 1.900091906006291e-05, "loss": 0.18512455224990845, "step": 1670 }, { "epoch": 0.1703303318526592, "grad_norm": 2.2008895874023438, "learning_rate": 1.8986564628264527e-05, "loss": 0.18008005619049072, "step": 1680 }, { "epoch": 0.17134420287559168, "grad_norm": 2.2996907234191895, "learning_rate": 1.8972113312764432e-05, "loss": 0.16530574560165406, "step": 1690 }, { "epoch": 0.17235807389852417, "grad_norm": 2.7414591312408447, "learning_rate": 1.895756526936153e-05, "loss": 0.1677762508392334, "step": 1700 }, { "epoch": 0.1733719449214567, "grad_norm": 3.998300313949585, "learning_rate": 1.8942920654897553e-05, "loss": 0.17886919975280763, "step": 1710 }, { "epoch": 0.17438581594438918, "grad_norm": 1.5593184232711792, "learning_rate": 1.8928179627255347e-05, "loss": 0.18745567798614501, "step": 1720 }, { "epoch": 0.17539968696732167, "grad_norm": 3.4035770893096924, "learning_rate": 1.891334234535719e-05, "loss": 0.18033384084701537, "step": 1730 }, { "epoch": 0.17641355799025416, "grad_norm": 3.590315580368042, "learning_rate": 1.8898408969163078e-05, "loss": 0.16178200244903565, "step": 1740 }, { "epoch": 0.17742742901318667, "grad_norm": 2.6033828258514404, "learning_rate": 1.8883379659668987e-05, "loss": 0.1841306209564209, "step": 1750 }, { "epoch": 0.17844130003611916, "grad_norm": 5.042605876922607, "learning_rate": 1.8868254578905147e-05, "loss": 0.18538169860839843, "step": 1760 }, { "epoch": 0.17945517105905165, "grad_norm": 3.4817183017730713, "learning_rate": 1.8853033889934293e-05, "loss": 0.14793480634689332, "step": 1770 }, { "epoch": 0.18046904208198414, "grad_norm": 2.228550672531128, "learning_rate": 1.883771775684991e-05, "loss": 0.15494861602783203, "step": 1780 }, { "epoch": 0.18148291310491665, "grad_norm": 5.2305192947387695, "learning_rate": 1.882230634477446e-05, "loss": 0.1757431983947754, "step": 1790 }, { "epoch": 0.18249678412784914, "grad_norm": 5.082123756408691, "learning_rate": 1.8806799819857598e-05, "loss": 0.18390678167343139, "step": 1800 }, { "epoch": 0.18351065515078163, "grad_norm": 2.4519565105438232, "learning_rate": 1.8791198349274393e-05, "loss": 0.16217124462127686, "step": 1810 }, { "epoch": 0.18452452617371412, "grad_norm": 3.3334152698516846, "learning_rate": 1.8775502101223516e-05, "loss": 0.18717586994171143, "step": 1820 }, { "epoch": 0.1855383971966466, "grad_norm": 6.539174556732178, "learning_rate": 1.8759711244925424e-05, "loss": 0.1750849485397339, "step": 1830 }, { "epoch": 0.18655226821957913, "grad_norm": 2.141798734664917, "learning_rate": 1.874382595062055e-05, "loss": 0.15058544874191285, "step": 1840 }, { "epoch": 0.18756613924251161, "grad_norm": 1.7195626497268677, "learning_rate": 1.8727846389567457e-05, "loss": 0.17000839710235596, "step": 1850 }, { "epoch": 0.1885800102654441, "grad_norm": 3.736764669418335, "learning_rate": 1.871177273404098e-05, "loss": 0.1839374303817749, "step": 1860 }, { "epoch": 0.1895938812883766, "grad_norm": 4.085079193115234, "learning_rate": 1.8695605157330398e-05, "loss": 0.15277607440948487, "step": 1870 }, { "epoch": 0.1906077523113091, "grad_norm": 3.944794178009033, "learning_rate": 1.8679343833737546e-05, "loss": 0.19020895957946776, "step": 1880 }, { "epoch": 0.1916216233342416, "grad_norm": 3.326385498046875, "learning_rate": 1.8662988938574926e-05, "loss": 0.17483596801757811, "step": 1890 }, { "epoch": 0.1926354943571741, "grad_norm": 2.7712783813476562, "learning_rate": 1.8646540648163853e-05, "loss": 0.1604238271713257, "step": 1900 }, { "epoch": 0.19364936538010658, "grad_norm": 3.667792797088623, "learning_rate": 1.862999913983251e-05, "loss": 0.18005073070526123, "step": 1910 }, { "epoch": 0.1946632364030391, "grad_norm": 3.7287473678588867, "learning_rate": 1.8613364591914073e-05, "loss": 0.16084756851196289, "step": 1920 }, { "epoch": 0.19567710742597158, "grad_norm": 4.000404357910156, "learning_rate": 1.8596637183744762e-05, "loss": 0.15982942581176757, "step": 1930 }, { "epoch": 0.19669097844890407, "grad_norm": 4.82677698135376, "learning_rate": 1.857981709566193e-05, "loss": 0.18506927490234376, "step": 1940 }, { "epoch": 0.19770484947183656, "grad_norm": 3.5581159591674805, "learning_rate": 1.85629045090021e-05, "loss": 0.16716216802597045, "step": 1950 }, { "epoch": 0.19871872049476905, "grad_norm": 1.9139454364776611, "learning_rate": 1.854589960609902e-05, "loss": 0.14113919734954833, "step": 1960 }, { "epoch": 0.19973259151770156, "grad_norm": 3.3047378063201904, "learning_rate": 1.8528802570281686e-05, "loss": 0.18284027576446532, "step": 1970 }, { "epoch": 0.20074646254063405, "grad_norm": 6.071436405181885, "learning_rate": 1.851161358587239e-05, "loss": 0.16734676361083983, "step": 1980 }, { "epoch": 0.20176033356356654, "grad_norm": 4.218473434448242, "learning_rate": 1.8494332838184707e-05, "loss": 0.18762476444244386, "step": 1990 }, { "epoch": 0.20277420458649903, "grad_norm": 3.1957690715789795, "learning_rate": 1.847696051352151e-05, "loss": 0.1711023211479187, "step": 2000 }, { "epoch": 0.20378807560943155, "grad_norm": 2.622096538543701, "learning_rate": 1.8459496799172957e-05, "loss": 0.16365506649017333, "step": 2010 }, { "epoch": 0.20480194663236403, "grad_norm": 7.009904861450195, "learning_rate": 1.8441941883414475e-05, "loss": 0.1930461645126343, "step": 2020 }, { "epoch": 0.20581581765529652, "grad_norm": 3.3173980712890625, "learning_rate": 1.8424295955504727e-05, "loss": 0.16084713935852052, "step": 2030 }, { "epoch": 0.206829688678229, "grad_norm": 2.44771146774292, "learning_rate": 1.840655920568358e-05, "loss": 0.1825677752494812, "step": 2040 }, { "epoch": 0.20784355970116153, "grad_norm": 3.53401517868042, "learning_rate": 1.838873182517004e-05, "loss": 0.17280490398406984, "step": 2050 }, { "epoch": 0.20885743072409402, "grad_norm": 3.6340763568878174, "learning_rate": 1.83708140061602e-05, "loss": 0.17874839305877685, "step": 2060 }, { "epoch": 0.2098713017470265, "grad_norm": 3.9101343154907227, "learning_rate": 1.835280594182517e-05, "loss": 0.16378943920135497, "step": 2070 }, { "epoch": 0.210885172769959, "grad_norm": 2.7655560970306396, "learning_rate": 1.833470782630898e-05, "loss": 0.17389062643051148, "step": 2080 }, { "epoch": 0.21189904379289148, "grad_norm": 5.017838954925537, "learning_rate": 1.831651985472651e-05, "loss": 0.17456300258636476, "step": 2090 }, { "epoch": 0.212912914815824, "grad_norm": 5.426383972167969, "learning_rate": 1.8298242223161362e-05, "loss": 0.18809338808059692, "step": 2100 }, { "epoch": 0.2139267858387565, "grad_norm": 6.358447074890137, "learning_rate": 1.827987512866377e-05, "loss": 0.16582982540130614, "step": 2110 }, { "epoch": 0.21494065686168898, "grad_norm": 4.604915142059326, "learning_rate": 1.826141876924845e-05, "loss": 0.16502951383590697, "step": 2120 }, { "epoch": 0.21595452788462147, "grad_norm": 7.161838531494141, "learning_rate": 1.8242873343892494e-05, "loss": 0.18845340013504028, "step": 2130 }, { "epoch": 0.21696839890755398, "grad_norm": 2.8916618824005127, "learning_rate": 1.8224239052533194e-05, "loss": 0.17408318519592286, "step": 2140 }, { "epoch": 0.21798226993048647, "grad_norm": 4.2335429191589355, "learning_rate": 1.820551609606591e-05, "loss": 0.1716212034225464, "step": 2150 }, { "epoch": 0.21899614095341896, "grad_norm": 2.2072935104370117, "learning_rate": 1.81867046763419e-05, "loss": 0.18640540838241576, "step": 2160 }, { "epoch": 0.22001001197635145, "grad_norm": 3.153362274169922, "learning_rate": 1.816780499616613e-05, "loss": 0.18029110431671141, "step": 2170 }, { "epoch": 0.22102388299928397, "grad_norm": 2.3341481685638428, "learning_rate": 1.81488172592951e-05, "loss": 0.16624232530593872, "step": 2180 }, { "epoch": 0.22203775402221645, "grad_norm": 2.3849427700042725, "learning_rate": 1.812974167043465e-05, "loss": 0.1738212823867798, "step": 2190 }, { "epoch": 0.22305162504514894, "grad_norm": 2.2778351306915283, "learning_rate": 1.8110578435237748e-05, "loss": 0.17333707809448243, "step": 2200 }, { "epoch": 0.22406549606808143, "grad_norm": 2.7515206336975098, "learning_rate": 1.8091327760302267e-05, "loss": 0.18010516166687013, "step": 2210 }, { "epoch": 0.22507936709101392, "grad_norm": 10.790781021118164, "learning_rate": 1.8071989853168765e-05, "loss": 0.2147979497909546, "step": 2220 }, { "epoch": 0.22609323811394644, "grad_norm": 1.4795092344284058, "learning_rate": 1.8052564922318247e-05, "loss": 0.17883093357086183, "step": 2230 }, { "epoch": 0.22710710913687893, "grad_norm": 6.384800434112549, "learning_rate": 1.803305317716992e-05, "loss": 0.1799437880516052, "step": 2240 }, { "epoch": 0.22812098015981142, "grad_norm": 4.902544021606445, "learning_rate": 1.8013454828078925e-05, "loss": 0.16137821674346925, "step": 2250 }, { "epoch": 0.2291348511827439, "grad_norm": 3.18807315826416, "learning_rate": 1.7993770086334082e-05, "loss": 0.16014958620071412, "step": 2260 }, { "epoch": 0.23014872220567642, "grad_norm": 3.1672346591949463, "learning_rate": 1.7973999164155597e-05, "loss": 0.16048042774200438, "step": 2270 }, { "epoch": 0.2311625932286089, "grad_norm": 3.612168073654175, "learning_rate": 1.795414227469279e-05, "loss": 0.1521836996078491, "step": 2280 }, { "epoch": 0.2321764642515414, "grad_norm": 3.3856821060180664, "learning_rate": 1.7934199632021795e-05, "loss": 0.16845252513885497, "step": 2290 }, { "epoch": 0.2331903352744739, "grad_norm": 2.824951171875, "learning_rate": 1.7914171451143235e-05, "loss": 0.1802909255027771, "step": 2300 }, { "epoch": 0.2342042062974064, "grad_norm": 1.8973057270050049, "learning_rate": 1.7894057947979923e-05, "loss": 0.16302382946014404, "step": 2310 }, { "epoch": 0.2352180773203389, "grad_norm": 4.029202461242676, "learning_rate": 1.7873859339374528e-05, "loss": 0.18916542530059816, "step": 2320 }, { "epoch": 0.23623194834327138, "grad_norm": 6.45179557800293, "learning_rate": 1.7853575843087227e-05, "loss": 0.16492094993591308, "step": 2330 }, { "epoch": 0.23724581936620387, "grad_norm": 2.6063263416290283, "learning_rate": 1.7833207677793382e-05, "loss": 0.1679621696472168, "step": 2340 }, { "epoch": 0.23825969038913636, "grad_norm": 1.7064225673675537, "learning_rate": 1.7812755063081156e-05, "loss": 0.16452376842498778, "step": 2350 }, { "epoch": 0.23927356141206887, "grad_norm": 3.8834385871887207, "learning_rate": 1.7792218219449165e-05, "loss": 0.16758580207824708, "step": 2360 }, { "epoch": 0.24028743243500136, "grad_norm": 4.209020137786865, "learning_rate": 1.777159736830408e-05, "loss": 0.16042823791503907, "step": 2370 }, { "epoch": 0.24130130345793385, "grad_norm": 2.435249090194702, "learning_rate": 1.7750892731958268e-05, "loss": 0.16390614509582518, "step": 2380 }, { "epoch": 0.24231517448086634, "grad_norm": 2.016329050064087, "learning_rate": 1.773010453362737e-05, "loss": 0.1644516706466675, "step": 2390 }, { "epoch": 0.24332904550379886, "grad_norm": 1.8088144063949585, "learning_rate": 1.770923299742791e-05, "loss": 0.1619895339012146, "step": 2400 }, { "epoch": 0.24434291652673135, "grad_norm": 2.6573781967163086, "learning_rate": 1.768827834837487e-05, "loss": 0.1632648229598999, "step": 2410 }, { "epoch": 0.24535678754966384, "grad_norm": 6.772780418395996, "learning_rate": 1.7667240812379266e-05, "loss": 0.15115861892700194, "step": 2420 }, { "epoch": 0.24637065857259632, "grad_norm": 10.981486320495605, "learning_rate": 1.7646120616245724e-05, "loss": 0.8582809448242188, "step": 2430 }, { "epoch": 0.24738452959552884, "grad_norm": 7.959832191467285, "learning_rate": 1.7624917987670006e-05, "loss": 0.3126258850097656, "step": 2440 }, { "epoch": 0.24839840061846133, "grad_norm": 4.006941318511963, "learning_rate": 1.7603633155236595e-05, "loss": 0.26241168975830076, "step": 2450 }, { "epoch": 0.24941227164139382, "grad_norm": 4.295755863189697, "learning_rate": 1.7582266348416194e-05, "loss": 0.29906747341156004, "step": 2460 }, { "epoch": 0.25042614266432633, "grad_norm": 3.127108097076416, "learning_rate": 1.7560817797563275e-05, "loss": 0.2668452262878418, "step": 2470 }, { "epoch": 0.2514400136872588, "grad_norm": 1.5118516683578491, "learning_rate": 1.7539287733913592e-05, "loss": 0.26598546504974363, "step": 2480 }, { "epoch": 0.2524538847101913, "grad_norm": 3.257399082183838, "learning_rate": 1.7517676389581675e-05, "loss": 0.251536226272583, "step": 2490 }, { "epoch": 0.2534677557331238, "grad_norm": 3.399141788482666, "learning_rate": 1.7495983997558342e-05, "loss": 0.22569761276245118, "step": 2500 }, { "epoch": 0.2544816267560563, "grad_norm": 7.952875137329102, "learning_rate": 1.7474210791708177e-05, "loss": 0.26285016536712646, "step": 2510 }, { "epoch": 0.2554954977789888, "grad_norm": 2.8520424365997314, "learning_rate": 1.7452357006767026e-05, "loss": 0.23818569183349608, "step": 2520 }, { "epoch": 0.25650936880192127, "grad_norm": 3.010012149810791, "learning_rate": 1.7430422878339443e-05, "loss": 0.2211090326309204, "step": 2530 }, { "epoch": 0.25752323982485376, "grad_norm": 5.0672407150268555, "learning_rate": 1.740840864289616e-05, "loss": 0.20726125240325927, "step": 2540 }, { "epoch": 0.2585371108477863, "grad_norm": 2.9761931896209717, "learning_rate": 1.7386314537771553e-05, "loss": 0.221229887008667, "step": 2550 }, { "epoch": 0.2595509818707188, "grad_norm": 9.730382919311523, "learning_rate": 1.736414080116105e-05, "loss": 0.2609580993652344, "step": 2560 }, { "epoch": 0.2605648528936513, "grad_norm": 3.4034693241119385, "learning_rate": 1.7341887672118596e-05, "loss": 0.22977979183197023, "step": 2570 }, { "epoch": 0.26157872391658377, "grad_norm": 4.1712422370910645, "learning_rate": 1.7319555390554054e-05, "loss": 0.27167131900787356, "step": 2580 }, { "epoch": 0.26259259493951626, "grad_norm": 2.878018856048584, "learning_rate": 1.7297144197230637e-05, "loss": 0.2498851776123047, "step": 2590 }, { "epoch": 0.26360646596244874, "grad_norm": 2.8747172355651855, "learning_rate": 1.7274654333762284e-05, "loss": 0.20545487403869628, "step": 2600 }, { "epoch": 0.26462033698538123, "grad_norm": 7.618738174438477, "learning_rate": 1.7252086042611086e-05, "loss": 0.2328094482421875, "step": 2610 }, { "epoch": 0.2656342080083137, "grad_norm": 4.777221202850342, "learning_rate": 1.722943956708466e-05, "loss": 0.21067399978637696, "step": 2620 }, { "epoch": 0.2666480790312462, "grad_norm": 3.8839306831359863, "learning_rate": 1.720671515133352e-05, "loss": 0.20731358528137206, "step": 2630 }, { "epoch": 0.26766195005417875, "grad_norm": 2.842724561691284, "learning_rate": 1.7183913040348447e-05, "loss": 0.2179274082183838, "step": 2640 }, { "epoch": 0.26867582107711124, "grad_norm": 4.04484748840332, "learning_rate": 1.716103347995785e-05, "loss": 0.20264091491699218, "step": 2650 }, { "epoch": 0.26968969210004373, "grad_norm": 2.3277571201324463, "learning_rate": 1.713807671682513e-05, "loss": 0.17479166984558106, "step": 2660 }, { "epoch": 0.2707035631229762, "grad_norm": 2.062134265899658, "learning_rate": 1.711504299844599e-05, "loss": 0.18953193426132203, "step": 2670 }, { "epoch": 0.2717174341459087, "grad_norm": 2.493117570877075, "learning_rate": 1.7091932573145798e-05, "loss": 0.19633909463882446, "step": 2680 }, { "epoch": 0.2727313051688412, "grad_norm": 6.903107166290283, "learning_rate": 1.706874569007688e-05, "loss": 0.193939208984375, "step": 2690 }, { "epoch": 0.2737451761917737, "grad_norm": 1.7162383794784546, "learning_rate": 1.7045482599215856e-05, "loss": 0.21271839141845703, "step": 2700 }, { "epoch": 0.2747590472147062, "grad_norm": 2.2109053134918213, "learning_rate": 1.7022143551360947e-05, "loss": 0.18175873756408692, "step": 2710 }, { "epoch": 0.2757729182376387, "grad_norm": 8.229119300842285, "learning_rate": 1.699872879812925e-05, "loss": 0.20843329429626464, "step": 2720 }, { "epoch": 0.2767867892605712, "grad_norm": 1.9713021516799927, "learning_rate": 1.6975238591954048e-05, "loss": 0.2161174774169922, "step": 2730 }, { "epoch": 0.2778006602835037, "grad_norm": 1.2033495903015137, "learning_rate": 1.695167318608206e-05, "loss": 0.2160245180130005, "step": 2740 }, { "epoch": 0.2788145313064362, "grad_norm": 3.8006844520568848, "learning_rate": 1.6928032834570767e-05, "loss": 0.21439573764801026, "step": 2750 }, { "epoch": 0.2798284023293687, "grad_norm": 2.9423110485076904, "learning_rate": 1.690431779228559e-05, "loss": 0.1954509973526001, "step": 2760 }, { "epoch": 0.28084227335230116, "grad_norm": 6.681204795837402, "learning_rate": 1.6880528314897212e-05, "loss": 0.18985222578048705, "step": 2770 }, { "epoch": 0.28185614437523365, "grad_norm": 3.352804183959961, "learning_rate": 1.6856664658878797e-05, "loss": 0.19194926023483277, "step": 2780 }, { "epoch": 0.28287001539816614, "grad_norm": 6.842539310455322, "learning_rate": 1.6832727081503227e-05, "loss": 0.19248008728027344, "step": 2790 }, { "epoch": 0.28388388642109863, "grad_norm": 3.366776466369629, "learning_rate": 1.6808715840840308e-05, "loss": 0.1839269995689392, "step": 2800 }, { "epoch": 0.2848977574440312, "grad_norm": 2.9577889442443848, "learning_rate": 1.6784631195754027e-05, "loss": 0.19292573928833007, "step": 2810 }, { "epoch": 0.28591162846696366, "grad_norm": 2.6954293251037598, "learning_rate": 1.6760473405899733e-05, "loss": 0.16808403730392457, "step": 2820 }, { "epoch": 0.28692549948989615, "grad_norm": 3.39117693901062, "learning_rate": 1.673624273172134e-05, "loss": 0.189668869972229, "step": 2830 }, { "epoch": 0.28793937051282864, "grad_norm": 2.362302541732788, "learning_rate": 1.6711939434448537e-05, "loss": 0.1819828987121582, "step": 2840 }, { "epoch": 0.28895324153576113, "grad_norm": 4.770489692687988, "learning_rate": 1.6687563776093943e-05, "loss": 0.20799508094787597, "step": 2850 }, { "epoch": 0.2899671125586936, "grad_norm": 2.042795181274414, "learning_rate": 1.6663116019450306e-05, "loss": 0.17942328453063966, "step": 2860 }, { "epoch": 0.2909809835816261, "grad_norm": 1.8765950202941895, "learning_rate": 1.6638596428087662e-05, "loss": 0.20492768287658691, "step": 2870 }, { "epoch": 0.2919948546045586, "grad_norm": 3.911595582962036, "learning_rate": 1.66140052663505e-05, "loss": 0.19505782127380372, "step": 2880 }, { "epoch": 0.29300872562749114, "grad_norm": 2.817464828491211, "learning_rate": 1.6589342799354895e-05, "loss": 0.1786690354347229, "step": 2890 }, { "epoch": 0.29402259665042363, "grad_norm": 2.2122037410736084, "learning_rate": 1.6564609292985663e-05, "loss": 0.1852052927017212, "step": 2900 }, { "epoch": 0.2950364676733561, "grad_norm": 4.5369672775268555, "learning_rate": 1.6539805013893493e-05, "loss": 0.20005388259887696, "step": 2910 }, { "epoch": 0.2960503386962886, "grad_norm": 6.399098873138428, "learning_rate": 1.6514930229492073e-05, "loss": 0.1990559935569763, "step": 2920 }, { "epoch": 0.2970642097192211, "grad_norm": 3.112576961517334, "learning_rate": 1.6489985207955207e-05, "loss": 0.19227277040481566, "step": 2930 }, { "epoch": 0.2980780807421536, "grad_norm": 4.577297687530518, "learning_rate": 1.6464970218213912e-05, "loss": 0.2100353240966797, "step": 2940 }, { "epoch": 0.2990919517650861, "grad_norm": 2.418912649154663, "learning_rate": 1.643988552995354e-05, "loss": 0.19691452980041504, "step": 2950 }, { "epoch": 0.30010582278801856, "grad_norm": 3.1403145790100098, "learning_rate": 1.6414731413610856e-05, "loss": 0.17516689300537108, "step": 2960 }, { "epoch": 0.30111969381095105, "grad_norm": 2.802436351776123, "learning_rate": 1.638950814037112e-05, "loss": 0.17058911323547363, "step": 2970 }, { "epoch": 0.3021335648338836, "grad_norm": 4.1535868644714355, "learning_rate": 1.6364215982165178e-05, "loss": 0.17612658739089965, "step": 2980 }, { "epoch": 0.3031474358568161, "grad_norm": 1.2995615005493164, "learning_rate": 1.633885521166651e-05, "loss": 0.18052700757980347, "step": 2990 }, { "epoch": 0.30416130687974857, "grad_norm": 1.086655855178833, "learning_rate": 1.6313426102288315e-05, "loss": 0.1776759386062622, "step": 3000 }, { "epoch": 0.30517517790268106, "grad_norm": 5.386715888977051, "learning_rate": 1.6287928928180544e-05, "loss": 0.20213568210601807, "step": 3010 }, { "epoch": 0.30618904892561355, "grad_norm": 1.6605138778686523, "learning_rate": 1.6262363964226943e-05, "loss": 0.17024667263031007, "step": 3020 }, { "epoch": 0.30720291994854604, "grad_norm": 4.638996124267578, "learning_rate": 1.623673148604211e-05, "loss": 0.1691967010498047, "step": 3030 }, { "epoch": 0.3082167909714785, "grad_norm": 2.934467077255249, "learning_rate": 1.6211031769968503e-05, "loss": 0.17619717121124268, "step": 3040 }, { "epoch": 0.309230661994411, "grad_norm": 5.414168834686279, "learning_rate": 1.6185265093073468e-05, "loss": 0.18505903482437133, "step": 3050 }, { "epoch": 0.3102445330173435, "grad_norm": 2.4969613552093506, "learning_rate": 1.6159431733146255e-05, "loss": 0.18167576789855958, "step": 3060 }, { "epoch": 0.31125840404027605, "grad_norm": 2.393145799636841, "learning_rate": 1.613353196869502e-05, "loss": 0.1869611620903015, "step": 3070 }, { "epoch": 0.31227227506320854, "grad_norm": 2.444002151489258, "learning_rate": 1.6107566078943818e-05, "loss": 0.19019919633865356, "step": 3080 }, { "epoch": 0.313286146086141, "grad_norm": 2.027569532394409, "learning_rate": 1.608153434382961e-05, "loss": 0.18489493131637574, "step": 3090 }, { "epoch": 0.3143000171090735, "grad_norm": 2.137690305709839, "learning_rate": 1.6055437043999215e-05, "loss": 0.16111197471618652, "step": 3100 }, { "epoch": 0.315313888132006, "grad_norm": 1.2246978282928467, "learning_rate": 1.6029274460806318e-05, "loss": 0.18395456075668334, "step": 3110 }, { "epoch": 0.3163277591549385, "grad_norm": 3.1867289543151855, "learning_rate": 1.6003046876308413e-05, "loss": 0.18580771684646608, "step": 3120 }, { "epoch": 0.317341630177871, "grad_norm": 2.4827253818511963, "learning_rate": 1.5976754573263767e-05, "loss": 0.16579737663269042, "step": 3130 }, { "epoch": 0.31835550120080347, "grad_norm": 2.307408571243286, "learning_rate": 1.5950397835128378e-05, "loss": 0.18545209169387816, "step": 3140 }, { "epoch": 0.319369372223736, "grad_norm": 1.784104347229004, "learning_rate": 1.5923976946052918e-05, "loss": 0.1550575852394104, "step": 3150 }, { "epoch": 0.3203832432466685, "grad_norm": 4.558605194091797, "learning_rate": 1.5897492190879667e-05, "loss": 0.1856433629989624, "step": 3160 }, { "epoch": 0.321397114269601, "grad_norm": 1.5677778720855713, "learning_rate": 1.5870943855139437e-05, "loss": 0.1788732409477234, "step": 3170 }, { "epoch": 0.3224109852925335, "grad_norm": 1.840512752532959, "learning_rate": 1.5844332225048496e-05, "loss": 0.16411787271499634, "step": 3180 }, { "epoch": 0.32342485631546597, "grad_norm": 2.984316349029541, "learning_rate": 1.5817657587505503e-05, "loss": 0.17873631715774535, "step": 3190 }, { "epoch": 0.32443872733839846, "grad_norm": 3.8818347454071045, "learning_rate": 1.5790920230088375e-05, "loss": 0.17636656761169434, "step": 3200 }, { "epoch": 0.32545259836133095, "grad_norm": 6.057239055633545, "learning_rate": 1.576412044105122e-05, "loss": 0.18374783992767335, "step": 3210 }, { "epoch": 0.32646646938426344, "grad_norm": 3.1834299564361572, "learning_rate": 1.5737258509321224e-05, "loss": 0.17864564657211304, "step": 3220 }, { "epoch": 0.3274803404071959, "grad_norm": 5.576935291290283, "learning_rate": 1.5710334724495514e-05, "loss": 0.17236711978912353, "step": 3230 }, { "epoch": 0.32849421143012847, "grad_norm": 1.1973732709884644, "learning_rate": 1.5683349376838067e-05, "loss": 0.18418751955032348, "step": 3240 }, { "epoch": 0.32950808245306096, "grad_norm": 2.8689920902252197, "learning_rate": 1.565630275727656e-05, "loss": 0.17814652919769286, "step": 3250 }, { "epoch": 0.33052195347599345, "grad_norm": 3.591428279876709, "learning_rate": 1.5629195157399236e-05, "loss": 0.18873609304428102, "step": 3260 }, { "epoch": 0.33153582449892594, "grad_norm": 4.107968330383301, "learning_rate": 1.5602026869451773e-05, "loss": 0.17980828285217285, "step": 3270 }, { "epoch": 0.3325496955218584, "grad_norm": 2.950343132019043, "learning_rate": 1.5574798186334112e-05, "loss": 0.17170946598052977, "step": 3280 }, { "epoch": 0.3335635665447909, "grad_norm": 3.857664108276367, "learning_rate": 1.5547509401597322e-05, "loss": 0.1802617311477661, "step": 3290 }, { "epoch": 0.3345774375677234, "grad_norm": 2.373537540435791, "learning_rate": 1.552016080944042e-05, "loss": 0.17171767950057984, "step": 3300 }, { "epoch": 0.3355913085906559, "grad_norm": 2.316955089569092, "learning_rate": 1.5492752704707198e-05, "loss": 0.18230575323104858, "step": 3310 }, { "epoch": 0.3366051796135884, "grad_norm": 4.959774971008301, "learning_rate": 1.5465285382883065e-05, "loss": 0.18898017406463624, "step": 3320 }, { "epoch": 0.3376190506365209, "grad_norm": 4.040923118591309, "learning_rate": 1.5437759140091827e-05, "loss": 0.18795287609100342, "step": 3330 }, { "epoch": 0.3386329216594534, "grad_norm": 2.709061861038208, "learning_rate": 1.541017427309254e-05, "loss": 0.17660720348358155, "step": 3340 }, { "epoch": 0.3396467926823859, "grad_norm": 2.874387502670288, "learning_rate": 1.538253107927625e-05, "loss": 0.16537787914276122, "step": 3350 }, { "epoch": 0.3406606637053184, "grad_norm": 4.082601547241211, "learning_rate": 1.535482985666285e-05, "loss": 0.1692793846130371, "step": 3360 }, { "epoch": 0.3416745347282509, "grad_norm": 4.821821689605713, "learning_rate": 1.5327070903897832e-05, "loss": 0.1901423454284668, "step": 3370 }, { "epoch": 0.34268840575118337, "grad_norm": 6.084152698516846, "learning_rate": 1.529925452024907e-05, "loss": 0.17803528308868408, "step": 3380 }, { "epoch": 0.34370227677411586, "grad_norm": 3.994408130645752, "learning_rate": 1.5271381005603593e-05, "loss": 0.18389796018600463, "step": 3390 }, { "epoch": 0.34471614779704834, "grad_norm": 4.294947147369385, "learning_rate": 1.5243450660464368e-05, "loss": 0.166870641708374, "step": 3400 }, { "epoch": 0.3457300188199809, "grad_norm": 3.83144211769104, "learning_rate": 1.5215463785947036e-05, "loss": 0.18264539241790773, "step": 3410 }, { "epoch": 0.3467438898429134, "grad_norm": 2.3546576499938965, "learning_rate": 1.518742068377669e-05, "loss": 0.16996872425079346, "step": 3420 }, { "epoch": 0.34775776086584587, "grad_norm": 2.149394989013672, "learning_rate": 1.5159321656284602e-05, "loss": 0.1711132764816284, "step": 3430 }, { "epoch": 0.34877163188877836, "grad_norm": 1.8135818243026733, "learning_rate": 1.5131167006404978e-05, "loss": 0.18652589321136476, "step": 3440 }, { "epoch": 0.34978550291171084, "grad_norm": 5.2615227699279785, "learning_rate": 1.5102957037671689e-05, "loss": 0.1652579426765442, "step": 3450 }, { "epoch": 0.35079937393464333, "grad_norm": 2.259398937225342, "learning_rate": 1.5074692054214977e-05, "loss": 0.17163897752761842, "step": 3460 }, { "epoch": 0.3518132449575758, "grad_norm": 2.285489797592163, "learning_rate": 1.504637236075822e-05, "loss": 0.156475293636322, "step": 3470 }, { "epoch": 0.3528271159805083, "grad_norm": 2.376579999923706, "learning_rate": 1.5017998262614609e-05, "loss": 0.17399110794067382, "step": 3480 }, { "epoch": 0.3538409870034408, "grad_norm": 1.4235644340515137, "learning_rate": 1.498957006568386e-05, "loss": 0.16802003383636474, "step": 3490 }, { "epoch": 0.35485485802637334, "grad_norm": 4.9538493156433105, "learning_rate": 1.4961088076448947e-05, "loss": 0.17010209560394288, "step": 3500 }, { "epoch": 0.35586872904930583, "grad_norm": 2.205472707748413, "learning_rate": 1.4932552601972763e-05, "loss": 0.19214541912078859, "step": 3510 }, { "epoch": 0.3568826000722383, "grad_norm": 5.25868034362793, "learning_rate": 1.490396394989482e-05, "loss": 0.1823093056678772, "step": 3520 }, { "epoch": 0.3578964710951708, "grad_norm": 2.071333646774292, "learning_rate": 1.4875322428427943e-05, "loss": 0.16439391374588014, "step": 3530 }, { "epoch": 0.3589103421181033, "grad_norm": 1.9281165599822998, "learning_rate": 1.4846628346354934e-05, "loss": 0.16677181720733641, "step": 3540 }, { "epoch": 0.3599242131410358, "grad_norm": 4.5595550537109375, "learning_rate": 1.4817882013025253e-05, "loss": 0.18730692863464354, "step": 3550 }, { "epoch": 0.3609380841639683, "grad_norm": 2.357835054397583, "learning_rate": 1.478908373835167e-05, "loss": 0.17840995788574218, "step": 3560 }, { "epoch": 0.36195195518690076, "grad_norm": 2.4984853267669678, "learning_rate": 1.476023383280694e-05, "loss": 0.16893455982208253, "step": 3570 }, { "epoch": 0.3629658262098333, "grad_norm": 3.205329179763794, "learning_rate": 1.473133260742045e-05, "loss": 0.17847638130187987, "step": 3580 }, { "epoch": 0.3639796972327658, "grad_norm": 4.127205848693848, "learning_rate": 1.4702380373774852e-05, "loss": 0.17623448371887207, "step": 3590 }, { "epoch": 0.3649935682556983, "grad_norm": 3.4790213108062744, "learning_rate": 1.4673377444002724e-05, "loss": 0.15532419681549073, "step": 3600 }, { "epoch": 0.3660074392786308, "grad_norm": 5.545375347137451, "learning_rate": 1.4644324130783197e-05, "loss": 0.1711595892906189, "step": 3610 }, { "epoch": 0.36702131030156326, "grad_norm": 1.9564255475997925, "learning_rate": 1.4615220747338574e-05, "loss": 0.18311665058135987, "step": 3620 }, { "epoch": 0.36803518132449575, "grad_norm": 3.506014108657837, "learning_rate": 1.4586067607430976e-05, "loss": 0.16632814407348634, "step": 3630 }, { "epoch": 0.36904905234742824, "grad_norm": 3.0203897953033447, "learning_rate": 1.4556865025358942e-05, "loss": 0.18297089338302613, "step": 3640 }, { "epoch": 0.37006292337036073, "grad_norm": 3.0247464179992676, "learning_rate": 1.4527613315954035e-05, "loss": 0.17856335639953613, "step": 3650 }, { "epoch": 0.3710767943932932, "grad_norm": 1.8630574941635132, "learning_rate": 1.4498312794577465e-05, "loss": 0.17448875904083253, "step": 3660 }, { "epoch": 0.37209066541622576, "grad_norm": 1.9325183629989624, "learning_rate": 1.4468963777116686e-05, "loss": 0.19616293907165527, "step": 3670 }, { "epoch": 0.37310453643915825, "grad_norm": 4.521261215209961, "learning_rate": 1.4439566579981979e-05, "loss": 0.1849150538444519, "step": 3680 }, { "epoch": 0.37411840746209074, "grad_norm": 2.3663737773895264, "learning_rate": 1.4410121520103045e-05, "loss": 0.16768492460250856, "step": 3690 }, { "epoch": 0.37513227848502323, "grad_norm": 2.106260061264038, "learning_rate": 1.4380628914925597e-05, "loss": 0.15372687578201294, "step": 3700 }, { "epoch": 0.3761461495079557, "grad_norm": 2.69887113571167, "learning_rate": 1.4351089082407929e-05, "loss": 0.16869134902954103, "step": 3710 }, { "epoch": 0.3771600205308882, "grad_norm": 3.526265859603882, "learning_rate": 1.4321502341017496e-05, "loss": 0.17242830991744995, "step": 3720 }, { "epoch": 0.3781738915538207, "grad_norm": 3.688901662826538, "learning_rate": 1.4291869009727463e-05, "loss": 0.1633615016937256, "step": 3730 }, { "epoch": 0.3791877625767532, "grad_norm": 3.0295827388763428, "learning_rate": 1.4262189408013294e-05, "loss": 0.16214264631271363, "step": 3740 }, { "epoch": 0.3802016335996857, "grad_norm": 4.561550617218018, "learning_rate": 1.4232463855849275e-05, "loss": 0.17571725845336914, "step": 3750 }, { "epoch": 0.3812155046226182, "grad_norm": 2.4309492111206055, "learning_rate": 1.4202692673705097e-05, "loss": 0.18426311016082764, "step": 3760 }, { "epoch": 0.3822293756455507, "grad_norm": 2.901784658432007, "learning_rate": 1.4172876182542372e-05, "loss": 0.17190239429473878, "step": 3770 }, { "epoch": 0.3832432466684832, "grad_norm": 3.508105754852295, "learning_rate": 1.41430147038112e-05, "loss": 0.16798088550567628, "step": 3780 }, { "epoch": 0.3842571176914157, "grad_norm": 1.7633824348449707, "learning_rate": 1.411310855944668e-05, "loss": 0.17639142274856567, "step": 3790 }, { "epoch": 0.3852709887143482, "grad_norm": 2.9126670360565186, "learning_rate": 1.4083158071865451e-05, "loss": 0.18098851442337036, "step": 3800 }, { "epoch": 0.38628485973728066, "grad_norm": 1.605804681777954, "learning_rate": 1.4053163563962215e-05, "loss": 0.16948928833007812, "step": 3810 }, { "epoch": 0.38729873076021315, "grad_norm": 3.2441351413726807, "learning_rate": 1.4023125359106253e-05, "loss": 0.1606533169746399, "step": 3820 }, { "epoch": 0.38831260178314564, "grad_norm": 3.705984354019165, "learning_rate": 1.3993043781137945e-05, "loss": 0.1690284490585327, "step": 3830 }, { "epoch": 0.3893264728060782, "grad_norm": 1.8879975080490112, "learning_rate": 1.3962919154365273e-05, "loss": 0.18819308280944824, "step": 3840 }, { "epoch": 0.39034034382901067, "grad_norm": 1.9085471630096436, "learning_rate": 1.393275180356032e-05, "loss": 0.17349542379379274, "step": 3850 }, { "epoch": 0.39135421485194316, "grad_norm": 4.039549827575684, "learning_rate": 1.3902542053955781e-05, "loss": 0.17779767513275146, "step": 3860 }, { "epoch": 0.39236808587487565, "grad_norm": 2.035957098007202, "learning_rate": 1.387229023124145e-05, "loss": 0.17574304342269897, "step": 3870 }, { "epoch": 0.39338195689780814, "grad_norm": 2.719813585281372, "learning_rate": 1.3841996661560706e-05, "loss": 0.16164767742156982, "step": 3880 }, { "epoch": 0.3943958279207406, "grad_norm": 2.863463878631592, "learning_rate": 1.3811661671507004e-05, "loss": 0.15072567462921144, "step": 3890 }, { "epoch": 0.3954096989436731, "grad_norm": 6.471496105194092, "learning_rate": 1.3781285588120343e-05, "loss": 0.16015433073043822, "step": 3900 }, { "epoch": 0.3964235699666056, "grad_norm": 2.1184771060943604, "learning_rate": 1.3750868738883755e-05, "loss": 0.160658860206604, "step": 3910 }, { "epoch": 0.3974374409895381, "grad_norm": 5.324803829193115, "learning_rate": 1.3720411451719762e-05, "loss": 0.17575371265411377, "step": 3920 }, { "epoch": 0.39845131201247064, "grad_norm": 2.20900821685791, "learning_rate": 1.3689914054986849e-05, "loss": 0.17584142684936524, "step": 3930 }, { "epoch": 0.3994651830354031, "grad_norm": 2.357877254486084, "learning_rate": 1.3659376877475916e-05, "loss": 0.17102397680282594, "step": 3940 }, { "epoch": 0.4004790540583356, "grad_norm": 4.45941162109375, "learning_rate": 1.3628800248406738e-05, "loss": 0.17365585565567015, "step": 3950 }, { "epoch": 0.4014929250812681, "grad_norm": 4.179808139801025, "learning_rate": 1.3598184497424416e-05, "loss": 0.16364812850952148, "step": 3960 }, { "epoch": 0.4025067961042006, "grad_norm": 3.709749937057495, "learning_rate": 1.3567529954595826e-05, "loss": 0.17191786766052247, "step": 3970 }, { "epoch": 0.4035206671271331, "grad_norm": 2.612276792526245, "learning_rate": 1.3536836950406057e-05, "loss": 0.1637474775314331, "step": 3980 }, { "epoch": 0.40453453815006557, "grad_norm": 1.791259765625, "learning_rate": 1.3506105815754836e-05, "loss": 0.155581271648407, "step": 3990 }, { "epoch": 0.40554840917299806, "grad_norm": 4.676018238067627, "learning_rate": 1.3475336881952988e-05, "loss": 0.19478819370269776, "step": 4000 }, { "epoch": 0.40656228019593055, "grad_norm": 1.9305484294891357, "learning_rate": 1.3444530480718838e-05, "loss": 0.17702919244766235, "step": 4010 }, { "epoch": 0.4075761512188631, "grad_norm": 1.4422626495361328, "learning_rate": 1.3413686944174655e-05, "loss": 0.1547333836555481, "step": 4020 }, { "epoch": 0.4085900222417956, "grad_norm": 2.0834031105041504, "learning_rate": 1.3382806604843053e-05, "loss": 0.17348941564559936, "step": 4030 }, { "epoch": 0.40960389326472807, "grad_norm": 2.212472438812256, "learning_rate": 1.3351889795643423e-05, "loss": 0.1518407344818115, "step": 4040 }, { "epoch": 0.41061776428766056, "grad_norm": 5.1342692375183105, "learning_rate": 1.3320936849888322e-05, "loss": 0.18022069931030274, "step": 4050 }, { "epoch": 0.41163163531059305, "grad_norm": 1.8534444570541382, "learning_rate": 1.3289948101279912e-05, "loss": 0.18035850524902344, "step": 4060 }, { "epoch": 0.41264550633352554, "grad_norm": 4.085660934448242, "learning_rate": 1.3258923883906337e-05, "loss": 0.16571424007415772, "step": 4070 }, { "epoch": 0.413659377356458, "grad_norm": 1.7402312755584717, "learning_rate": 1.3227864532238113e-05, "loss": 0.16965744495391846, "step": 4080 }, { "epoch": 0.4146732483793905, "grad_norm": 1.4885066747665405, "learning_rate": 1.3196770381124557e-05, "loss": 0.16359691619873046, "step": 4090 }, { "epoch": 0.41568711940232306, "grad_norm": 3.134516477584839, "learning_rate": 1.3165641765790153e-05, "loss": 0.14895930290222167, "step": 4100 }, { "epoch": 0.41670099042525555, "grad_norm": 1.632849931716919, "learning_rate": 1.3134479021830938e-05, "loss": 0.17103867530822753, "step": 4110 }, { "epoch": 0.41771486144818804, "grad_norm": 4.24514627456665, "learning_rate": 1.3103282485210882e-05, "loss": 0.1525915741920471, "step": 4120 }, { "epoch": 0.4187287324711205, "grad_norm": 1.46393620967865, "learning_rate": 1.3072052492258286e-05, "loss": 0.15599886178970337, "step": 4130 }, { "epoch": 0.419742603494053, "grad_norm": 2.33296799659729, "learning_rate": 1.3040789379662131e-05, "loss": 0.14586548805236815, "step": 4140 }, { "epoch": 0.4207564745169855, "grad_norm": 2.251786708831787, "learning_rate": 1.3009493484468464e-05, "loss": 0.17117574214935302, "step": 4150 }, { "epoch": 0.421770345539918, "grad_norm": 2.2459545135498047, "learning_rate": 1.2978165144076757e-05, "loss": 0.1626502752304077, "step": 4160 }, { "epoch": 0.4227842165628505, "grad_norm": 1.9941112995147705, "learning_rate": 1.2946804696236277e-05, "loss": 0.15333096981048583, "step": 4170 }, { "epoch": 0.42379808758578297, "grad_norm": 2.44681978225708, "learning_rate": 1.2915412479042436e-05, "loss": 0.1575390100479126, "step": 4180 }, { "epoch": 0.4248119586087155, "grad_norm": 1.228768229484558, "learning_rate": 1.2883988830933148e-05, "loss": 0.15973939895629882, "step": 4190 }, { "epoch": 0.425825829631648, "grad_norm": 2.1503818035125732, "learning_rate": 1.2852534090685184e-05, "loss": 0.15626132488250732, "step": 4200 }, { "epoch": 0.4268397006545805, "grad_norm": 2.4758853912353516, "learning_rate": 1.282104859741052e-05, "loss": 0.17503957748413085, "step": 4210 }, { "epoch": 0.427853571677513, "grad_norm": 2.307262897491455, "learning_rate": 1.2789532690552673e-05, "loss": 0.17222969532012938, "step": 4220 }, { "epoch": 0.42886744270044547, "grad_norm": 6.076901912689209, "learning_rate": 1.2757986709883059e-05, "loss": 0.16323509216308593, "step": 4230 }, { "epoch": 0.42988131372337796, "grad_norm": 4.674138069152832, "learning_rate": 1.2726410995497304e-05, "loss": 0.1596430540084839, "step": 4240 }, { "epoch": 0.43089518474631044, "grad_norm": 2.6154251098632812, "learning_rate": 1.2694805887811601e-05, "loss": 0.1386547088623047, "step": 4250 }, { "epoch": 0.43190905576924293, "grad_norm": 2.467550754547119, "learning_rate": 1.2663171727559025e-05, "loss": 0.1694718599319458, "step": 4260 }, { "epoch": 0.4329229267921755, "grad_norm": 1.7959070205688477, "learning_rate": 1.2631508855785877e-05, "loss": 0.16652109622955322, "step": 4270 }, { "epoch": 0.43393679781510797, "grad_norm": 2.6836752891540527, "learning_rate": 1.2599817613847973e-05, "loss": 0.17835115194320678, "step": 4280 }, { "epoch": 0.43495066883804046, "grad_norm": 2.574186325073242, "learning_rate": 1.2568098343407007e-05, "loss": 0.16272345781326295, "step": 4290 }, { "epoch": 0.43596453986097294, "grad_norm": 3.9124910831451416, "learning_rate": 1.2536351386426844e-05, "loss": 0.1612618088722229, "step": 4300 }, { "epoch": 0.43697841088390543, "grad_norm": 3.7747690677642822, "learning_rate": 1.2504577085169826e-05, "loss": 0.17131431102752687, "step": 4310 }, { "epoch": 0.4379922819068379, "grad_norm": 3.4612836837768555, "learning_rate": 1.2472775782193099e-05, "loss": 0.1678980588912964, "step": 4320 }, { "epoch": 0.4390061529297704, "grad_norm": 2.175718069076538, "learning_rate": 1.2440947820344916e-05, "loss": 0.16452817916870116, "step": 4330 }, { "epoch": 0.4400200239527029, "grad_norm": 2.6230247020721436, "learning_rate": 1.2409093542760925e-05, "loss": 0.15321135520935059, "step": 4340 }, { "epoch": 0.4410338949756354, "grad_norm": 6.111915588378906, "learning_rate": 1.2377213292860506e-05, "loss": 0.18565034866333008, "step": 4350 }, { "epoch": 0.44204776599856793, "grad_norm": 5.396814346313477, "learning_rate": 1.2345307414343021e-05, "loss": 0.1613368034362793, "step": 4360 }, { "epoch": 0.4430616370215004, "grad_norm": 2.1081674098968506, "learning_rate": 1.2313376251184148e-05, "loss": 0.15773406028747558, "step": 4370 }, { "epoch": 0.4440755080444329, "grad_norm": 2.868680477142334, "learning_rate": 1.2281420147632148e-05, "loss": 0.14965803623199464, "step": 4380 }, { "epoch": 0.4450893790673654, "grad_norm": 4.447704315185547, "learning_rate": 1.2249439448204172e-05, "loss": 0.14170147180557252, "step": 4390 }, { "epoch": 0.4461032500902979, "grad_norm": 3.0970685482025146, "learning_rate": 1.2217434497682537e-05, "loss": 0.16816858053207398, "step": 4400 }, { "epoch": 0.4471171211132304, "grad_norm": 5.543230056762695, "learning_rate": 1.2185405641110997e-05, "loss": 0.17297070026397704, "step": 4410 }, { "epoch": 0.44813099213616286, "grad_norm": 2.984118938446045, "learning_rate": 1.2153353223791049e-05, "loss": 0.1634351372718811, "step": 4420 }, { "epoch": 0.44914486315909535, "grad_norm": 4.679759502410889, "learning_rate": 1.2121277591278197e-05, "loss": 0.17628304958343505, "step": 4430 }, { "epoch": 0.45015873418202784, "grad_norm": 4.0854878425598145, "learning_rate": 1.2089179089378222e-05, "loss": 0.1645501136779785, "step": 4440 }, { "epoch": 0.4511726052049604, "grad_norm": 3.758087635040283, "learning_rate": 1.2057058064143456e-05, "loss": 0.15519531965255737, "step": 4450 }, { "epoch": 0.4521864762278929, "grad_norm": 5.0319952964782715, "learning_rate": 1.2024914861869064e-05, "loss": 0.16896580457687377, "step": 4460 }, { "epoch": 0.45320034725082536, "grad_norm": 2.0205979347229004, "learning_rate": 1.199274982908929e-05, "loss": 0.1626990556716919, "step": 4470 }, { "epoch": 0.45421421827375785, "grad_norm": 3.2760355472564697, "learning_rate": 1.196056331257374e-05, "loss": 0.15435960292816162, "step": 4480 }, { "epoch": 0.45522808929669034, "grad_norm": 4.093352317810059, "learning_rate": 1.1928355659323627e-05, "loss": 0.1545414686203003, "step": 4490 }, { "epoch": 0.45624196031962283, "grad_norm": 3.060483694076538, "learning_rate": 1.1896127216568047e-05, "loss": 0.17152061462402343, "step": 4500 }, { "epoch": 0.4572558313425553, "grad_norm": 3.5712578296661377, "learning_rate": 1.1863878331760217e-05, "loss": 0.16212737560272217, "step": 4510 }, { "epoch": 0.4582697023654878, "grad_norm": 2.6438121795654297, "learning_rate": 1.183160935257375e-05, "loss": 0.16331701278686522, "step": 4520 }, { "epoch": 0.45928357338842035, "grad_norm": 2.5863125324249268, "learning_rate": 1.1799320626898883e-05, "loss": 0.14666881561279296, "step": 4530 }, { "epoch": 0.46029744441135284, "grad_norm": 3.2400825023651123, "learning_rate": 1.1767012502838746e-05, "loss": 0.1521628499031067, "step": 4540 }, { "epoch": 0.46131131543428533, "grad_norm": 4.7086615562438965, "learning_rate": 1.1734685328705604e-05, "loss": 0.1682875633239746, "step": 4550 }, { "epoch": 0.4623251864572178, "grad_norm": 1.7710435390472412, "learning_rate": 1.17023394530171e-05, "loss": 0.17764136791229249, "step": 4560 }, { "epoch": 0.4633390574801503, "grad_norm": 2.9086716175079346, "learning_rate": 1.1669975224492486e-05, "loss": 0.15788357257843016, "step": 4570 }, { "epoch": 0.4643529285030828, "grad_norm": 3.5737123489379883, "learning_rate": 1.1637592992048888e-05, "loss": 0.14947295188903809, "step": 4580 }, { "epoch": 0.4653667995260153, "grad_norm": 4.333691120147705, "learning_rate": 1.160519310479753e-05, "loss": 0.17342774868011473, "step": 4590 }, { "epoch": 0.4663806705489478, "grad_norm": 2.1281604766845703, "learning_rate": 1.157277591203996e-05, "loss": 0.15316892862319947, "step": 4600 }, { "epoch": 0.46739454157188026, "grad_norm": 4.417381763458252, "learning_rate": 1.1540341763264314e-05, "loss": 0.1481050968170166, "step": 4610 }, { "epoch": 0.4684084125948128, "grad_norm": 2.086369037628174, "learning_rate": 1.1507891008141512e-05, "loss": 0.14970476627349855, "step": 4620 }, { "epoch": 0.4694222836177453, "grad_norm": 1.7743817567825317, "learning_rate": 1.147542399652152e-05, "loss": 0.16142451763153076, "step": 4630 }, { "epoch": 0.4704361546406778, "grad_norm": 2.1507227420806885, "learning_rate": 1.1442941078429554e-05, "loss": 0.14584323167800903, "step": 4640 }, { "epoch": 0.4714500256636103, "grad_norm": 2.522905111312866, "learning_rate": 1.141044260406233e-05, "loss": 0.16107709407806398, "step": 4650 }, { "epoch": 0.47246389668654276, "grad_norm": 4.8506646156311035, "learning_rate": 1.1377928923784261e-05, "loss": 0.16274222135543823, "step": 4660 }, { "epoch": 0.47347776770947525, "grad_norm": 2.9747543334960938, "learning_rate": 1.1345400388123698e-05, "loss": 0.1504684329032898, "step": 4670 }, { "epoch": 0.47449163873240774, "grad_norm": 2.3640081882476807, "learning_rate": 1.1312857347769153e-05, "loss": 0.15062217712402343, "step": 4680 }, { "epoch": 0.4755055097553402, "grad_norm": 2.522637367248535, "learning_rate": 1.128030015356551e-05, "loss": 0.1608656406402588, "step": 4690 }, { "epoch": 0.4765193807782727, "grad_norm": 1.7829285860061646, "learning_rate": 1.1247729156510245e-05, "loss": 0.15576388835906982, "step": 4700 }, { "epoch": 0.47753325180120526, "grad_norm": 3.098085641860962, "learning_rate": 1.1215144707749635e-05, "loss": 0.15989491939544678, "step": 4710 }, { "epoch": 0.47854712282413775, "grad_norm": 3.063441753387451, "learning_rate": 1.1182547158574988e-05, "loss": 0.13914761543273926, "step": 4720 }, { "epoch": 0.47956099384707024, "grad_norm": 2.078371524810791, "learning_rate": 1.1149936860418846e-05, "loss": 0.16830546855926515, "step": 4730 }, { "epoch": 0.4805748648700027, "grad_norm": 1.2813124656677246, "learning_rate": 1.1117314164851191e-05, "loss": 0.16205902099609376, "step": 4740 }, { "epoch": 0.4815887358929352, "grad_norm": 3.2236316204071045, "learning_rate": 1.1084679423575666e-05, "loss": 0.15253257751464844, "step": 4750 }, { "epoch": 0.4826026069158677, "grad_norm": 2.0521984100341797, "learning_rate": 1.1052032988425778e-05, "loss": 0.14506981372833253, "step": 4760 }, { "epoch": 0.4836164779388002, "grad_norm": 6.4925971031188965, "learning_rate": 1.1019375211361104e-05, "loss": 0.1396000623703003, "step": 4770 }, { "epoch": 0.4846303489617327, "grad_norm": 1.796690821647644, "learning_rate": 1.0986706444463496e-05, "loss": 0.16615407466888427, "step": 4780 }, { "epoch": 0.4856442199846652, "grad_norm": 3.58060884475708, "learning_rate": 1.0954027039933288e-05, "loss": 0.1473178505897522, "step": 4790 }, { "epoch": 0.4866580910075977, "grad_norm": 6.725644111633301, "learning_rate": 1.09213373500855e-05, "loss": 0.161183500289917, "step": 4800 }, { "epoch": 0.4876719620305302, "grad_norm": 2.500011920928955, "learning_rate": 1.0888637727346032e-05, "loss": 0.1667497992515564, "step": 4810 }, { "epoch": 0.4886858330534627, "grad_norm": 4.833351135253906, "learning_rate": 1.0855928524247884e-05, "loss": 0.1621102809906006, "step": 4820 }, { "epoch": 0.4896997040763952, "grad_norm": 2.0678961277008057, "learning_rate": 1.0823210093427318e-05, "loss": 0.14431365728378295, "step": 4830 }, { "epoch": 0.49071357509932767, "grad_norm": 2.9403839111328125, "learning_rate": 1.07904827876201e-05, "loss": 0.16116621494293212, "step": 4840 }, { "epoch": 0.49172744612226016, "grad_norm": 3.199512004852295, "learning_rate": 1.0757746959657666e-05, "loss": 0.16532042026519775, "step": 4850 }, { "epoch": 0.49274131714519265, "grad_norm": 4.470888614654541, "learning_rate": 1.072500296246334e-05, "loss": 0.1499765396118164, "step": 4860 }, { "epoch": 0.49375518816812514, "grad_norm": 3.858199119567871, "learning_rate": 1.06922511490485e-05, "loss": 0.1465756893157959, "step": 4870 }, { "epoch": 0.4947690591910577, "grad_norm": 2.4100215435028076, "learning_rate": 1.0659491872508807e-05, "loss": 0.15688732862472535, "step": 4880 }, { "epoch": 0.49578293021399017, "grad_norm": 5.231399059295654, "learning_rate": 1.0626725486020374e-05, "loss": 0.1533513307571411, "step": 4890 }, { "epoch": 0.49679680123692266, "grad_norm": 3.7797539234161377, "learning_rate": 1.059395234283597e-05, "loss": 0.14769736528396607, "step": 4900 }, { "epoch": 0.49781067225985515, "grad_norm": 3.87239933013916, "learning_rate": 1.0561172796281196e-05, "loss": 0.1635688066482544, "step": 4910 }, { "epoch": 0.49882454328278764, "grad_norm": 2.9051530361175537, "learning_rate": 1.0528387199750706e-05, "loss": 0.15575380325317384, "step": 4920 }, { "epoch": 0.4998384143057201, "grad_norm": 2.522587776184082, "learning_rate": 1.0495595906704365e-05, "loss": 0.13845824003219603, "step": 4930 }, { "epoch": 0.5008522853286527, "grad_norm": 3.1731507778167725, "learning_rate": 1.0462799270663457e-05, "loss": 0.13974510431289672, "step": 4940 }, { "epoch": 0.5018661563515852, "grad_norm": 2.059563636779785, "learning_rate": 1.0429997645206865e-05, "loss": 0.14378957748413085, "step": 4950 }, { "epoch": 0.5028800273745176, "grad_norm": 3.435500144958496, "learning_rate": 1.0397191383967267e-05, "loss": 0.14639314413070678, "step": 4960 }, { "epoch": 0.5038938983974501, "grad_norm": 3.0771896839141846, "learning_rate": 1.0364380840627315e-05, "loss": 0.15345802307128906, "step": 4970 }, { "epoch": 0.5049077694203826, "grad_norm": 2.3581011295318604, "learning_rate": 1.033156636891583e-05, "loss": 0.16371129751205443, "step": 4980 }, { "epoch": 0.5059216404433151, "grad_norm": 2.366361141204834, "learning_rate": 1.0298748322603982e-05, "loss": 0.14798099994659425, "step": 4990 }, { "epoch": 0.5069355114662476, "grad_norm": 3.754837989807129, "learning_rate": 1.0265927055501476e-05, "loss": 0.1569281816482544, "step": 5000 }, { "epoch": 0.5079493824891801, "grad_norm": 1.929952621459961, "learning_rate": 1.023310292145275e-05, "loss": 0.1413918375968933, "step": 5010 }, { "epoch": 0.5089632535121126, "grad_norm": 4.656583786010742, "learning_rate": 1.020027627433314e-05, "loss": 0.1511002779006958, "step": 5020 }, { "epoch": 0.5099771245350451, "grad_norm": 4.406658172607422, "learning_rate": 1.0167447468045083e-05, "loss": 0.14770463705062867, "step": 5030 }, { "epoch": 0.5109909955579776, "grad_norm": 4.423664093017578, "learning_rate": 1.0134616856514282e-05, "loss": 0.160895037651062, "step": 5040 }, { "epoch": 0.51200486658091, "grad_norm": 3.007443904876709, "learning_rate": 1.0101784793685914e-05, "loss": 0.15709145069122316, "step": 5050 }, { "epoch": 0.5130187376038425, "grad_norm": 4.256622314453125, "learning_rate": 1.0068951633520802e-05, "loss": 0.1427950978279114, "step": 5060 }, { "epoch": 0.514032608626775, "grad_norm": 2.8404483795166016, "learning_rate": 1.0036117729991595e-05, "loss": 0.1458382248878479, "step": 5070 }, { "epoch": 0.5150464796497075, "grad_norm": 4.495455741882324, "learning_rate": 1.0003283437078951e-05, "loss": 0.15526877641677855, "step": 5080 }, { "epoch": 0.5160603506726401, "grad_norm": 3.5927493572235107, "learning_rate": 9.970449108767742e-06, "loss": 0.14955176115036012, "step": 5090 }, { "epoch": 0.5170742216955726, "grad_norm": 2.7862348556518555, "learning_rate": 9.937615099043206e-06, "loss": 0.1456256628036499, "step": 5100 }, { "epoch": 0.5180880927185051, "grad_norm": 3.446277379989624, "learning_rate": 9.904781761887147e-06, "loss": 0.15703208446502687, "step": 5110 }, { "epoch": 0.5191019637414376, "grad_norm": 2.6717758178710938, "learning_rate": 9.871949451274137e-06, "loss": 0.1546523690223694, "step": 5120 }, { "epoch": 0.5201158347643701, "grad_norm": 1.845005989074707, "learning_rate": 9.839118521167656e-06, "loss": 0.15152361392974853, "step": 5130 }, { "epoch": 0.5211297057873026, "grad_norm": 2.980091094970703, "learning_rate": 9.80628932551631e-06, "loss": 0.16191694736480713, "step": 5140 }, { "epoch": 0.522143576810235, "grad_norm": 3.3525948524475098, "learning_rate": 9.773462218250014e-06, "loss": 0.13924458026885986, "step": 5150 }, { "epoch": 0.5231574478331675, "grad_norm": 3.558845043182373, "learning_rate": 9.740637553276162e-06, "loss": 0.16880602836608888, "step": 5160 }, { "epoch": 0.5241713188561, "grad_norm": 3.340935230255127, "learning_rate": 9.707815684475817e-06, "loss": 0.14823169708251954, "step": 5170 }, { "epoch": 0.5251851898790325, "grad_norm": 3.0335466861724854, "learning_rate": 9.674996965699895e-06, "loss": 0.14887055158615112, "step": 5180 }, { "epoch": 0.526199060901965, "grad_norm": 2.9788570404052734, "learning_rate": 9.642181750765354e-06, "loss": 0.15566089153289794, "step": 5190 }, { "epoch": 0.5272129319248975, "grad_norm": 2.334498882293701, "learning_rate": 9.60937039345138e-06, "loss": 0.16643434762954712, "step": 5200 }, { "epoch": 0.52822680294783, "grad_norm": 2.440229892730713, "learning_rate": 9.576563247495566e-06, "loss": 0.14143526554107666, "step": 5210 }, { "epoch": 0.5292406739707625, "grad_norm": 2.641052484512329, "learning_rate": 9.543760666590105e-06, "loss": 0.15166635513305665, "step": 5220 }, { "epoch": 0.530254544993695, "grad_norm": 2.160968780517578, "learning_rate": 9.510963004377974e-06, "loss": 0.14926328659057617, "step": 5230 }, { "epoch": 0.5312684160166274, "grad_norm": 2.8957951068878174, "learning_rate": 9.478170614449114e-06, "loss": 0.16120003461837767, "step": 5240 }, { "epoch": 0.5322822870395599, "grad_norm": 2.3994140625, "learning_rate": 9.445383850336648e-06, "loss": 0.1358851671218872, "step": 5250 }, { "epoch": 0.5332961580624924, "grad_norm": 3.4132819175720215, "learning_rate": 9.412603065513021e-06, "loss": 0.15576066970825195, "step": 5260 }, { "epoch": 0.534310029085425, "grad_norm": 3.8969361782073975, "learning_rate": 9.379828613386225e-06, "loss": 0.16283607482910156, "step": 5270 }, { "epoch": 0.5353239001083575, "grad_norm": 2.465200662612915, "learning_rate": 9.347060847295991e-06, "loss": 0.15297327041625977, "step": 5280 }, { "epoch": 0.53633777113129, "grad_norm": 2.095524549484253, "learning_rate": 9.314300120509952e-06, "loss": 0.15082283020019532, "step": 5290 }, { "epoch": 0.5373516421542225, "grad_norm": 2.155587673187256, "learning_rate": 9.281546786219861e-06, "loss": 0.15125696659088134, "step": 5300 }, { "epoch": 0.538365513177155, "grad_norm": 5.19185209274292, "learning_rate": 9.24880119753777e-06, "loss": 0.15250377655029296, "step": 5310 }, { "epoch": 0.5393793842000875, "grad_norm": 5.881664276123047, "learning_rate": 9.216063707492218e-06, "loss": 0.15552012920379638, "step": 5320 }, { "epoch": 0.54039325522302, "grad_norm": 3.305224895477295, "learning_rate": 9.183334669024449e-06, "loss": 0.16523396968841553, "step": 5330 }, { "epoch": 0.5414071262459524, "grad_norm": 2.562227487564087, "learning_rate": 9.150614434984578e-06, "loss": 0.1472207188606262, "step": 5340 }, { "epoch": 0.5424209972688849, "grad_norm": 3.4959328174591064, "learning_rate": 9.117903358127801e-06, "loss": 0.14088199138641358, "step": 5350 }, { "epoch": 0.5434348682918174, "grad_norm": 2.3997251987457275, "learning_rate": 9.085201791110602e-06, "loss": 0.13491377830505372, "step": 5360 }, { "epoch": 0.5444487393147499, "grad_norm": 2.9847264289855957, "learning_rate": 9.052510086486922e-06, "loss": 0.14185047149658203, "step": 5370 }, { "epoch": 0.5454626103376824, "grad_norm": 2.0852572917938232, "learning_rate": 9.019828596704394e-06, "loss": 0.14733879566192626, "step": 5380 }, { "epoch": 0.5464764813606149, "grad_norm": 3.1345770359039307, "learning_rate": 8.987157674100519e-06, "loss": 0.14075804948806764, "step": 5390 }, { "epoch": 0.5474903523835474, "grad_norm": 2.8463082313537598, "learning_rate": 8.954497670898858e-06, "loss": 0.13538541793823242, "step": 5400 }, { "epoch": 0.5485042234064799, "grad_norm": 3.7055389881134033, "learning_rate": 8.92184893920528e-06, "loss": 0.14181902408599853, "step": 5410 }, { "epoch": 0.5495180944294124, "grad_norm": 2.973778486251831, "learning_rate": 8.889211831004112e-06, "loss": 0.14812791347503662, "step": 5420 }, { "epoch": 0.5505319654523448, "grad_norm": 4.828948020935059, "learning_rate": 8.856586698154382e-06, "loss": 0.1561928391456604, "step": 5430 }, { "epoch": 0.5515458364752774, "grad_norm": 3.509084701538086, "learning_rate": 8.823973892386007e-06, "loss": 0.1694760799407959, "step": 5440 }, { "epoch": 0.5525597074982099, "grad_norm": 4.461091995239258, "learning_rate": 8.791373765296006e-06, "loss": 0.1444391131401062, "step": 5450 }, { "epoch": 0.5535735785211424, "grad_norm": 2.2410755157470703, "learning_rate": 8.758786668344711e-06, "loss": 0.1495032548904419, "step": 5460 }, { "epoch": 0.5545874495440749, "grad_norm": 2.088507652282715, "learning_rate": 8.726212952851978e-06, "loss": 0.15614382028579712, "step": 5470 }, { "epoch": 0.5556013205670074, "grad_norm": 3.054004669189453, "learning_rate": 8.693652969993396e-06, "loss": 0.14559404850006102, "step": 5480 }, { "epoch": 0.5566151915899399, "grad_norm": 2.155768394470215, "learning_rate": 8.661107070796504e-06, "loss": 0.15541837215423585, "step": 5490 }, { "epoch": 0.5576290626128724, "grad_norm": 3.167189836502075, "learning_rate": 8.628575606137005e-06, "loss": 0.15627706050872803, "step": 5500 }, { "epoch": 0.5586429336358049, "grad_norm": 2.8153603076934814, "learning_rate": 8.59605892673499e-06, "loss": 0.16863045692443848, "step": 5510 }, { "epoch": 0.5596568046587374, "grad_norm": 3.0109169483184814, "learning_rate": 8.563557383151143e-06, "loss": 0.15575704574584961, "step": 5520 }, { "epoch": 0.5606706756816698, "grad_norm": 2.499075174331665, "learning_rate": 8.531071325782965e-06, "loss": 0.15759512186050414, "step": 5530 }, { "epoch": 0.5616845467046023, "grad_norm": 1.9210201501846313, "learning_rate": 8.49860110486102e-06, "loss": 0.12964179515838622, "step": 5540 }, { "epoch": 0.5626984177275348, "grad_norm": 2.5370614528656006, "learning_rate": 8.466147070445123e-06, "loss": 0.15110173225402831, "step": 5550 }, { "epoch": 0.5637122887504673, "grad_norm": 3.765767812728882, "learning_rate": 8.433709572420586e-06, "loss": 0.13576176166534423, "step": 5560 }, { "epoch": 0.5647261597733998, "grad_norm": 3.04896879196167, "learning_rate": 8.40128896049445e-06, "loss": 0.14321813583374024, "step": 5570 }, { "epoch": 0.5657400307963323, "grad_norm": 2.9086568355560303, "learning_rate": 8.368885584191698e-06, "loss": 0.13838634490966797, "step": 5580 }, { "epoch": 0.5667539018192648, "grad_norm": 2.7609384059906006, "learning_rate": 8.336499792851505e-06, "loss": 0.13801541328430175, "step": 5590 }, { "epoch": 0.5677677728421973, "grad_norm": 2.3377225399017334, "learning_rate": 8.304131935623461e-06, "loss": 0.1526058316230774, "step": 5600 }, { "epoch": 0.5687816438651299, "grad_norm": 2.5156586170196533, "learning_rate": 8.271782361463806e-06, "loss": 0.14056005477905273, "step": 5610 }, { "epoch": 0.5697955148880623, "grad_norm": 2.091398000717163, "learning_rate": 8.239451419131676e-06, "loss": 0.1375560760498047, "step": 5620 }, { "epoch": 0.5708093859109948, "grad_norm": 4.181243896484375, "learning_rate": 8.207139457185328e-06, "loss": 0.14716676473617554, "step": 5630 }, { "epoch": 0.5718232569339273, "grad_norm": 4.4343037605285645, "learning_rate": 8.174846823978412e-06, "loss": 0.14299701452255248, "step": 5640 }, { "epoch": 0.5728371279568598, "grad_norm": 2.4637207984924316, "learning_rate": 8.142573867656182e-06, "loss": 0.13553693294525146, "step": 5650 }, { "epoch": 0.5738509989797923, "grad_norm": 2.990638256072998, "learning_rate": 8.110320936151746e-06, "loss": 0.12610201835632323, "step": 5660 }, { "epoch": 0.5748648700027248, "grad_norm": 2.502162218093872, "learning_rate": 8.078088377182352e-06, "loss": 0.11982247829437256, "step": 5670 }, { "epoch": 0.5758787410256573, "grad_norm": 3.481815814971924, "learning_rate": 8.045876538245595e-06, "loss": 0.14511115550994874, "step": 5680 }, { "epoch": 0.5768926120485898, "grad_norm": 2.2737128734588623, "learning_rate": 8.013685766615687e-06, "loss": 0.14467029571533202, "step": 5690 }, { "epoch": 0.5779064830715223, "grad_norm": 4.6814470291137695, "learning_rate": 7.981516409339726e-06, "loss": 0.15831255912780762, "step": 5700 }, { "epoch": 0.5789203540944547, "grad_norm": 3.130192756652832, "learning_rate": 7.94936881323393e-06, "loss": 0.13875654935836793, "step": 5710 }, { "epoch": 0.5799342251173872, "grad_norm": 4.117372989654541, "learning_rate": 7.917243324879924e-06, "loss": 0.15516005754470824, "step": 5720 }, { "epoch": 0.5809480961403197, "grad_norm": 3.271695613861084, "learning_rate": 7.88514029062098e-06, "loss": 0.14362766742706298, "step": 5730 }, { "epoch": 0.5819619671632522, "grad_norm": 2.469412326812744, "learning_rate": 7.853060056558294e-06, "loss": 0.13984622955322265, "step": 5740 }, { "epoch": 0.5829758381861847, "grad_norm": 2.8134765625, "learning_rate": 7.821002968547266e-06, "loss": 0.1616925358772278, "step": 5750 }, { "epoch": 0.5839897092091172, "grad_norm": 2.119581699371338, "learning_rate": 7.788969372193744e-06, "loss": 0.14377145767211913, "step": 5760 }, { "epoch": 0.5850035802320497, "grad_norm": 2.989133358001709, "learning_rate": 7.75695961285032e-06, "loss": 0.12898285388946534, "step": 5770 }, { "epoch": 0.5860174512549823, "grad_norm": 2.73699688911438, "learning_rate": 7.724974035612611e-06, "loss": 0.13289716243743896, "step": 5780 }, { "epoch": 0.5870313222779148, "grad_norm": 3.327615737915039, "learning_rate": 7.693012985315503e-06, "loss": 0.15831589698791504, "step": 5790 }, { "epoch": 0.5880451933008473, "grad_norm": 3.9518837928771973, "learning_rate": 7.661076806529486e-06, "loss": 0.12960100173950195, "step": 5800 }, { "epoch": 0.5890590643237797, "grad_norm": 2.6792194843292236, "learning_rate": 7.629165843556896e-06, "loss": 0.15007610321044923, "step": 5810 }, { "epoch": 0.5900729353467122, "grad_norm": 2.5863828659057617, "learning_rate": 7.597280440428216e-06, "loss": 0.14594576358795167, "step": 5820 }, { "epoch": 0.5910868063696447, "grad_norm": 3.3310043811798096, "learning_rate": 7.565420940898381e-06, "loss": 0.13770201206207275, "step": 5830 }, { "epoch": 0.5921006773925772, "grad_norm": 3.3448708057403564, "learning_rate": 7.5335876884430495e-06, "loss": 0.1502063035964966, "step": 5840 }, { "epoch": 0.5931145484155097, "grad_norm": 3.6712794303894043, "learning_rate": 7.501781026254922e-06, "loss": 0.14628909826278685, "step": 5850 }, { "epoch": 0.5941284194384422, "grad_norm": 3.7568328380584717, "learning_rate": 7.4700012972400224e-06, "loss": 0.1477779984474182, "step": 5860 }, { "epoch": 0.5951422904613747, "grad_norm": 1.8712328672409058, "learning_rate": 7.438248844014011e-06, "loss": 0.1502874970436096, "step": 5870 }, { "epoch": 0.5961561614843072, "grad_norm": 3.671171188354492, "learning_rate": 7.4065240088984944e-06, "loss": 0.13489129543304443, "step": 5880 }, { "epoch": 0.5971700325072397, "grad_norm": 4.254022121429443, "learning_rate": 7.3748271339173224e-06, "loss": 0.1496071457862854, "step": 5890 }, { "epoch": 0.5981839035301721, "grad_norm": 3.699650764465332, "learning_rate": 7.34315856079291e-06, "loss": 0.1591769576072693, "step": 5900 }, { "epoch": 0.5991977745531046, "grad_norm": 2.86504864692688, "learning_rate": 7.311518630942562e-06, "loss": 0.14769959449768066, "step": 5910 }, { "epoch": 0.6002116455760371, "grad_norm": 2.953585386276245, "learning_rate": 7.279907685474759e-06, "loss": 0.14885562658309937, "step": 5920 }, { "epoch": 0.6012255165989696, "grad_norm": 3.0778284072875977, "learning_rate": 7.248326065185527e-06, "loss": 0.1575820803642273, "step": 5930 }, { "epoch": 0.6022393876219021, "grad_norm": 1.9994312524795532, "learning_rate": 7.216774110554724e-06, "loss": 0.13365254402160645, "step": 5940 }, { "epoch": 0.6032532586448346, "grad_norm": 2.702272415161133, "learning_rate": 7.185252161742385e-06, "loss": 0.14872989654541016, "step": 5950 }, { "epoch": 0.6042671296677672, "grad_norm": 2.5348708629608154, "learning_rate": 7.153760558585059e-06, "loss": 0.11719400882720947, "step": 5960 }, { "epoch": 0.6052810006906997, "grad_norm": 3.3107779026031494, "learning_rate": 7.122299640592135e-06, "loss": 0.1293196678161621, "step": 5970 }, { "epoch": 0.6062948717136322, "grad_norm": 2.665560483932495, "learning_rate": 7.090869746942191e-06, "loss": 0.13128355741500855, "step": 5980 }, { "epoch": 0.6073087427365647, "grad_norm": 3.4412968158721924, "learning_rate": 7.05947121647933e-06, "loss": 0.13999329805374144, "step": 5990 }, { "epoch": 0.6083226137594971, "grad_norm": 4.718621730804443, "learning_rate": 7.028104387709531e-06, "loss": 0.13155653476715087, "step": 6000 }, { "epoch": 0.6093364847824296, "grad_norm": 2.9516477584838867, "learning_rate": 6.996769598797001e-06, "loss": 0.13349621295928954, "step": 6010 }, { "epoch": 0.6103503558053621, "grad_norm": 3.115609884262085, "learning_rate": 6.965467187560524e-06, "loss": 0.12831190824508668, "step": 6020 }, { "epoch": 0.6113642268282946, "grad_norm": 2.922041177749634, "learning_rate": 6.934197491469818e-06, "loss": 0.12278759479522705, "step": 6030 }, { "epoch": 0.6123780978512271, "grad_norm": 3.150496482849121, "learning_rate": 6.902960847641915e-06, "loss": 0.13003020286560057, "step": 6040 }, { "epoch": 0.6133919688741596, "grad_norm": 2.9897494316101074, "learning_rate": 6.8717575928374915e-06, "loss": 0.14452714920043946, "step": 6050 }, { "epoch": 0.6144058398970921, "grad_norm": 3.140655279159546, "learning_rate": 6.840588063457278e-06, "loss": 0.13440983295440673, "step": 6060 }, { "epoch": 0.6154197109200246, "grad_norm": 2.3669919967651367, "learning_rate": 6.809452595538403e-06, "loss": 0.1340573787689209, "step": 6070 }, { "epoch": 0.616433581942957, "grad_norm": 3.3537659645080566, "learning_rate": 6.778351524750777e-06, "loss": 0.1330895185470581, "step": 6080 }, { "epoch": 0.6174474529658895, "grad_norm": 2.5425703525543213, "learning_rate": 6.747285186393488e-06, "loss": 0.13141589164733886, "step": 6090 }, { "epoch": 0.618461323988822, "grad_norm": 7.418219089508057, "learning_rate": 6.716253915391167e-06, "loss": 0.15156272649765015, "step": 6100 }, { "epoch": 0.6194751950117545, "grad_norm": 3.5109310150146484, "learning_rate": 6.685258046290381e-06, "loss": 0.14476011991500853, "step": 6110 }, { "epoch": 0.620489066034687, "grad_norm": 4.248937129974365, "learning_rate": 6.654297913256047e-06, "loss": 0.15777870416641235, "step": 6120 }, { "epoch": 0.6215029370576196, "grad_norm": 2.5140626430511475, "learning_rate": 6.623373850067794e-06, "loss": 0.15185681581497193, "step": 6130 }, { "epoch": 0.6225168080805521, "grad_norm": 4.408506393432617, "learning_rate": 6.592486190116405e-06, "loss": 0.14573745727539061, "step": 6140 }, { "epoch": 0.6235306791034846, "grad_norm": 3.6144344806671143, "learning_rate": 6.561635266400181e-06, "loss": 0.1282370924949646, "step": 6150 }, { "epoch": 0.6245445501264171, "grad_norm": 4.823043346405029, "learning_rate": 6.5308214115213785e-06, "loss": 0.13821982145309447, "step": 6160 }, { "epoch": 0.6255584211493496, "grad_norm": 3.1483538150787354, "learning_rate": 6.500044957682627e-06, "loss": 0.13847461938858033, "step": 6170 }, { "epoch": 0.626572292172282, "grad_norm": 3.129638195037842, "learning_rate": 6.469306236683324e-06, "loss": 0.12250170707702637, "step": 6180 }, { "epoch": 0.6275861631952145, "grad_norm": 3.6528372764587402, "learning_rate": 6.438605579916078e-06, "loss": 0.14802403450012208, "step": 6190 }, { "epoch": 0.628600034218147, "grad_norm": 5.385506629943848, "learning_rate": 6.4079433183631255e-06, "loss": 0.12948824167251588, "step": 6200 }, { "epoch": 0.6296139052410795, "grad_norm": 3.880145788192749, "learning_rate": 6.377319782592767e-06, "loss": 0.1297578454017639, "step": 6210 }, { "epoch": 0.630627776264012, "grad_norm": 3.936742067337036, "learning_rate": 6.346735302755805e-06, "loss": 0.14913393259048463, "step": 6220 }, { "epoch": 0.6316416472869445, "grad_norm": 4.3577880859375, "learning_rate": 6.316190208581979e-06, "loss": 0.12378395795822143, "step": 6230 }, { "epoch": 0.632655518309877, "grad_norm": 2.276432752609253, "learning_rate": 6.285684829376413e-06, "loss": 0.14194142818450928, "step": 6240 }, { "epoch": 0.6336693893328095, "grad_norm": 5.047995567321777, "learning_rate": 6.25521949401607e-06, "loss": 0.1342092752456665, "step": 6250 }, { "epoch": 0.634683260355742, "grad_norm": 3.2214014530181885, "learning_rate": 6.2247945309461955e-06, "loss": 0.13787716627120972, "step": 6260 }, { "epoch": 0.6356971313786745, "grad_norm": 3.351928234100342, "learning_rate": 6.194410268176796e-06, "loss": 0.14075782299041747, "step": 6270 }, { "epoch": 0.6367110024016069, "grad_norm": 2.2535624504089355, "learning_rate": 6.164067033279073e-06, "loss": 0.1259325385093689, "step": 6280 }, { "epoch": 0.6377248734245394, "grad_norm": 3.24190354347229, "learning_rate": 6.133765153381918e-06, "loss": 0.14222235679626466, "step": 6290 }, { "epoch": 0.638738744447472, "grad_norm": 4.283137798309326, "learning_rate": 6.103504955168382e-06, "loss": 0.1300611138343811, "step": 6300 }, { "epoch": 0.6397526154704045, "grad_norm": 4.634685039520264, "learning_rate": 6.07328676487214e-06, "loss": 0.14292827844619752, "step": 6310 }, { "epoch": 0.640766486493337, "grad_norm": 3.5357697010040283, "learning_rate": 6.043110908273973e-06, "loss": 0.1334986209869385, "step": 6320 }, { "epoch": 0.6417803575162695, "grad_norm": 6.7381157875061035, "learning_rate": 6.012977710698288e-06, "loss": 0.12762702703475953, "step": 6330 }, { "epoch": 0.642794228539202, "grad_norm": 4.35365104675293, "learning_rate": 5.982887497009566e-06, "loss": 0.14120278358459473, "step": 6340 }, { "epoch": 0.6438080995621345, "grad_norm": 3.4878506660461426, "learning_rate": 5.9528405916088926e-06, "loss": 0.12576525211334227, "step": 6350 }, { "epoch": 0.644821970585067, "grad_norm": 4.050229072570801, "learning_rate": 5.9228373184304455e-06, "loss": 0.12987115383148193, "step": 6360 }, { "epoch": 0.6458358416079995, "grad_norm": 4.462668418884277, "learning_rate": 5.892878000938001e-06, "loss": 0.12724816799163818, "step": 6370 }, { "epoch": 0.6468497126309319, "grad_norm": 3.2944252490997314, "learning_rate": 5.86296296212146e-06, "loss": 0.13403228521347046, "step": 6380 }, { "epoch": 0.6478635836538644, "grad_norm": 2.5523507595062256, "learning_rate": 5.833092524493349e-06, "loss": 0.13019082546234131, "step": 6390 }, { "epoch": 0.6488774546767969, "grad_norm": 4.036607265472412, "learning_rate": 5.80326701008536e-06, "loss": 0.13473887443542482, "step": 6400 }, { "epoch": 0.6498913256997294, "grad_norm": 3.466766595840454, "learning_rate": 5.773486740444862e-06, "loss": 0.12180800437927246, "step": 6410 }, { "epoch": 0.6509051967226619, "grad_norm": 2.9528703689575195, "learning_rate": 5.743752036631443e-06, "loss": 0.13732032775878905, "step": 6420 }, { "epoch": 0.6519190677455944, "grad_norm": 3.6881346702575684, "learning_rate": 5.714063219213456e-06, "loss": 0.11564650535583496, "step": 6430 }, { "epoch": 0.6529329387685269, "grad_norm": 2.952211856842041, "learning_rate": 5.684420608264549e-06, "loss": 0.1311144709587097, "step": 6440 }, { "epoch": 0.6539468097914594, "grad_norm": 2.981379508972168, "learning_rate": 5.654824523360219e-06, "loss": 0.12766640186309813, "step": 6450 }, { "epoch": 0.6549606808143918, "grad_norm": 3.4478118419647217, "learning_rate": 5.625275283574372e-06, "loss": 0.11936190128326415, "step": 6460 }, { "epoch": 0.6559745518373244, "grad_norm": 3.8747498989105225, "learning_rate": 5.595773207475872e-06, "loss": 0.12809903621673585, "step": 6470 }, { "epoch": 0.6569884228602569, "grad_norm": 3.0893232822418213, "learning_rate": 5.566318613125128e-06, "loss": 0.13412971496582032, "step": 6480 }, { "epoch": 0.6580022938831894, "grad_norm": 2.5496714115142822, "learning_rate": 5.536911818070636e-06, "loss": 0.12897289991378785, "step": 6490 }, { "epoch": 0.6590161649061219, "grad_norm": 2.38222336769104, "learning_rate": 5.507553139345574e-06, "loss": 0.12906596660614014, "step": 6500 }, { "epoch": 0.6600300359290544, "grad_norm": 2.5875346660614014, "learning_rate": 5.478242893464389e-06, "loss": 0.12889788150787354, "step": 6510 }, { "epoch": 0.6610439069519869, "grad_norm": 3.5746097564697266, "learning_rate": 5.448981396419366e-06, "loss": 0.12472677230834961, "step": 6520 }, { "epoch": 0.6620577779749194, "grad_norm": 3.568962335586548, "learning_rate": 5.419768963677233e-06, "loss": 0.12711340188980103, "step": 6530 }, { "epoch": 0.6630716489978519, "grad_norm": 3.0243639945983887, "learning_rate": 5.39060591017576e-06, "loss": 0.14445141553878785, "step": 6540 }, { "epoch": 0.6640855200207844, "grad_norm": 2.870370864868164, "learning_rate": 5.3614925503203586e-06, "loss": 0.13696517944335937, "step": 6550 }, { "epoch": 0.6650993910437168, "grad_norm": 4.2380170822143555, "learning_rate": 5.332429197980706e-06, "loss": 0.1244422197341919, "step": 6560 }, { "epoch": 0.6661132620666493, "grad_norm": 3.019507884979248, "learning_rate": 5.303416166487337e-06, "loss": 0.13348519802093506, "step": 6570 }, { "epoch": 0.6671271330895818, "grad_norm": 5.846681118011475, "learning_rate": 5.274453768628289e-06, "loss": 0.13609769344329833, "step": 6580 }, { "epoch": 0.6681410041125143, "grad_norm": 3.464313268661499, "learning_rate": 5.245542316645718e-06, "loss": 0.12173019647598267, "step": 6590 }, { "epoch": 0.6691548751354468, "grad_norm": 4.612417221069336, "learning_rate": 5.2166821222325306e-06, "loss": 0.11494085788726807, "step": 6600 }, { "epoch": 0.6701687461583793, "grad_norm": 3.126760721206665, "learning_rate": 5.187873496529041e-06, "loss": 0.1169811487197876, "step": 6610 }, { "epoch": 0.6711826171813118, "grad_norm": 4.210911750793457, "learning_rate": 5.15911675011959e-06, "loss": 0.13004026412963868, "step": 6620 }, { "epoch": 0.6721964882042443, "grad_norm": 2.71085524559021, "learning_rate": 5.130412193029213e-06, "loss": 0.12407608032226562, "step": 6630 }, { "epoch": 0.6732103592271768, "grad_norm": 5.013385772705078, "learning_rate": 5.101760134720306e-06, "loss": 0.12994496822357177, "step": 6640 }, { "epoch": 0.6742242302501094, "grad_norm": 4.6224141120910645, "learning_rate": 5.073160884089263e-06, "loss": 0.13262467384338378, "step": 6650 }, { "epoch": 0.6752381012730418, "grad_norm": 4.262375831604004, "learning_rate": 5.044614749463173e-06, "loss": 0.13302299976348878, "step": 6660 }, { "epoch": 0.6762519722959743, "grad_norm": 3.5532848834991455, "learning_rate": 5.0161220385964745e-06, "loss": 0.12366718053817749, "step": 6670 }, { "epoch": 0.6772658433189068, "grad_norm": 3.8228397369384766, "learning_rate": 4.987683058667651e-06, "loss": 0.13080711364746095, "step": 6680 }, { "epoch": 0.6782797143418393, "grad_norm": 4.026787281036377, "learning_rate": 4.9592981162759215e-06, "loss": 0.13416730165481566, "step": 6690 }, { "epoch": 0.6792935853647718, "grad_norm": 3.506101369857788, "learning_rate": 4.930967517437922e-06, "loss": 0.11465880870819092, "step": 6700 }, { "epoch": 0.6803074563877043, "grad_norm": 4.732848644256592, "learning_rate": 4.902691567584412e-06, "loss": 0.13594018220901488, "step": 6710 }, { "epoch": 0.6813213274106368, "grad_norm": 2.7556567192077637, "learning_rate": 4.87447057155699e-06, "loss": 0.11386902332305908, "step": 6720 }, { "epoch": 0.6823351984335693, "grad_norm": 3.0781235694885254, "learning_rate": 4.846304833604792e-06, "loss": 0.11917515993118286, "step": 6730 }, { "epoch": 0.6833490694565018, "grad_norm": 6.109532833099365, "learning_rate": 4.8181946573812236e-06, "loss": 0.13799809217453002, "step": 6740 }, { "epoch": 0.6843629404794342, "grad_norm": 2.7225711345672607, "learning_rate": 4.790140345940688e-06, "loss": 0.11913795471191406, "step": 6750 }, { "epoch": 0.6853768115023667, "grad_norm": 5.342756271362305, "learning_rate": 4.762142201735299e-06, "loss": 0.12290217876434326, "step": 6760 }, { "epoch": 0.6863906825252992, "grad_norm": 4.3056159019470215, "learning_rate": 4.734200526611652e-06, "loss": 0.12846119403839112, "step": 6770 }, { "epoch": 0.6874045535482317, "grad_norm": 3.6138529777526855, "learning_rate": 4.706315621807537e-06, "loss": 0.12934434413909912, "step": 6780 }, { "epoch": 0.6884184245711642, "grad_norm": 3.4969513416290283, "learning_rate": 4.678487787948711e-06, "loss": 0.12200322151184081, "step": 6790 }, { "epoch": 0.6894322955940967, "grad_norm": 3.984917402267456, "learning_rate": 4.650717325045655e-06, "loss": 0.11501283645629883, "step": 6800 }, { "epoch": 0.6904461666170292, "grad_norm": 3.890134811401367, "learning_rate": 4.623004532490328e-06, "loss": 0.12741737365722655, "step": 6810 }, { "epoch": 0.6914600376399618, "grad_norm": 4.891021251678467, "learning_rate": 4.595349709052964e-06, "loss": 0.11527297496795655, "step": 6820 }, { "epoch": 0.6924739086628943, "grad_norm": 3.7361507415771484, "learning_rate": 4.5677531528788196e-06, "loss": 0.1163823962211609, "step": 6830 }, { "epoch": 0.6934877796858268, "grad_norm": 4.925938129425049, "learning_rate": 4.54021516148498e-06, "loss": 0.12933467626571654, "step": 6840 }, { "epoch": 0.6945016507087592, "grad_norm": 3.703672409057617, "learning_rate": 4.5127360317571475e-06, "loss": 0.12737321853637695, "step": 6850 }, { "epoch": 0.6955155217316917, "grad_norm": 4.467517852783203, "learning_rate": 4.485316059946438e-06, "loss": 0.1202894926071167, "step": 6860 }, { "epoch": 0.6965293927546242, "grad_norm": 5.7273736000061035, "learning_rate": 4.457955541666188e-06, "loss": 0.12387599945068359, "step": 6870 }, { "epoch": 0.6975432637775567, "grad_norm": 3.9140281677246094, "learning_rate": 4.430654771888776e-06, "loss": 0.10882689952850341, "step": 6880 }, { "epoch": 0.6985571348004892, "grad_norm": 4.8695549964904785, "learning_rate": 4.403414044942422e-06, "loss": 0.11911183595657349, "step": 6890 }, { "epoch": 0.6995710058234217, "grad_norm": 6.7610368728637695, "learning_rate": 4.376233654508042e-06, "loss": 0.11083142757415772, "step": 6900 }, { "epoch": 0.7005848768463542, "grad_norm": 4.070235252380371, "learning_rate": 4.349113893616056e-06, "loss": 0.11761400699615479, "step": 6910 }, { "epoch": 0.7015987478692867, "grad_norm": 4.601709842681885, "learning_rate": 4.322055054643244e-06, "loss": 0.11122281551361084, "step": 6920 }, { "epoch": 0.7026126188922192, "grad_norm": 6.667792320251465, "learning_rate": 4.295057429309589e-06, "loss": 0.11997240781784058, "step": 6930 }, { "epoch": 0.7036264899151516, "grad_norm": 4.72371244430542, "learning_rate": 4.268121308675132e-06, "loss": 0.11022696495056153, "step": 6940 }, { "epoch": 0.7046403609380841, "grad_norm": 2.902867555618286, "learning_rate": 4.241246983136834e-06, "loss": 0.1127133846282959, "step": 6950 }, { "epoch": 0.7056542319610166, "grad_norm": 3.9696550369262695, "learning_rate": 4.214434742425455e-06, "loss": 0.1175950288772583, "step": 6960 }, { "epoch": 0.7066681029839491, "grad_norm": 5.22468900680542, "learning_rate": 4.1876848756024116e-06, "loss": 0.10952872037887573, "step": 6970 }, { "epoch": 0.7076819740068816, "grad_norm": 3.11588191986084, "learning_rate": 4.1609976710566735e-06, "loss": 0.1340220093727112, "step": 6980 }, { "epoch": 0.7086958450298142, "grad_norm": 3.0759589672088623, "learning_rate": 4.134373416501652e-06, "loss": 0.12169348001480103, "step": 6990 }, { "epoch": 0.7097097160527467, "grad_norm": 6.039734363555908, "learning_rate": 4.107812398972093e-06, "loss": 0.12229359149932861, "step": 7000 }, { "epoch": 0.7107235870756792, "grad_norm": 4.667007923126221, "learning_rate": 4.081314904821001e-06, "loss": 0.11639153957366943, "step": 7010 }, { "epoch": 0.7117374580986117, "grad_norm": 3.581035852432251, "learning_rate": 4.054881219716521e-06, "loss": 0.12065010070800782, "step": 7020 }, { "epoch": 0.7127513291215442, "grad_norm": 5.454896926879883, "learning_rate": 4.0285116286388914e-06, "loss": 0.11107778549194336, "step": 7030 }, { "epoch": 0.7137652001444766, "grad_norm": 5.117547512054443, "learning_rate": 4.0022064158773445e-06, "loss": 0.1269879937171936, "step": 7040 }, { "epoch": 0.7147790711674091, "grad_norm": 3.8097946643829346, "learning_rate": 3.9759658650270575e-06, "loss": 0.14115025997161865, "step": 7050 }, { "epoch": 0.7157929421903416, "grad_norm": 3.4203474521636963, "learning_rate": 3.94979025898609e-06, "loss": 0.10807390213012695, "step": 7060 }, { "epoch": 0.7168068132132741, "grad_norm": 4.138892650604248, "learning_rate": 3.9236798799523375e-06, "loss": 0.12261967658996582, "step": 7070 }, { "epoch": 0.7178206842362066, "grad_norm": 4.067795753479004, "learning_rate": 3.89763500942048e-06, "loss": 0.13964438438415527, "step": 7080 }, { "epoch": 0.7188345552591391, "grad_norm": 2.956080913543701, "learning_rate": 3.871655928178962e-06, "loss": 0.11420962810516358, "step": 7090 }, { "epoch": 0.7198484262820716, "grad_norm": 3.885470390319824, "learning_rate": 3.8457429163069534e-06, "loss": 0.13264203071594238, "step": 7100 }, { "epoch": 0.7208622973050041, "grad_norm": 3.78692364692688, "learning_rate": 3.819896253171332e-06, "loss": 0.12570440769195557, "step": 7110 }, { "epoch": 0.7218761683279366, "grad_norm": 3.993077278137207, "learning_rate": 3.7941162174236745e-06, "loss": 0.11418694257736206, "step": 7120 }, { "epoch": 0.722890039350869, "grad_norm": 3.834749698638916, "learning_rate": 3.7684030869972464e-06, "loss": 0.09894397854804993, "step": 7130 }, { "epoch": 0.7239039103738015, "grad_norm": 5.35507345199585, "learning_rate": 3.742757139104023e-06, "loss": 0.12658849954605103, "step": 7140 }, { "epoch": 0.724917781396734, "grad_norm": 5.1663312911987305, "learning_rate": 3.7171786502316767e-06, "loss": 0.1278180718421936, "step": 7150 }, { "epoch": 0.7259316524196666, "grad_norm": 4.22108268737793, "learning_rate": 3.691667896140605e-06, "loss": 0.11281635761260986, "step": 7160 }, { "epoch": 0.7269455234425991, "grad_norm": 4.242372989654541, "learning_rate": 3.6662251518609747e-06, "loss": 0.11219189167022706, "step": 7170 }, { "epoch": 0.7279593944655316, "grad_norm": 5.025190353393555, "learning_rate": 3.64085069168973e-06, "loss": 0.11954324245452881, "step": 7180 }, { "epoch": 0.7289732654884641, "grad_norm": 3.8606972694396973, "learning_rate": 3.6155447891876518e-06, "loss": 0.11092431545257568, "step": 7190 }, { "epoch": 0.7299871365113966, "grad_norm": 4.092825889587402, "learning_rate": 3.590307717176401e-06, "loss": 0.10668175220489502, "step": 7200 }, { "epoch": 0.7310010075343291, "grad_norm": 7.149838447570801, "learning_rate": 3.565139747735581e-06, "loss": 0.11174547672271729, "step": 7210 }, { "epoch": 0.7320148785572616, "grad_norm": 3.284205198287964, "learning_rate": 3.5400411521998123e-06, "loss": 0.10113648176193238, "step": 7220 }, { "epoch": 0.733028749580194, "grad_norm": 4.014682769775391, "learning_rate": 3.5150122011557888e-06, "loss": 0.11273802518844604, "step": 7230 }, { "epoch": 0.7340426206031265, "grad_norm": 3.928431272506714, "learning_rate": 3.4900531644393744e-06, "loss": 0.10815713405609131, "step": 7240 }, { "epoch": 0.735056491626059, "grad_norm": 4.8838887214660645, "learning_rate": 3.4651643111326895e-06, "loss": 0.12747522592544555, "step": 7250 }, { "epoch": 0.7360703626489915, "grad_norm": 4.042419910430908, "learning_rate": 3.440345909561208e-06, "loss": 0.09965988397598266, "step": 7260 }, { "epoch": 0.737084233671924, "grad_norm": 3.4488868713378906, "learning_rate": 3.415598227290877e-06, "loss": 0.10849831104278565, "step": 7270 }, { "epoch": 0.7380981046948565, "grad_norm": 3.457470178604126, "learning_rate": 3.390921531125211e-06, "loss": 0.10677542686462402, "step": 7280 }, { "epoch": 0.739111975717789, "grad_norm": 4.329112529754639, "learning_rate": 3.366316087102429e-06, "loss": 0.0972703218460083, "step": 7290 }, { "epoch": 0.7401258467407215, "grad_norm": 6.676194190979004, "learning_rate": 3.3417821604925937e-06, "loss": 0.10293588638305665, "step": 7300 }, { "epoch": 0.741139717763654, "grad_norm": 4.413027286529541, "learning_rate": 3.3173200157947315e-06, "loss": 0.12414398193359374, "step": 7310 }, { "epoch": 0.7421535887865864, "grad_norm": 7.431371688842773, "learning_rate": 3.2929299167339955e-06, "loss": 0.11910377740859986, "step": 7320 }, { "epoch": 0.7431674598095189, "grad_norm": 3.1568822860717773, "learning_rate": 3.2686121262588165e-06, "loss": 0.1143963098526001, "step": 7330 }, { "epoch": 0.7441813308324515, "grad_norm": 4.981686115264893, "learning_rate": 3.244366906538071e-06, "loss": 0.1060139536857605, "step": 7340 }, { "epoch": 0.745195201855384, "grad_norm": 3.7188217639923096, "learning_rate": 3.2201945189582597e-06, "loss": 0.10599894523620605, "step": 7350 }, { "epoch": 0.7462090728783165, "grad_norm": 4.45810079574585, "learning_rate": 3.1960952241206745e-06, "loss": 0.10549752712249756, "step": 7360 }, { "epoch": 0.747222943901249, "grad_norm": 7.282859802246094, "learning_rate": 3.172069281838603e-06, "loss": 0.10542244911193847, "step": 7370 }, { "epoch": 0.7482368149241815, "grad_norm": 7.102052688598633, "learning_rate": 3.148116951134522e-06, "loss": 0.11055755615234375, "step": 7380 }, { "epoch": 0.749250685947114, "grad_norm": 4.021765232086182, "learning_rate": 3.1242384902373024e-06, "loss": 0.1023187518119812, "step": 7390 }, { "epoch": 0.7502645569700465, "grad_norm": 3.401089906692505, "learning_rate": 3.1004341565794373e-06, "loss": 0.11114835739135742, "step": 7400 }, { "epoch": 0.751278427992979, "grad_norm": 4.2021636962890625, "learning_rate": 3.0767042067942475e-06, "loss": 0.10867799520492553, "step": 7410 }, { "epoch": 0.7522922990159114, "grad_norm": 4.7854461669921875, "learning_rate": 3.0530488967131265e-06, "loss": 0.10333828926086426, "step": 7420 }, { "epoch": 0.7533061700388439, "grad_norm": 4.083970069885254, "learning_rate": 3.0294684813627917e-06, "loss": 0.09977574944496155, "step": 7430 }, { "epoch": 0.7543200410617764, "grad_norm": 5.489826202392578, "learning_rate": 3.0059632149625118e-06, "loss": 0.09425526857376099, "step": 7440 }, { "epoch": 0.7553339120847089, "grad_norm": 5.6994428634643555, "learning_rate": 2.982533350921383e-06, "loss": 0.10830943584442139, "step": 7450 }, { "epoch": 0.7563477831076414, "grad_norm": 3.2898190021514893, "learning_rate": 2.959179141835591e-06, "loss": 0.0967804253101349, "step": 7460 }, { "epoch": 0.7573616541305739, "grad_norm": 3.869109869003296, "learning_rate": 2.935900839485688e-06, "loss": 0.1158525824546814, "step": 7470 }, { "epoch": 0.7583755251535064, "grad_norm": 4.697089672088623, "learning_rate": 2.9126986948338898e-06, "loss": 0.0875544548034668, "step": 7480 }, { "epoch": 0.7593893961764389, "grad_norm": 4.096963405609131, "learning_rate": 2.889572958021347e-06, "loss": 0.1109933614730835, "step": 7490 }, { "epoch": 0.7604032671993713, "grad_norm": 4.247376918792725, "learning_rate": 2.866523878365468e-06, "loss": 0.09730291962623597, "step": 7500 }, { "epoch": 0.761417138222304, "grad_norm": 4.848324298858643, "learning_rate": 2.8435517043572204e-06, "loss": 0.10712188482284546, "step": 7510 }, { "epoch": 0.7624310092452364, "grad_norm": 4.232396125793457, "learning_rate": 2.820656683658456e-06, "loss": 0.11654512882232666, "step": 7520 }, { "epoch": 0.7634448802681689, "grad_norm": 4.980061054229736, "learning_rate": 2.797839063099249e-06, "loss": 0.10484366416931153, "step": 7530 }, { "epoch": 0.7644587512911014, "grad_norm": 3.8789243698120117, "learning_rate": 2.775099088675216e-06, "loss": 0.12214598655700684, "step": 7540 }, { "epoch": 0.7654726223140339, "grad_norm": 4.8325700759887695, "learning_rate": 2.7524370055448755e-06, "loss": 0.11099293231964111, "step": 7550 }, { "epoch": 0.7664864933369664, "grad_norm": 4.524445056915283, "learning_rate": 2.7298530580270154e-06, "loss": 0.09901257157325745, "step": 7560 }, { "epoch": 0.7675003643598989, "grad_norm": 3.4364442825317383, "learning_rate": 2.7073474895980333e-06, "loss": 0.09858832359313965, "step": 7570 }, { "epoch": 0.7685142353828314, "grad_norm": 6.098334789276123, "learning_rate": 2.6849205428893334e-06, "loss": 0.10248486995697022, "step": 7580 }, { "epoch": 0.7695281064057639, "grad_norm": 3.5714588165283203, "learning_rate": 2.662572459684699e-06, "loss": 0.09323228597640991, "step": 7590 }, { "epoch": 0.7705419774286963, "grad_norm": 3.170008897781372, "learning_rate": 2.640303480917693e-06, "loss": 0.09883933067321778, "step": 7600 }, { "epoch": 0.7715558484516288, "grad_norm": 3.5615732669830322, "learning_rate": 2.618113846669059e-06, "loss": 0.11557029485702515, "step": 7610 }, { "epoch": 0.7725697194745613, "grad_norm": 6.178597450256348, "learning_rate": 2.596003796164127e-06, "loss": 0.10330057144165039, "step": 7620 }, { "epoch": 0.7735835904974938, "grad_norm": 4.990747451782227, "learning_rate": 2.5739735677702416e-06, "loss": 0.10126607418060303, "step": 7630 }, { "epoch": 0.7745974615204263, "grad_norm": 4.926615238189697, "learning_rate": 2.552023398994188e-06, "loss": 0.10320491790771484, "step": 7640 }, { "epoch": 0.7756113325433588, "grad_norm": 4.724055767059326, "learning_rate": 2.5301535264796274e-06, "loss": 0.11369864940643311, "step": 7650 }, { "epoch": 0.7766252035662913, "grad_norm": 5.655747413635254, "learning_rate": 2.508364186004566e-06, "loss": 0.11672896146774292, "step": 7660 }, { "epoch": 0.7776390745892238, "grad_norm": 4.2659783363342285, "learning_rate": 2.486655612478782e-06, "loss": 0.09410192966461181, "step": 7670 }, { "epoch": 0.7786529456121564, "grad_norm": 4.706676006317139, "learning_rate": 2.465028039941316e-06, "loss": 0.08614500761032104, "step": 7680 }, { "epoch": 0.7796668166350889, "grad_norm": 4.025252342224121, "learning_rate": 2.443481701557946e-06, "loss": 0.0901565432548523, "step": 7690 }, { "epoch": 0.7806806876580213, "grad_norm": 4.339155197143555, "learning_rate": 2.4220168296186587e-06, "loss": 0.08766357898712158, "step": 7700 }, { "epoch": 0.7816945586809538, "grad_norm": 5.947693347930908, "learning_rate": 2.4006336555351615e-06, "loss": 0.09656726717948913, "step": 7710 }, { "epoch": 0.7827084297038863, "grad_norm": 5.469015598297119, "learning_rate": 2.3793324098383796e-06, "loss": 0.10164500474929809, "step": 7720 }, { "epoch": 0.7837223007268188, "grad_norm": 7.741672992706299, "learning_rate": 2.35811332217597e-06, "loss": 0.08996909260749816, "step": 7730 }, { "epoch": 0.7847361717497513, "grad_norm": 4.80124044418335, "learning_rate": 2.3369766213098553e-06, "loss": 0.10194540023803711, "step": 7740 }, { "epoch": 0.7857500427726838, "grad_norm": 3.903132677078247, "learning_rate": 2.315922535113743e-06, "loss": 0.09439104795455933, "step": 7750 }, { "epoch": 0.7867639137956163, "grad_norm": 4.837513446807861, "learning_rate": 2.2949512905706793e-06, "loss": 0.09238967895507813, "step": 7760 }, { "epoch": 0.7877777848185488, "grad_norm": 6.4469380378723145, "learning_rate": 2.274063113770597e-06, "loss": 0.09371460676193237, "step": 7770 }, { "epoch": 0.7887916558414813, "grad_norm": 4.775465488433838, "learning_rate": 2.2532582299078775e-06, "loss": 0.10386288166046143, "step": 7780 }, { "epoch": 0.7898055268644137, "grad_norm": 4.63199520111084, "learning_rate": 2.2325368632789345e-06, "loss": 0.0949113428592682, "step": 7790 }, { "epoch": 0.7908193978873462, "grad_norm": 5.499833583831787, "learning_rate": 2.211899237279779e-06, "loss": 0.0965012788772583, "step": 7800 }, { "epoch": 0.7918332689102787, "grad_norm": 4.107534408569336, "learning_rate": 2.1913455744036138e-06, "loss": 0.12462728023529053, "step": 7810 }, { "epoch": 0.7928471399332112, "grad_norm": 3.7006402015686035, "learning_rate": 2.1708760962384545e-06, "loss": 0.10697157382965088, "step": 7820 }, { "epoch": 0.7938610109561437, "grad_norm": 4.408971786499023, "learning_rate": 2.1504910234647112e-06, "loss": 0.09173510074615479, "step": 7830 }, { "epoch": 0.7948748819790762, "grad_norm": 5.312666893005371, "learning_rate": 2.130190575852832e-06, "loss": 0.09338643550872802, "step": 7840 }, { "epoch": 0.7958887530020088, "grad_norm": 4.342568874359131, "learning_rate": 2.109974972260921e-06, "loss": 0.08913659453392028, "step": 7850 }, { "epoch": 0.7969026240249413, "grad_norm": 6.3937764167785645, "learning_rate": 2.0898444306323807e-06, "loss": 0.09069312810897827, "step": 7860 }, { "epoch": 0.7979164950478738, "grad_norm": 4.384931564331055, "learning_rate": 2.069799167993577e-06, "loss": 0.08695077896118164, "step": 7870 }, { "epoch": 0.7989303660708063, "grad_norm": 6.601479530334473, "learning_rate": 2.0498394004514745e-06, "loss": 0.09124878644943238, "step": 7880 }, { "epoch": 0.7999442370937387, "grad_norm": 4.5479736328125, "learning_rate": 2.029965343191326e-06, "loss": 0.11412537097930908, "step": 7890 }, { "epoch": 0.8009581081166712, "grad_norm": 5.334273338317871, "learning_rate": 2.0101772104743422e-06, "loss": 0.11103165149688721, "step": 7900 }, { "epoch": 0.8019719791396037, "grad_norm": 5.0291314125061035, "learning_rate": 1.990475215635388e-06, "loss": 0.08306378722190857, "step": 7910 }, { "epoch": 0.8029858501625362, "grad_norm": 5.477987766265869, "learning_rate": 1.9708595710806787e-06, "loss": 0.09237111806869507, "step": 7920 }, { "epoch": 0.8039997211854687, "grad_norm": 4.856706619262695, "learning_rate": 1.9513304882854966e-06, "loss": 0.0821602463722229, "step": 7930 }, { "epoch": 0.8050135922084012, "grad_norm": 4.901946067810059, "learning_rate": 1.9318881777918973e-06, "loss": 0.0867269515991211, "step": 7940 }, { "epoch": 0.8060274632313337, "grad_norm": 5.759316444396973, "learning_rate": 1.9125328492064575e-06, "loss": 0.08669208288192749, "step": 7950 }, { "epoch": 0.8070413342542662, "grad_norm": 5.8878068923950195, "learning_rate": 1.8932647111980007e-06, "loss": 0.09651718139648438, "step": 7960 }, { "epoch": 0.8080552052771987, "grad_norm": 5.267746925354004, "learning_rate": 1.8740839714953552e-06, "loss": 0.09352638125419617, "step": 7970 }, { "epoch": 0.8090690763001311, "grad_norm": 5.091507911682129, "learning_rate": 1.8549908368851099e-06, "loss": 0.10027939081192017, "step": 7980 }, { "epoch": 0.8100829473230636, "grad_norm": 4.156858921051025, "learning_rate": 1.8359855132093884e-06, "loss": 0.0829850673675537, "step": 7990 }, { "epoch": 0.8110968183459961, "grad_norm": 4.723456859588623, "learning_rate": 1.8170682053636358e-06, "loss": 0.09112454652786255, "step": 8000 }, { "epoch": 0.8121106893689286, "grad_norm": 5.891902446746826, "learning_rate": 1.7982391172943936e-06, "loss": 0.09160175919532776, "step": 8010 }, { "epoch": 0.8131245603918611, "grad_norm": 5.539313316345215, "learning_rate": 1.7794984519971126e-06, "loss": 0.10523844957351684, "step": 8020 }, { "epoch": 0.8141384314147937, "grad_norm": 4.249697208404541, "learning_rate": 1.7608464115139712e-06, "loss": 0.08340676426887512, "step": 8030 }, { "epoch": 0.8151523024377262, "grad_norm": 4.727532863616943, "learning_rate": 1.7422831969316724e-06, "loss": 0.09814491271972656, "step": 8040 }, { "epoch": 0.8161661734606587, "grad_norm": 6.145285606384277, "learning_rate": 1.7238090083793003e-06, "loss": 0.08798856139183045, "step": 8050 }, { "epoch": 0.8171800444835912, "grad_norm": 4.172557830810547, "learning_rate": 1.7054240450261594e-06, "loss": 0.08113476634025574, "step": 8060 }, { "epoch": 0.8181939155065237, "grad_norm": 3.9860620498657227, "learning_rate": 1.6871285050796093e-06, "loss": 0.08934528827667236, "step": 8070 }, { "epoch": 0.8192077865294561, "grad_norm": 5.243678092956543, "learning_rate": 1.6689225857829527e-06, "loss": 0.08458730578422546, "step": 8080 }, { "epoch": 0.8202216575523886, "grad_norm": 4.585949897766113, "learning_rate": 1.6508064834132875e-06, "loss": 0.09676519632339478, "step": 8090 }, { "epoch": 0.8212355285753211, "grad_norm": 7.196340560913086, "learning_rate": 1.632780393279404e-06, "loss": 0.09427220821380615, "step": 8100 }, { "epoch": 0.8222493995982536, "grad_norm": 5.416752815246582, "learning_rate": 1.614844509719674e-06, "loss": 0.08551243543624878, "step": 8110 }, { "epoch": 0.8232632706211861, "grad_norm": 4.697057723999023, "learning_rate": 1.5969990260999569e-06, "loss": 0.08866882920265198, "step": 8120 }, { "epoch": 0.8242771416441186, "grad_norm": 2.6527934074401855, "learning_rate": 1.5792441348115116e-06, "loss": 0.08249115347862243, "step": 8130 }, { "epoch": 0.8252910126670511, "grad_norm": 5.503770351409912, "learning_rate": 1.5615800272689352e-06, "loss": 0.07259811162948608, "step": 8140 }, { "epoch": 0.8263048836899836, "grad_norm": 4.882474422454834, "learning_rate": 1.5440068939080776e-06, "loss": 0.08170753717422485, "step": 8150 }, { "epoch": 0.827318754712916, "grad_norm": 5.063050270080566, "learning_rate": 1.5265249241840153e-06, "loss": 0.09211691617965698, "step": 8160 }, { "epoch": 0.8283326257358485, "grad_norm": 4.694667816162109, "learning_rate": 1.5091343065689756e-06, "loss": 0.09465165138244629, "step": 8170 }, { "epoch": 0.829346496758781, "grad_norm": 5.262328624725342, "learning_rate": 1.4918352285503357e-06, "loss": 0.08186529874801636, "step": 8180 }, { "epoch": 0.8303603677817135, "grad_norm": 5.46805477142334, "learning_rate": 1.4746278766285905e-06, "loss": 0.08158503770828247, "step": 8190 }, { "epoch": 0.8313742388046461, "grad_norm": 5.3114471435546875, "learning_rate": 1.4575124363153315e-06, "loss": 0.0941901981830597, "step": 8200 }, { "epoch": 0.8323881098275786, "grad_norm": 5.149500846862793, "learning_rate": 1.4404890921312654e-06, "loss": 0.09329066276550294, "step": 8210 }, { "epoch": 0.8334019808505111, "grad_norm": 5.680479526519775, "learning_rate": 1.4235580276042071e-06, "loss": 0.08054632544517518, "step": 8220 }, { "epoch": 0.8344158518734436, "grad_norm": 4.1020026206970215, "learning_rate": 1.4067194252671157e-06, "loss": 0.08190642595291138, "step": 8230 }, { "epoch": 0.8354297228963761, "grad_norm": 5.094693660736084, "learning_rate": 1.3899734666561138e-06, "loss": 0.0950078010559082, "step": 8240 }, { "epoch": 0.8364435939193086, "grad_norm": 5.231489181518555, "learning_rate": 1.373320332308541e-06, "loss": 0.0923021137714386, "step": 8250 }, { "epoch": 0.837457464942241, "grad_norm": 4.612964630126953, "learning_rate": 1.3567602017609981e-06, "loss": 0.08082551956176758, "step": 8260 }, { "epoch": 0.8384713359651735, "grad_norm": 5.680703163146973, "learning_rate": 1.3402932535474277e-06, "loss": 0.0809893012046814, "step": 8270 }, { "epoch": 0.839485206988106, "grad_norm": 6.6310930252075195, "learning_rate": 1.3239196651971654e-06, "loss": 0.09475595355033875, "step": 8280 }, { "epoch": 0.8404990780110385, "grad_norm": 4.030436038970947, "learning_rate": 1.3076396132330516e-06, "loss": 0.07261584997177124, "step": 8290 }, { "epoch": 0.841512949033971, "grad_norm": 4.324150085449219, "learning_rate": 1.2914532731694996e-06, "loss": 0.0753787875175476, "step": 8300 }, { "epoch": 0.8425268200569035, "grad_norm": 4.652535438537598, "learning_rate": 1.2753608195106314e-06, "loss": 0.08563754558563233, "step": 8310 }, { "epoch": 0.843540691079836, "grad_norm": 5.1582255363464355, "learning_rate": 1.2593624257483838e-06, "loss": 0.08307428359985351, "step": 8320 }, { "epoch": 0.8445545621027685, "grad_norm": 4.828760147094727, "learning_rate": 1.243458264360634e-06, "loss": 0.07590364217758179, "step": 8330 }, { "epoch": 0.845568433125701, "grad_norm": 5.6583571434021, "learning_rate": 1.2276485068093447e-06, "loss": 0.08446954488754273, "step": 8340 }, { "epoch": 0.8465823041486334, "grad_norm": 7.829843997955322, "learning_rate": 1.2119333235387232e-06, "loss": 0.08255720138549805, "step": 8350 }, { "epoch": 0.8475961751715659, "grad_norm": 5.137041091918945, "learning_rate": 1.1963128839733674e-06, "loss": 0.07315125465393066, "step": 8360 }, { "epoch": 0.8486100461944985, "grad_norm": 4.825721740722656, "learning_rate": 1.1807873565164507e-06, "loss": 0.08031931519508362, "step": 8370 }, { "epoch": 0.849623917217431, "grad_norm": 5.02724552154541, "learning_rate": 1.1653569085479067e-06, "loss": 0.08772346377372742, "step": 8380 }, { "epoch": 0.8506377882403635, "grad_norm": 4.356783390045166, "learning_rate": 1.150021706422615e-06, "loss": 0.08760892152786255, "step": 8390 }, { "epoch": 0.851651659263296, "grad_norm": 5.14143705368042, "learning_rate": 1.1347819154686246e-06, "loss": 0.08384116291999817, "step": 8400 }, { "epoch": 0.8526655302862285, "grad_norm": 5.239612579345703, "learning_rate": 1.1196376999853531e-06, "loss": 0.08415011167526246, "step": 8410 }, { "epoch": 0.853679401309161, "grad_norm": 4.018215179443359, "learning_rate": 1.104589223241831e-06, "loss": 0.0773701548576355, "step": 8420 }, { "epoch": 0.8546932723320935, "grad_norm": 5.223018646240234, "learning_rate": 1.089636647474923e-06, "loss": 0.08247218132019044, "step": 8430 }, { "epoch": 0.855707143355026, "grad_norm": 3.889371633529663, "learning_rate": 1.0747801338876006e-06, "loss": 0.07262318134307862, "step": 8440 }, { "epoch": 0.8567210143779584, "grad_norm": 5.6633687019348145, "learning_rate": 1.0600198426471908e-06, "loss": 0.07865828275680542, "step": 8450 }, { "epoch": 0.8577348854008909, "grad_norm": 4.849819660186768, "learning_rate": 1.0453559328836517e-06, "loss": 0.08208908438682556, "step": 8460 }, { "epoch": 0.8587487564238234, "grad_norm": 5.933138370513916, "learning_rate": 1.0307885626878555e-06, "loss": 0.07168176770210266, "step": 8470 }, { "epoch": 0.8597626274467559, "grad_norm": 5.303300857543945, "learning_rate": 1.0163178891098912e-06, "loss": 0.07524607181549073, "step": 8480 }, { "epoch": 0.8607764984696884, "grad_norm": 5.137148857116699, "learning_rate": 1.0019440681573633e-06, "loss": 0.07318562269210815, "step": 8490 }, { "epoch": 0.8617903694926209, "grad_norm": 4.8498640060424805, "learning_rate": 9.876672547937117e-07, "loss": 0.07492645978927612, "step": 8500 }, { "epoch": 0.8628042405155534, "grad_norm": 7.548851490020752, "learning_rate": 9.734876029365448e-07, "loss": 0.07995496988296509, "step": 8510 }, { "epoch": 0.8638181115384859, "grad_norm": 5.879611968994141, "learning_rate": 9.594052654559737e-07, "loss": 0.07030402421951294, "step": 8520 }, { "epoch": 0.8648319825614184, "grad_norm": 5.300173282623291, "learning_rate": 9.454203941729767e-07, "loss": 0.07033746242523194, "step": 8530 }, { "epoch": 0.865845853584351, "grad_norm": 4.799980640411377, "learning_rate": 9.315331398577454e-07, "loss": 0.07308410406112671, "step": 8540 }, { "epoch": 0.8668597246072834, "grad_norm": 4.763209342956543, "learning_rate": 9.177436522280714e-07, "loss": 0.07821374535560607, "step": 8550 }, { "epoch": 0.8678735956302159, "grad_norm": 6.308379173278809, "learning_rate": 9.04052079947727e-07, "loss": 0.07809398174285889, "step": 8560 }, { "epoch": 0.8688874666531484, "grad_norm": 6.82426118850708, "learning_rate": 8.904585706248637e-07, "loss": 0.06704331040382386, "step": 8570 }, { "epoch": 0.8699013376760809, "grad_norm": 5.4584736824035645, "learning_rate": 8.76963270810427e-07, "loss": 0.08239327669143677, "step": 8580 }, { "epoch": 0.8709152086990134, "grad_norm": 3.941917657852173, "learning_rate": 8.635663259965632e-07, "loss": 0.08434160947799682, "step": 8590 }, { "epoch": 0.8719290797219459, "grad_norm": 4.210510730743408, "learning_rate": 8.502678806150588e-07, "loss": 0.06549115180969238, "step": 8600 }, { "epoch": 0.8729429507448784, "grad_norm": 5.41467809677124, "learning_rate": 8.370680780357909e-07, "loss": 0.07275999784469604, "step": 8610 }, { "epoch": 0.8739568217678109, "grad_norm": 4.013291358947754, "learning_rate": 8.23967060565164e-07, "loss": 0.06556012630462646, "step": 8620 }, { "epoch": 0.8749706927907434, "grad_norm": 5.323051452636719, "learning_rate": 8.109649694445898e-07, "loss": 0.07569139003753662, "step": 8630 }, { "epoch": 0.8759845638136758, "grad_norm": 5.401780605316162, "learning_rate": 7.980619448489601e-07, "loss": 0.0750801682472229, "step": 8640 }, { "epoch": 0.8769984348366083, "grad_norm": 4.2115654945373535, "learning_rate": 7.852581258851333e-07, "loss": 0.06609644889831542, "step": 8650 }, { "epoch": 0.8780123058595408, "grad_norm": 7.008636951446533, "learning_rate": 7.725536505904396e-07, "loss": 0.06567134857177734, "step": 8660 }, { "epoch": 0.8790261768824733, "grad_norm": 4.129462718963623, "learning_rate": 7.599486559311887e-07, "loss": 0.07776172161102295, "step": 8670 }, { "epoch": 0.8800400479054058, "grad_norm": 5.315987586975098, "learning_rate": 7.474432778011953e-07, "loss": 0.07777782678604125, "step": 8680 }, { "epoch": 0.8810539189283383, "grad_norm": 4.4022111892700195, "learning_rate": 7.350376510203105e-07, "loss": 0.06975040435791016, "step": 8690 }, { "epoch": 0.8820677899512708, "grad_norm": 3.310058355331421, "learning_rate": 7.227319093329732e-07, "loss": 0.06725041270256042, "step": 8700 }, { "epoch": 0.8830816609742033, "grad_norm": 5.3232011795043945, "learning_rate": 7.105261854067691e-07, "loss": 0.06423087120056152, "step": 8710 }, { "epoch": 0.8840955319971359, "grad_norm": 4.7997002601623535, "learning_rate": 6.984206108309932e-07, "loss": 0.06790922284126281, "step": 8720 }, { "epoch": 0.8851094030200684, "grad_norm": 3.821206569671631, "learning_rate": 6.864153161152354e-07, "loss": 0.05581852197647095, "step": 8730 }, { "epoch": 0.8861232740430008, "grad_norm": 4.764118194580078, "learning_rate": 6.745104306879769e-07, "loss": 0.07816423177719116, "step": 8740 }, { "epoch": 0.8871371450659333, "grad_norm": 5.111538887023926, "learning_rate": 6.627060828951881e-07, "loss": 0.07219235897064209, "step": 8750 }, { "epoch": 0.8881510160888658, "grad_norm": 5.471410751342773, "learning_rate": 6.510023999989501e-07, "loss": 0.08342283368110656, "step": 8760 }, { "epoch": 0.8891648871117983, "grad_norm": 6.248427391052246, "learning_rate": 6.393995081760795e-07, "loss": 0.06734535694122315, "step": 8770 }, { "epoch": 0.8901787581347308, "grad_norm": 4.840617656707764, "learning_rate": 6.278975325167691e-07, "loss": 0.06994056105613708, "step": 8780 }, { "epoch": 0.8911926291576633, "grad_norm": 8.027692794799805, "learning_rate": 6.164965970232417e-07, "loss": 0.09474731087684632, "step": 8790 }, { "epoch": 0.8922065001805958, "grad_norm": 4.949733257293701, "learning_rate": 6.051968246084117e-07, "loss": 0.07374169826507568, "step": 8800 }, { "epoch": 0.8932203712035283, "grad_norm": 6.045738220214844, "learning_rate": 5.939983370945535e-07, "loss": 0.08116617202758789, "step": 8810 }, { "epoch": 0.8942342422264608, "grad_norm": 2.763157606124878, "learning_rate": 5.829012552120039e-07, "loss": 0.08118182420730591, "step": 8820 }, { "epoch": 0.8952481132493932, "grad_norm": 4.378904342651367, "learning_rate": 5.719056985978388e-07, "loss": 0.06549746990203857, "step": 8830 }, { "epoch": 0.8962619842723257, "grad_norm": 7.278682231903076, "learning_rate": 5.610117857946062e-07, "loss": 0.07046255469322205, "step": 8840 }, { "epoch": 0.8972758552952582, "grad_norm": 4.194280624389648, "learning_rate": 5.502196342490318e-07, "loss": 0.06778375506401062, "step": 8850 }, { "epoch": 0.8982897263181907, "grad_norm": 5.285728931427002, "learning_rate": 5.395293603107566e-07, "loss": 0.0643242359161377, "step": 8860 }, { "epoch": 0.8993035973411232, "grad_norm": 4.990285396575928, "learning_rate": 5.2894107923109e-07, "loss": 0.07259148359298706, "step": 8870 }, { "epoch": 0.9003174683640557, "grad_norm": 5.343204021453857, "learning_rate": 5.184549051617571e-07, "loss": 0.08548024892807007, "step": 8880 }, { "epoch": 0.9013313393869883, "grad_norm": 4.498987674713135, "learning_rate": 5.08070951153673e-07, "loss": 0.06253716349601746, "step": 8890 }, { "epoch": 0.9023452104099208, "grad_norm": 4.717721462249756, "learning_rate": 4.977893291557256e-07, "loss": 0.0716368556022644, "step": 8900 }, { "epoch": 0.9033590814328533, "grad_norm": 4.933304786682129, "learning_rate": 4.876101500135621e-07, "loss": 0.0746053397655487, "step": 8910 }, { "epoch": 0.9043729524557858, "grad_norm": 4.99575662612915, "learning_rate": 4.775335234684042e-07, "loss": 0.0676955223083496, "step": 8920 }, { "epoch": 0.9053868234787182, "grad_norm": 4.6440229415893555, "learning_rate": 4.675595581558556e-07, "loss": 0.0690782129764557, "step": 8930 }, { "epoch": 0.9064006945016507, "grad_norm": 7.099537372589111, "learning_rate": 4.576883616047345e-07, "loss": 0.07415879964828491, "step": 8940 }, { "epoch": 0.9074145655245832, "grad_norm": 4.807840347290039, "learning_rate": 4.479200402359174e-07, "loss": 0.06314472556114196, "step": 8950 }, { "epoch": 0.9084284365475157, "grad_norm": 5.212149620056152, "learning_rate": 4.382546993611836e-07, "loss": 0.06500855684280396, "step": 8960 }, { "epoch": 0.9094423075704482, "grad_norm": 5.751489639282227, "learning_rate": 4.28692443182086e-07, "loss": 0.08059783577919007, "step": 8970 }, { "epoch": 0.9104561785933807, "grad_norm": 3.395752429962158, "learning_rate": 4.192333747888311e-07, "loss": 0.06224068999290466, "step": 8980 }, { "epoch": 0.9114700496163132, "grad_norm": 4.6740193367004395, "learning_rate": 4.0987759615915837e-07, "loss": 0.07012410163879394, "step": 8990 }, { "epoch": 0.9124839206392457, "grad_norm": 5.886908054351807, "learning_rate": 4.0062520815724816e-07, "loss": 0.06716815829277038, "step": 9000 }, { "epoch": 0.9134977916621781, "grad_norm": 5.465592861175537, "learning_rate": 3.9147631053263027e-07, "loss": 0.05923886895179749, "step": 9010 }, { "epoch": 0.9145116626851106, "grad_norm": 6.546334266662598, "learning_rate": 3.824310019191102e-07, "loss": 0.07484527826309204, "step": 9020 }, { "epoch": 0.9155255337080431, "grad_norm": 4.738012790679932, "learning_rate": 3.734893798337058e-07, "loss": 0.06671984195709228, "step": 9030 }, { "epoch": 0.9165394047309756, "grad_norm": 3.2938997745513916, "learning_rate": 3.646515406755946e-07, "loss": 0.06348904371261596, "step": 9040 }, { "epoch": 0.9175532757539081, "grad_norm": 5.419658660888672, "learning_rate": 3.559175797250769e-07, "loss": 0.06781934499740601, "step": 9050 }, { "epoch": 0.9185671467768407, "grad_norm": 5.675634860992432, "learning_rate": 3.4728759114254774e-07, "loss": 0.05889980792999268, "step": 9060 }, { "epoch": 0.9195810177997732, "grad_norm": 8.840157508850098, "learning_rate": 3.3876166796747877e-07, "loss": 0.07381661534309387, "step": 9070 }, { "epoch": 0.9205948888227057, "grad_norm": 3.186100721359253, "learning_rate": 3.303399021174214e-07, "loss": 0.06216585636138916, "step": 9080 }, { "epoch": 0.9216087598456382, "grad_norm": 6.521738052368164, "learning_rate": 3.220223843870096e-07, "loss": 0.06056736707687378, "step": 9090 }, { "epoch": 0.9226226308685707, "grad_norm": 7.8054399490356445, "learning_rate": 3.1380920444698093e-07, "loss": 0.07388252019882202, "step": 9100 }, { "epoch": 0.9236365018915031, "grad_norm": 6.224954605102539, "learning_rate": 3.057004508432193e-07, "loss": 0.059563732147216795, "step": 9110 }, { "epoch": 0.9246503729144356, "grad_norm": 5.597144603729248, "learning_rate": 2.976962109957882e-07, "loss": 0.06114659309387207, "step": 9120 }, { "epoch": 0.9256642439373681, "grad_norm": 4.35439395904541, "learning_rate": 2.8979657119799667e-07, "loss": 0.06043771505355835, "step": 9130 }, { "epoch": 0.9266781149603006, "grad_norm": 5.901611328125, "learning_rate": 2.8200161661546377e-07, "loss": 0.06197583079338074, "step": 9140 }, { "epoch": 0.9276919859832331, "grad_norm": 4.474691867828369, "learning_rate": 2.7431143128520243e-07, "loss": 0.06256280541419983, "step": 9150 }, { "epoch": 0.9287058570061656, "grad_norm": 7.352850914001465, "learning_rate": 2.667260981147157e-07, "loss": 0.06236893534660339, "step": 9160 }, { "epoch": 0.9297197280290981, "grad_norm": 7.194684028625488, "learning_rate": 2.5924569888109654e-07, "loss": 0.06597267389297486, "step": 9170 }, { "epoch": 0.9307335990520306, "grad_norm": 5.285149097442627, "learning_rate": 2.5187031423015597e-07, "loss": 0.06070758700370789, "step": 9180 }, { "epoch": 0.9317474700749631, "grad_norm": 5.494590759277344, "learning_rate": 2.4460002367554523e-07, "loss": 0.05629706382751465, "step": 9190 }, { "epoch": 0.9327613410978955, "grad_norm": 6.328568458557129, "learning_rate": 2.3743490559789973e-07, "loss": 0.06911391019821167, "step": 9200 }, { "epoch": 0.933775212120828, "grad_norm": 4.530700206756592, "learning_rate": 2.3037503724399946e-07, "loss": 0.04873259961605072, "step": 9210 }, { "epoch": 0.9347890831437605, "grad_norm": 5.6673665046691895, "learning_rate": 2.2342049472592996e-07, "loss": 0.060074257850646975, "step": 9220 }, { "epoch": 0.9358029541666931, "grad_norm": 9.29339599609375, "learning_rate": 2.1657135302026177e-07, "loss": 0.062366056442260745, "step": 9230 }, { "epoch": 0.9368168251896256, "grad_norm": 5.341702461242676, "learning_rate": 2.09827685967251e-07, "loss": 0.0511034369468689, "step": 9240 }, { "epoch": 0.9378306962125581, "grad_norm": 3.714892864227295, "learning_rate": 2.0318956627003227e-07, "loss": 0.050633412599563596, "step": 9250 }, { "epoch": 0.9388445672354906, "grad_norm": 4.153395175933838, "learning_rate": 1.9665706549384044e-07, "loss": 0.06643577814102172, "step": 9260 }, { "epoch": 0.9398584382584231, "grad_norm": 6.414623260498047, "learning_rate": 1.9023025406523787e-07, "loss": 0.07029213905334472, "step": 9270 }, { "epoch": 0.9408723092813556, "grad_norm": 5.105737209320068, "learning_rate": 1.8390920127135613e-07, "loss": 0.06473629474639893, "step": 9280 }, { "epoch": 0.9418861803042881, "grad_norm": 7.0333781242370605, "learning_rate": 1.7769397525914668e-07, "loss": 0.0660608172416687, "step": 9290 }, { "epoch": 0.9429000513272205, "grad_norm": 4.536887168884277, "learning_rate": 1.7158464303465017e-07, "loss": 0.05682269930839538, "step": 9300 }, { "epoch": 0.943913922350153, "grad_norm": 7.161233901977539, "learning_rate": 1.6558127046226945e-07, "loss": 0.06029815077781677, "step": 9310 }, { "epoch": 0.9449277933730855, "grad_norm": 6.020457744598389, "learning_rate": 1.5968392226406337e-07, "loss": 0.05922548770904541, "step": 9320 }, { "epoch": 0.945941664396018, "grad_norm": 7.158957004547119, "learning_rate": 1.5389266201904506e-07, "loss": 0.059452056884765625, "step": 9330 }, { "epoch": 0.9469555354189505, "grad_norm": 2.625957727432251, "learning_rate": 1.482075521625026e-07, "loss": 0.06439943313598633, "step": 9340 }, { "epoch": 0.947969406441883, "grad_norm": 6.071551322937012, "learning_rate": 1.4262865398531834e-07, "loss": 0.055946624279022215, "step": 9350 }, { "epoch": 0.9489832774648155, "grad_norm": 3.6196677684783936, "learning_rate": 1.3715602763331172e-07, "loss": 0.06395949721336365, "step": 9360 }, { "epoch": 0.949997148487748, "grad_norm": 3.323636531829834, "learning_rate": 1.3178973210659528e-07, "loss": 0.06544008255004882, "step": 9370 }, { "epoch": 0.9510110195106805, "grad_norm": 5.977285861968994, "learning_rate": 1.2652982525892975e-07, "loss": 0.06188926100730896, "step": 9380 }, { "epoch": 0.9520248905336129, "grad_norm": 7.111263275146484, "learning_rate": 1.213763637971066e-07, "loss": 0.06413892507553101, "step": 9390 }, { "epoch": 0.9530387615565454, "grad_norm": 5.612044334411621, "learning_rate": 1.1632940328033526e-07, "loss": 0.06455941200256347, "step": 9400 }, { "epoch": 0.954052632579478, "grad_norm": 8.03442096710205, "learning_rate": 1.1138899811964477e-07, "loss": 0.05776607394218445, "step": 9410 }, { "epoch": 0.9550665036024105, "grad_norm": 5.869856357574463, "learning_rate": 1.0655520157729194e-07, "loss": 0.06513325572013855, "step": 9420 }, { "epoch": 0.956080374625343, "grad_norm": 1.6400763988494873, "learning_rate": 1.0182806576619742e-07, "loss": 0.05117011070251465, "step": 9430 }, { "epoch": 0.9570942456482755, "grad_norm": 5.802017688751221, "learning_rate": 9.72076416493728e-08, "loss": 0.053011494874954226, "step": 9440 }, { "epoch": 0.958108116671208, "grad_norm": 5.288753032684326, "learning_rate": 9.269397903937883e-08, "loss": 0.06080374717712402, "step": 9450 }, { "epoch": 0.9591219876941405, "grad_norm": 5.57733154296875, "learning_rate": 8.828712659778471e-08, "loss": 0.06232792139053345, "step": 9460 }, { "epoch": 0.960135858717073, "grad_norm": 6.398001194000244, "learning_rate": 8.398713183464857e-08, "loss": 0.0499932587146759, "step": 9470 }, { "epoch": 0.9611497297400055, "grad_norm": 6.852885723114014, "learning_rate": 7.979404110799338e-08, "loss": 0.06417288780212402, "step": 9480 }, { "epoch": 0.9621636007629379, "grad_norm": 7.836142539978027, "learning_rate": 7.570789962332181e-08, "loss": 0.05887174606323242, "step": 9490 }, { "epoch": 0.9631774717858704, "grad_norm": 5.690162658691406, "learning_rate": 7.172875143311996e-08, "loss": 0.051335692405700684, "step": 9500 }, { "epoch": 0.9641913428088029, "grad_norm": 6.7453413009643555, "learning_rate": 6.785663943638333e-08, "loss": 0.06081380844116211, "step": 9510 }, { "epoch": 0.9652052138317354, "grad_norm": 4.826602458953857, "learning_rate": 6.409160537815818e-08, "loss": 0.05491544604301453, "step": 9520 }, { "epoch": 0.9662190848546679, "grad_norm": 7.488425254821777, "learning_rate": 6.043368984908759e-08, "loss": 0.07291160821914673, "step": 9530 }, { "epoch": 0.9672329558776004, "grad_norm": 4.8560791015625, "learning_rate": 5.688293228497399e-08, "loss": 0.0674433946609497, "step": 9540 }, { "epoch": 0.9682468269005329, "grad_norm": 4.499194622039795, "learning_rate": 5.34393709663561e-08, "loss": 0.061751097440719604, "step": 9550 }, { "epoch": 0.9692606979234654, "grad_norm": 4.263469219207764, "learning_rate": 5.0103043018097096e-08, "loss": 0.06735597848892212, "step": 9560 }, { "epoch": 0.9702745689463979, "grad_norm": 4.414453983306885, "learning_rate": 4.687398440897828e-08, "loss": 0.06406843662261963, "step": 9570 }, { "epoch": 0.9712884399693305, "grad_norm": 5.803241729736328, "learning_rate": 4.3752229951321553e-08, "loss": 0.054632818698883055, "step": 9580 }, { "epoch": 0.9723023109922629, "grad_norm": 4.926906108856201, "learning_rate": 4.0737813300602e-08, "loss": 0.06545217633247376, "step": 9590 }, { "epoch": 0.9733161820151954, "grad_norm": 4.899991035461426, "learning_rate": 3.783076695509702e-08, "loss": 0.05808581113815307, "step": 9600 }, { "epoch": 0.9743300530381279, "grad_norm": 5.4755940437316895, "learning_rate": 3.5031122255524406e-08, "loss": 0.06729114055633545, "step": 9610 }, { "epoch": 0.9753439240610604, "grad_norm": 4.449978351593018, "learning_rate": 3.233890938471373e-08, "loss": 0.0751528024673462, "step": 9620 }, { "epoch": 0.9763577950839929, "grad_norm": 3.943305492401123, "learning_rate": 2.9754157367277715e-08, "loss": 0.06445578932762146, "step": 9630 }, { "epoch": 0.9773716661069254, "grad_norm": 7.869267463684082, "learning_rate": 2.72768940692969e-08, "loss": 0.05603246688842774, "step": 9640 }, { "epoch": 0.9783855371298579, "grad_norm": 5.561990737915039, "learning_rate": 2.4907146198023256e-08, "loss": 0.06972824335098267, "step": 9650 }, { "epoch": 0.9793994081527904, "grad_norm": 6.476644039154053, "learning_rate": 2.2644939301588174e-08, "loss": 0.05850441455841064, "step": 9660 }, { "epoch": 0.9804132791757229, "grad_norm": 5.984586715698242, "learning_rate": 2.049029776873268e-08, "loss": 0.050501036643981936, "step": 9670 }, { "epoch": 0.9814271501986553, "grad_norm": 5.901840686798096, "learning_rate": 1.8443244828536544e-08, "loss": 0.06178112626075745, "step": 9680 }, { "epoch": 0.9824410212215878, "grad_norm": 5.9356489181518555, "learning_rate": 1.650380255017625e-08, "loss": 0.06489756107330322, "step": 9690 }, { "epoch": 0.9834548922445203, "grad_norm": 5.800255298614502, "learning_rate": 1.4671991842680756e-08, "loss": 0.05970967411994934, "step": 9700 }, { "epoch": 0.9844687632674528, "grad_norm": 5.427921295166016, "learning_rate": 1.294783245470943e-08, "loss": 0.0669666886329651, "step": 9710 }, { "epoch": 0.9854826342903853, "grad_norm": 6.5321455001831055, "learning_rate": 1.13313429743378e-08, "loss": 0.06161799430847168, "step": 9720 }, { "epoch": 0.9864965053133178, "grad_norm": 4.353568077087402, "learning_rate": 9.822540828858807e-09, "loss": 0.059774643182754515, "step": 9730 }, { "epoch": 0.9875103763362503, "grad_norm": 5.450153350830078, "learning_rate": 8.421442284591852e-09, "loss": 0.06092180013656616, "step": 9740 }, { "epoch": 0.9885242473591829, "grad_norm": 5.520995616912842, "learning_rate": 7.128062446709605e-09, "loss": 0.05292767286300659, "step": 9750 }, { "epoch": 0.9895381183821154, "grad_norm": 6.790454864501953, "learning_rate": 5.942415259074796e-09, "loss": 0.0557295560836792, "step": 9760 }, { "epoch": 0.9905519894050479, "grad_norm": 4.029415130615234, "learning_rate": 4.86451350409145e-09, "loss": 0.058049130439758304, "step": 9770 }, { "epoch": 0.9915658604279803, "grad_norm": 4.317828178405762, "learning_rate": 3.894368802563886e-09, "loss": 0.05351538062095642, "step": 9780 }, { "epoch": 0.9925797314509128, "grad_norm": 7.700816631317139, "learning_rate": 3.0319916135723713e-09, "loss": 0.06962435245513916, "step": 9790 }, { "epoch": 0.9935936024738453, "grad_norm": 5.787010669708252, "learning_rate": 2.277391234363213e-09, "loss": 0.055367791652679445, "step": 9800 }, { "epoch": 0.9946074734967778, "grad_norm": 5.6526947021484375, "learning_rate": 1.6305758002443939e-09, "loss": 0.049034598469734195, "step": 9810 }, { "epoch": 0.9956213445197103, "grad_norm": 4.730515003204346, "learning_rate": 1.091552284500086e-09, "loss": 0.06789255738258362, "step": 9820 }, { "epoch": 0.9966352155426428, "grad_norm": 6.726901054382324, "learning_rate": 6.603264983173762e-10, "loss": 0.06828256845474243, "step": 9830 }, { "epoch": 0.9976490865655753, "grad_norm": 2.9571022987365723, "learning_rate": 3.3690309071965355e-10, "loss": 0.05634838342666626, "step": 9840 }, { "epoch": 0.9986629575885078, "grad_norm": 5.751891613006592, "learning_rate": 1.2128554851664754e-10, "loss": 0.05607469081878662, "step": 9850 }, { "epoch": 0.9996768286114402, "grad_norm": 5.215901851654053, "learning_rate": 1.3476196272232955e-11, "loss": 0.04916470050811768, "step": 9860 }, { "epoch": 1.0, "step": 9864, "total_flos": 5.070703459485876e+19, "train_loss": 0.14537333479847545, "train_runtime": 240791.1701, "train_samples_per_second": 2.622, "train_steps_per_second": 0.041 } ], "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 }