{ "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": 57.887168884277344, "learning_rate": 6.081081081081082e-07, "loss": 1.5100223541259765, "step": 10 }, { "epoch": 0.0020277420458649905, "grad_norm": 17.78829574584961, "learning_rate": 1.2837837837837838e-06, "loss": 0.267812180519104, "step": 20 }, { "epoch": 0.003041613068797486, "grad_norm": 12.52128791809082, "learning_rate": 1.9594594594594595e-06, "loss": 0.2192361831665039, "step": 30 }, { "epoch": 0.004055484091729981, "grad_norm": 17.47190284729004, "learning_rate": 2.6351351351351353e-06, "loss": 0.212783145904541, "step": 40 }, { "epoch": 0.005069355114662476, "grad_norm": 12.710747718811035, "learning_rate": 3.310810810810811e-06, "loss": 0.21273045539855956, "step": 50 }, { "epoch": 0.006083226137594972, "grad_norm": 7.339081764221191, "learning_rate": 3.986486486486487e-06, "loss": 0.222636079788208, "step": 60 }, { "epoch": 0.0070970971605274664, "grad_norm": 6.537971019744873, "learning_rate": 4.6621621621621625e-06, "loss": 0.19962410926818847, "step": 70 }, { "epoch": 0.008110968183459962, "grad_norm": 8.965970993041992, "learning_rate": 5.337837837837838e-06, "loss": 0.22268452644348144, "step": 80 }, { "epoch": 0.009124839206392456, "grad_norm": 7.125879764556885, "learning_rate": 6.013513513513514e-06, "loss": 0.21179020404815674, "step": 90 }, { "epoch": 0.010138710229324952, "grad_norm": 5.449974536895752, "learning_rate": 6.689189189189191e-06, "loss": 0.19693716764450073, "step": 100 }, { "epoch": 0.011152581252257448, "grad_norm": 6.625723361968994, "learning_rate": 7.3648648648648655e-06, "loss": 0.227156400680542, "step": 110 }, { "epoch": 0.012166452275189943, "grad_norm": 11.515022277832031, "learning_rate": 8.040540540540541e-06, "loss": 0.20647015571594238, "step": 120 }, { "epoch": 0.013180323298122437, "grad_norm": 5.358216285705566, "learning_rate": 8.716216216216217e-06, "loss": 0.20749256610870362, "step": 130 }, { "epoch": 0.014194194321054933, "grad_norm": 8.961630821228027, "learning_rate": 9.391891891891893e-06, "loss": 0.21280407905578613, "step": 140 }, { "epoch": 0.015208065343987429, "grad_norm": 13.731043815612793, "learning_rate": 1.0067567567567569e-05, "loss": 0.1996963858604431, "step": 150 }, { "epoch": 0.016221936366919924, "grad_norm": 6.621375560760498, "learning_rate": 1.0743243243243244e-05, "loss": 0.18208050727844238, "step": 160 }, { "epoch": 0.01723580738985242, "grad_norm": 9.285578727722168, "learning_rate": 1.141891891891892e-05, "loss": 0.1844698429107666, "step": 170 }, { "epoch": 0.018249678412784912, "grad_norm": 10.348749160766602, "learning_rate": 1.2094594594594596e-05, "loss": 0.18674393892288207, "step": 180 }, { "epoch": 0.019263549435717408, "grad_norm": 11.87913703918457, "learning_rate": 1.2770270270270272e-05, "loss": 0.1855762481689453, "step": 190 }, { "epoch": 0.020277420458649904, "grad_norm": 10.442253112792969, "learning_rate": 1.3445945945945946e-05, "loss": 0.21377363204956054, "step": 200 }, { "epoch": 0.0212912914815824, "grad_norm": 5.261147499084473, "learning_rate": 1.4121621621621621e-05, "loss": 0.2085629940032959, "step": 210 }, { "epoch": 0.022305162504514895, "grad_norm": 6.824250221252441, "learning_rate": 1.4797297297297299e-05, "loss": 0.1901831030845642, "step": 220 }, { "epoch": 0.02331903352744739, "grad_norm": 5.519252777099609, "learning_rate": 1.5472972972972976e-05, "loss": 0.1822934031486511, "step": 230 }, { "epoch": 0.024332904550379886, "grad_norm": 6.068868637084961, "learning_rate": 1.614864864864865e-05, "loss": 0.18216226100921631, "step": 240 }, { "epoch": 0.02534677557331238, "grad_norm": 10.310834884643555, "learning_rate": 1.6824324324324324e-05, "loss": 0.2026702880859375, "step": 250 }, { "epoch": 0.026360646596244874, "grad_norm": 10.324403762817383, "learning_rate": 1.7500000000000002e-05, "loss": 0.200927734375, "step": 260 }, { "epoch": 0.02737451761917737, "grad_norm": 7.49036979675293, "learning_rate": 1.8175675675675676e-05, "loss": 0.19561502933502198, "step": 270 }, { "epoch": 0.028388388642109866, "grad_norm": 8.047456741333008, "learning_rate": 1.8851351351351353e-05, "loss": 0.206878662109375, "step": 280 }, { "epoch": 0.02940225966504236, "grad_norm": 4.599889755249023, "learning_rate": 1.9527027027027027e-05, "loss": 0.19169039726257325, "step": 290 }, { "epoch": 0.030416130687974857, "grad_norm": 3.9791972637176514, "learning_rate": 1.999999514856865e-05, "loss": 0.17692790031433106, "step": 300 }, { "epoch": 0.03143000171090735, "grad_norm": 4.909348011016846, "learning_rate": 1.999990890103106e-05, "loss": 0.18332276344299317, "step": 310 }, { "epoch": 0.03244387273383985, "grad_norm": 4.173277854919434, "learning_rate": 1.999971484497808e-05, "loss": 0.18760411739349364, "step": 320 }, { "epoch": 0.033457743756772344, "grad_norm": 3.5210635662078857, "learning_rate": 1.9999412982501806e-05, "loss": 0.17149871587753296, "step": 330 }, { "epoch": 0.03447161477970484, "grad_norm": 7.477321624755859, "learning_rate": 1.9999003316856605e-05, "loss": 0.17650330066680908, "step": 340 }, { "epoch": 0.03548548580263733, "grad_norm": 6.1498260498046875, "learning_rate": 1.9998485852459068e-05, "loss": 0.16985387802124025, "step": 350 }, { "epoch": 0.036499356825569824, "grad_norm": 3.4967503547668457, "learning_rate": 1.9997860594887947e-05, "loss": 0.1876138210296631, "step": 360 }, { "epoch": 0.03751322784850232, "grad_norm": 10.890799522399902, "learning_rate": 1.9997127550884116e-05, "loss": 0.19223475456237793, "step": 370 }, { "epoch": 0.038527098871434816, "grad_norm": 5.181928634643555, "learning_rate": 1.9996286728350484e-05, "loss": 0.17754474878311158, "step": 380 }, { "epoch": 0.03954096989436731, "grad_norm": 5.034743309020996, "learning_rate": 1.9995338136351913e-05, "loss": 0.19507335424423217, "step": 390 }, { "epoch": 0.04055484091729981, "grad_norm": 5.877169132232666, "learning_rate": 1.9994281785115127e-05, "loss": 0.18146772384643556, "step": 400 }, { "epoch": 0.0415687119402323, "grad_norm": 3.926165819168091, "learning_rate": 1.9993117686028603e-05, "loss": 0.1739284038543701, "step": 410 }, { "epoch": 0.0425825829631648, "grad_norm": 8.755548477172852, "learning_rate": 1.9991845851642426e-05, "loss": 0.20004191398620605, "step": 420 }, { "epoch": 0.043596453986097294, "grad_norm": 5.652449607849121, "learning_rate": 1.999046629566818e-05, "loss": 0.17711200714111328, "step": 430 }, { "epoch": 0.04461032500902979, "grad_norm": 2.9701151847839355, "learning_rate": 1.998897903297879e-05, "loss": 0.18716135025024414, "step": 440 }, { "epoch": 0.045624196031962286, "grad_norm": 8.107536315917969, "learning_rate": 1.9987384079608362e-05, "loss": 0.18003085851669312, "step": 450 }, { "epoch": 0.04663806705489478, "grad_norm": 6.3902363777160645, "learning_rate": 1.998568145275201e-05, "loss": 0.1899322748184204, "step": 460 }, { "epoch": 0.04765193807782728, "grad_norm": 3.495497465133667, "learning_rate": 1.998387117076566e-05, "loss": 0.1901268482208252, "step": 470 }, { "epoch": 0.04866580910075977, "grad_norm": 4.924668312072754, "learning_rate": 1.998195325316588e-05, "loss": 0.18628463745117188, "step": 480 }, { "epoch": 0.04967968012369226, "grad_norm": 4.0991597175598145, "learning_rate": 1.997992772062964e-05, "loss": 0.19769904613494874, "step": 490 }, { "epoch": 0.05069355114662476, "grad_norm": 7.869717597961426, "learning_rate": 1.9977794594994103e-05, "loss": 0.19369930028915405, "step": 500 }, { "epoch": 0.05170742216955725, "grad_norm": 2.341923952102661, "learning_rate": 1.9975553899256388e-05, "loss": 0.17802939414978028, "step": 510 }, { "epoch": 0.05272129319248975, "grad_norm": 3.7285594940185547, "learning_rate": 1.9973205657573328e-05, "loss": 0.18253982067108154, "step": 520 }, { "epoch": 0.053735164215422244, "grad_norm": 5.8869948387146, "learning_rate": 1.99707498952612e-05, "loss": 0.17532141208648683, "step": 530 }, { "epoch": 0.05474903523835474, "grad_norm": 4.500014781951904, "learning_rate": 1.9968186638795445e-05, "loss": 0.1666810393333435, "step": 540 }, { "epoch": 0.055762906261287236, "grad_norm": 5.895591735839844, "learning_rate": 1.9965515915810408e-05, "loss": 0.16637948751449586, "step": 550 }, { "epoch": 0.05677677728421973, "grad_norm": 4.134588718414307, "learning_rate": 1.9962737755099023e-05, "loss": 0.18440409898757934, "step": 560 }, { "epoch": 0.05779064830715223, "grad_norm": 3.6712965965270996, "learning_rate": 1.9959852186612492e-05, "loss": 0.18325599431991577, "step": 570 }, { "epoch": 0.05880451933008472, "grad_norm": 4.367828369140625, "learning_rate": 1.995685924145999e-05, "loss": 0.17663846015930176, "step": 580 }, { "epoch": 0.05981839035301722, "grad_norm": 6.543181896209717, "learning_rate": 1.9953758951908305e-05, "loss": 0.1569183349609375, "step": 590 }, { "epoch": 0.060832261375949714, "grad_norm": 3.7749531269073486, "learning_rate": 1.995055135138151e-05, "loss": 0.18010995388031006, "step": 600 }, { "epoch": 0.06184613239888221, "grad_norm": 4.73658561706543, "learning_rate": 1.994723647446058e-05, "loss": 0.1846585750579834, "step": 610 }, { "epoch": 0.0628600034218147, "grad_norm": 2.859647035598755, "learning_rate": 1.994381435688303e-05, "loss": 0.17976630926132203, "step": 620 }, { "epoch": 0.0638738744447472, "grad_norm": 4.406439304351807, "learning_rate": 1.994028503554255e-05, "loss": 0.16925218105316162, "step": 630 }, { "epoch": 0.0648877454676797, "grad_norm": 5.089962959289551, "learning_rate": 1.9936648548488568e-05, "loss": 0.18515973091125487, "step": 640 }, { "epoch": 0.06590161649061219, "grad_norm": 5.989006042480469, "learning_rate": 1.993290493492587e-05, "loss": 0.17210218906402588, "step": 650 }, { "epoch": 0.06691548751354469, "grad_norm": 6.582070827484131, "learning_rate": 1.9929054235214168e-05, "loss": 0.1700972557067871, "step": 660 }, { "epoch": 0.06792935853647718, "grad_norm": 4.912936210632324, "learning_rate": 1.992509649086766e-05, "loss": 0.14795323610305786, "step": 670 }, { "epoch": 0.06894322955940968, "grad_norm": 3.3434126377105713, "learning_rate": 1.9921031744554588e-05, "loss": 0.19495800733566285, "step": 680 }, { "epoch": 0.06995710058234217, "grad_norm": 5.485063552856445, "learning_rate": 1.991686004009678e-05, "loss": 0.18127403259277344, "step": 690 }, { "epoch": 0.07097097160527466, "grad_norm": 3.6610538959503174, "learning_rate": 1.991258142246917e-05, "loss": 0.1807011365890503, "step": 700 }, { "epoch": 0.07198484262820716, "grad_norm": 5.108860015869141, "learning_rate": 1.990819593779932e-05, "loss": 0.18156895637512208, "step": 710 }, { "epoch": 0.07299871365113965, "grad_norm": 4.481272220611572, "learning_rate": 1.9903703633366923e-05, "loss": 0.1698295831680298, "step": 720 }, { "epoch": 0.07401258467407215, "grad_norm": 7.138021469116211, "learning_rate": 1.9899104557603285e-05, "loss": 0.16496312618255615, "step": 730 }, { "epoch": 0.07502645569700464, "grad_norm": 8.2594633102417, "learning_rate": 1.9894398760090807e-05, "loss": 0.1920299530029297, "step": 740 }, { "epoch": 0.07604032671993714, "grad_norm": 4.356945991516113, "learning_rate": 1.988958629156246e-05, "loss": 0.17069792747497559, "step": 750 }, { "epoch": 0.07705419774286963, "grad_norm": 3.3892691135406494, "learning_rate": 1.988466720390123e-05, "loss": 0.1815131425857544, "step": 760 }, { "epoch": 0.07806806876580213, "grad_norm": 4.842170238494873, "learning_rate": 1.9879641550139545e-05, "loss": 0.17855433225631714, "step": 770 }, { "epoch": 0.07908193978873462, "grad_norm": 4.792759418487549, "learning_rate": 1.9874509384458726e-05, "loss": 0.174753737449646, "step": 780 }, { "epoch": 0.08009581081166713, "grad_norm": 2.5914807319641113, "learning_rate": 1.9869270762188402e-05, "loss": 0.1755758047103882, "step": 790 }, { "epoch": 0.08110968183459961, "grad_norm": 4.079227447509766, "learning_rate": 1.986392573980589e-05, "loss": 0.18660321235656738, "step": 800 }, { "epoch": 0.08212355285753212, "grad_norm": 3.8443477153778076, "learning_rate": 1.9858474374935606e-05, "loss": 0.17596936225891113, "step": 810 }, { "epoch": 0.0831374238804646, "grad_norm": 2.3138976097106934, "learning_rate": 1.9852916726348446e-05, "loss": 0.17804358005523682, "step": 820 }, { "epoch": 0.0841512949033971, "grad_norm": 2.618846893310547, "learning_rate": 1.9847252853961136e-05, "loss": 0.16779134273529053, "step": 830 }, { "epoch": 0.0851651659263296, "grad_norm": 5.887131214141846, "learning_rate": 1.98414828188356e-05, "loss": 0.1783642053604126, "step": 840 }, { "epoch": 0.08617903694926209, "grad_norm": 3.2871437072753906, "learning_rate": 1.98356066831783e-05, "loss": 0.17296000719070434, "step": 850 }, { "epoch": 0.08719290797219459, "grad_norm": 4.333361625671387, "learning_rate": 1.982962451033956e-05, "loss": 0.17266526222229003, "step": 860 }, { "epoch": 0.08820677899512708, "grad_norm": 4.660800933837891, "learning_rate": 1.9823536364812875e-05, "loss": 0.16728469133377075, "step": 870 }, { "epoch": 0.08922065001805958, "grad_norm": 3.104961633682251, "learning_rate": 1.981734231223425e-05, "loss": 0.15802406072616576, "step": 880 }, { "epoch": 0.09023452104099207, "grad_norm": 5.319479465484619, "learning_rate": 1.9811042419381444e-05, "loss": 0.17489964962005616, "step": 890 }, { "epoch": 0.09124839206392457, "grad_norm": 6.088720321655273, "learning_rate": 1.980463675417329e-05, "loss": 0.17647595405578614, "step": 900 }, { "epoch": 0.09226226308685706, "grad_norm": 5.68226957321167, "learning_rate": 1.9798125385668942e-05, "loss": 0.18619771003723146, "step": 910 }, { "epoch": 0.09327613410978956, "grad_norm": 3.15401291847229, "learning_rate": 1.9791508384067138e-05, "loss": 0.1735630989074707, "step": 920 }, { "epoch": 0.09429000513272205, "grad_norm": 3.0715112686157227, "learning_rate": 1.9784785820705435e-05, "loss": 0.17848854064941405, "step": 930 }, { "epoch": 0.09530387615565455, "grad_norm": 5.7040629386901855, "learning_rate": 1.9777957768059456e-05, "loss": 0.17021706104278564, "step": 940 }, { "epoch": 0.09631774717858704, "grad_norm": 7.18923807144165, "learning_rate": 1.977102429974209e-05, "loss": 0.17519071102142333, "step": 950 }, { "epoch": 0.09733161820151955, "grad_norm": 4.027462959289551, "learning_rate": 1.9763985490502714e-05, "loss": 0.15370457172393798, "step": 960 }, { "epoch": 0.09834548922445203, "grad_norm": 4.43635892868042, "learning_rate": 1.9756841416226372e-05, "loss": 0.17919092178344725, "step": 970 }, { "epoch": 0.09935936024738452, "grad_norm": 3.8433022499084473, "learning_rate": 1.9749592153932974e-05, "loss": 0.1695672392845154, "step": 980 }, { "epoch": 0.10037323127031703, "grad_norm": 6.309394359588623, "learning_rate": 1.9742237781776455e-05, "loss": 0.16796338558197021, "step": 990 }, { "epoch": 0.10138710229324951, "grad_norm": 3.6725282669067383, "learning_rate": 1.9734778379043923e-05, "loss": 0.1796330451965332, "step": 1000 }, { "epoch": 0.10240097331618202, "grad_norm": 3.3963427543640137, "learning_rate": 1.9727214026154827e-05, "loss": 0.16556333303451537, "step": 1010 }, { "epoch": 0.1034148443391145, "grad_norm": 5.347284317016602, "learning_rate": 1.9719544804660084e-05, "loss": 0.17472280263900758, "step": 1020 }, { "epoch": 0.10442871536204701, "grad_norm": 9.250009536743164, "learning_rate": 1.9711770797241174e-05, "loss": 0.18139772415161132, "step": 1030 }, { "epoch": 0.1054425863849795, "grad_norm": 3.353905200958252, "learning_rate": 1.9703892087709287e-05, "loss": 0.15506669282913207, "step": 1040 }, { "epoch": 0.106456457407912, "grad_norm": 2.4752368927001953, "learning_rate": 1.9695908761004392e-05, "loss": 0.16252251863479614, "step": 1050 }, { "epoch": 0.10747032843084449, "grad_norm": 3.1644325256347656, "learning_rate": 1.9687820903194335e-05, "loss": 0.15150024890899658, "step": 1060 }, { "epoch": 0.10848419945377699, "grad_norm": 3.648042678833008, "learning_rate": 1.9679628601473905e-05, "loss": 0.18368473052978515, "step": 1070 }, { "epoch": 0.10949807047670948, "grad_norm": 6.257554054260254, "learning_rate": 1.967133194416389e-05, "loss": 0.167461359500885, "step": 1080 }, { "epoch": 0.11051194149964198, "grad_norm": 5.202861309051514, "learning_rate": 1.9662931020710138e-05, "loss": 0.17000880241394042, "step": 1090 }, { "epoch": 0.11152581252257447, "grad_norm": 1.7786145210266113, "learning_rate": 1.965442592168259e-05, "loss": 0.19261033535003663, "step": 1100 }, { "epoch": 0.11253968354550696, "grad_norm": 4.36144495010376, "learning_rate": 1.964581673877428e-05, "loss": 0.16308705806732177, "step": 1110 }, { "epoch": 0.11355355456843946, "grad_norm": 1.9865257740020752, "learning_rate": 1.9637103564800384e-05, "loss": 0.16401513814926147, "step": 1120 }, { "epoch": 0.11456742559137195, "grad_norm": 3.2175142765045166, "learning_rate": 1.962828649369719e-05, "loss": 0.1746414303779602, "step": 1130 }, { "epoch": 0.11558129661430445, "grad_norm": 6.116086006164551, "learning_rate": 1.96193656205211e-05, "loss": 0.17196580171585082, "step": 1140 }, { "epoch": 0.11659516763723694, "grad_norm": 2.12505841255188, "learning_rate": 1.9610341041447595e-05, "loss": 0.1684585452079773, "step": 1150 }, { "epoch": 0.11760903866016945, "grad_norm": 2.2416622638702393, "learning_rate": 1.9601212853770214e-05, "loss": 0.16089423894882202, "step": 1160 }, { "epoch": 0.11862290968310193, "grad_norm": 6.472573280334473, "learning_rate": 1.959198115589949e-05, "loss": 0.19062408208847045, "step": 1170 }, { "epoch": 0.11963678070603444, "grad_norm": 2.376678943634033, "learning_rate": 1.9582646047361888e-05, "loss": 0.15986573696136475, "step": 1180 }, { "epoch": 0.12065065172896693, "grad_norm": 2.1693246364593506, "learning_rate": 1.9573207628798747e-05, "loss": 0.16040468215942383, "step": 1190 }, { "epoch": 0.12166452275189943, "grad_norm": 2.045145034790039, "learning_rate": 1.956366600196519e-05, "loss": 0.17835460901260375, "step": 1200 }, { "epoch": 0.12267839377483192, "grad_norm": 1.9980888366699219, "learning_rate": 1.9554021269729003e-05, "loss": 0.15725302696228027, "step": 1210 }, { "epoch": 0.12369226479776442, "grad_norm": 3.915468692779541, "learning_rate": 1.9544273536069573e-05, "loss": 0.1648217558860779, "step": 1220 }, { "epoch": 0.12470613582069691, "grad_norm": 5.47515344619751, "learning_rate": 1.9534422906076714e-05, "loss": 0.17939199209213258, "step": 1230 }, { "epoch": 0.1257200068436294, "grad_norm": 2.409425735473633, "learning_rate": 1.9524469485949586e-05, "loss": 0.1786069393157959, "step": 1240 }, { "epoch": 0.1267338778665619, "grad_norm": 5.003690719604492, "learning_rate": 1.9514413382995498e-05, "loss": 0.18294092416763305, "step": 1250 }, { "epoch": 0.1277477488894944, "grad_norm": 5.568807601928711, "learning_rate": 1.9504254705628806e-05, "loss": 0.16942908763885497, "step": 1260 }, { "epoch": 0.12876161991242688, "grad_norm": 2.0356686115264893, "learning_rate": 1.9493993563369688e-05, "loss": 0.18103501796722413, "step": 1270 }, { "epoch": 0.1297754909353594, "grad_norm": 4.929194450378418, "learning_rate": 1.9483630066843005e-05, "loss": 0.1619269609451294, "step": 1280 }, { "epoch": 0.13078936195829188, "grad_norm": 3.1066794395446777, "learning_rate": 1.9473164327777095e-05, "loss": 0.15005912780761718, "step": 1290 }, { "epoch": 0.13180323298122437, "grad_norm": 3.8166704177856445, "learning_rate": 1.9462596459002565e-05, "loss": 0.17625079154968262, "step": 1300 }, { "epoch": 0.13281710400415686, "grad_norm": 1.3917489051818848, "learning_rate": 1.9451926574451074e-05, "loss": 0.15964143276214598, "step": 1310 }, { "epoch": 0.13383097502708938, "grad_norm": 2.91855525970459, "learning_rate": 1.944115478915412e-05, "loss": 0.16890349388122558, "step": 1320 }, { "epoch": 0.13484484605002187, "grad_norm": 3.2602312564849854, "learning_rate": 1.9430281219241767e-05, "loss": 0.16292848587036132, "step": 1330 }, { "epoch": 0.13585871707295435, "grad_norm": 2.3313145637512207, "learning_rate": 1.9419305981941436e-05, "loss": 0.17204599380493163, "step": 1340 }, { "epoch": 0.13687258809588684, "grad_norm": 3.96158504486084, "learning_rate": 1.94082291955766e-05, "loss": 0.15902338027954102, "step": 1350 }, { "epoch": 0.13788645911881936, "grad_norm": 4.994528770446777, "learning_rate": 1.939705097956554e-05, "loss": 0.16279969215393067, "step": 1360 }, { "epoch": 0.13890033014175185, "grad_norm": 2.2692747116088867, "learning_rate": 1.9385771454420048e-05, "loss": 0.1740660548210144, "step": 1370 }, { "epoch": 0.13991420116468434, "grad_norm": 3.867779493331909, "learning_rate": 1.9374390741744107e-05, "loss": 0.16136088371276855, "step": 1380 }, { "epoch": 0.14092807218761683, "grad_norm": 7.0925726890563965, "learning_rate": 1.9362908964232616e-05, "loss": 0.18385485410690308, "step": 1390 }, { "epoch": 0.14194194321054932, "grad_norm": 2.3019702434539795, "learning_rate": 1.9351326245670038e-05, "loss": 0.1670374870300293, "step": 1400 }, { "epoch": 0.14295581423348183, "grad_norm": 3.8711998462677, "learning_rate": 1.933964271092908e-05, "loss": 0.1583112120628357, "step": 1410 }, { "epoch": 0.14396968525641432, "grad_norm": 2.6984384059906006, "learning_rate": 1.932785848596934e-05, "loss": 0.18558286428451537, "step": 1420 }, { "epoch": 0.1449835562793468, "grad_norm": 3.3320229053497314, "learning_rate": 1.9315973697835966e-05, "loss": 0.17506022453308107, "step": 1430 }, { "epoch": 0.1459974273022793, "grad_norm": 2.279148578643799, "learning_rate": 1.930398847465825e-05, "loss": 0.15959998369216918, "step": 1440 }, { "epoch": 0.14701129832521181, "grad_norm": 2.9426021575927734, "learning_rate": 1.9291902945648283e-05, "loss": 0.1517794370651245, "step": 1450 }, { "epoch": 0.1480251693481443, "grad_norm": 3.2552249431610107, "learning_rate": 1.9279717241099554e-05, "loss": 0.18209218978881836, "step": 1460 }, { "epoch": 0.1490390403710768, "grad_norm": 1.6886539459228516, "learning_rate": 1.9267431492385524e-05, "loss": 0.16790100336074829, "step": 1470 }, { "epoch": 0.15005291139400928, "grad_norm": 2.720479726791382, "learning_rate": 1.925504583195823e-05, "loss": 0.16220335960388182, "step": 1480 }, { "epoch": 0.1510667824169418, "grad_norm": 2.143296241760254, "learning_rate": 1.924256039334686e-05, "loss": 0.17522003650665283, "step": 1490 }, { "epoch": 0.15208065343987429, "grad_norm": 3.0463790893554688, "learning_rate": 1.9229975311156305e-05, "loss": 0.17202160358428956, "step": 1500 }, { "epoch": 0.15309452446280677, "grad_norm": 2.959078073501587, "learning_rate": 1.9217290721065693e-05, "loss": 0.17794909477233886, "step": 1510 }, { "epoch": 0.15410839548573926, "grad_norm": 4.582688808441162, "learning_rate": 1.9204506759826957e-05, "loss": 0.16484448909759522, "step": 1520 }, { "epoch": 0.15512226650867175, "grad_norm": 1.5785353183746338, "learning_rate": 1.9191623565263342e-05, "loss": 0.16525617837905884, "step": 1530 }, { "epoch": 0.15613613753160427, "grad_norm": 2.510150909423828, "learning_rate": 1.9178641276267922e-05, "loss": 0.16846600770950318, "step": 1540 }, { "epoch": 0.15715000855453676, "grad_norm": 2.5427660942077637, "learning_rate": 1.91655600328021e-05, "loss": 0.16686879396438598, "step": 1550 }, { "epoch": 0.15816387957746925, "grad_norm": 5.966403007507324, "learning_rate": 1.91523799758941e-05, "loss": 0.154645836353302, "step": 1560 }, { "epoch": 0.15917775060040174, "grad_norm": 6.52335786819458, "learning_rate": 1.9139101247637465e-05, "loss": 0.16586599349975586, "step": 1570 }, { "epoch": 0.16019162162333425, "grad_norm": 5.391699314117432, "learning_rate": 1.912572399118949e-05, "loss": 0.16416993141174316, "step": 1580 }, { "epoch": 0.16120549264626674, "grad_norm": 2.782485246658325, "learning_rate": 1.9112248350769704e-05, "loss": 0.1853319764137268, "step": 1590 }, { "epoch": 0.16221936366919923, "grad_norm": 3.920682430267334, "learning_rate": 1.909867447165831e-05, "loss": 0.1606764554977417, "step": 1600 }, { "epoch": 0.16323323469213172, "grad_norm": 1.8314231634140015, "learning_rate": 1.908500250019462e-05, "loss": 0.16481660604476928, "step": 1610 }, { "epoch": 0.16424710571506423, "grad_norm": 4.999827861785889, "learning_rate": 1.9071232583775465e-05, "loss": 0.164534330368042, "step": 1620 }, { "epoch": 0.16526097673799672, "grad_norm": 2.9521703720092773, "learning_rate": 1.9057364870853628e-05, "loss": 0.14395999908447266, "step": 1630 }, { "epoch": 0.1662748477609292, "grad_norm": 3.2498412132263184, "learning_rate": 1.904339951093622e-05, "loss": 0.16442145109176637, "step": 1640 }, { "epoch": 0.1672887187838617, "grad_norm": 2.733187675476074, "learning_rate": 1.902933665458309e-05, "loss": 0.16438454389572144, "step": 1650 }, { "epoch": 0.1683025898067942, "grad_norm": 3.4620420932769775, "learning_rate": 1.901517645340518e-05, "loss": 0.17742059230804444, "step": 1660 }, { "epoch": 0.1693164608297267, "grad_norm": 4.742125034332275, "learning_rate": 1.900091906006291e-05, "loss": 0.1771172046661377, "step": 1670 }, { "epoch": 0.1703303318526592, "grad_norm": 2.1982836723327637, "learning_rate": 1.8986564628264527e-05, "loss": 0.1738884210586548, "step": 1680 }, { "epoch": 0.17134420287559168, "grad_norm": 1.8898519277572632, "learning_rate": 1.8972113312764432e-05, "loss": 0.15950790643692017, "step": 1690 }, { "epoch": 0.17235807389852417, "grad_norm": 2.428860902786255, "learning_rate": 1.895756526936153e-05, "loss": 0.16970493793487548, "step": 1700 }, { "epoch": 0.1733719449214567, "grad_norm": 1.758950114250183, "learning_rate": 1.8942920654897553e-05, "loss": 0.1700923800468445, "step": 1710 }, { "epoch": 0.17438581594438918, "grad_norm": 1.898521900177002, "learning_rate": 1.8928179627255347e-05, "loss": 0.18166953325271606, "step": 1720 }, { "epoch": 0.17539968696732167, "grad_norm": 2.037672758102417, "learning_rate": 1.891334234535719e-05, "loss": 0.17397390604019164, "step": 1730 }, { "epoch": 0.17641355799025416, "grad_norm": 2.540271043777466, "learning_rate": 1.8898408969163078e-05, "loss": 0.1579749822616577, "step": 1740 }, { "epoch": 0.17742742901318667, "grad_norm": 2.982161283493042, "learning_rate": 1.8883379659668987e-05, "loss": 0.16944355964660646, "step": 1750 }, { "epoch": 0.17844130003611916, "grad_norm": 4.36820650100708, "learning_rate": 1.8868254578905147e-05, "loss": 0.1747223138809204, "step": 1760 }, { "epoch": 0.17945517105905165, "grad_norm": 3.099410057067871, "learning_rate": 1.8853033889934293e-05, "loss": 0.14802327156066894, "step": 1770 }, { "epoch": 0.18046904208198414, "grad_norm": 2.6631321907043457, "learning_rate": 1.883771775684991e-05, "loss": 0.14714041948318482, "step": 1780 }, { "epoch": 0.18148291310491665, "grad_norm": 4.778295993804932, "learning_rate": 1.882230634477446e-05, "loss": 0.1697157382965088, "step": 1790 }, { "epoch": 0.18249678412784914, "grad_norm": 5.557197570800781, "learning_rate": 1.8806799819857598e-05, "loss": 0.1802119255065918, "step": 1800 }, { "epoch": 0.18351065515078163, "grad_norm": 2.00936222076416, "learning_rate": 1.8791198349274393e-05, "loss": 0.15767561197280883, "step": 1810 }, { "epoch": 0.18452452617371412, "grad_norm": 2.2285525798797607, "learning_rate": 1.8775502101223516e-05, "loss": 0.1701484203338623, "step": 1820 }, { "epoch": 0.1855383971966466, "grad_norm": 2.8564305305480957, "learning_rate": 1.8759711244925424e-05, "loss": 0.1644144296646118, "step": 1830 }, { "epoch": 0.18655226821957913, "grad_norm": 2.7100281715393066, "learning_rate": 1.874382595062055e-05, "loss": 0.1451506495475769, "step": 1840 }, { "epoch": 0.18756613924251161, "grad_norm": 1.3656063079833984, "learning_rate": 1.8727846389567457e-05, "loss": 0.16116034984588623, "step": 1850 }, { "epoch": 0.1885800102654441, "grad_norm": 3.5437042713165283, "learning_rate": 1.871177273404098e-05, "loss": 0.17172677516937257, "step": 1860 }, { "epoch": 0.1895938812883766, "grad_norm": 3.693664789199829, "learning_rate": 1.8695605157330398e-05, "loss": 0.1474416136741638, "step": 1870 }, { "epoch": 0.1906077523113091, "grad_norm": 2.9101316928863525, "learning_rate": 1.8679343833737546e-05, "loss": 0.17083296775817872, "step": 1880 }, { "epoch": 0.1916216233342416, "grad_norm": 2.1744697093963623, "learning_rate": 1.8662988938574926e-05, "loss": 0.16659300327301024, "step": 1890 }, { "epoch": 0.1926354943571741, "grad_norm": 2.548187732696533, "learning_rate": 1.8646540648163853e-05, "loss": 0.15984005928039552, "step": 1900 }, { "epoch": 0.19364936538010658, "grad_norm": 2.592898368835449, "learning_rate": 1.862999913983251e-05, "loss": 0.1723705768585205, "step": 1910 }, { "epoch": 0.1946632364030391, "grad_norm": 3.857332706451416, "learning_rate": 1.8613364591914073e-05, "loss": 0.15771820545196533, "step": 1920 }, { "epoch": 0.19567710742597158, "grad_norm": 2.813542366027832, "learning_rate": 1.8596637183744762e-05, "loss": 0.15499234199523926, "step": 1930 }, { "epoch": 0.19669097844890407, "grad_norm": 4.026238441467285, "learning_rate": 1.857981709566193e-05, "loss": 0.17305436134338378, "step": 1940 }, { "epoch": 0.19770484947183656, "grad_norm": 3.055750846862793, "learning_rate": 1.85629045090021e-05, "loss": 0.1589686393737793, "step": 1950 }, { "epoch": 0.19871872049476905, "grad_norm": 2.4405782222747803, "learning_rate": 1.854589960609902e-05, "loss": 0.137645423412323, "step": 1960 }, { "epoch": 0.19973259151770156, "grad_norm": 2.6958858966827393, "learning_rate": 1.8528802570281686e-05, "loss": 0.17476837635040282, "step": 1970 }, { "epoch": 0.20074646254063405, "grad_norm": 6.7624640464782715, "learning_rate": 1.851161358587239e-05, "loss": 0.15996255874633789, "step": 1980 }, { "epoch": 0.20176033356356654, "grad_norm": 5.572185039520264, "learning_rate": 1.8494332838184707e-05, "loss": 0.17487037181854248, "step": 1990 }, { "epoch": 0.20277420458649903, "grad_norm": 2.136486768722534, "learning_rate": 1.847696051352151e-05, "loss": 0.15967129468917846, "step": 2000 }, { "epoch": 0.20378807560943155, "grad_norm": 1.9227817058563232, "learning_rate": 1.8459496799172957e-05, "loss": 0.15789570808410644, "step": 2010 }, { "epoch": 0.20480194663236403, "grad_norm": 6.60166597366333, "learning_rate": 1.8441941883414475e-05, "loss": 0.1827412486076355, "step": 2020 }, { "epoch": 0.20581581765529652, "grad_norm": 3.0033459663391113, "learning_rate": 1.8424295955504727e-05, "loss": 0.15448598861694335, "step": 2030 }, { "epoch": 0.206829688678229, "grad_norm": 3.186479091644287, "learning_rate": 1.840655920568358e-05, "loss": 0.17613173723220826, "step": 2040 }, { "epoch": 0.20784355970116153, "grad_norm": 2.952876567840576, "learning_rate": 1.838873182517004e-05, "loss": 0.16531314849853515, "step": 2050 }, { "epoch": 0.20885743072409402, "grad_norm": 2.9867682456970215, "learning_rate": 1.83708140061602e-05, "loss": 0.17008137702941895, "step": 2060 }, { "epoch": 0.2098713017470265, "grad_norm": 2.7316248416900635, "learning_rate": 1.835280594182517e-05, "loss": 0.15959709882736206, "step": 2070 }, { "epoch": 0.210885172769959, "grad_norm": 2.3180789947509766, "learning_rate": 1.833470782630898e-05, "loss": 0.1620887279510498, "step": 2080 }, { "epoch": 0.21189904379289148, "grad_norm": 3.3655712604522705, "learning_rate": 1.831651985472651e-05, "loss": 0.16235657930374145, "step": 2090 }, { "epoch": 0.212912914815824, "grad_norm": 5.705491065979004, "learning_rate": 1.8298242223161362e-05, "loss": 0.17657902240753173, "step": 2100 }, { "epoch": 0.2139267858387565, "grad_norm": 3.8528330326080322, "learning_rate": 1.827987512866377e-05, "loss": 0.15954744815826416, "step": 2110 }, { "epoch": 0.21494065686168898, "grad_norm": 3.562946319580078, "learning_rate": 1.826141876924845e-05, "loss": 0.15873154401779174, "step": 2120 }, { "epoch": 0.21595452788462147, "grad_norm": 7.036778926849365, "learning_rate": 1.8242873343892494e-05, "loss": 0.1764995813369751, "step": 2130 }, { "epoch": 0.21696839890755398, "grad_norm": 3.89369535446167, "learning_rate": 1.8224239052533194e-05, "loss": 0.1637122869491577, "step": 2140 }, { "epoch": 0.21798226993048647, "grad_norm": 4.554950714111328, "learning_rate": 1.820551609606591e-05, "loss": 0.16799033880233766, "step": 2150 }, { "epoch": 0.21899614095341896, "grad_norm": 1.282916784286499, "learning_rate": 1.81867046763419e-05, "loss": 0.17040321826934815, "step": 2160 }, { "epoch": 0.22001001197635145, "grad_norm": 2.170133590698242, "learning_rate": 1.816780499616613e-05, "loss": 0.17003365755081176, "step": 2170 }, { "epoch": 0.22102388299928397, "grad_norm": 2.8979949951171875, "learning_rate": 1.81488172592951e-05, "loss": 0.15836480855941773, "step": 2180 }, { "epoch": 0.22203775402221645, "grad_norm": 2.0147621631622314, "learning_rate": 1.812974167043465e-05, "loss": 0.16000304222106934, "step": 2190 }, { "epoch": 0.22305162504514894, "grad_norm": 2.38761568069458, "learning_rate": 1.8110578435237748e-05, "loss": 0.16130770444869996, "step": 2200 }, { "epoch": 0.22406549606808143, "grad_norm": 3.8335084915161133, "learning_rate": 1.8091327760302267e-05, "loss": 0.16785608530044555, "step": 2210 }, { "epoch": 0.22507936709101392, "grad_norm": 9.97524356842041, "learning_rate": 1.8071989853168765e-05, "loss": 0.19787968397140504, "step": 2220 }, { "epoch": 0.22609323811394644, "grad_norm": 1.6619950532913208, "learning_rate": 1.8052564922318247e-05, "loss": 0.16678072214126588, "step": 2230 }, { "epoch": 0.22710710913687893, "grad_norm": 5.837013244628906, "learning_rate": 1.803305317716992e-05, "loss": 0.17305930852890014, "step": 2240 }, { "epoch": 0.22812098015981142, "grad_norm": 2.8334240913391113, "learning_rate": 1.8013454828078925e-05, "loss": 0.15115480422973632, "step": 2250 }, { "epoch": 0.2291348511827439, "grad_norm": 2.210146188735962, "learning_rate": 1.7993770086334082e-05, "loss": 0.15413613319396974, "step": 2260 }, { "epoch": 0.23014872220567642, "grad_norm": 2.993828535079956, "learning_rate": 1.7973999164155597e-05, "loss": 0.14756252765655517, "step": 2270 }, { "epoch": 0.2311625932286089, "grad_norm": 3.8337900638580322, "learning_rate": 1.795414227469279e-05, "loss": 0.1499997615814209, "step": 2280 }, { "epoch": 0.2321764642515414, "grad_norm": 3.0372745990753174, "learning_rate": 1.7934199632021795e-05, "loss": 0.16831417083740235, "step": 2290 }, { "epoch": 0.2331903352744739, "grad_norm": 2.206388473510742, "learning_rate": 1.7914171451143235e-05, "loss": 0.1687668204307556, "step": 2300 }, { "epoch": 0.2342042062974064, "grad_norm": 2.243229389190674, "learning_rate": 1.7894057947979923e-05, "loss": 0.15561236143112184, "step": 2310 }, { "epoch": 0.2352180773203389, "grad_norm": 4.323564529418945, "learning_rate": 1.7873859339374528e-05, "loss": 0.1746011734008789, "step": 2320 }, { "epoch": 0.23623194834327138, "grad_norm": 5.462931156158447, "learning_rate": 1.7853575843087227e-05, "loss": 0.15606377124786378, "step": 2330 }, { "epoch": 0.23724581936620387, "grad_norm": 2.402329206466675, "learning_rate": 1.7833207677793382e-05, "loss": 0.15749084949493408, "step": 2340 }, { "epoch": 0.23825969038913636, "grad_norm": 1.5799375772476196, "learning_rate": 1.7812755063081156e-05, "loss": 0.15349314212799073, "step": 2350 }, { "epoch": 0.23927356141206887, "grad_norm": 2.978671073913574, "learning_rate": 1.7792218219449165e-05, "loss": 0.156256103515625, "step": 2360 }, { "epoch": 0.24028743243500136, "grad_norm": 3.588956832885742, "learning_rate": 1.777159736830408e-05, "loss": 0.1540140390396118, "step": 2370 }, { "epoch": 0.24130130345793385, "grad_norm": 2.9946584701538086, "learning_rate": 1.7750892731958268e-05, "loss": 0.15472352504730225, "step": 2380 }, { "epoch": 0.24231517448086634, "grad_norm": 2.089050531387329, "learning_rate": 1.773010453362737e-05, "loss": 0.16025540828704835, "step": 2390 }, { "epoch": 0.24332904550379886, "grad_norm": 2.231520652770996, "learning_rate": 1.770923299742791e-05, "loss": 0.15219922065734864, "step": 2400 }, { "epoch": 0.24434291652673135, "grad_norm": 1.9533305168151855, "learning_rate": 1.768827834837487e-05, "loss": 0.15624183416366577, "step": 2410 }, { "epoch": 0.24535678754966384, "grad_norm": 2.9389376640319824, "learning_rate": 1.7667240812379266e-05, "loss": 0.1409616708755493, "step": 2420 }, { "epoch": 0.24637065857259632, "grad_norm": 4.227266311645508, "learning_rate": 1.7646120616245724e-05, "loss": 0.1679254412651062, "step": 2430 }, { "epoch": 0.24738452959552884, "grad_norm": 3.3143017292022705, "learning_rate": 1.7624917987670006e-05, "loss": 0.1735844373703003, "step": 2440 }, { "epoch": 0.24839840061846133, "grad_norm": 2.9818718433380127, "learning_rate": 1.7603633155236595e-05, "loss": 0.15605947971343995, "step": 2450 }, { "epoch": 0.24941227164139382, "grad_norm": 2.6569926738739014, "learning_rate": 1.7582266348416194e-05, "loss": 0.17058401107788085, "step": 2460 }, { "epoch": 0.25042614266432633, "grad_norm": 1.68171226978302, "learning_rate": 1.7560817797563275e-05, "loss": 0.15918842554092408, "step": 2470 }, { "epoch": 0.2514400136872588, "grad_norm": 2.234426259994507, "learning_rate": 1.7539287733913592e-05, "loss": 0.16042957305908204, "step": 2480 }, { "epoch": 0.2524538847101913, "grad_norm": 4.608878135681152, "learning_rate": 1.7517676389581675e-05, "loss": 0.16499783992767333, "step": 2490 }, { "epoch": 0.2534677557331238, "grad_norm": 4.346975326538086, "learning_rate": 1.7495983997558342e-05, "loss": 0.15699293613433837, "step": 2500 }, { "epoch": 0.2544816267560563, "grad_norm": 3.332237720489502, "learning_rate": 1.7474210791708177e-05, "loss": 0.16388018131256105, "step": 2510 }, { "epoch": 0.2554954977789888, "grad_norm": 3.002452850341797, "learning_rate": 1.7452357006767026e-05, "loss": 0.15076091289520263, "step": 2520 }, { "epoch": 0.25650936880192127, "grad_norm": 2.7016985416412354, "learning_rate": 1.7430422878339443e-05, "loss": 0.1603492021560669, "step": 2530 }, { "epoch": 0.25752323982485376, "grad_norm": 2.5164942741394043, "learning_rate": 1.740840864289616e-05, "loss": 0.15624006986618041, "step": 2540 }, { "epoch": 0.2585371108477863, "grad_norm": 2.9446918964385986, "learning_rate": 1.7386314537771553e-05, "loss": 0.1576442003250122, "step": 2550 }, { "epoch": 0.2595509818707188, "grad_norm": 4.065415382385254, "learning_rate": 1.736414080116105e-05, "loss": 0.1699345588684082, "step": 2560 }, { "epoch": 0.2605648528936513, "grad_norm": 2.567525625228882, "learning_rate": 1.7341887672118596e-05, "loss": 0.1591294527053833, "step": 2570 }, { "epoch": 0.26157872391658377, "grad_norm": 2.940670967102051, "learning_rate": 1.7319555390554054e-05, "loss": 0.17932455539703368, "step": 2580 }, { "epoch": 0.26259259493951626, "grad_norm": 2.656224489212036, "learning_rate": 1.7297144197230637e-05, "loss": 0.16730321645736695, "step": 2590 }, { "epoch": 0.26360646596244874, "grad_norm": 2.301396131515503, "learning_rate": 1.7274654333762284e-05, "loss": 0.15231140851974487, "step": 2600 }, { "epoch": 0.26462033698538123, "grad_norm": 4.708564281463623, "learning_rate": 1.7252086042611086e-05, "loss": 0.16832325458526612, "step": 2610 }, { "epoch": 0.2656342080083137, "grad_norm": 2.6038122177124023, "learning_rate": 1.722943956708466e-05, "loss": 0.15317466259002685, "step": 2620 }, { "epoch": 0.2666480790312462, "grad_norm": 2.2758188247680664, "learning_rate": 1.720671515133352e-05, "loss": 0.1507347345352173, "step": 2630 }, { "epoch": 0.26766195005417875, "grad_norm": 5.088016033172607, "learning_rate": 1.7183913040348447e-05, "loss": 0.16100844144821166, "step": 2640 }, { "epoch": 0.26867582107711124, "grad_norm": 3.1559293270111084, "learning_rate": 1.716103347995785e-05, "loss": 0.15944867134094237, "step": 2650 }, { "epoch": 0.26968969210004373, "grad_norm": 2.095235586166382, "learning_rate": 1.713807671682513e-05, "loss": 0.14700287580490112, "step": 2660 }, { "epoch": 0.2707035631229762, "grad_norm": 1.9981255531311035, "learning_rate": 1.711504299844599e-05, "loss": 0.15389276742935182, "step": 2670 }, { "epoch": 0.2717174341459087, "grad_norm": 1.8777432441711426, "learning_rate": 1.7091932573145798e-05, "loss": 0.16521350145339966, "step": 2680 }, { "epoch": 0.2727313051688412, "grad_norm": 4.691732406616211, "learning_rate": 1.706874569007688e-05, "loss": 0.15149756669998168, "step": 2690 }, { "epoch": 0.2737451761917737, "grad_norm": 1.941796064376831, "learning_rate": 1.7045482599215856e-05, "loss": 0.16393609046936036, "step": 2700 }, { "epoch": 0.2747590472147062, "grad_norm": 3.039436101913452, "learning_rate": 1.7022143551360947e-05, "loss": 0.14994680881500244, "step": 2710 }, { "epoch": 0.2757729182376387, "grad_norm": 3.470899820327759, "learning_rate": 1.699872879812925e-05, "loss": 0.16836962699890137, "step": 2720 }, { "epoch": 0.2767867892605712, "grad_norm": 4.02808141708374, "learning_rate": 1.6975238591954048e-05, "loss": 0.17455264329910278, "step": 2730 }, { "epoch": 0.2778006602835037, "grad_norm": 2.9995975494384766, "learning_rate": 1.695167318608206e-05, "loss": 0.16629838943481445, "step": 2740 }, { "epoch": 0.2788145313064362, "grad_norm": 2.544487953186035, "learning_rate": 1.6928032834570767e-05, "loss": 0.15945980548858643, "step": 2750 }, { "epoch": 0.2798284023293687, "grad_norm": 3.2295937538146973, "learning_rate": 1.690431779228559e-05, "loss": 0.16505124568939208, "step": 2760 }, { "epoch": 0.28084227335230116, "grad_norm": 4.877310752868652, "learning_rate": 1.6880528314897212e-05, "loss": 0.1660470724105835, "step": 2770 }, { "epoch": 0.28185614437523365, "grad_norm": 4.358966827392578, "learning_rate": 1.6856664658878797e-05, "loss": 0.15821285247802735, "step": 2780 }, { "epoch": 0.28287001539816614, "grad_norm": 2.633716106414795, "learning_rate": 1.6832727081503227e-05, "loss": 0.15533132553100587, "step": 2790 }, { "epoch": 0.28388388642109863, "grad_norm": 3.4207923412323, "learning_rate": 1.6808715840840308e-05, "loss": 0.15003565549850464, "step": 2800 }, { "epoch": 0.2848977574440312, "grad_norm": 4.090699672698975, "learning_rate": 1.6784631195754027e-05, "loss": 0.15907483100891112, "step": 2810 }, { "epoch": 0.28591162846696366, "grad_norm": 1.8363982439041138, "learning_rate": 1.6760473405899733e-05, "loss": 0.14158201217651367, "step": 2820 }, { "epoch": 0.28692549948989615, "grad_norm": 3.0453760623931885, "learning_rate": 1.673624273172134e-05, "loss": 0.15563253164291382, "step": 2830 }, { "epoch": 0.28793937051282864, "grad_norm": 1.877868413925171, "learning_rate": 1.6711939434448537e-05, "loss": 0.15189709663391113, "step": 2840 }, { "epoch": 0.28895324153576113, "grad_norm": 5.5112409591674805, "learning_rate": 1.6687563776093943e-05, "loss": 0.16811597347259521, "step": 2850 }, { "epoch": 0.2899671125586936, "grad_norm": 1.9502710103988647, "learning_rate": 1.6663116019450306e-05, "loss": 0.1546842336654663, "step": 2860 }, { "epoch": 0.2909809835816261, "grad_norm": 2.101079225540161, "learning_rate": 1.6638596428087662e-05, "loss": 0.16613754034042358, "step": 2870 }, { "epoch": 0.2919948546045586, "grad_norm": 4.711236000061035, "learning_rate": 1.66140052663505e-05, "loss": 0.15921250581741334, "step": 2880 }, { "epoch": 0.29300872562749114, "grad_norm": 2.3854901790618896, "learning_rate": 1.6589342799354895e-05, "loss": 0.1571942925453186, "step": 2890 }, { "epoch": 0.29402259665042363, "grad_norm": 1.6886838674545288, "learning_rate": 1.6564609292985663e-05, "loss": 0.15219416618347167, "step": 2900 }, { "epoch": 0.2950364676733561, "grad_norm": 4.203446388244629, "learning_rate": 1.6539805013893493e-05, "loss": 0.1663384199142456, "step": 2910 }, { "epoch": 0.2960503386962886, "grad_norm": 5.693994522094727, "learning_rate": 1.6514930229492073e-05, "loss": 0.16570136547088624, "step": 2920 }, { "epoch": 0.2970642097192211, "grad_norm": 5.254156589508057, "learning_rate": 1.6489985207955207e-05, "loss": 0.16055337190628052, "step": 2930 }, { "epoch": 0.2980780807421536, "grad_norm": 3.1982789039611816, "learning_rate": 1.6464970218213912e-05, "loss": 0.1593184232711792, "step": 2940 }, { "epoch": 0.2990919517650861, "grad_norm": 3.4516823291778564, "learning_rate": 1.643988552995354e-05, "loss": 0.15692936182022094, "step": 2950 }, { "epoch": 0.30010582278801856, "grad_norm": 4.254360675811768, "learning_rate": 1.6414731413610856e-05, "loss": 0.1466346263885498, "step": 2960 }, { "epoch": 0.30111969381095105, "grad_norm": 2.7940561771392822, "learning_rate": 1.638950814037112e-05, "loss": 0.15741881132125854, "step": 2970 }, { "epoch": 0.3021335648338836, "grad_norm": 3.1661226749420166, "learning_rate": 1.6364215982165178e-05, "loss": 0.1524566888809204, "step": 2980 }, { "epoch": 0.3031474358568161, "grad_norm": 1.890060544013977, "learning_rate": 1.633885521166651e-05, "loss": 0.14740874767303466, "step": 2990 }, { "epoch": 0.30416130687974857, "grad_norm": 2.6355862617492676, "learning_rate": 1.6313426102288315e-05, "loss": 0.15829668045043946, "step": 3000 }, { "epoch": 0.30517517790268106, "grad_norm": 5.047800064086914, "learning_rate": 1.6287928928180544e-05, "loss": 0.16943185329437255, "step": 3010 }, { "epoch": 0.30618904892561355, "grad_norm": 1.936468482017517, "learning_rate": 1.6262363964226943e-05, "loss": 0.14459373950958251, "step": 3020 }, { "epoch": 0.30720291994854604, "grad_norm": 4.624034881591797, "learning_rate": 1.623673148604211e-05, "loss": 0.147642183303833, "step": 3030 }, { "epoch": 0.3082167909714785, "grad_norm": 2.7684640884399414, "learning_rate": 1.6211031769968503e-05, "loss": 0.1570690393447876, "step": 3040 }, { "epoch": 0.309230661994411, "grad_norm": 2.7421722412109375, "learning_rate": 1.6185265093073468e-05, "loss": 0.147374427318573, "step": 3050 }, { "epoch": 0.3102445330173435, "grad_norm": 2.2578649520874023, "learning_rate": 1.6159431733146255e-05, "loss": 0.15285351276397705, "step": 3060 }, { "epoch": 0.31125840404027605, "grad_norm": 2.87424898147583, "learning_rate": 1.613353196869502e-05, "loss": 0.1562211513519287, "step": 3070 }, { "epoch": 0.31227227506320854, "grad_norm": 2.327862024307251, "learning_rate": 1.6107566078943818e-05, "loss": 0.1650901198387146, "step": 3080 }, { "epoch": 0.313286146086141, "grad_norm": 2.3317365646362305, "learning_rate": 1.608153434382961e-05, "loss": 0.1583418369293213, "step": 3090 }, { "epoch": 0.3143000171090735, "grad_norm": 1.5518780946731567, "learning_rate": 1.6055437043999215e-05, "loss": 0.14287573099136353, "step": 3100 }, { "epoch": 0.315313888132006, "grad_norm": 2.2722508907318115, "learning_rate": 1.6029274460806318e-05, "loss": 0.1564253330230713, "step": 3110 }, { "epoch": 0.3163277591549385, "grad_norm": 3.425718069076538, "learning_rate": 1.6003046876308413e-05, "loss": 0.1581033706665039, "step": 3120 }, { "epoch": 0.317341630177871, "grad_norm": 2.4223134517669678, "learning_rate": 1.5976754573263767e-05, "loss": 0.14281873703002929, "step": 3130 }, { "epoch": 0.31835550120080347, "grad_norm": 3.105069875717163, "learning_rate": 1.5950397835128378e-05, "loss": 0.15680198669433593, "step": 3140 }, { "epoch": 0.319369372223736, "grad_norm": 3.1416208744049072, "learning_rate": 1.5923976946052918e-05, "loss": 0.1351870059967041, "step": 3150 }, { "epoch": 0.3203832432466685, "grad_norm": 5.076584815979004, "learning_rate": 1.5897492190879667e-05, "loss": 0.16294350624084472, "step": 3160 }, { "epoch": 0.321397114269601, "grad_norm": 2.0026047229766846, "learning_rate": 1.5870943855139437e-05, "loss": 0.1588146924972534, "step": 3170 }, { "epoch": 0.3224109852925335, "grad_norm": 2.582730770111084, "learning_rate": 1.5844332225048496e-05, "loss": 0.1436535596847534, "step": 3180 }, { "epoch": 0.32342485631546597, "grad_norm": 3.9403131008148193, "learning_rate": 1.5817657587505503e-05, "loss": 0.15444490909576417, "step": 3190 }, { "epoch": 0.32443872733839846, "grad_norm": 3.101351022720337, "learning_rate": 1.5790920230088375e-05, "loss": 0.15180859565734864, "step": 3200 }, { "epoch": 0.32545259836133095, "grad_norm": 4.558833122253418, "learning_rate": 1.576412044105122e-05, "loss": 0.14899419546127318, "step": 3210 }, { "epoch": 0.32646646938426344, "grad_norm": 4.053749084472656, "learning_rate": 1.5737258509321224e-05, "loss": 0.14964616298675537, "step": 3220 }, { "epoch": 0.3274803404071959, "grad_norm": 5.155595302581787, "learning_rate": 1.5710334724495514e-05, "loss": 0.1495351552963257, "step": 3230 }, { "epoch": 0.32849421143012847, "grad_norm": 2.035580635070801, "learning_rate": 1.5683349376838067e-05, "loss": 0.15032644271850587, "step": 3240 }, { "epoch": 0.32950808245306096, "grad_norm": 3.0947813987731934, "learning_rate": 1.565630275727656e-05, "loss": 0.14778671264648438, "step": 3250 }, { "epoch": 0.33052195347599345, "grad_norm": 2.9875705242156982, "learning_rate": 1.5629195157399236e-05, "loss": 0.16330015659332275, "step": 3260 }, { "epoch": 0.33153582449892594, "grad_norm": 2.8546760082244873, "learning_rate": 1.5602026869451773e-05, "loss": 0.15288317203521729, "step": 3270 }, { "epoch": 0.3325496955218584, "grad_norm": 2.758695125579834, "learning_rate": 1.5574798186334112e-05, "loss": 0.1422516107559204, "step": 3280 }, { "epoch": 0.3335635665447909, "grad_norm": 2.3996407985687256, "learning_rate": 1.5547509401597322e-05, "loss": 0.1578064441680908, "step": 3290 }, { "epoch": 0.3345774375677234, "grad_norm": 1.7553632259368896, "learning_rate": 1.552016080944042e-05, "loss": 0.15253875255584717, "step": 3300 }, { "epoch": 0.3355913085906559, "grad_norm": 2.1129889488220215, "learning_rate": 1.5492752704707198e-05, "loss": 0.15568100214004515, "step": 3310 }, { "epoch": 0.3366051796135884, "grad_norm": 3.622875928878784, "learning_rate": 1.5465285382883065e-05, "loss": 0.15560517311096192, "step": 3320 }, { "epoch": 0.3376190506365209, "grad_norm": 4.551002025604248, "learning_rate": 1.5437759140091827e-05, "loss": 0.1608382821083069, "step": 3330 }, { "epoch": 0.3386329216594534, "grad_norm": 2.6183230876922607, "learning_rate": 1.541017427309254e-05, "loss": 0.15511417388916016, "step": 3340 }, { "epoch": 0.3396467926823859, "grad_norm": 2.7801454067230225, "learning_rate": 1.538253107927625e-05, "loss": 0.14202661514282228, "step": 3350 }, { "epoch": 0.3406606637053184, "grad_norm": 3.741300582885742, "learning_rate": 1.535482985666285e-05, "loss": 0.1468135952949524, "step": 3360 }, { "epoch": 0.3416745347282509, "grad_norm": 5.544553756713867, "learning_rate": 1.5327070903897832e-05, "loss": 0.16633765697479247, "step": 3370 }, { "epoch": 0.34268840575118337, "grad_norm": 5.249739170074463, "learning_rate": 1.529925452024907e-05, "loss": 0.1525956392288208, "step": 3380 }, { "epoch": 0.34370227677411586, "grad_norm": 4.452854633331299, "learning_rate": 1.5271381005603593e-05, "loss": 0.16051688194274902, "step": 3390 }, { "epoch": 0.34471614779704834, "grad_norm": 4.186001777648926, "learning_rate": 1.5243450660464368e-05, "loss": 0.14232957363128662, "step": 3400 }, { "epoch": 0.3457300188199809, "grad_norm": 2.7128374576568604, "learning_rate": 1.5215463785947036e-05, "loss": 0.1575575590133667, "step": 3410 }, { "epoch": 0.3467438898429134, "grad_norm": 2.1481618881225586, "learning_rate": 1.518742068377669e-05, "loss": 0.1486102819442749, "step": 3420 }, { "epoch": 0.34775776086584587, "grad_norm": 1.961363673210144, "learning_rate": 1.5159321656284602e-05, "loss": 0.14486467838287354, "step": 3430 }, { "epoch": 0.34877163188877836, "grad_norm": 2.091744899749756, "learning_rate": 1.5131167006404978e-05, "loss": 0.15973706245422364, "step": 3440 }, { "epoch": 0.34978550291171084, "grad_norm": 5.871787071228027, "learning_rate": 1.5102957037671689e-05, "loss": 0.14258667230606079, "step": 3450 }, { "epoch": 0.35079937393464333, "grad_norm": 2.2932777404785156, "learning_rate": 1.5074692054214977e-05, "loss": 0.15170408487319947, "step": 3460 }, { "epoch": 0.3518132449575758, "grad_norm": 3.2042744159698486, "learning_rate": 1.504637236075822e-05, "loss": 0.14050328731536865, "step": 3470 }, { "epoch": 0.3528271159805083, "grad_norm": 3.9033381938934326, "learning_rate": 1.5017998262614609e-05, "loss": 0.15942282676696778, "step": 3480 }, { "epoch": 0.3538409870034408, "grad_norm": 1.7650761604309082, "learning_rate": 1.498957006568386e-05, "loss": 0.1502516508102417, "step": 3490 }, { "epoch": 0.35485485802637334, "grad_norm": 4.401268005371094, "learning_rate": 1.4961088076448947e-05, "loss": 0.143050217628479, "step": 3500 }, { "epoch": 0.35586872904930583, "grad_norm": 2.0800695419311523, "learning_rate": 1.4932552601972763e-05, "loss": 0.16569790840148926, "step": 3510 }, { "epoch": 0.3568826000722383, "grad_norm": 4.794235706329346, "learning_rate": 1.490396394989482e-05, "loss": 0.15651116371154786, "step": 3520 }, { "epoch": 0.3578964710951708, "grad_norm": 2.421689748764038, "learning_rate": 1.4875322428427943e-05, "loss": 0.1404447078704834, "step": 3530 }, { "epoch": 0.3589103421181033, "grad_norm": 1.9938987493515015, "learning_rate": 1.4846628346354934e-05, "loss": 0.1480499505996704, "step": 3540 }, { "epoch": 0.3599242131410358, "grad_norm": 3.6864781379699707, "learning_rate": 1.4817882013025253e-05, "loss": 0.16203200817108154, "step": 3550 }, { "epoch": 0.3609380841639683, "grad_norm": 2.8638877868652344, "learning_rate": 1.478908373835167e-05, "loss": 0.15544424057006836, "step": 3560 }, { "epoch": 0.36195195518690076, "grad_norm": 2.084744691848755, "learning_rate": 1.476023383280694e-05, "loss": 0.14895185232162475, "step": 3570 }, { "epoch": 0.3629658262098333, "grad_norm": 3.062613010406494, "learning_rate": 1.473133260742045e-05, "loss": 0.14629132747650148, "step": 3580 }, { "epoch": 0.3639796972327658, "grad_norm": 3.5503830909729004, "learning_rate": 1.4702380373774852e-05, "loss": 0.15464566946029662, "step": 3590 }, { "epoch": 0.3649935682556983, "grad_norm": 4.65009880065918, "learning_rate": 1.4673377444002724e-05, "loss": 0.139099383354187, "step": 3600 }, { "epoch": 0.3660074392786308, "grad_norm": 4.521289825439453, "learning_rate": 1.4644324130783197e-05, "loss": 0.1479010820388794, "step": 3610 }, { "epoch": 0.36702131030156326, "grad_norm": 1.2899210453033447, "learning_rate": 1.4615220747338574e-05, "loss": 0.1577986478805542, "step": 3620 }, { "epoch": 0.36803518132449575, "grad_norm": 3.402790069580078, "learning_rate": 1.4586067607430976e-05, "loss": 0.15679428577423096, "step": 3630 }, { "epoch": 0.36904905234742824, "grad_norm": 4.0878143310546875, "learning_rate": 1.4556865025358942e-05, "loss": 0.16043027639389038, "step": 3640 }, { "epoch": 0.37006292337036073, "grad_norm": 2.9415547847747803, "learning_rate": 1.4527613315954035e-05, "loss": 0.15390572547912598, "step": 3650 }, { "epoch": 0.3710767943932932, "grad_norm": 2.2908737659454346, "learning_rate": 1.4498312794577465e-05, "loss": 0.14144504070281982, "step": 3660 }, { "epoch": 0.37209066541622576, "grad_norm": 3.4672534465789795, "learning_rate": 1.4468963777116686e-05, "loss": 0.17337896823883056, "step": 3670 }, { "epoch": 0.37310453643915825, "grad_norm": 3.134831428527832, "learning_rate": 1.4439566579981979e-05, "loss": 0.15329456329345703, "step": 3680 }, { "epoch": 0.37411840746209074, "grad_norm": 2.7788186073303223, "learning_rate": 1.4410121520103045e-05, "loss": 0.14446699619293213, "step": 3690 }, { "epoch": 0.37513227848502323, "grad_norm": 1.7648528814315796, "learning_rate": 1.4380628914925597e-05, "loss": 0.13792819976806642, "step": 3700 }, { "epoch": 0.3761461495079557, "grad_norm": 3.5057835578918457, "learning_rate": 1.4351089082407929e-05, "loss": 0.1506505012512207, "step": 3710 }, { "epoch": 0.3771600205308882, "grad_norm": 3.6561856269836426, "learning_rate": 1.4321502341017496e-05, "loss": 0.16116379499435424, "step": 3720 }, { "epoch": 0.3781738915538207, "grad_norm": 3.400299310684204, "learning_rate": 1.4291869009727463e-05, "loss": 0.14954819679260253, "step": 3730 }, { "epoch": 0.3791877625767532, "grad_norm": 2.67903733253479, "learning_rate": 1.4262189408013294e-05, "loss": 0.14533255100250245, "step": 3740 }, { "epoch": 0.3802016335996857, "grad_norm": 3.900916337966919, "learning_rate": 1.4232463855849275e-05, "loss": 0.16536444425582886, "step": 3750 }, { "epoch": 0.3812155046226182, "grad_norm": 2.022252321243286, "learning_rate": 1.4202692673705097e-05, "loss": 0.16282339096069337, "step": 3760 }, { "epoch": 0.3822293756455507, "grad_norm": 2.3827788829803467, "learning_rate": 1.4172876182542372e-05, "loss": 0.1474597930908203, "step": 3770 }, { "epoch": 0.3832432466684832, "grad_norm": 3.562056541442871, "learning_rate": 1.41430147038112e-05, "loss": 0.1466339111328125, "step": 3780 }, { "epoch": 0.3842571176914157, "grad_norm": 2.644800901412964, "learning_rate": 1.411310855944668e-05, "loss": 0.15589098930358886, "step": 3790 }, { "epoch": 0.3852709887143482, "grad_norm": 3.1385951042175293, "learning_rate": 1.4083158071865451e-05, "loss": 0.1630543828010559, "step": 3800 }, { "epoch": 0.38628485973728066, "grad_norm": 1.8495049476623535, "learning_rate": 1.4053163563962215e-05, "loss": 0.15304083824157716, "step": 3810 }, { "epoch": 0.38729873076021315, "grad_norm": 4.667942523956299, "learning_rate": 1.4023125359106253e-05, "loss": 0.15214192867279053, "step": 3820 }, { "epoch": 0.38831260178314564, "grad_norm": 2.6622016429901123, "learning_rate": 1.3993043781137945e-05, "loss": 0.15192145109176636, "step": 3830 }, { "epoch": 0.3893264728060782, "grad_norm": 2.6242682933807373, "learning_rate": 1.3962919154365273e-05, "loss": 0.15792226791381836, "step": 3840 }, { "epoch": 0.39034034382901067, "grad_norm": 1.531636357307434, "learning_rate": 1.393275180356032e-05, "loss": 0.1530697226524353, "step": 3850 }, { "epoch": 0.39135421485194316, "grad_norm": 3.5414528846740723, "learning_rate": 1.3902542053955781e-05, "loss": 0.15685181617736815, "step": 3860 }, { "epoch": 0.39236808587487565, "grad_norm": 2.2568869590759277, "learning_rate": 1.387229023124145e-05, "loss": 0.15607140064239503, "step": 3870 }, { "epoch": 0.39338195689780814, "grad_norm": 2.3033523559570312, "learning_rate": 1.3841996661560706e-05, "loss": 0.14632070064544678, "step": 3880 }, { "epoch": 0.3943958279207406, "grad_norm": 3.8469128608703613, "learning_rate": 1.3811661671507004e-05, "loss": 0.13728710412979125, "step": 3890 }, { "epoch": 0.3954096989436731, "grad_norm": 5.74001932144165, "learning_rate": 1.3781285588120343e-05, "loss": 0.1463695764541626, "step": 3900 }, { "epoch": 0.3964235699666056, "grad_norm": 2.004648208618164, "learning_rate": 1.3750868738883755e-05, "loss": 0.14474622011184693, "step": 3910 }, { "epoch": 0.3974374409895381, "grad_norm": 3.1004798412323, "learning_rate": 1.3720411451719762e-05, "loss": 0.16037815809249878, "step": 3920 }, { "epoch": 0.39845131201247064, "grad_norm": 2.5369656085968018, "learning_rate": 1.3689914054986849e-05, "loss": 0.15212371349334716, "step": 3930 }, { "epoch": 0.3994651830354031, "grad_norm": 3.1749050617218018, "learning_rate": 1.3659376877475916e-05, "loss": 0.1496928572654724, "step": 3940 }, { "epoch": 0.4004790540583356, "grad_norm": 4.515805721282959, "learning_rate": 1.3628800248406738e-05, "loss": 0.14369816780090333, "step": 3950 }, { "epoch": 0.4014929250812681, "grad_norm": 3.738903760910034, "learning_rate": 1.3598184497424416e-05, "loss": 0.14581968784332275, "step": 3960 }, { "epoch": 0.4025067961042006, "grad_norm": 2.6014654636383057, "learning_rate": 1.3567529954595826e-05, "loss": 0.1474970579147339, "step": 3970 }, { "epoch": 0.4035206671271331, "grad_norm": 2.993068218231201, "learning_rate": 1.3536836950406057e-05, "loss": 0.144827938079834, "step": 3980 }, { "epoch": 0.40453453815006557, "grad_norm": 2.279703378677368, "learning_rate": 1.3506105815754836e-05, "loss": 0.14292480945587158, "step": 3990 }, { "epoch": 0.40554840917299806, "grad_norm": 3.533926248550415, "learning_rate": 1.3475336881952988e-05, "loss": 0.1736437439918518, "step": 4000 }, { "epoch": 0.40656228019593055, "grad_norm": 1.4680147171020508, "learning_rate": 1.3444530480718838e-05, "loss": 0.16107994318008423, "step": 4010 }, { "epoch": 0.4075761512188631, "grad_norm": 2.0438344478607178, "learning_rate": 1.3413686944174655e-05, "loss": 0.13635165691375734, "step": 4020 }, { "epoch": 0.4085900222417956, "grad_norm": 2.802722454071045, "learning_rate": 1.3382806604843053e-05, "loss": 0.1555931329727173, "step": 4030 }, { "epoch": 0.40960389326472807, "grad_norm": 2.103214979171753, "learning_rate": 1.3351889795643423e-05, "loss": 0.13642059564590453, "step": 4040 }, { "epoch": 0.41061776428766056, "grad_norm": 4.25733757019043, "learning_rate": 1.3320936849888322e-05, "loss": 0.15271743535995483, "step": 4050 }, { "epoch": 0.41163163531059305, "grad_norm": 2.4007303714752197, "learning_rate": 1.3289948101279912e-05, "loss": 0.16402597427368165, "step": 4060 }, { "epoch": 0.41264550633352554, "grad_norm": 4.807609558105469, "learning_rate": 1.3258923883906337e-05, "loss": 0.1489248037338257, "step": 4070 }, { "epoch": 0.413659377356458, "grad_norm": 2.9536077976226807, "learning_rate": 1.3227864532238113e-05, "loss": 0.1613439440727234, "step": 4080 }, { "epoch": 0.4146732483793905, "grad_norm": 2.304858922958374, "learning_rate": 1.3196770381124557e-05, "loss": 0.14649622440338134, "step": 4090 }, { "epoch": 0.41568711940232306, "grad_norm": 2.536712169647217, "learning_rate": 1.3165641765790153e-05, "loss": 0.13216739892959595, "step": 4100 }, { "epoch": 0.41670099042525555, "grad_norm": 1.6415927410125732, "learning_rate": 1.3134479021830938e-05, "loss": 0.153473424911499, "step": 4110 }, { "epoch": 0.41771486144818804, "grad_norm": 5.121954917907715, "learning_rate": 1.3103282485210882e-05, "loss": 0.14301717281341553, "step": 4120 }, { "epoch": 0.4187287324711205, "grad_norm": 1.9531311988830566, "learning_rate": 1.3072052492258286e-05, "loss": 0.1363493800163269, "step": 4130 }, { "epoch": 0.419742603494053, "grad_norm": 3.6318795680999756, "learning_rate": 1.3040789379662131e-05, "loss": 0.13203556537628175, "step": 4140 }, { "epoch": 0.4207564745169855, "grad_norm": 2.187572956085205, "learning_rate": 1.3009493484468464e-05, "loss": 0.14510560035705566, "step": 4150 }, { "epoch": 0.421770345539918, "grad_norm": 1.7752931118011475, "learning_rate": 1.2978165144076757e-05, "loss": 0.14722465276718139, "step": 4160 }, { "epoch": 0.4227842165628505, "grad_norm": 2.6613025665283203, "learning_rate": 1.2946804696236277e-05, "loss": 0.13303124904632568, "step": 4170 }, { "epoch": 0.42379808758578297, "grad_norm": 3.359238624572754, "learning_rate": 1.2915412479042436e-05, "loss": 0.14212566614151, "step": 4180 }, { "epoch": 0.4248119586087155, "grad_norm": 1.3472294807434082, "learning_rate": 1.2883988830933148e-05, "loss": 0.14418118000030516, "step": 4190 }, { "epoch": 0.425825829631648, "grad_norm": 2.7330453395843506, "learning_rate": 1.2852534090685184e-05, "loss": 0.14577195644378663, "step": 4200 }, { "epoch": 0.4268397006545805, "grad_norm": 2.240291118621826, "learning_rate": 1.282104859741052e-05, "loss": 0.15531547069549562, "step": 4210 }, { "epoch": 0.427853571677513, "grad_norm": 1.6219615936279297, "learning_rate": 1.2789532690552673e-05, "loss": 0.15029797554016114, "step": 4220 }, { "epoch": 0.42886744270044547, "grad_norm": 6.641350746154785, "learning_rate": 1.2757986709883059e-05, "loss": 0.14271776676177977, "step": 4230 }, { "epoch": 0.42988131372337796, "grad_norm": 4.113741874694824, "learning_rate": 1.2726410995497304e-05, "loss": 0.1502019166946411, "step": 4240 }, { "epoch": 0.43089518474631044, "grad_norm": 2.3067526817321777, "learning_rate": 1.2694805887811601e-05, "loss": 0.12352322340011597, "step": 4250 }, { "epoch": 0.43190905576924293, "grad_norm": 2.2938735485076904, "learning_rate": 1.2663171727559025e-05, "loss": 0.14521321058273315, "step": 4260 }, { "epoch": 0.4329229267921755, "grad_norm": 2.3354151248931885, "learning_rate": 1.2631508855785877e-05, "loss": 0.14378975629806517, "step": 4270 }, { "epoch": 0.43393679781510797, "grad_norm": 3.196964979171753, "learning_rate": 1.2599817613847973e-05, "loss": 0.15399781465530396, "step": 4280 }, { "epoch": 0.43495066883804046, "grad_norm": 2.3287832736968994, "learning_rate": 1.2568098343407007e-05, "loss": 0.1419387936592102, "step": 4290 }, { "epoch": 0.43596453986097294, "grad_norm": 4.2012553215026855, "learning_rate": 1.2536351386426844e-05, "loss": 0.14278998374938964, "step": 4300 }, { "epoch": 0.43697841088390543, "grad_norm": 2.2879695892333984, "learning_rate": 1.2504577085169826e-05, "loss": 0.15482403039932252, "step": 4310 }, { "epoch": 0.4379922819068379, "grad_norm": 3.285437822341919, "learning_rate": 1.2472775782193099e-05, "loss": 0.15098893642425537, "step": 4320 }, { "epoch": 0.4390061529297704, "grad_norm": 3.94504714012146, "learning_rate": 1.2440947820344916e-05, "loss": 0.14708466529846193, "step": 4330 }, { "epoch": 0.4400200239527029, "grad_norm": 2.549346446990967, "learning_rate": 1.2409093542760925e-05, "loss": 0.13750138282775878, "step": 4340 }, { "epoch": 0.4410338949756354, "grad_norm": 4.730139255523682, "learning_rate": 1.2377213292860506e-05, "loss": 0.1591203212738037, "step": 4350 }, { "epoch": 0.44204776599856793, "grad_norm": 4.858018398284912, "learning_rate": 1.2345307414343021e-05, "loss": 0.1381489634513855, "step": 4360 }, { "epoch": 0.4430616370215004, "grad_norm": 2.643033504486084, "learning_rate": 1.2313376251184148e-05, "loss": 0.1463140606880188, "step": 4370 }, { "epoch": 0.4440755080444329, "grad_norm": 2.593172550201416, "learning_rate": 1.2281420147632148e-05, "loss": 0.13715875148773193, "step": 4380 }, { "epoch": 0.4450893790673654, "grad_norm": 4.50272798538208, "learning_rate": 1.2249439448204172e-05, "loss": 0.1318100094795227, "step": 4390 }, { "epoch": 0.4461032500902979, "grad_norm": 2.9052815437316895, "learning_rate": 1.2217434497682537e-05, "loss": 0.14173303842544555, "step": 4400 }, { "epoch": 0.4471171211132304, "grad_norm": 5.274563789367676, "learning_rate": 1.2185405641110997e-05, "loss": 0.15540022850036622, "step": 4410 }, { "epoch": 0.44813099213616286, "grad_norm": 3.259366512298584, "learning_rate": 1.2153353223791049e-05, "loss": 0.14497106075286864, "step": 4420 }, { "epoch": 0.44914486315909535, "grad_norm": 4.117847919464111, "learning_rate": 1.2121277591278197e-05, "loss": 0.15410252809524536, "step": 4430 }, { "epoch": 0.45015873418202784, "grad_norm": 3.100250005722046, "learning_rate": 1.2089179089378222e-05, "loss": 0.14428091049194336, "step": 4440 }, { "epoch": 0.4511726052049604, "grad_norm": 5.1612772941589355, "learning_rate": 1.2057058064143456e-05, "loss": 0.13945798873901366, "step": 4450 }, { "epoch": 0.4521864762278929, "grad_norm": 3.8656363487243652, "learning_rate": 1.2024914861869064e-05, "loss": 0.14960169792175293, "step": 4460 }, { "epoch": 0.45320034725082536, "grad_norm": 2.0977931022644043, "learning_rate": 1.199274982908929e-05, "loss": 0.14313615560531617, "step": 4470 }, { "epoch": 0.45421421827375785, "grad_norm": 2.8993382453918457, "learning_rate": 1.196056331257374e-05, "loss": 0.14220821857452393, "step": 4480 }, { "epoch": 0.45522808929669034, "grad_norm": 4.284337997436523, "learning_rate": 1.1928355659323627e-05, "loss": 0.1349737286567688, "step": 4490 }, { "epoch": 0.45624196031962283, "grad_norm": 2.839418649673462, "learning_rate": 1.1896127216568047e-05, "loss": 0.14845497608184816, "step": 4500 }, { "epoch": 0.4572558313425553, "grad_norm": 4.2744879722595215, "learning_rate": 1.1863878331760217e-05, "loss": 0.1437307119369507, "step": 4510 }, { "epoch": 0.4582697023654878, "grad_norm": 2.3570995330810547, "learning_rate": 1.183160935257375e-05, "loss": 0.14508435726165772, "step": 4520 }, { "epoch": 0.45928357338842035, "grad_norm": 1.8771443367004395, "learning_rate": 1.1799320626898883e-05, "loss": 0.1335239052772522, "step": 4530 }, { "epoch": 0.46029744441135284, "grad_norm": 2.6667537689208984, "learning_rate": 1.1767012502838746e-05, "loss": 0.1416757583618164, "step": 4540 }, { "epoch": 0.46131131543428533, "grad_norm": 4.203596591949463, "learning_rate": 1.1734685328705604e-05, "loss": 0.15227704048156737, "step": 4550 }, { "epoch": 0.4623251864572178, "grad_norm": 1.802058458328247, "learning_rate": 1.17023394530171e-05, "loss": 0.1652788519859314, "step": 4560 }, { "epoch": 0.4633390574801503, "grad_norm": 3.8090853691101074, "learning_rate": 1.1669975224492486e-05, "loss": 0.14666173458099366, "step": 4570 }, { "epoch": 0.4643529285030828, "grad_norm": 3.5921902656555176, "learning_rate": 1.1637592992048888e-05, "loss": 0.13914268016815184, "step": 4580 }, { "epoch": 0.4653667995260153, "grad_norm": 4.5801825523376465, "learning_rate": 1.160519310479753e-05, "loss": 0.16174569129943847, "step": 4590 }, { "epoch": 0.4663806705489478, "grad_norm": 1.8589283227920532, "learning_rate": 1.157277591203996e-05, "loss": 0.14474527835845946, "step": 4600 }, { "epoch": 0.46739454157188026, "grad_norm": 3.126523733139038, "learning_rate": 1.1540341763264314e-05, "loss": 0.13757357597351075, "step": 4610 }, { "epoch": 0.4684084125948128, "grad_norm": 2.085341215133667, "learning_rate": 1.1507891008141512e-05, "loss": 0.1331005334854126, "step": 4620 }, { "epoch": 0.4694222836177453, "grad_norm": 1.6538134813308716, "learning_rate": 1.147542399652152e-05, "loss": 0.14499101638793946, "step": 4630 }, { "epoch": 0.4704361546406778, "grad_norm": 2.0050206184387207, "learning_rate": 1.1442941078429554e-05, "loss": 0.12892699241638184, "step": 4640 }, { "epoch": 0.4714500256636103, "grad_norm": 3.2843453884124756, "learning_rate": 1.141044260406233e-05, "loss": 0.14098645448684693, "step": 4650 }, { "epoch": 0.47246389668654276, "grad_norm": 4.994617462158203, "learning_rate": 1.1377928923784261e-05, "loss": 0.14029855728149415, "step": 4660 }, { "epoch": 0.47347776770947525, "grad_norm": 2.6460976600646973, "learning_rate": 1.1345400388123698e-05, "loss": 0.13502322435379027, "step": 4670 }, { "epoch": 0.47449163873240774, "grad_norm": 3.0175182819366455, "learning_rate": 1.1312857347769153e-05, "loss": 0.13649463653564453, "step": 4680 }, { "epoch": 0.4755055097553402, "grad_norm": 2.3481647968292236, "learning_rate": 1.128030015356551e-05, "loss": 0.1442612051963806, "step": 4690 }, { "epoch": 0.4765193807782727, "grad_norm": 2.357677936553955, "learning_rate": 1.1247729156510245e-05, "loss": 0.1392465591430664, "step": 4700 }, { "epoch": 0.47753325180120526, "grad_norm": 2.7225563526153564, "learning_rate": 1.1215144707749635e-05, "loss": 0.14297596216201783, "step": 4710 }, { "epoch": 0.47854712282413775, "grad_norm": 2.714143991470337, "learning_rate": 1.1182547158574988e-05, "loss": 0.12946361303329468, "step": 4720 }, { "epoch": 0.47956099384707024, "grad_norm": 2.406722068786621, "learning_rate": 1.1149936860418846e-05, "loss": 0.14636800289154053, "step": 4730 }, { "epoch": 0.4805748648700027, "grad_norm": 1.8074076175689697, "learning_rate": 1.1117314164851191e-05, "loss": 0.14066002368927003, "step": 4740 }, { "epoch": 0.4815887358929352, "grad_norm": 3.042856454849243, "learning_rate": 1.1084679423575666e-05, "loss": 0.13793742656707764, "step": 4750 }, { "epoch": 0.4826026069158677, "grad_norm": 2.4325037002563477, "learning_rate": 1.1052032988425778e-05, "loss": 0.12737293243408204, "step": 4760 }, { "epoch": 0.4836164779388002, "grad_norm": 5.932355880737305, "learning_rate": 1.1019375211361104e-05, "loss": 0.12078700065612794, "step": 4770 }, { "epoch": 0.4846303489617327, "grad_norm": 1.7559539079666138, "learning_rate": 1.0986706444463496e-05, "loss": 0.14828544855117798, "step": 4780 }, { "epoch": 0.4856442199846652, "grad_norm": 2.951458215713501, "learning_rate": 1.0954027039933288e-05, "loss": 0.13091381788253784, "step": 4790 }, { "epoch": 0.4866580910075977, "grad_norm": 6.318810939788818, "learning_rate": 1.09213373500855e-05, "loss": 0.14641158580780028, "step": 4800 }, { "epoch": 0.4876719620305302, "grad_norm": 2.769814968109131, "learning_rate": 1.0888637727346032e-05, "loss": 0.15645413398742675, "step": 4810 }, { "epoch": 0.4886858330534627, "grad_norm": 4.684559345245361, "learning_rate": 1.0855928524247884e-05, "loss": 0.1499415397644043, "step": 4820 }, { "epoch": 0.4896997040763952, "grad_norm": 2.0940260887145996, "learning_rate": 1.0823210093427318e-05, "loss": 0.12691859006881714, "step": 4830 }, { "epoch": 0.49071357509932767, "grad_norm": 3.195258378982544, "learning_rate": 1.07904827876201e-05, "loss": 0.1376262426376343, "step": 4840 }, { "epoch": 0.49172744612226016, "grad_norm": 3.4807169437408447, "learning_rate": 1.0757746959657666e-05, "loss": 0.14742720127105713, "step": 4850 }, { "epoch": 0.49274131714519265, "grad_norm": 5.691077709197998, "learning_rate": 1.072500296246334e-05, "loss": 0.13317534923553467, "step": 4860 }, { "epoch": 0.49375518816812514, "grad_norm": 4.70474100112915, "learning_rate": 1.06922511490485e-05, "loss": 0.13284757137298583, "step": 4870 }, { "epoch": 0.4947690591910577, "grad_norm": 2.8352701663970947, "learning_rate": 1.0659491872508807e-05, "loss": 0.13966580629348754, "step": 4880 }, { "epoch": 0.49578293021399017, "grad_norm": 6.670705795288086, "learning_rate": 1.0626725486020374e-05, "loss": 0.13782596588134766, "step": 4890 }, { "epoch": 0.49679680123692266, "grad_norm": 3.1715357303619385, "learning_rate": 1.059395234283597e-05, "loss": 0.13456351757049562, "step": 4900 }, { "epoch": 0.49781067225985515, "grad_norm": 2.607346773147583, "learning_rate": 1.0561172796281196e-05, "loss": 0.1478526473045349, "step": 4910 }, { "epoch": 0.49882454328278764, "grad_norm": 2.5800070762634277, "learning_rate": 1.0528387199750706e-05, "loss": 0.14025076627731323, "step": 4920 }, { "epoch": 0.4998384143057201, "grad_norm": 1.9813618659973145, "learning_rate": 1.0495595906704365e-05, "loss": 0.13135509490966796, "step": 4930 }, { "epoch": 0.5008522853286527, "grad_norm": 3.2796456813812256, "learning_rate": 1.0462799270663457e-05, "loss": 0.12576385736465454, "step": 4940 }, { "epoch": 0.5018661563515852, "grad_norm": 2.1008825302124023, "learning_rate": 1.0429997645206865e-05, "loss": 0.12675824165344238, "step": 4950 }, { "epoch": 0.5028800273745176, "grad_norm": 2.7158114910125732, "learning_rate": 1.0397191383967267e-05, "loss": 0.1312201976776123, "step": 4960 }, { "epoch": 0.5038938983974501, "grad_norm": 2.786522626876831, "learning_rate": 1.0364380840627315e-05, "loss": 0.13892762660980223, "step": 4970 }, { "epoch": 0.5049077694203826, "grad_norm": 3.2070531845092773, "learning_rate": 1.033156636891583e-05, "loss": 0.14420974254608154, "step": 4980 }, { "epoch": 0.5059216404433151, "grad_norm": 1.7686384916305542, "learning_rate": 1.0298748322603982e-05, "loss": 0.1345226764678955, "step": 4990 }, { "epoch": 0.5069355114662476, "grad_norm": 4.100856304168701, "learning_rate": 1.0265927055501476e-05, "loss": 0.14867409467697143, "step": 5000 }, { "epoch": 0.5079493824891801, "grad_norm": 1.6972650289535522, "learning_rate": 1.023310292145275e-05, "loss": 0.13013193607330323, "step": 5010 }, { "epoch": 0.5089632535121126, "grad_norm": 5.254079341888428, "learning_rate": 1.020027627433314e-05, "loss": 0.13378944396972656, "step": 5020 }, { "epoch": 0.5099771245350451, "grad_norm": 3.2500925064086914, "learning_rate": 1.0167447468045083e-05, "loss": 0.13348727226257323, "step": 5030 }, { "epoch": 0.5109909955579776, "grad_norm": 3.8882954120635986, "learning_rate": 1.0134616856514282e-05, "loss": 0.13761396408081056, "step": 5040 }, { "epoch": 0.51200486658091, "grad_norm": 2.8657524585723877, "learning_rate": 1.0101784793685914e-05, "loss": 0.13658359050750732, "step": 5050 }, { "epoch": 0.5130187376038425, "grad_norm": 4.737550735473633, "learning_rate": 1.0068951633520802e-05, "loss": 0.12391297817230225, "step": 5060 }, { "epoch": 0.514032608626775, "grad_norm": 3.8991901874542236, "learning_rate": 1.0036117729991595e-05, "loss": 0.13821300268173217, "step": 5070 }, { "epoch": 0.5150464796497075, "grad_norm": 4.999031066894531, "learning_rate": 1.0003283437078951e-05, "loss": 0.1351325035095215, "step": 5080 }, { "epoch": 0.5160603506726401, "grad_norm": 3.430272102355957, "learning_rate": 9.970449108767742e-06, "loss": 0.13118082284927368, "step": 5090 }, { "epoch": 0.5170742216955726, "grad_norm": 2.9164466857910156, "learning_rate": 9.937615099043206e-06, "loss": 0.12881700992584227, "step": 5100 }, { "epoch": 0.5180880927185051, "grad_norm": 3.306415557861328, "learning_rate": 9.904781761887147e-06, "loss": 0.14161148071289062, "step": 5110 }, { "epoch": 0.5191019637414376, "grad_norm": 2.1679182052612305, "learning_rate": 9.871949451274137e-06, "loss": 0.13584176301956177, "step": 5120 }, { "epoch": 0.5201158347643701, "grad_norm": 2.533827304840088, "learning_rate": 9.839118521167656e-06, "loss": 0.13418335914611818, "step": 5130 }, { "epoch": 0.5211297057873026, "grad_norm": 3.615363836288452, "learning_rate": 9.80628932551631e-06, "loss": 0.14101710319519042, "step": 5140 }, { "epoch": 0.522143576810235, "grad_norm": 3.5718488693237305, "learning_rate": 9.773462218250014e-06, "loss": 0.12802385091781615, "step": 5150 }, { "epoch": 0.5231574478331675, "grad_norm": 4.081605434417725, "learning_rate": 9.740637553276162e-06, "loss": 0.1423037528991699, "step": 5160 }, { "epoch": 0.5241713188561, "grad_norm": 3.2185111045837402, "learning_rate": 9.707815684475817e-06, "loss": 0.13885760307312012, "step": 5170 }, { "epoch": 0.5251851898790325, "grad_norm": 2.9527382850646973, "learning_rate": 9.674996965699895e-06, "loss": 0.1336628556251526, "step": 5180 }, { "epoch": 0.526199060901965, "grad_norm": 2.579040765762329, "learning_rate": 9.642181750765354e-06, "loss": 0.14119120836257934, "step": 5190 }, { "epoch": 0.5272129319248975, "grad_norm": 2.047131061553955, "learning_rate": 9.60937039345138e-06, "loss": 0.14830693006515502, "step": 5200 }, { "epoch": 0.52822680294783, "grad_norm": 1.6307241916656494, "learning_rate": 9.576563247495566e-06, "loss": 0.1281350374221802, "step": 5210 }, { "epoch": 0.5292406739707625, "grad_norm": 2.340203046798706, "learning_rate": 9.543760666590105e-06, "loss": 0.13521382808685303, "step": 5220 }, { "epoch": 0.530254544993695, "grad_norm": 2.786709785461426, "learning_rate": 9.510963004377974e-06, "loss": 0.128520667552948, "step": 5230 }, { "epoch": 0.5312684160166274, "grad_norm": 2.6176507472991943, "learning_rate": 9.478170614449114e-06, "loss": 0.1473011255264282, "step": 5240 }, { "epoch": 0.5322822870395599, "grad_norm": 2.031390905380249, "learning_rate": 9.445383850336648e-06, "loss": 0.12991389036178588, "step": 5250 }, { "epoch": 0.5332961580624924, "grad_norm": 2.8113555908203125, "learning_rate": 9.412603065513021e-06, "loss": 0.1412829875946045, "step": 5260 }, { "epoch": 0.534310029085425, "grad_norm": 2.703230619430542, "learning_rate": 9.379828613386225e-06, "loss": 0.1412431240081787, "step": 5270 }, { "epoch": 0.5353239001083575, "grad_norm": 2.368061065673828, "learning_rate": 9.347060847295991e-06, "loss": 0.13623858690261842, "step": 5280 }, { "epoch": 0.53633777113129, "grad_norm": 2.8693225383758545, "learning_rate": 9.314300120509952e-06, "loss": 0.13660109043121338, "step": 5290 }, { "epoch": 0.5373516421542225, "grad_norm": 2.0510342121124268, "learning_rate": 9.281546786219861e-06, "loss": 0.13379371166229248, "step": 5300 }, { "epoch": 0.538365513177155, "grad_norm": 2.8913540840148926, "learning_rate": 9.24880119753777e-06, "loss": 0.130684494972229, "step": 5310 }, { "epoch": 0.5393793842000875, "grad_norm": 5.661214828491211, "learning_rate": 9.216063707492218e-06, "loss": 0.13795708417892455, "step": 5320 }, { "epoch": 0.54039325522302, "grad_norm": 2.4227097034454346, "learning_rate": 9.183334669024449e-06, "loss": 0.13358452320098876, "step": 5330 }, { "epoch": 0.5414071262459524, "grad_norm": 2.450150489807129, "learning_rate": 9.150614434984578e-06, "loss": 0.14227001667022704, "step": 5340 }, { "epoch": 0.5424209972688849, "grad_norm": 3.746767997741699, "learning_rate": 9.117903358127801e-06, "loss": 0.1280686855316162, "step": 5350 }, { "epoch": 0.5434348682918174, "grad_norm": 2.9699015617370605, "learning_rate": 9.085201791110602e-06, "loss": 0.12200255393981933, "step": 5360 }, { "epoch": 0.5444487393147499, "grad_norm": 3.9434356689453125, "learning_rate": 9.052510086486922e-06, "loss": 0.12785500288009644, "step": 5370 }, { "epoch": 0.5454626103376824, "grad_norm": 2.0072696208953857, "learning_rate": 9.019828596704394e-06, "loss": 0.13219218254089354, "step": 5380 }, { "epoch": 0.5464764813606149, "grad_norm": 3.8763620853424072, "learning_rate": 8.987157674100519e-06, "loss": 0.1303451180458069, "step": 5390 }, { "epoch": 0.5474903523835474, "grad_norm": 3.676152229309082, "learning_rate": 8.954497670898858e-06, "loss": 0.12223864793777466, "step": 5400 }, { "epoch": 0.5485042234064799, "grad_norm": 3.5542566776275635, "learning_rate": 8.92184893920528e-06, "loss": 0.12710766792297362, "step": 5410 }, { "epoch": 0.5495180944294124, "grad_norm": 2.3699395656585693, "learning_rate": 8.889211831004112e-06, "loss": 0.13478503227233887, "step": 5420 }, { "epoch": 0.5505319654523448, "grad_norm": 4.767969608306885, "learning_rate": 8.856586698154382e-06, "loss": 0.12837350368499756, "step": 5430 }, { "epoch": 0.5515458364752774, "grad_norm": 2.6724491119384766, "learning_rate": 8.823973892386007e-06, "loss": 0.14749854803085327, "step": 5440 }, { "epoch": 0.5525597074982099, "grad_norm": 2.96171236038208, "learning_rate": 8.791373765296006e-06, "loss": 0.1260218143463135, "step": 5450 }, { "epoch": 0.5535735785211424, "grad_norm": 3.087376594543457, "learning_rate": 8.758786668344711e-06, "loss": 0.131753408908844, "step": 5460 }, { "epoch": 0.5545874495440749, "grad_norm": 3.845649003982544, "learning_rate": 8.726212952851978e-06, "loss": 0.14206899404525758, "step": 5470 }, { "epoch": 0.5556013205670074, "grad_norm": 2.2423675060272217, "learning_rate": 8.693652969993396e-06, "loss": 0.12943145036697387, "step": 5480 }, { "epoch": 0.5566151915899399, "grad_norm": 2.7321486473083496, "learning_rate": 8.661107070796504e-06, "loss": 0.1343296527862549, "step": 5490 }, { "epoch": 0.5576290626128724, "grad_norm": 3.6738386154174805, "learning_rate": 8.628575606137005e-06, "loss": 0.13872108459472657, "step": 5500 }, { "epoch": 0.5586429336358049, "grad_norm": 3.1377952098846436, "learning_rate": 8.59605892673499e-06, "loss": 0.14173609018325806, "step": 5510 }, { "epoch": 0.5596568046587374, "grad_norm": 3.4463746547698975, "learning_rate": 8.563557383151143e-06, "loss": 0.13179070949554444, "step": 5520 }, { "epoch": 0.5606706756816698, "grad_norm": 2.8005120754241943, "learning_rate": 8.531071325782965e-06, "loss": 0.14184970855712892, "step": 5530 }, { "epoch": 0.5616845467046023, "grad_norm": 2.116513967514038, "learning_rate": 8.49860110486102e-06, "loss": 0.1118852138519287, "step": 5540 }, { "epoch": 0.5626984177275348, "grad_norm": 2.8790297508239746, "learning_rate": 8.466147070445123e-06, "loss": 0.13273786306381224, "step": 5550 }, { "epoch": 0.5637122887504673, "grad_norm": 4.202235221862793, "learning_rate": 8.433709572420586e-06, "loss": 0.11134276390075684, "step": 5560 }, { "epoch": 0.5647261597733998, "grad_norm": 3.165518045425415, "learning_rate": 8.40128896049445e-06, "loss": 0.12610180377960206, "step": 5570 }, { "epoch": 0.5657400307963323, "grad_norm": 3.0670082569122314, "learning_rate": 8.368885584191698e-06, "loss": 0.11712111234664917, "step": 5580 }, { "epoch": 0.5667539018192648, "grad_norm": 2.933936595916748, "learning_rate": 8.336499792851505e-06, "loss": 0.12384723424911499, "step": 5590 }, { "epoch": 0.5677677728421973, "grad_norm": 2.443248748779297, "learning_rate": 8.304131935623461e-06, "loss": 0.13320907354354858, "step": 5600 }, { "epoch": 0.5687816438651299, "grad_norm": 2.8166329860687256, "learning_rate": 8.271782361463806e-06, "loss": 0.13030542135238649, "step": 5610 }, { "epoch": 0.5697955148880623, "grad_norm": 2.107572317123413, "learning_rate": 8.239451419131676e-06, "loss": 0.1202441930770874, "step": 5620 }, { "epoch": 0.5708093859109948, "grad_norm": 4.540679931640625, "learning_rate": 8.207139457185328e-06, "loss": 0.13174428939819335, "step": 5630 }, { "epoch": 0.5718232569339273, "grad_norm": 4.650473117828369, "learning_rate": 8.174846823978412e-06, "loss": 0.12688332796096802, "step": 5640 }, { "epoch": 0.5728371279568598, "grad_norm": 3.185056686401367, "learning_rate": 8.142573867656182e-06, "loss": 0.12019228935241699, "step": 5650 }, { "epoch": 0.5738509989797923, "grad_norm": 4.239306926727295, "learning_rate": 8.110320936151746e-06, "loss": 0.1168712854385376, "step": 5660 }, { "epoch": 0.5748648700027248, "grad_norm": 3.1540331840515137, "learning_rate": 8.078088377182352e-06, "loss": 0.10454356670379639, "step": 5670 }, { "epoch": 0.5758787410256573, "grad_norm": 2.5941197872161865, "learning_rate": 8.045876538245595e-06, "loss": 0.12094879150390625, "step": 5680 }, { "epoch": 0.5768926120485898, "grad_norm": 2.4507784843444824, "learning_rate": 8.013685766615687e-06, "loss": 0.12706834077835083, "step": 5690 }, { "epoch": 0.5779064830715223, "grad_norm": 2.6886682510375977, "learning_rate": 7.981516409339726e-06, "loss": 0.13755922317504882, "step": 5700 }, { "epoch": 0.5789203540944547, "grad_norm": 3.0289690494537354, "learning_rate": 7.94936881323393e-06, "loss": 0.12122206687927246, "step": 5710 }, { "epoch": 0.5799342251173872, "grad_norm": 3.530205011367798, "learning_rate": 7.917243324879924e-06, "loss": 0.13164381980895995, "step": 5720 }, { "epoch": 0.5809480961403197, "grad_norm": 2.473759889602661, "learning_rate": 7.88514029062098e-06, "loss": 0.12386324405670165, "step": 5730 }, { "epoch": 0.5819619671632522, "grad_norm": 2.3323967456817627, "learning_rate": 7.853060056558294e-06, "loss": 0.125921368598938, "step": 5740 }, { "epoch": 0.5829758381861847, "grad_norm": 3.453550100326538, "learning_rate": 7.821002968547266e-06, "loss": 1.0985286712646485, "step": 5750 }, { "epoch": 0.5839897092091172, "grad_norm": 4.9840192794799805, "learning_rate": 7.788969372193744e-06, "loss": 0.1496274709701538, "step": 5760 }, { "epoch": 0.5850035802320497, "grad_norm": 3.479893922805786, "learning_rate": 7.75695961285032e-06, "loss": 0.13570990562438964, "step": 5770 }, { "epoch": 0.5860174512549823, "grad_norm": 4.453908443450928, "learning_rate": 7.724974035612611e-06, "loss": 0.14156492948532104, "step": 5780 }, { "epoch": 0.5870313222779148, "grad_norm": 3.2609169483184814, "learning_rate": 7.693012985315503e-06, "loss": 0.16290323734283446, "step": 5790 }, { "epoch": 0.5880451933008473, "grad_norm": 5.3774189949035645, "learning_rate": 7.661076806529486e-06, "loss": 0.1276684045791626, "step": 5800 }, { "epoch": 0.5890590643237797, "grad_norm": 2.7535438537597656, "learning_rate": 7.629165843556896e-06, "loss": 0.1380927085876465, "step": 5810 }, { "epoch": 0.5900729353467122, "grad_norm": 3.4832382202148438, "learning_rate": 7.597280440428216e-06, "loss": 0.1375141143798828, "step": 5820 }, { "epoch": 0.5910868063696447, "grad_norm": 3.3184688091278076, "learning_rate": 7.565420940898381e-06, "loss": 0.1228818416595459, "step": 5830 }, { "epoch": 0.5921006773925772, "grad_norm": 3.433357000350952, "learning_rate": 7.5335876884430495e-06, "loss": 0.13781291246414185, "step": 5840 }, { "epoch": 0.5931145484155097, "grad_norm": 2.8850581645965576, "learning_rate": 7.501781026254922e-06, "loss": 0.13215718269348145, "step": 5850 }, { "epoch": 0.5941284194384422, "grad_norm": 3.988701105117798, "learning_rate": 7.4700012972400224e-06, "loss": 0.1354856014251709, "step": 5860 }, { "epoch": 0.5951422904613747, "grad_norm": 2.4894115924835205, "learning_rate": 7.438248844014011e-06, "loss": 0.1322303056716919, "step": 5870 }, { "epoch": 0.5961561614843072, "grad_norm": 3.3048224449157715, "learning_rate": 7.4065240088984944e-06, "loss": 0.12389895915985108, "step": 5880 }, { "epoch": 0.5971700325072397, "grad_norm": 3.3732824325561523, "learning_rate": 7.3748271339173224e-06, "loss": 0.12567509412765504, "step": 5890 }, { "epoch": 0.5981839035301721, "grad_norm": 3.419358253479004, "learning_rate": 7.34315856079291e-06, "loss": 0.1386150002479553, "step": 5900 }, { "epoch": 0.5991977745531046, "grad_norm": 4.04534912109375, "learning_rate": 7.311518630942562e-06, "loss": 0.13168518543243407, "step": 5910 }, { "epoch": 0.6002116455760371, "grad_norm": 2.990039110183716, "learning_rate": 7.279907685474759e-06, "loss": 0.13477120399475098, "step": 5920 }, { "epoch": 0.6012255165989696, "grad_norm": 3.430328845977783, "learning_rate": 7.248326065185527e-06, "loss": 0.13193317651748657, "step": 5930 }, { "epoch": 0.6022393876219021, "grad_norm": 2.6699681282043457, "learning_rate": 7.216774110554724e-06, "loss": 0.10902462005615235, "step": 5940 }, { "epoch": 0.6032532586448346, "grad_norm": 3.477548837661743, "learning_rate": 7.185252161742385e-06, "loss": 0.1317470669746399, "step": 5950 }, { "epoch": 0.6042671296677672, "grad_norm": 3.2379348278045654, "learning_rate": 7.153760558585059e-06, "loss": 0.10409555435180665, "step": 5960 }, { "epoch": 0.6052810006906997, "grad_norm": 3.233971357345581, "learning_rate": 7.122299640592135e-06, "loss": 0.12131278514862061, "step": 5970 }, { "epoch": 0.6062948717136322, "grad_norm": 3.340738296508789, "learning_rate": 7.090869746942191e-06, "loss": 0.11617543697357177, "step": 5980 }, { "epoch": 0.6073087427365647, "grad_norm": 3.6958725452423096, "learning_rate": 7.05947121647933e-06, "loss": 0.12011793851852418, "step": 5990 }, { "epoch": 0.6083226137594971, "grad_norm": 3.4929099082946777, "learning_rate": 7.028104387709531e-06, "loss": 0.11097608804702759, "step": 6000 }, { "epoch": 0.6093364847824296, "grad_norm": 4.11629056930542, "learning_rate": 6.996769598797001e-06, "loss": 0.11429378986358643, "step": 6010 }, { "epoch": 0.6103503558053621, "grad_norm": 3.2614550590515137, "learning_rate": 6.965467187560524e-06, "loss": 0.10316736698150634, "step": 6020 }, { "epoch": 0.6113642268282946, "grad_norm": 3.6850318908691406, "learning_rate": 6.934197491469818e-06, "loss": 0.10309169292449952, "step": 6030 }, { "epoch": 0.6123780978512271, "grad_norm": 3.8161003589630127, "learning_rate": 6.902960847641915e-06, "loss": 0.11550726890563964, "step": 6040 }, { "epoch": 0.6133919688741596, "grad_norm": 3.0861613750457764, "learning_rate": 6.8717575928374915e-06, "loss": 0.12964541912078859, "step": 6050 }, { "epoch": 0.6144058398970921, "grad_norm": 3.0890302658081055, "learning_rate": 6.840588063457278e-06, "loss": 0.11883158683776855, "step": 6060 }, { "epoch": 0.6154197109200246, "grad_norm": 3.4920334815979004, "learning_rate": 6.809452595538403e-06, "loss": 0.12078652381896973, "step": 6070 }, { "epoch": 0.616433581942957, "grad_norm": 2.922935962677002, "learning_rate": 6.778351524750777e-06, "loss": 0.1073068380355835, "step": 6080 }, { "epoch": 0.6174474529658895, "grad_norm": 3.4416465759277344, "learning_rate": 6.747285186393488e-06, "loss": 0.11025760173797608, "step": 6090 }, { "epoch": 0.618461323988822, "grad_norm": 5.377946376800537, "learning_rate": 6.716253915391167e-06, "loss": 0.12502806186676024, "step": 6100 }, { "epoch": 0.6194751950117545, "grad_norm": 3.2641565799713135, "learning_rate": 6.685258046290381e-06, "loss": 0.12451584339141845, "step": 6110 }, { "epoch": 0.620489066034687, "grad_norm": 4.387883186340332, "learning_rate": 6.654297913256047e-06, "loss": 0.13261895179748534, "step": 6120 }, { "epoch": 0.6215029370576196, "grad_norm": 3.303156852722168, "learning_rate": 6.623373850067794e-06, "loss": 0.12847483158111572, "step": 6130 }, { "epoch": 0.6225168080805521, "grad_norm": 4.72877311706543, "learning_rate": 6.592486190116405e-06, "loss": 0.12617638111114501, "step": 6140 }, { "epoch": 0.6235306791034846, "grad_norm": 4.615585803985596, "learning_rate": 6.561635266400181e-06, "loss": 0.10726983547210693, "step": 6150 }, { "epoch": 0.6245445501264171, "grad_norm": 5.626424789428711, "learning_rate": 6.5308214115213785e-06, "loss": 0.12444436550140381, "step": 6160 }, { "epoch": 0.6255584211493496, "grad_norm": 3.5010123252868652, "learning_rate": 6.500044957682627e-06, "loss": 0.11943643093109131, "step": 6170 }, { "epoch": 0.626572292172282, "grad_norm": 3.2253761291503906, "learning_rate": 6.469306236683324e-06, "loss": 0.1067192792892456, "step": 6180 }, { "epoch": 0.6275861631952145, "grad_norm": 3.298469305038452, "learning_rate": 6.438605579916078e-06, "loss": 0.12739901542663573, "step": 6190 }, { "epoch": 0.628600034218147, "grad_norm": 4.010951042175293, "learning_rate": 6.4079433183631255e-06, "loss": 0.10857770442962647, "step": 6200 }, { "epoch": 0.6296139052410795, "grad_norm": 2.985495090484619, "learning_rate": 6.377319782592767e-06, "loss": 0.1179491400718689, "step": 6210 }, { "epoch": 0.630627776264012, "grad_norm": 3.889695167541504, "learning_rate": 6.346735302755805e-06, "loss": 0.12236595153808594, "step": 6220 }, { "epoch": 0.6316416472869445, "grad_norm": 4.4549880027771, "learning_rate": 6.316190208581979e-06, "loss": 0.1107557773590088, "step": 6230 }, { "epoch": 0.632655518309877, "grad_norm": 3.594379186630249, "learning_rate": 6.285684829376413e-06, "loss": 0.11889300346374512, "step": 6240 }, { "epoch": 0.6336693893328095, "grad_norm": 3.8376171588897705, "learning_rate": 6.25521949401607e-06, "loss": 0.10896427631378174, "step": 6250 }, { "epoch": 0.634683260355742, "grad_norm": 4.201729774475098, "learning_rate": 6.2247945309461955e-06, "loss": 0.10780954360961914, "step": 6260 }, { "epoch": 0.6356971313786745, "grad_norm": 4.628962516784668, "learning_rate": 6.194410268176796e-06, "loss": 0.11455401182174682, "step": 6270 }, { "epoch": 0.6367110024016069, "grad_norm": 4.741269588470459, "learning_rate": 6.164067033279073e-06, "loss": 0.10864839553833008, "step": 6280 }, { "epoch": 0.6377248734245394, "grad_norm": 3.9872326850891113, "learning_rate": 6.133765153381918e-06, "loss": 0.12558290958404542, "step": 6290 }, { "epoch": 0.638738744447472, "grad_norm": 4.57774543762207, "learning_rate": 6.103504955168382e-06, "loss": 0.11183087825775147, "step": 6300 }, { "epoch": 0.6397526154704045, "grad_norm": 3.9448747634887695, "learning_rate": 6.07328676487214e-06, "loss": 0.11873044967651367, "step": 6310 }, { "epoch": 0.640766486493337, "grad_norm": 3.4398910999298096, "learning_rate": 6.043110908273973e-06, "loss": 0.1070025086402893, "step": 6320 }, { "epoch": 0.6417803575162695, "grad_norm": 5.455602645874023, "learning_rate": 6.012977710698288e-06, "loss": 0.10642495155334472, "step": 6330 }, { "epoch": 0.642794228539202, "grad_norm": 4.29721212387085, "learning_rate": 5.982887497009566e-06, "loss": 0.11482229232788085, "step": 6340 }, { "epoch": 0.6438080995621345, "grad_norm": 3.4316859245300293, "learning_rate": 5.9528405916088926e-06, "loss": 0.10221760272979737, "step": 6350 }, { "epoch": 0.644821970585067, "grad_norm": 5.9279069900512695, "learning_rate": 5.9228373184304455e-06, "loss": 0.11682066917419434, "step": 6360 }, { "epoch": 0.6458358416079995, "grad_norm": 2.920234203338623, "learning_rate": 5.892878000938001e-06, "loss": 0.09569292664527893, "step": 6370 }, { "epoch": 0.6468497126309319, "grad_norm": 3.5599637031555176, "learning_rate": 5.86296296212146e-06, "loss": 0.11398760080337525, "step": 6380 }, { "epoch": 0.6478635836538644, "grad_norm": 3.624500036239624, "learning_rate": 5.833092524493349e-06, "loss": 0.10037486553192139, "step": 6390 }, { "epoch": 0.6488774546767969, "grad_norm": 4.669022083282471, "learning_rate": 5.80326701008536e-06, "loss": 0.11281071901321411, "step": 6400 }, { "epoch": 0.6498913256997294, "grad_norm": 3.3894810676574707, "learning_rate": 5.773486740444862e-06, "loss": 0.09384037256240844, "step": 6410 }, { "epoch": 0.6509051967226619, "grad_norm": 3.7439403533935547, "learning_rate": 5.743752036631443e-06, "loss": 0.12027393579483033, "step": 6420 }, { "epoch": 0.6519190677455944, "grad_norm": 3.416057825088501, "learning_rate": 5.714063219213456e-06, "loss": 0.08771792650222779, "step": 6430 }, { "epoch": 0.6529329387685269, "grad_norm": 3.835667610168457, "learning_rate": 5.684420608264549e-06, "loss": 0.11025006771087646, "step": 6440 }, { "epoch": 0.6539468097914594, "grad_norm": 3.326174259185791, "learning_rate": 5.654824523360219e-06, "loss": 0.09615771770477295, "step": 6450 }, { "epoch": 0.6549606808143918, "grad_norm": 3.061687469482422, "learning_rate": 5.625275283574372e-06, "loss": 0.10457291603088378, "step": 6460 }, { "epoch": 0.6559745518373244, "grad_norm": 4.3225626945495605, "learning_rate": 5.595773207475872e-06, "loss": 0.11027133464813232, "step": 6470 }, { "epoch": 0.6569884228602569, "grad_norm": 3.2638378143310547, "learning_rate": 5.566318613125128e-06, "loss": 0.10350303649902344, "step": 6480 }, { "epoch": 0.6580022938831894, "grad_norm": 4.836357593536377, "learning_rate": 5.536911818070636e-06, "loss": 0.10360724925994873, "step": 6490 }, { "epoch": 0.6590161649061219, "grad_norm": 3.842188596725464, "learning_rate": 5.507553139345574e-06, "loss": 0.09976305961608886, "step": 6500 }, { "epoch": 0.6600300359290544, "grad_norm": 3.6786866188049316, "learning_rate": 5.478242893464389e-06, "loss": 0.09607034921646118, "step": 6510 }, { "epoch": 0.6610439069519869, "grad_norm": 4.034080982208252, "learning_rate": 5.448981396419366e-06, "loss": 0.09723885059356689, "step": 6520 }, { "epoch": 0.6620577779749194, "grad_norm": 3.6768460273742676, "learning_rate": 5.419768963677233e-06, "loss": 0.0989957332611084, "step": 6530 }, { "epoch": 0.6630716489978519, "grad_norm": 4.970784664154053, "learning_rate": 5.39060591017576e-06, "loss": 0.11440260410308838, "step": 6540 }, { "epoch": 0.6640855200207844, "grad_norm": 3.433850049972534, "learning_rate": 5.3614925503203586e-06, "loss": 0.10907988548278809, "step": 6550 }, { "epoch": 0.6650993910437168, "grad_norm": 3.4458203315734863, "learning_rate": 5.332429197980706e-06, "loss": 0.09440051317214966, "step": 6560 }, { "epoch": 0.6661132620666493, "grad_norm": 4.830300331115723, "learning_rate": 5.303416166487337e-06, "loss": 0.10733731985092163, "step": 6570 }, { "epoch": 0.6671271330895818, "grad_norm": 5.505436420440674, "learning_rate": 5.274453768628289e-06, "loss": 0.1126604676246643, "step": 6580 }, { "epoch": 0.6681410041125143, "grad_norm": 4.586561679840088, "learning_rate": 5.245542316645718e-06, "loss": 0.09200599193572997, "step": 6590 }, { "epoch": 0.6691548751354468, "grad_norm": 4.6326375007629395, "learning_rate": 5.2166821222325306e-06, "loss": 0.09638018012046815, "step": 6600 }, { "epoch": 0.6701687461583793, "grad_norm": 3.151327610015869, "learning_rate": 5.187873496529041e-06, "loss": 0.09332774877548218, "step": 6610 }, { "epoch": 0.6711826171813118, "grad_norm": 4.0977935791015625, "learning_rate": 5.15911675011959e-06, "loss": 0.1030843734741211, "step": 6620 }, { "epoch": 0.6721964882042443, "grad_norm": 4.037744522094727, "learning_rate": 5.130412193029213e-06, "loss": 0.09959390759468079, "step": 6630 }, { "epoch": 0.6732103592271768, "grad_norm": 4.173819541931152, "learning_rate": 5.101760134720306e-06, "loss": 0.10998728275299072, "step": 6640 }, { "epoch": 0.6742242302501094, "grad_norm": 3.5546698570251465, "learning_rate": 5.073160884089263e-06, "loss": 0.1076932668685913, "step": 6650 }, { "epoch": 0.6752381012730418, "grad_norm": 4.617072582244873, "learning_rate": 5.044614749463173e-06, "loss": 0.10136921405792236, "step": 6660 }, { "epoch": 0.6762519722959743, "grad_norm": 3.749058961868286, "learning_rate": 5.0161220385964745e-06, "loss": 0.09253754615783691, "step": 6670 }, { "epoch": 0.6772658433189068, "grad_norm": 3.957720994949341, "learning_rate": 4.987683058667651e-06, "loss": 0.10239667892456054, "step": 6680 }, { "epoch": 0.6782797143418393, "grad_norm": 5.221437454223633, "learning_rate": 4.9592981162759215e-06, "loss": 0.10482628345489502, "step": 6690 }, { "epoch": 0.6792935853647718, "grad_norm": 3.267587900161743, "learning_rate": 4.930967517437922e-06, "loss": 0.08442767262458802, "step": 6700 }, { "epoch": 0.6803074563877043, "grad_norm": 6.4589080810546875, "learning_rate": 4.902691567584412e-06, "loss": 0.10502340793609619, "step": 6710 }, { "epoch": 0.6813213274106368, "grad_norm": 3.9900243282318115, "learning_rate": 4.87447057155699e-06, "loss": 0.09669051170349122, "step": 6720 }, { "epoch": 0.6823351984335693, "grad_norm": 5.491718292236328, "learning_rate": 4.846304833604792e-06, "loss": 0.09890642762184143, "step": 6730 }, { "epoch": 0.6833490694565018, "grad_norm": 5.0225605964660645, "learning_rate": 4.8181946573812236e-06, "loss": 0.1072490930557251, "step": 6740 }, { "epoch": 0.6843629404794342, "grad_norm": 3.3110549449920654, "learning_rate": 4.790140345940688e-06, "loss": 0.08943923711776733, "step": 6750 }, { "epoch": 0.6853768115023667, "grad_norm": 5.209028720855713, "learning_rate": 4.762142201735299e-06, "loss": 0.10152144432067871, "step": 6760 }, { "epoch": 0.6863906825252992, "grad_norm": 3.9574062824249268, "learning_rate": 4.734200526611652e-06, "loss": 0.09357306957244874, "step": 6770 }, { "epoch": 0.6874045535482317, "grad_norm": 4.3360161781311035, "learning_rate": 4.706315621807537e-06, "loss": 0.10427087545394897, "step": 6780 }, { "epoch": 0.6884184245711642, "grad_norm": 4.14574670791626, "learning_rate": 4.678487787948711e-06, "loss": 0.0952952265739441, "step": 6790 }, { "epoch": 0.6894322955940967, "grad_norm": 4.154153823852539, "learning_rate": 4.650717325045655e-06, "loss": 0.09066500067710877, "step": 6800 }, { "epoch": 0.6904461666170292, "grad_norm": 4.579039573669434, "learning_rate": 4.623004532490328e-06, "loss": 0.10608644485473633, "step": 6810 }, { "epoch": 0.6914600376399618, "grad_norm": 3.697855234146118, "learning_rate": 4.595349709052964e-06, "loss": 0.09329633712768555, "step": 6820 }, { "epoch": 0.6924739086628943, "grad_norm": 4.098947048187256, "learning_rate": 4.5677531528788196e-06, "loss": 0.08779191970825195, "step": 6830 }, { "epoch": 0.6934877796858268, "grad_norm": 3.881850004196167, "learning_rate": 4.54021516148498e-06, "loss": 0.10180715322494507, "step": 6840 }, { "epoch": 0.6945016507087592, "grad_norm": 4.61552095413208, "learning_rate": 4.5127360317571475e-06, "loss": 0.09006150364875794, "step": 6850 }, { "epoch": 0.6955155217316917, "grad_norm": 5.0566534996032715, "learning_rate": 4.485316059946438e-06, "loss": 0.08372846841812134, "step": 6860 }, { "epoch": 0.6965293927546242, "grad_norm": 6.034775257110596, "learning_rate": 4.457955541666188e-06, "loss": 0.10205588340759278, "step": 6870 }, { "epoch": 0.6975432637775567, "grad_norm": 4.634587287902832, "learning_rate": 4.430654771888776e-06, "loss": 0.08927594423294068, "step": 6880 }, { "epoch": 0.6985571348004892, "grad_norm": 6.203177452087402, "learning_rate": 4.403414044942422e-06, "loss": 0.09784172773361206, "step": 6890 }, { "epoch": 0.6995710058234217, "grad_norm": 4.4337477684021, "learning_rate": 4.376233654508042e-06, "loss": 0.0896354079246521, "step": 6900 }, { "epoch": 0.7005848768463542, "grad_norm": 4.7602410316467285, "learning_rate": 4.349113893616056e-06, "loss": 0.09177712798118591, "step": 6910 }, { "epoch": 0.7015987478692867, "grad_norm": 4.899464130401611, "learning_rate": 4.322055054643244e-06, "loss": 0.08823144435882568, "step": 6920 }, { "epoch": 0.7026126188922192, "grad_norm": 4.0180439949035645, "learning_rate": 4.295057429309589e-06, "loss": 0.09152565598487854, "step": 6930 }, { "epoch": 0.7036264899151516, "grad_norm": 5.045207500457764, "learning_rate": 4.268121308675132e-06, "loss": 0.0883746862411499, "step": 6940 }, { "epoch": 0.7046403609380841, "grad_norm": 4.507814884185791, "learning_rate": 4.241246983136834e-06, "loss": 0.09175611138343812, "step": 6950 }, { "epoch": 0.7056542319610166, "grad_norm": 4.989742755889893, "learning_rate": 4.214434742425455e-06, "loss": 0.09093902111053467, "step": 6960 }, { "epoch": 0.7066681029839491, "grad_norm": 4.946935176849365, "learning_rate": 4.1876848756024116e-06, "loss": 0.09258288741111756, "step": 6970 }, { "epoch": 0.7076819740068816, "grad_norm": 4.398747444152832, "learning_rate": 4.1609976710566735e-06, "loss": 0.10742330551147461, "step": 6980 }, { "epoch": 0.7086958450298142, "grad_norm": 3.2165534496307373, "learning_rate": 4.134373416501652e-06, "loss": 0.08525891900062561, "step": 6990 }, { "epoch": 0.7097097160527467, "grad_norm": 4.896624565124512, "learning_rate": 4.107812398972093e-06, "loss": 0.09613355994224548, "step": 7000 }, { "epoch": 0.7107235870756792, "grad_norm": 4.3233866691589355, "learning_rate": 4.081314904821001e-06, "loss": 0.08252601027488708, "step": 7010 }, { "epoch": 0.7117374580986117, "grad_norm": 4.653258323669434, "learning_rate": 4.054881219716521e-06, "loss": 0.09128519296646118, "step": 7020 }, { "epoch": 0.7127513291215442, "grad_norm": 5.488613128662109, "learning_rate": 4.0285116286388914e-06, "loss": 0.08689682483673096, "step": 7030 }, { "epoch": 0.7137652001444766, "grad_norm": 5.701637268066406, "learning_rate": 4.0022064158773445e-06, "loss": 0.10102005004882812, "step": 7040 }, { "epoch": 0.7147790711674091, "grad_norm": 4.338482856750488, "learning_rate": 3.9759658650270575e-06, "loss": 0.09978389739990234, "step": 7050 }, { "epoch": 0.7157929421903416, "grad_norm": 5.83087158203125, "learning_rate": 3.94979025898609e-06, "loss": 0.08630655407905578, "step": 7060 }, { "epoch": 0.7168068132132741, "grad_norm": 5.200270175933838, "learning_rate": 3.9236798799523375e-06, "loss": 0.09365291595458984, "step": 7070 }, { "epoch": 0.7178206842362066, "grad_norm": 5.152169704437256, "learning_rate": 3.89763500942048e-06, "loss": 0.10231071710586548, "step": 7080 }, { "epoch": 0.7188345552591391, "grad_norm": 5.25978422164917, "learning_rate": 3.871655928178962e-06, "loss": 0.08385360240936279, "step": 7090 }, { "epoch": 0.7198484262820716, "grad_norm": 3.6993319988250732, "learning_rate": 3.8457429163069534e-06, "loss": 0.10359230041503906, "step": 7100 }, { "epoch": 0.7208622973050041, "grad_norm": 3.357050657272339, "learning_rate": 3.819896253171332e-06, "loss": 0.10270497798919678, "step": 7110 }, { "epoch": 0.7218761683279366, "grad_norm": 3.791306495666504, "learning_rate": 3.7941162174236745e-06, "loss": 0.0912910282611847, "step": 7120 }, { "epoch": 0.722890039350869, "grad_norm": 3.5715434551239014, "learning_rate": 3.7684030869972464e-06, "loss": 0.07867514491081237, "step": 7130 }, { "epoch": 0.7239039103738015, "grad_norm": 4.866431713104248, "learning_rate": 3.742757139104023e-06, "loss": 0.10085523128509521, "step": 7140 }, { "epoch": 0.724917781396734, "grad_norm": 4.76292610168457, "learning_rate": 3.7171786502316767e-06, "loss": 0.09331519603729248, "step": 7150 }, { "epoch": 0.7259316524196666, "grad_norm": 2.6143431663513184, "learning_rate": 3.691667896140605e-06, "loss": 0.0824885606765747, "step": 7160 }, { "epoch": 0.7269455234425991, "grad_norm": 4.924977779388428, "learning_rate": 3.6662251518609747e-06, "loss": 0.08765910863876343, "step": 7170 }, { "epoch": 0.7279593944655316, "grad_norm": 5.87029504776001, "learning_rate": 3.64085069168973e-06, "loss": 0.09576289653778076, "step": 7180 }, { "epoch": 0.7289732654884641, "grad_norm": 4.793969631195068, "learning_rate": 3.6155447891876518e-06, "loss": 0.08826314210891724, "step": 7190 }, { "epoch": 0.7299871365113966, "grad_norm": 2.4084880352020264, "learning_rate": 3.590307717176401e-06, "loss": 0.08044683337211608, "step": 7200 }, { "epoch": 0.7310010075343291, "grad_norm": 5.707688808441162, "learning_rate": 3.565139747735581e-06, "loss": 0.0751950740814209, "step": 7210 }, { "epoch": 0.7320148785572616, "grad_norm": 4.249905586242676, "learning_rate": 3.5400411521998123e-06, "loss": 0.07065709829330444, "step": 7220 }, { "epoch": 0.733028749580194, "grad_norm": 6.373660564422607, "learning_rate": 3.5150122011557888e-06, "loss": 0.089998859167099, "step": 7230 }, { "epoch": 0.7340426206031265, "grad_norm": 3.9607670307159424, "learning_rate": 3.4900531644393744e-06, "loss": 0.0821211576461792, "step": 7240 }, { "epoch": 0.735056491626059, "grad_norm": 4.625057697296143, "learning_rate": 3.4651643111326895e-06, "loss": 0.0860491931438446, "step": 7250 }, { "epoch": 0.7360703626489915, "grad_norm": 4.987703800201416, "learning_rate": 3.440345909561208e-06, "loss": 0.07790063619613648, "step": 7260 }, { "epoch": 0.737084233671924, "grad_norm": 2.8730733394622803, "learning_rate": 3.415598227290877e-06, "loss": 0.07556827664375305, "step": 7270 }, { "epoch": 0.7380981046948565, "grad_norm": 5.643927097320557, "learning_rate": 3.390921531125211e-06, "loss": 0.08159675598144531, "step": 7280 }, { "epoch": 0.739111975717789, "grad_norm": 4.322878837585449, "learning_rate": 3.366316087102429e-06, "loss": 0.0705053448677063, "step": 7290 }, { "epoch": 0.7401258467407215, "grad_norm": 4.072985649108887, "learning_rate": 3.3417821604925937e-06, "loss": 0.08702404499053955, "step": 7300 }, { "epoch": 0.741139717763654, "grad_norm": 4.7999091148376465, "learning_rate": 3.3173200157947315e-06, "loss": 0.09816064834594726, "step": 7310 }, { "epoch": 0.7421535887865864, "grad_norm": 5.890957355499268, "learning_rate": 3.2929299167339955e-06, "loss": 0.08921180963516236, "step": 7320 }, { "epoch": 0.7431674598095189, "grad_norm": 4.180719375610352, "learning_rate": 3.2686121262588165e-06, "loss": 0.09197762608528137, "step": 7330 }, { "epoch": 0.7441813308324515, "grad_norm": 4.358659744262695, "learning_rate": 3.244366906538071e-06, "loss": 0.08340044021606445, "step": 7340 }, { "epoch": 0.745195201855384, "grad_norm": 3.316676139831543, "learning_rate": 3.2201945189582597e-06, "loss": 0.09222968816757202, "step": 7350 }, { "epoch": 0.7462090728783165, "grad_norm": 4.37500524520874, "learning_rate": 3.1960952241206745e-06, "loss": 0.0836795449256897, "step": 7360 }, { "epoch": 0.747222943901249, "grad_norm": 6.108333110809326, "learning_rate": 3.172069281838603e-06, "loss": 0.08763335943222046, "step": 7370 }, { "epoch": 0.7482368149241815, "grad_norm": 5.642562389373779, "learning_rate": 3.148116951134522e-06, "loss": 0.08506987094879151, "step": 7380 }, { "epoch": 0.749250685947114, "grad_norm": 3.4164648056030273, "learning_rate": 3.1242384902373024e-06, "loss": 0.08690423965454101, "step": 7390 }, { "epoch": 0.7502645569700465, "grad_norm": 4.085449695587158, "learning_rate": 3.1004341565794373e-06, "loss": 0.08318432569503784, "step": 7400 }, { "epoch": 0.751278427992979, "grad_norm": 4.595078945159912, "learning_rate": 3.0767042067942475e-06, "loss": 0.08337429761886597, "step": 7410 }, { "epoch": 0.7522922990159114, "grad_norm": 5.551756858825684, "learning_rate": 3.0530488967131265e-06, "loss": 0.08119826912879943, "step": 7420 }, { "epoch": 0.7533061700388439, "grad_norm": 5.460245132446289, "learning_rate": 3.0294684813627917e-06, "loss": 0.0725701093673706, "step": 7430 }, { "epoch": 0.7543200410617764, "grad_norm": 7.036880970001221, "learning_rate": 3.0059632149625118e-06, "loss": 0.0808856725692749, "step": 7440 }, { "epoch": 0.7553339120847089, "grad_norm": 5.444082736968994, "learning_rate": 2.982533350921383e-06, "loss": 0.08302765488624572, "step": 7450 }, { "epoch": 0.7563477831076414, "grad_norm": 3.661741256713867, "learning_rate": 2.959179141835591e-06, "loss": 0.07956656813621521, "step": 7460 }, { "epoch": 0.7573616541305739, "grad_norm": 4.81581449508667, "learning_rate": 2.935900839485688e-06, "loss": 0.08586111664772034, "step": 7470 }, { "epoch": 0.7583755251535064, "grad_norm": 5.817996501922607, "learning_rate": 2.9126986948338898e-06, "loss": 0.07123862504959107, "step": 7480 }, { "epoch": 0.7593893961764389, "grad_norm": 3.579739809036255, "learning_rate": 2.889572958021347e-06, "loss": 0.09135737419128417, "step": 7490 }, { "epoch": 0.7604032671993713, "grad_norm": 4.3440141677856445, "learning_rate": 2.866523878365468e-06, "loss": 0.07238221168518066, "step": 7500 }, { "epoch": 0.761417138222304, "grad_norm": 4.333150863647461, "learning_rate": 2.8435517043572204e-06, "loss": 0.07974476814270019, "step": 7510 }, { "epoch": 0.7624310092452364, "grad_norm": 4.428470611572266, "learning_rate": 2.820656683658456e-06, "loss": 0.09238430857658386, "step": 7520 }, { "epoch": 0.7634448802681689, "grad_norm": 5.558040142059326, "learning_rate": 2.797839063099249e-06, "loss": 0.07968822717666627, "step": 7530 }, { "epoch": 0.7644587512911014, "grad_norm": 3.56781268119812, "learning_rate": 2.775099088675216e-06, "loss": 0.0918438196182251, "step": 7540 }, { "epoch": 0.7654726223140339, "grad_norm": 4.754489898681641, "learning_rate": 2.7524370055448755e-06, "loss": 0.08195865750312806, "step": 7550 }, { "epoch": 0.7664864933369664, "grad_norm": 4.9619622230529785, "learning_rate": 2.7298530580270154e-06, "loss": 0.07894928455352783, "step": 7560 }, { "epoch": 0.7675003643598989, "grad_norm": 6.1133012771606445, "learning_rate": 2.7073474895980333e-06, "loss": 0.08253569602966308, "step": 7570 }, { "epoch": 0.7685142353828314, "grad_norm": 6.125894069671631, "learning_rate": 2.6849205428893334e-06, "loss": 0.08028270006179809, "step": 7580 }, { "epoch": 0.7695281064057639, "grad_norm": 2.96803879737854, "learning_rate": 2.662572459684699e-06, "loss": 0.0731706976890564, "step": 7590 }, { "epoch": 0.7705419774286963, "grad_norm": 4.807223796844482, "learning_rate": 2.640303480917693e-06, "loss": 0.07653366923332214, "step": 7600 }, { "epoch": 0.7715558484516288, "grad_norm": 4.878784656524658, "learning_rate": 2.618113846669059e-06, "loss": 0.08695849776268005, "step": 7610 }, { "epoch": 0.7725697194745613, "grad_norm": 5.289469242095947, "learning_rate": 2.596003796164127e-06, "loss": 0.07639166712760925, "step": 7620 }, { "epoch": 0.7735835904974938, "grad_norm": 7.031376361846924, "learning_rate": 2.5739735677702416e-06, "loss": 0.07722892761230468, "step": 7630 }, { "epoch": 0.7745974615204263, "grad_norm": 4.906088829040527, "learning_rate": 2.552023398994188e-06, "loss": 0.08364912271499633, "step": 7640 }, { "epoch": 0.7756113325433588, "grad_norm": 4.850829124450684, "learning_rate": 2.5301535264796274e-06, "loss": 0.08129492402076721, "step": 7650 }, { "epoch": 0.7766252035662913, "grad_norm": 5.003366470336914, "learning_rate": 2.508364186004566e-06, "loss": 0.08399842977523804, "step": 7660 }, { "epoch": 0.7776390745892238, "grad_norm": 6.221800804138184, "learning_rate": 2.486655612478782e-06, "loss": 0.06915123462677002, "step": 7670 }, { "epoch": 0.7786529456121564, "grad_norm": 5.2833147048950195, "learning_rate": 2.465028039941316e-06, "loss": 0.06959491968154907, "step": 7680 }, { "epoch": 0.7796668166350889, "grad_norm": 3.8645243644714355, "learning_rate": 2.443481701557946e-06, "loss": 0.07732255458831787, "step": 7690 }, { "epoch": 0.7806806876580213, "grad_norm": 5.2747321128845215, "learning_rate": 2.4220168296186587e-06, "loss": 0.0784985899925232, "step": 7700 }, { "epoch": 0.7816945586809538, "grad_norm": 5.659622669219971, "learning_rate": 2.4006336555351615e-06, "loss": 0.07442994713783264, "step": 7710 }, { "epoch": 0.7827084297038863, "grad_norm": 6.312918663024902, "learning_rate": 2.3793324098383796e-06, "loss": 0.076465904712677, "step": 7720 }, { "epoch": 0.7837223007268188, "grad_norm": 6.047651767730713, "learning_rate": 2.35811332217597e-06, "loss": 0.06194765567779541, "step": 7730 }, { "epoch": 0.7847361717497513, "grad_norm": 4.979971408843994, "learning_rate": 2.3369766213098553e-06, "loss": 0.07525562047958374, "step": 7740 }, { "epoch": 0.7857500427726838, "grad_norm": 5.15762996673584, "learning_rate": 2.315922535113743e-06, "loss": 0.07418574094772339, "step": 7750 }, { "epoch": 0.7867639137956163, "grad_norm": 4.969974994659424, "learning_rate": 2.2949512905706793e-06, "loss": 0.07334471940994262, "step": 7760 }, { "epoch": 0.7877777848185488, "grad_norm": 7.444607734680176, "learning_rate": 2.274063113770597e-06, "loss": 0.07597590684890747, "step": 7770 }, { "epoch": 0.7887916558414813, "grad_norm": 4.5998640060424805, "learning_rate": 2.2532582299078775e-06, "loss": 0.07964273691177368, "step": 7780 }, { "epoch": 0.7898055268644137, "grad_norm": 4.203415393829346, "learning_rate": 2.2325368632789345e-06, "loss": 0.07438335418701172, "step": 7790 }, { "epoch": 0.7908193978873462, "grad_norm": 5.300208568572998, "learning_rate": 2.211899237279779e-06, "loss": 0.07116752862930298, "step": 7800 }, { "epoch": 0.7918332689102787, "grad_norm": 5.753981113433838, "learning_rate": 2.1913455744036138e-06, "loss": 0.10257375240325928, "step": 7810 }, { "epoch": 0.7928471399332112, "grad_norm": 3.9860215187072754, "learning_rate": 2.1708760962384545e-06, "loss": 0.08305623531341552, "step": 7820 }, { "epoch": 0.7938610109561437, "grad_norm": 4.789848327636719, "learning_rate": 2.1504910234647112e-06, "loss": 0.0762325644493103, "step": 7830 }, { "epoch": 0.7948748819790762, "grad_norm": 4.478184223175049, "learning_rate": 2.130190575852832e-06, "loss": 0.07149927020072937, "step": 7840 }, { "epoch": 0.7958887530020088, "grad_norm": 5.39515495300293, "learning_rate": 2.109974972260921e-06, "loss": 0.06598966121673584, "step": 7850 }, { "epoch": 0.7969026240249413, "grad_norm": 5.496165752410889, "learning_rate": 2.0898444306323807e-06, "loss": 0.06781507134437562, "step": 7860 }, { "epoch": 0.7979164950478738, "grad_norm": 5.223907470703125, "learning_rate": 2.069799167993577e-06, "loss": 0.0778745710849762, "step": 7870 }, { "epoch": 0.7989303660708063, "grad_norm": 7.244438171386719, "learning_rate": 2.0498394004514745e-06, "loss": 0.07507836818695068, "step": 7880 }, { "epoch": 0.7999442370937387, "grad_norm": 5.0708513259887695, "learning_rate": 2.029965343191326e-06, "loss": 0.08446595668792725, "step": 7890 }, { "epoch": 0.8009581081166712, "grad_norm": 4.659949779510498, "learning_rate": 2.0101772104743422e-06, "loss": 0.08021347522735596, "step": 7900 }, { "epoch": 0.8019719791396037, "grad_norm": 4.883636474609375, "learning_rate": 1.990475215635388e-06, "loss": 0.0703702986240387, "step": 7910 }, { "epoch": 0.8029858501625362, "grad_norm": 3.9864609241485596, "learning_rate": 1.9708595710806787e-06, "loss": 0.07180232405662537, "step": 7920 }, { "epoch": 0.8039997211854687, "grad_norm": 4.6548051834106445, "learning_rate": 1.9513304882854966e-06, "loss": 0.061666733026504515, "step": 7930 }, { "epoch": 0.8050135922084012, "grad_norm": 7.059704780578613, "learning_rate": 1.9318881777918973e-06, "loss": 0.06046028137207031, "step": 7940 }, { "epoch": 0.8060274632313337, "grad_norm": 5.559469223022461, "learning_rate": 1.9125328492064575e-06, "loss": 0.07649005055427552, "step": 7950 }, { "epoch": 0.8070413342542662, "grad_norm": 4.825205326080322, "learning_rate": 1.8932647111980007e-06, "loss": 0.07123495936393738, "step": 7960 }, { "epoch": 0.8080552052771987, "grad_norm": 5.746438980102539, "learning_rate": 1.8740839714953552e-06, "loss": 0.07118858098983764, "step": 7970 }, { "epoch": 0.8090690763001311, "grad_norm": 6.28489351272583, "learning_rate": 1.8549908368851099e-06, "loss": 0.07407329678535461, "step": 7980 }, { "epoch": 0.8100829473230636, "grad_norm": 3.7705907821655273, "learning_rate": 1.8359855132093884e-06, "loss": 0.061246728897094725, "step": 7990 }, { "epoch": 0.8110968183459961, "grad_norm": 3.4619293212890625, "learning_rate": 1.8170682053636358e-06, "loss": 0.07747706174850463, "step": 8000 }, { "epoch": 0.8121106893689286, "grad_norm": 5.059840202331543, "learning_rate": 1.7982391172943936e-06, "loss": 0.07638556361198426, "step": 8010 }, { "epoch": 0.8131245603918611, "grad_norm": 4.896632194519043, "learning_rate": 1.7794984519971126e-06, "loss": 0.08006895184516907, "step": 8020 }, { "epoch": 0.8141384314147937, "grad_norm": 3.4052205085754395, "learning_rate": 1.7608464115139712e-06, "loss": 0.06124530434608459, "step": 8030 }, { "epoch": 0.8151523024377262, "grad_norm": 3.9259157180786133, "learning_rate": 1.7422831969316724e-06, "loss": 0.0791073501110077, "step": 8040 }, { "epoch": 0.8161661734606587, "grad_norm": 5.6471052169799805, "learning_rate": 1.7238090083793003e-06, "loss": 0.06683880090713501, "step": 8050 }, { "epoch": 0.8171800444835912, "grad_norm": 2.8069255352020264, "learning_rate": 1.7054240450261594e-06, "loss": 0.058871471881866456, "step": 8060 }, { "epoch": 0.8181939155065237, "grad_norm": 4.808670520782471, "learning_rate": 1.6871285050796093e-06, "loss": 0.0661916971206665, "step": 8070 }, { "epoch": 0.8192077865294561, "grad_norm": 4.906832218170166, "learning_rate": 1.6689225857829527e-06, "loss": 0.06632201075553894, "step": 8080 }, { "epoch": 0.8202216575523886, "grad_norm": 5.804471492767334, "learning_rate": 1.6508064834132875e-06, "loss": 0.08035061359405518, "step": 8090 }, { "epoch": 0.8212355285753211, "grad_norm": 6.948111057281494, "learning_rate": 1.632780393279404e-06, "loss": 0.0636484146118164, "step": 8100 }, { "epoch": 0.8222493995982536, "grad_norm": 5.835695743560791, "learning_rate": 1.614844509719674e-06, "loss": 0.06697829365730286, "step": 8110 }, { "epoch": 0.8232632706211861, "grad_norm": 5.0662312507629395, "learning_rate": 1.5969990260999569e-06, "loss": 0.07367977499961853, "step": 8120 }, { "epoch": 0.8242771416441186, "grad_norm": 3.8939924240112305, "learning_rate": 1.5792441348115116e-06, "loss": 0.06381847858428955, "step": 8130 }, { "epoch": 0.8252910126670511, "grad_norm": 6.33149528503418, "learning_rate": 1.5615800272689352e-06, "loss": 0.05610214471817017, "step": 8140 }, { "epoch": 0.8263048836899836, "grad_norm": 4.902711391448975, "learning_rate": 1.5440068939080776e-06, "loss": 0.05658842921257019, "step": 8150 }, { "epoch": 0.827318754712916, "grad_norm": 5.773613929748535, "learning_rate": 1.5265249241840153e-06, "loss": 0.06624383330345154, "step": 8160 }, { "epoch": 0.8283326257358485, "grad_norm": 5.249154567718506, "learning_rate": 1.5091343065689756e-06, "loss": 0.06917842626571655, "step": 8170 }, { "epoch": 0.829346496758781, "grad_norm": 5.533671855926514, "learning_rate": 1.4918352285503357e-06, "loss": 0.06061675548553467, "step": 8180 }, { "epoch": 0.8303603677817135, "grad_norm": 4.736386299133301, "learning_rate": 1.4746278766285905e-06, "loss": 0.0684545874595642, "step": 8190 }, { "epoch": 0.8313742388046461, "grad_norm": 5.339535713195801, "learning_rate": 1.4575124363153315e-06, "loss": 0.06965160369873047, "step": 8200 }, { "epoch": 0.8323881098275786, "grad_norm": 6.106010437011719, "learning_rate": 1.4404890921312654e-06, "loss": 0.06783157587051392, "step": 8210 }, { "epoch": 0.8334019808505111, "grad_norm": 5.916169166564941, "learning_rate": 1.4235580276042071e-06, "loss": 0.06443643569946289, "step": 8220 }, { "epoch": 0.8344158518734436, "grad_norm": 4.796070575714111, "learning_rate": 1.4067194252671157e-06, "loss": 0.05679306983947754, "step": 8230 }, { "epoch": 0.8354297228963761, "grad_norm": 4.127147674560547, "learning_rate": 1.3899734666561138e-06, "loss": 0.07079203724861145, "step": 8240 }, { "epoch": 0.8364435939193086, "grad_norm": 6.088566303253174, "learning_rate": 1.373320332308541e-06, "loss": 0.07084354162216186, "step": 8250 }, { "epoch": 0.837457464942241, "grad_norm": 5.1720356941223145, "learning_rate": 1.3567602017609981e-06, "loss": 0.06627954840660095, "step": 8260 }, { "epoch": 0.8384713359651735, "grad_norm": 6.133883953094482, "learning_rate": 1.3402932535474277e-06, "loss": 0.06668938398361206, "step": 8270 }, { "epoch": 0.839485206988106, "grad_norm": 5.314329147338867, "learning_rate": 1.3239196651971654e-06, "loss": 0.07224236130714416, "step": 8280 }, { "epoch": 0.8404990780110385, "grad_norm": 4.082633972167969, "learning_rate": 1.3076396132330516e-06, "loss": 0.059988629817962644, "step": 8290 }, { "epoch": 0.841512949033971, "grad_norm": 4.551509380340576, "learning_rate": 1.2914532731694996e-06, "loss": 0.06053336262702942, "step": 8300 }, { "epoch": 0.8425268200569035, "grad_norm": 5.003586769104004, "learning_rate": 1.2753608195106314e-06, "loss": 0.058693927526473996, "step": 8310 }, { "epoch": 0.843540691079836, "grad_norm": 5.630955696105957, "learning_rate": 1.2593624257483838e-06, "loss": 0.06304698586463928, "step": 8320 }, { "epoch": 0.8445545621027685, "grad_norm": 5.3710503578186035, "learning_rate": 1.243458264360634e-06, "loss": 0.06001343131065369, "step": 8330 }, { "epoch": 0.845568433125701, "grad_norm": 4.231541633605957, "learning_rate": 1.2276485068093447e-06, "loss": 0.05882310271263123, "step": 8340 }, { "epoch": 0.8465823041486334, "grad_norm": 4.872186183929443, "learning_rate": 1.2119333235387232e-06, "loss": 0.05753637552261352, "step": 8350 }, { "epoch": 0.8475961751715659, "grad_norm": 4.836701393127441, "learning_rate": 1.1963128839733674e-06, "loss": 0.06098705530166626, "step": 8360 }, { "epoch": 0.8486100461944985, "grad_norm": 5.561583042144775, "learning_rate": 1.1807873565164507e-06, "loss": 0.06337891817092896, "step": 8370 }, { "epoch": 0.849623917217431, "grad_norm": 5.493315696716309, "learning_rate": 1.1653569085479067e-06, "loss": 0.06440221071243286, "step": 8380 }, { "epoch": 0.8506377882403635, "grad_norm": 4.42746114730835, "learning_rate": 1.150021706422615e-06, "loss": 0.06822453737258911, "step": 8390 }, { "epoch": 0.851651659263296, "grad_norm": 5.108514308929443, "learning_rate": 1.1347819154686246e-06, "loss": 0.07203163504600525, "step": 8400 }, { "epoch": 0.8526655302862285, "grad_norm": 5.042569160461426, "learning_rate": 1.1196376999853531e-06, "loss": 0.06249334812164307, "step": 8410 }, { "epoch": 0.853679401309161, "grad_norm": 4.2929534912109375, "learning_rate": 1.104589223241831e-06, "loss": 0.0692518711090088, "step": 8420 }, { "epoch": 0.8546932723320935, "grad_norm": 4.78687858581543, "learning_rate": 1.089636647474923e-06, "loss": 0.06686964631080627, "step": 8430 }, { "epoch": 0.855707143355026, "grad_norm": 4.433170795440674, "learning_rate": 1.0747801338876006e-06, "loss": 0.05410425662994385, "step": 8440 }, { "epoch": 0.8567210143779584, "grad_norm": 5.5953850746154785, "learning_rate": 1.0600198426471908e-06, "loss": 0.058712780475616455, "step": 8450 }, { "epoch": 0.8577348854008909, "grad_norm": 5.374488353729248, "learning_rate": 1.0453559328836517e-06, "loss": 0.06811522245407105, "step": 8460 }, { "epoch": 0.8587487564238234, "grad_norm": 5.382911682128906, "learning_rate": 1.0307885626878555e-06, "loss": 0.05623674392700195, "step": 8470 }, { "epoch": 0.8597626274467559, "grad_norm": 5.300976753234863, "learning_rate": 1.0163178891098912e-06, "loss": 0.05916545987129211, "step": 8480 }, { "epoch": 0.8607764984696884, "grad_norm": 4.747538089752197, "learning_rate": 1.0019440681573633e-06, "loss": 0.05533965826034546, "step": 8490 }, { "epoch": 0.8617903694926209, "grad_norm": 4.767800807952881, "learning_rate": 9.876672547937117e-07, "loss": 0.06057939529418945, "step": 8500 }, { "epoch": 0.8628042405155534, "grad_norm": 5.425280570983887, "learning_rate": 9.734876029365448e-07, "loss": 0.05746605396270752, "step": 8510 }, { "epoch": 0.8638181115384859, "grad_norm": 6.850799560546875, "learning_rate": 9.594052654559737e-07, "loss": 0.05630407333374023, "step": 8520 }, { "epoch": 0.8648319825614184, "grad_norm": 4.567721366882324, "learning_rate": 9.454203941729767e-07, "loss": 0.050064480304718016, "step": 8530 }, { "epoch": 0.865845853584351, "grad_norm": 3.714226007461548, "learning_rate": 9.315331398577454e-07, "loss": 0.05621944665908814, "step": 8540 }, { "epoch": 0.8668597246072834, "grad_norm": 4.955690383911133, "learning_rate": 9.177436522280714e-07, "loss": 0.05996768474578858, "step": 8550 }, { "epoch": 0.8678735956302159, "grad_norm": 5.197844505310059, "learning_rate": 9.04052079947727e-07, "loss": 0.0584868311882019, "step": 8560 }, { "epoch": 0.8688874666531484, "grad_norm": 6.3904900550842285, "learning_rate": 8.904585706248637e-07, "loss": 0.05470994710922241, "step": 8570 }, { "epoch": 0.8699013376760809, "grad_norm": 4.1480817794799805, "learning_rate": 8.76963270810427e-07, "loss": 0.06318782567977906, "step": 8580 }, { "epoch": 0.8709152086990134, "grad_norm": 4.235176086425781, "learning_rate": 8.635663259965632e-07, "loss": 0.06396482586860656, "step": 8590 }, { "epoch": 0.8719290797219459, "grad_norm": 5.737586975097656, "learning_rate": 8.502678806150588e-07, "loss": 0.05133946537971497, "step": 8600 }, { "epoch": 0.8729429507448784, "grad_norm": 4.633546352386475, "learning_rate": 8.370680780357909e-07, "loss": 0.059583580493927, "step": 8610 }, { "epoch": 0.8739568217678109, "grad_norm": 4.1093316078186035, "learning_rate": 8.23967060565164e-07, "loss": 0.05099324584007263, "step": 8620 }, { "epoch": 0.8749706927907434, "grad_norm": 2.83686900138855, "learning_rate": 8.109649694445898e-07, "loss": 0.048278889060020445, "step": 8630 }, { "epoch": 0.8759845638136758, "grad_norm": 5.330329418182373, "learning_rate": 7.980619448489601e-07, "loss": 0.06533851623535156, "step": 8640 }, { "epoch": 0.8769984348366083, "grad_norm": 4.082417011260986, "learning_rate": 7.852581258851333e-07, "loss": 0.04662171006202698, "step": 8650 }, { "epoch": 0.8780123058595408, "grad_norm": 5.013373374938965, "learning_rate": 7.725536505904396e-07, "loss": 0.040755856037139895, "step": 8660 }, { "epoch": 0.8790261768824733, "grad_norm": 5.024847030639648, "learning_rate": 7.599486559311887e-07, "loss": 0.05189507007598877, "step": 8670 }, { "epoch": 0.8800400479054058, "grad_norm": 5.247585296630859, "learning_rate": 7.474432778011953e-07, "loss": 0.05953971147537231, "step": 8680 }, { "epoch": 0.8810539189283383, "grad_norm": 4.876698017120361, "learning_rate": 7.350376510203105e-07, "loss": 0.05025558471679688, "step": 8690 }, { "epoch": 0.8820677899512708, "grad_norm": 4.793431758880615, "learning_rate": 7.227319093329732e-07, "loss": 0.06328981518745422, "step": 8700 }, { "epoch": 0.8830816609742033, "grad_norm": 4.168718338012695, "learning_rate": 7.105261854067691e-07, "loss": 0.04886254668235779, "step": 8710 }, { "epoch": 0.8840955319971359, "grad_norm": 5.084412574768066, "learning_rate": 6.984206108309932e-07, "loss": 0.054524511098861694, "step": 8720 }, { "epoch": 0.8851094030200684, "grad_norm": 2.7376439571380615, "learning_rate": 6.864153161152354e-07, "loss": 0.03685829639434814, "step": 8730 }, { "epoch": 0.8861232740430008, "grad_norm": 4.288018703460693, "learning_rate": 6.745104306879769e-07, "loss": 0.060113197565078734, "step": 8740 }, { "epoch": 0.8871371450659333, "grad_norm": 4.686915874481201, "learning_rate": 6.627060828951881e-07, "loss": 0.056988108158111575, "step": 8750 }, { "epoch": 0.8881510160888658, "grad_norm": 4.747193336486816, "learning_rate": 6.510023999989501e-07, "loss": 0.06947777271270753, "step": 8760 }, { "epoch": 0.8891648871117983, "grad_norm": 5.475988388061523, "learning_rate": 6.393995081760795e-07, "loss": 0.051690173149108884, "step": 8770 }, { "epoch": 0.8901787581347308, "grad_norm": 5.096240520477295, "learning_rate": 6.278975325167691e-07, "loss": 0.05507060885429382, "step": 8780 }, { "epoch": 0.8911926291576633, "grad_norm": 6.5569000244140625, "learning_rate": 6.164965970232417e-07, "loss": 0.0605499267578125, "step": 8790 }, { "epoch": 0.8922065001805958, "grad_norm": 5.827706336975098, "learning_rate": 6.051968246084117e-07, "loss": 0.06119743585586548, "step": 8800 }, { "epoch": 0.8932203712035283, "grad_norm": 5.459431171417236, "learning_rate": 5.939983370945535e-07, "loss": 0.05737078785896301, "step": 8810 }, { "epoch": 0.8942342422264608, "grad_norm": 4.077573776245117, "learning_rate": 5.829012552120039e-07, "loss": 0.06413388848304749, "step": 8820 }, { "epoch": 0.8952481132493932, "grad_norm": 5.587220191955566, "learning_rate": 5.719056985978388e-07, "loss": 0.05413188934326172, "step": 8830 }, { "epoch": 0.8962619842723257, "grad_norm": 6.953311920166016, "learning_rate": 5.610117857946062e-07, "loss": 0.0524446964263916, "step": 8840 }, { "epoch": 0.8972758552952582, "grad_norm": 5.318061828613281, "learning_rate": 5.502196342490318e-07, "loss": 0.05889509916305542, "step": 8850 }, { "epoch": 0.8982897263181907, "grad_norm": 5.9803595542907715, "learning_rate": 5.395293603107566e-07, "loss": 0.04217783212661743, "step": 8860 }, { "epoch": 0.8993035973411232, "grad_norm": 4.232280731201172, "learning_rate": 5.2894107923109e-07, "loss": 0.056142598390579224, "step": 8870 }, { "epoch": 0.9003174683640557, "grad_norm": 4.215583801269531, "learning_rate": 5.184549051617571e-07, "loss": 0.055416709184646605, "step": 8880 }, { "epoch": 0.9013313393869883, "grad_norm": 5.940876483917236, "learning_rate": 5.08070951153673e-07, "loss": 0.052827191352844236, "step": 8890 }, { "epoch": 0.9023452104099208, "grad_norm": 4.573044776916504, "learning_rate": 4.977893291557256e-07, "loss": 0.04959940612316131, "step": 8900 }, { "epoch": 0.9033590814328533, "grad_norm": 4.318954944610596, "learning_rate": 4.876101500135621e-07, "loss": 0.055960679054260255, "step": 8910 }, { "epoch": 0.9043729524557858, "grad_norm": 6.505980014801025, "learning_rate": 4.775335234684042e-07, "loss": 0.05048450231552124, "step": 8920 }, { "epoch": 0.9053868234787182, "grad_norm": 5.0496087074279785, "learning_rate": 4.675595581558556e-07, "loss": 0.05222088098526001, "step": 8930 }, { "epoch": 0.9064006945016507, "grad_norm": 5.8519978523254395, "learning_rate": 4.576883616047345e-07, "loss": 0.06404187083244324, "step": 8940 }, { "epoch": 0.9074145655245832, "grad_norm": 4.370904922485352, "learning_rate": 4.479200402359174e-07, "loss": 0.04772624373435974, "step": 8950 }, { "epoch": 0.9084284365475157, "grad_norm": 5.456799030303955, "learning_rate": 4.382546993611836e-07, "loss": 0.0514110803604126, "step": 8960 }, { "epoch": 0.9094423075704482, "grad_norm": 5.230767250061035, "learning_rate": 4.28692443182086e-07, "loss": 0.05345784425735474, "step": 8970 }, { "epoch": 0.9104561785933807, "grad_norm": 3.8498055934906006, "learning_rate": 4.192333747888311e-07, "loss": 0.048007276654243466, "step": 8980 }, { "epoch": 0.9114700496163132, "grad_norm": 5.91139030456543, "learning_rate": 4.0987759615915837e-07, "loss": 0.05494840145111084, "step": 8990 }, { "epoch": 0.9124839206392457, "grad_norm": 5.808679103851318, "learning_rate": 4.0062520815724816e-07, "loss": 0.05654096007347107, "step": 9000 }, { "epoch": 0.9134977916621781, "grad_norm": 4.6590776443481445, "learning_rate": 3.9147631053263027e-07, "loss": 0.04400959610939026, "step": 9010 }, { "epoch": 0.9145116626851106, "grad_norm": 6.4468464851379395, "learning_rate": 3.824310019191102e-07, "loss": 0.060762441158294676, "step": 9020 }, { "epoch": 0.9155255337080431, "grad_norm": 5.6311492919921875, "learning_rate": 3.734893798337058e-07, "loss": 0.04889492392539978, "step": 9030 }, { "epoch": 0.9165394047309756, "grad_norm": 3.4041483402252197, "learning_rate": 3.646515406755946e-07, "loss": 0.05444796681404114, "step": 9040 }, { "epoch": 0.9175532757539081, "grad_norm": 5.9292216300964355, "learning_rate": 3.559175797250769e-07, "loss": 0.05159125924110412, "step": 9050 }, { "epoch": 0.9185671467768407, "grad_norm": 4.313247203826904, "learning_rate": 3.4728759114254774e-07, "loss": 0.04746991991996765, "step": 9060 }, { "epoch": 0.9195810177997732, "grad_norm": 4.1722025871276855, "learning_rate": 3.3876166796747877e-07, "loss": 0.058013665676116946, "step": 9070 }, { "epoch": 0.9205948888227057, "grad_norm": 3.254392385482788, "learning_rate": 3.303399021174214e-07, "loss": 0.047249060869216916, "step": 9080 }, { "epoch": 0.9216087598456382, "grad_norm": 5.63811731338501, "learning_rate": 3.220223843870096e-07, "loss": 0.04977525472640991, "step": 9090 }, { "epoch": 0.9226226308685707, "grad_norm": 7.481564521789551, "learning_rate": 3.1380920444698093e-07, "loss": 0.056066316366195676, "step": 9100 }, { "epoch": 0.9236365018915031, "grad_norm": 4.154149532318115, "learning_rate": 3.057004508432193e-07, "loss": 0.04034147262573242, "step": 9110 }, { "epoch": 0.9246503729144356, "grad_norm": 3.8613505363464355, "learning_rate": 2.976962109957882e-07, "loss": 0.04678772091865539, "step": 9120 }, { "epoch": 0.9256642439373681, "grad_norm": 3.2497124671936035, "learning_rate": 2.8979657119799667e-07, "loss": 0.04509277045726776, "step": 9130 }, { "epoch": 0.9266781149603006, "grad_norm": 5.511162757873535, "learning_rate": 2.8200161661546377e-07, "loss": 0.044655972719192506, "step": 9140 }, { "epoch": 0.9276919859832331, "grad_norm": 4.274925231933594, "learning_rate": 2.7431143128520243e-07, "loss": 0.045601218938827515, "step": 9150 }, { "epoch": 0.9287058570061656, "grad_norm": 4.979913711547852, "learning_rate": 2.667260981147157e-07, "loss": 0.04156555235385895, "step": 9160 }, { "epoch": 0.9297197280290981, "grad_norm": 5.2591681480407715, "learning_rate": 2.5924569888109654e-07, "loss": 0.05790865421295166, "step": 9170 }, { "epoch": 0.9307335990520306, "grad_norm": 7.148556232452393, "learning_rate": 2.5187031423015597e-07, "loss": 0.042946469783782956, "step": 9180 }, { "epoch": 0.9317474700749631, "grad_norm": 3.68515944480896, "learning_rate": 2.4460002367554523e-07, "loss": 0.04124525785446167, "step": 9190 }, { "epoch": 0.9327613410978955, "grad_norm": 6.54945182800293, "learning_rate": 2.3743490559789973e-07, "loss": 0.05577017068862915, "step": 9200 }, { "epoch": 0.933775212120828, "grad_norm": 3.02951717376709, "learning_rate": 2.3037503724399946e-07, "loss": 0.038941627740859984, "step": 9210 }, { "epoch": 0.9347890831437605, "grad_norm": 6.035778999328613, "learning_rate": 2.2342049472592996e-07, "loss": 0.04274754524230957, "step": 9220 }, { "epoch": 0.9358029541666931, "grad_norm": 7.519543647766113, "learning_rate": 2.1657135302026177e-07, "loss": 0.04206355214118958, "step": 9230 }, { "epoch": 0.9368168251896256, "grad_norm": 5.111642837524414, "learning_rate": 2.09827685967251e-07, "loss": 0.04405514001846313, "step": 9240 }, { "epoch": 0.9378306962125581, "grad_norm": 4.112310409545898, "learning_rate": 2.0318956627003227e-07, "loss": 0.04169490933418274, "step": 9250 }, { "epoch": 0.9388445672354906, "grad_norm": 3.0048344135284424, "learning_rate": 1.9665706549384044e-07, "loss": 0.044167399406433105, "step": 9260 }, { "epoch": 0.9398584382584231, "grad_norm": 3.9658427238464355, "learning_rate": 1.9023025406523787e-07, "loss": 0.04947400093078613, "step": 9270 }, { "epoch": 0.9408723092813556, "grad_norm": 4.791296005249023, "learning_rate": 1.8390920127135613e-07, "loss": 0.044483023881912234, "step": 9280 }, { "epoch": 0.9418861803042881, "grad_norm": 7.458903789520264, "learning_rate": 1.7769397525914668e-07, "loss": 0.04987005591392517, "step": 9290 }, { "epoch": 0.9429000513272205, "grad_norm": 4.106653690338135, "learning_rate": 1.7158464303465017e-07, "loss": 0.04030983746051788, "step": 9300 }, { "epoch": 0.943913922350153, "grad_norm": 6.181607723236084, "learning_rate": 1.6558127046226945e-07, "loss": 0.046465945243835446, "step": 9310 }, { "epoch": 0.9449277933730855, "grad_norm": 5.014143943786621, "learning_rate": 1.5968392226406337e-07, "loss": 0.04713892936706543, "step": 9320 }, { "epoch": 0.945941664396018, "grad_norm": 8.611553192138672, "learning_rate": 1.5389266201904506e-07, "loss": 0.04367636740207672, "step": 9330 }, { "epoch": 0.9469555354189505, "grad_norm": 4.235472202301025, "learning_rate": 1.482075521625026e-07, "loss": 0.046830177307128906, "step": 9340 }, { "epoch": 0.947969406441883, "grad_norm": 3.30907940864563, "learning_rate": 1.4262865398531834e-07, "loss": 0.04275010228157043, "step": 9350 }, { "epoch": 0.9489832774648155, "grad_norm": 4.77037239074707, "learning_rate": 1.3715602763331172e-07, "loss": 0.05010094046592713, "step": 9360 }, { "epoch": 0.949997148487748, "grad_norm": 5.199641227722168, "learning_rate": 1.3178973210659528e-07, "loss": 0.04858386218547821, "step": 9370 }, { "epoch": 0.9510110195106805, "grad_norm": 5.610039234161377, "learning_rate": 1.2652982525892975e-07, "loss": 0.048996299505233765, "step": 9380 }, { "epoch": 0.9520248905336129, "grad_norm": 7.867613315582275, "learning_rate": 1.213763637971066e-07, "loss": 0.053688549995422365, "step": 9390 }, { "epoch": 0.9530387615565454, "grad_norm": 5.899295330047607, "learning_rate": 1.1632940328033526e-07, "loss": 0.04791654646396637, "step": 9400 }, { "epoch": 0.954052632579478, "grad_norm": 5.626562118530273, "learning_rate": 1.1138899811964477e-07, "loss": 0.04426780045032501, "step": 9410 }, { "epoch": 0.9550665036024105, "grad_norm": 4.7481231689453125, "learning_rate": 1.0655520157729194e-07, "loss": 0.046077513694763185, "step": 9420 }, { "epoch": 0.956080374625343, "grad_norm": 2.8143560886383057, "learning_rate": 1.0182806576619742e-07, "loss": 0.04246982932090759, "step": 9430 }, { "epoch": 0.9570942456482755, "grad_norm": 5.390624046325684, "learning_rate": 9.72076416493728e-08, "loss": 0.03447339534759521, "step": 9440 }, { "epoch": 0.958108116671208, "grad_norm": 5.978041648864746, "learning_rate": 9.269397903937883e-08, "loss": 0.04656773805618286, "step": 9450 }, { "epoch": 0.9591219876941405, "grad_norm": 3.9169042110443115, "learning_rate": 8.828712659778471e-08, "loss": 0.04153328239917755, "step": 9460 }, { "epoch": 0.960135858717073, "grad_norm": 5.914982795715332, "learning_rate": 8.398713183464857e-08, "loss": 0.03169049620628357, "step": 9470 }, { "epoch": 0.9611497297400055, "grad_norm": 7.719944953918457, "learning_rate": 7.979404110799338e-08, "loss": 0.05208643674850464, "step": 9480 }, { "epoch": 0.9621636007629379, "grad_norm": 3.162707567214966, "learning_rate": 7.570789962332181e-08, "loss": 0.04311830401420593, "step": 9490 }, { "epoch": 0.9631774717858704, "grad_norm": 6.1075286865234375, "learning_rate": 7.172875143311996e-08, "loss": 0.04467223286628723, "step": 9500 }, { "epoch": 0.9641913428088029, "grad_norm": 9.468648910522461, "learning_rate": 6.785663943638333e-08, "loss": 0.04647936820983887, "step": 9510 }, { "epoch": 0.9652052138317354, "grad_norm": 4.242889881134033, "learning_rate": 6.409160537815818e-08, "loss": 0.04828156530857086, "step": 9520 }, { "epoch": 0.9662190848546679, "grad_norm": 6.257077693939209, "learning_rate": 6.043368984908759e-08, "loss": 0.05290828943252564, "step": 9530 }, { "epoch": 0.9672329558776004, "grad_norm": 4.109161376953125, "learning_rate": 5.688293228497399e-08, "loss": 0.050607830286026, "step": 9540 }, { "epoch": 0.9682468269005329, "grad_norm": 3.6473684310913086, "learning_rate": 5.34393709663561e-08, "loss": 0.045180085301399234, "step": 9550 }, { "epoch": 0.9692606979234654, "grad_norm": 4.136952877044678, "learning_rate": 5.0103043018097096e-08, "loss": 0.05473998785018921, "step": 9560 }, { "epoch": 0.9702745689463979, "grad_norm": 3.138425827026367, "learning_rate": 4.687398440897828e-08, "loss": 0.042855563759803775, "step": 9570 }, { "epoch": 0.9712884399693305, "grad_norm": 5.040831089019775, "learning_rate": 4.3752229951321553e-08, "loss": 0.04447084665298462, "step": 9580 }, { "epoch": 0.9723023109922629, "grad_norm": 5.650908470153809, "learning_rate": 4.0737813300602e-08, "loss": 0.04641305208206177, "step": 9590 }, { "epoch": 0.9733161820151954, "grad_norm": 5.803855895996094, "learning_rate": 3.783076695509702e-08, "loss": 0.040504708886146545, "step": 9600 }, { "epoch": 0.9743300530381279, "grad_norm": 3.991659164428711, "learning_rate": 3.5031122255524406e-08, "loss": 0.03786005675792694, "step": 9610 }, { "epoch": 0.9753439240610604, "grad_norm": 4.755215644836426, "learning_rate": 3.233890938471373e-08, "loss": 0.05279897451400757, "step": 9620 }, { "epoch": 0.9763577950839929, "grad_norm": 4.7982916831970215, "learning_rate": 2.9754157367277715e-08, "loss": 0.052005434036254884, "step": 9630 }, { "epoch": 0.9773716661069254, "grad_norm": 5.146061897277832, "learning_rate": 2.72768940692969e-08, "loss": 0.0395075261592865, "step": 9640 }, { "epoch": 0.9783855371298579, "grad_norm": 5.342719554901123, "learning_rate": 2.4907146198023256e-08, "loss": 0.0528223991394043, "step": 9650 }, { "epoch": 0.9793994081527904, "grad_norm": 6.542340278625488, "learning_rate": 2.2644939301588174e-08, "loss": 0.04475674033164978, "step": 9660 }, { "epoch": 0.9804132791757229, "grad_norm": 6.385866165161133, "learning_rate": 2.049029776873268e-08, "loss": 0.03444611132144928, "step": 9670 }, { "epoch": 0.9814271501986553, "grad_norm": 3.294386386871338, "learning_rate": 1.8443244828536544e-08, "loss": 0.04815955758094788, "step": 9680 }, { "epoch": 0.9824410212215878, "grad_norm": 4.657988548278809, "learning_rate": 1.650380255017625e-08, "loss": 0.0520674467086792, "step": 9690 }, { "epoch": 0.9834548922445203, "grad_norm": 3.498767852783203, "learning_rate": 1.4671991842680756e-08, "loss": 0.03676204085350036, "step": 9700 }, { "epoch": 0.9844687632674528, "grad_norm": 6.240079879760742, "learning_rate": 1.294783245470943e-08, "loss": 0.04602474868297577, "step": 9710 }, { "epoch": 0.9854826342903853, "grad_norm": 6.68985652923584, "learning_rate": 1.13313429743378e-08, "loss": 0.041659051179885866, "step": 9720 }, { "epoch": 0.9864965053133178, "grad_norm": 4.057550430297852, "learning_rate": 9.822540828858807e-09, "loss": 0.04571613967418671, "step": 9730 }, { "epoch": 0.9875103763362503, "grad_norm": 5.839316368103027, "learning_rate": 8.421442284591852e-09, "loss": 0.0449409008026123, "step": 9740 }, { "epoch": 0.9885242473591829, "grad_norm": 6.876565456390381, "learning_rate": 7.128062446709605e-09, "loss": 0.046157240867614746, "step": 9750 }, { "epoch": 0.9895381183821154, "grad_norm": 5.687508583068848, "learning_rate": 5.942415259074796e-09, "loss": 0.04719183146953583, "step": 9760 }, { "epoch": 0.9905519894050479, "grad_norm": 5.304599761962891, "learning_rate": 4.86451350409145e-09, "loss": 0.04205496907234192, "step": 9770 }, { "epoch": 0.9915658604279803, "grad_norm": 5.8917236328125, "learning_rate": 3.894368802563886e-09, "loss": 0.04283034801483154, "step": 9780 }, { "epoch": 0.9925797314509128, "grad_norm": 5.883257865905762, "learning_rate": 3.0319916135723713e-09, "loss": 0.04779918789863587, "step": 9790 }, { "epoch": 0.9935936024738453, "grad_norm": 5.365874767303467, "learning_rate": 2.277391234363213e-09, "loss": 0.03659367561340332, "step": 9800 }, { "epoch": 0.9946074734967778, "grad_norm": 3.033179759979248, "learning_rate": 1.6305758002443939e-09, "loss": 0.038347238302230836, "step": 9810 }, { "epoch": 0.9956213445197103, "grad_norm": 4.685072422027588, "learning_rate": 1.091552284500086e-09, "loss": 0.04608907699584961, "step": 9820 }, { "epoch": 0.9966352155426428, "grad_norm": 7.374276161193848, "learning_rate": 6.603264983173762e-10, "loss": 0.048170754313468934, "step": 9830 }, { "epoch": 0.9976490865655753, "grad_norm": 3.590285062789917, "learning_rate": 3.3690309071965355e-10, "loss": 0.04551730751991272, "step": 9840 }, { "epoch": 0.9986629575885078, "grad_norm": 5.001296520233154, "learning_rate": 1.2128554851664754e-10, "loss": 0.040024766325950624, "step": 9850 }, { "epoch": 0.9996768286114402, "grad_norm": 3.747532844543457, "learning_rate": 1.3476196272232955e-11, "loss": 0.04129230976104736, "step": 9860 }, { "epoch": 1.0, "step": 9864, "total_flos": 5.019574154025134e+19, "train_loss": 0.05770318032471223, "train_runtime": 89312.6124, "train_samples_per_second": 7.068, "train_steps_per_second": 0.11 } ], "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": 5.019574154025134e+19, "train_batch_size": 1, "trial_name": null, "trial_params": null }