{ "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": 64.33531951904297, "learning_rate": 6.081081081081082e-07, "loss": 1.5731732368469238, "step": 10 }, { "epoch": 0.0020277420458649905, "grad_norm": 22.504240036010742, "learning_rate": 1.2837837837837838e-06, "loss": 0.2834433317184448, "step": 20 }, { "epoch": 0.003041613068797486, "grad_norm": 15.607647895812988, "learning_rate": 1.9594594594594595e-06, "loss": 0.23080971240997314, "step": 30 }, { "epoch": 0.004055484091729981, "grad_norm": 19.493419647216797, "learning_rate": 2.6351351351351353e-06, "loss": 0.2246990203857422, "step": 40 }, { "epoch": 0.005069355114662476, "grad_norm": 13.467429161071777, "learning_rate": 3.310810810810811e-06, "loss": 0.2280207633972168, "step": 50 }, { "epoch": 0.006083226137594972, "grad_norm": 10.652061462402344, "learning_rate": 3.986486486486487e-06, "loss": 0.24375686645507813, "step": 60 }, { "epoch": 0.0070970971605274664, "grad_norm": 9.171167373657227, "learning_rate": 4.6621621621621625e-06, "loss": 0.2160320281982422, "step": 70 }, { "epoch": 0.008110968183459962, "grad_norm": 10.744911193847656, "learning_rate": 5.337837837837838e-06, "loss": 0.2403956413269043, "step": 80 }, { "epoch": 0.009124839206392456, "grad_norm": 6.6313042640686035, "learning_rate": 6.013513513513514e-06, "loss": 0.22810254096984864, "step": 90 }, { "epoch": 0.010138710229324952, "grad_norm": 6.943337440490723, "learning_rate": 6.689189189189191e-06, "loss": 0.21166491508483887, "step": 100 }, { "epoch": 0.011152581252257448, "grad_norm": 10.840103149414062, "learning_rate": 7.3648648648648655e-06, "loss": 0.24102449417114258, "step": 110 }, { "epoch": 0.012166452275189943, "grad_norm": 11.913240432739258, "learning_rate": 8.040540540540541e-06, "loss": 0.22007901668548585, "step": 120 }, { "epoch": 0.013180323298122437, "grad_norm": 7.074462413787842, "learning_rate": 8.716216216216217e-06, "loss": 0.2244892120361328, "step": 130 }, { "epoch": 0.014194194321054933, "grad_norm": 8.960391998291016, "learning_rate": 9.391891891891893e-06, "loss": 0.22567782402038575, "step": 140 }, { "epoch": 0.015208065343987429, "grad_norm": 14.053265571594238, "learning_rate": 1.0067567567567569e-05, "loss": 0.2175224781036377, "step": 150 }, { "epoch": 0.016221936366919924, "grad_norm": 6.871337413787842, "learning_rate": 1.0743243243243244e-05, "loss": 0.19235516786575318, "step": 160 }, { "epoch": 0.01723580738985242, "grad_norm": 11.305193901062012, "learning_rate": 1.141891891891892e-05, "loss": 0.20222744941711426, "step": 170 }, { "epoch": 0.018249678412784912, "grad_norm": 8.359179496765137, "learning_rate": 1.2094594594594596e-05, "loss": 0.19641263484954835, "step": 180 }, { "epoch": 0.019263549435717408, "grad_norm": 9.733006477355957, "learning_rate": 1.2770270270270272e-05, "loss": 0.19702844619750975, "step": 190 }, { "epoch": 0.020277420458649904, "grad_norm": 14.779024124145508, "learning_rate": 1.3445945945945946e-05, "loss": 0.23746609687805176, "step": 200 }, { "epoch": 0.0212912914815824, "grad_norm": 6.3455281257629395, "learning_rate": 1.4121621621621621e-05, "loss": 0.22453432083129882, "step": 210 }, { "epoch": 0.022305162504514895, "grad_norm": 11.07302188873291, "learning_rate": 1.4797297297297299e-05, "loss": 0.20490169525146484, "step": 220 }, { "epoch": 0.02331903352744739, "grad_norm": 6.341692924499512, "learning_rate": 1.5472972972972976e-05, "loss": 0.2024329662322998, "step": 230 }, { "epoch": 0.024332904550379886, "grad_norm": 2.9971611499786377, "learning_rate": 1.614864864864865e-05, "loss": 0.20168333053588866, "step": 240 }, { "epoch": 0.02534677557331238, "grad_norm": 5.651436805725098, "learning_rate": 1.6824324324324324e-05, "loss": 0.2088179111480713, "step": 250 }, { "epoch": 0.026360646596244874, "grad_norm": 9.075505256652832, "learning_rate": 1.7500000000000002e-05, "loss": 0.2093043327331543, "step": 260 }, { "epoch": 0.02737451761917737, "grad_norm": 7.790342330932617, "learning_rate": 1.8175675675675676e-05, "loss": 0.20802013874053954, "step": 270 }, { "epoch": 0.028388388642109866, "grad_norm": 10.896117210388184, "learning_rate": 1.8851351351351353e-05, "loss": 0.22302215099334716, "step": 280 }, { "epoch": 0.02940225966504236, "grad_norm": 5.3397297859191895, "learning_rate": 1.9527027027027027e-05, "loss": 0.2132129430770874, "step": 290 }, { "epoch": 0.030416130687974857, "grad_norm": 3.4768753051757812, "learning_rate": 1.999999514856865e-05, "loss": 0.1904972791671753, "step": 300 }, { "epoch": 0.03143000171090735, "grad_norm": 3.894118309020996, "learning_rate": 1.999990890103106e-05, "loss": 0.1932985782623291, "step": 310 }, { "epoch": 0.03244387273383985, "grad_norm": 3.413132667541504, "learning_rate": 1.999971484497808e-05, "loss": 0.2027864933013916, "step": 320 }, { "epoch": 0.033457743756772344, "grad_norm": 2.6421635150909424, "learning_rate": 1.9999412982501806e-05, "loss": 0.18412922620773314, "step": 330 }, { "epoch": 0.03447161477970484, "grad_norm": 6.016620635986328, "learning_rate": 1.9999003316856605e-05, "loss": 0.18604358434677123, "step": 340 }, { "epoch": 0.03548548580263733, "grad_norm": 5.78879976272583, "learning_rate": 1.9998485852459068e-05, "loss": 0.182320237159729, "step": 350 }, { "epoch": 0.036499356825569824, "grad_norm": 4.2059454917907715, "learning_rate": 1.9997860594887947e-05, "loss": 0.2022219181060791, "step": 360 }, { "epoch": 0.03751322784850232, "grad_norm": 11.617647171020508, "learning_rate": 1.9997127550884116e-05, "loss": 0.20473141670227052, "step": 370 }, { "epoch": 0.038527098871434816, "grad_norm": 3.796731948852539, "learning_rate": 1.9996286728350484e-05, "loss": 0.18943854570388793, "step": 380 }, { "epoch": 0.03954096989436731, "grad_norm": 6.5443115234375, "learning_rate": 1.9995338136351913e-05, "loss": 0.20051827430725097, "step": 390 }, { "epoch": 0.04055484091729981, "grad_norm": 7.51162576675415, "learning_rate": 1.9994281785115127e-05, "loss": 0.1955112934112549, "step": 400 }, { "epoch": 0.0415687119402323, "grad_norm": 3.9869894981384277, "learning_rate": 1.9993117686028603e-05, "loss": 0.18166300058364868, "step": 410 }, { "epoch": 0.0425825829631648, "grad_norm": 9.078548431396484, "learning_rate": 1.9991845851642426e-05, "loss": 0.20461676120758057, "step": 420 }, { "epoch": 0.043596453986097294, "grad_norm": 4.426022052764893, "learning_rate": 1.999046629566818e-05, "loss": 0.1971288204193115, "step": 430 }, { "epoch": 0.04461032500902979, "grad_norm": 4.383369445800781, "learning_rate": 1.998897903297879e-05, "loss": 0.1980234146118164, "step": 440 }, { "epoch": 0.045624196031962286, "grad_norm": 8.82932186126709, "learning_rate": 1.9987384079608362e-05, "loss": 0.1970005989074707, "step": 450 }, { "epoch": 0.04663806705489478, "grad_norm": 4.693522930145264, "learning_rate": 1.998568145275201e-05, "loss": 0.21179935932159424, "step": 460 }, { "epoch": 0.04765193807782728, "grad_norm": 2.038274049758911, "learning_rate": 1.998387117076566e-05, "loss": 0.20955383777618408, "step": 470 }, { "epoch": 0.04866580910075977, "grad_norm": 6.128048896789551, "learning_rate": 1.998195325316588e-05, "loss": 0.19660887718200684, "step": 480 }, { "epoch": 0.04967968012369226, "grad_norm": 6.063856601715088, "learning_rate": 1.997992772062964e-05, "loss": 0.21331639289855958, "step": 490 }, { "epoch": 0.05069355114662476, "grad_norm": 10.046598434448242, "learning_rate": 1.9977794594994103e-05, "loss": 0.20576746463775636, "step": 500 }, { "epoch": 0.05170742216955725, "grad_norm": 4.544410705566406, "learning_rate": 1.9975553899256388e-05, "loss": 0.19188622236251832, "step": 510 }, { "epoch": 0.05272129319248975, "grad_norm": 3.813324213027954, "learning_rate": 1.9973205657573328e-05, "loss": 0.19135918617248535, "step": 520 }, { "epoch": 0.053735164215422244, "grad_norm": 6.5577287673950195, "learning_rate": 1.99707498952612e-05, "loss": 0.1840827226638794, "step": 530 }, { "epoch": 0.05474903523835474, "grad_norm": 3.6055965423583984, "learning_rate": 1.9968186638795445e-05, "loss": 0.17291443347930907, "step": 540 }, { "epoch": 0.055762906261287236, "grad_norm": 6.111795902252197, "learning_rate": 1.9965515915810408e-05, "loss": 0.17936476469039916, "step": 550 }, { "epoch": 0.05677677728421973, "grad_norm": 5.046782970428467, "learning_rate": 1.9962737755099023e-05, "loss": 0.20687036514282225, "step": 560 }, { "epoch": 0.05779064830715223, "grad_norm": 3.976566791534424, "learning_rate": 1.9959852186612492e-05, "loss": 0.1958516240119934, "step": 570 }, { "epoch": 0.05880451933008472, "grad_norm": 6.579321384429932, "learning_rate": 1.995685924145999e-05, "loss": 0.1913176655769348, "step": 580 }, { "epoch": 0.05981839035301722, "grad_norm": 7.051827430725098, "learning_rate": 1.9953758951908305e-05, "loss": 0.1767825484275818, "step": 590 }, { "epoch": 0.060832261375949714, "grad_norm": 3.9585726261138916, "learning_rate": 1.995055135138151e-05, "loss": 0.19146238565444945, "step": 600 }, { "epoch": 0.06184613239888221, "grad_norm": 5.241097450256348, "learning_rate": 1.994723647446058e-05, "loss": 0.19739198684692383, "step": 610 }, { "epoch": 0.0628600034218147, "grad_norm": 4.02030611038208, "learning_rate": 1.994381435688303e-05, "loss": 0.18472386598587037, "step": 620 }, { "epoch": 0.0638738744447472, "grad_norm": 3.474731922149658, "learning_rate": 1.994028503554255e-05, "loss": 0.1882715940475464, "step": 630 }, { "epoch": 0.0648877454676797, "grad_norm": 5.439525127410889, "learning_rate": 1.9936648548488568e-05, "loss": 0.19244825839996338, "step": 640 }, { "epoch": 0.06590161649061219, "grad_norm": 8.452714920043945, "learning_rate": 1.993290493492587e-05, "loss": 0.18374661207199097, "step": 650 }, { "epoch": 0.06691548751354469, "grad_norm": 10.213264465332031, "learning_rate": 1.9929054235214168e-05, "loss": 0.1845883846282959, "step": 660 }, { "epoch": 0.06792935853647718, "grad_norm": 6.3263139724731445, "learning_rate": 1.992509649086766e-05, "loss": 0.15310800075531006, "step": 670 }, { "epoch": 0.06894322955940968, "grad_norm": 3.8808176517486572, "learning_rate": 1.9921031744554588e-05, "loss": 0.21347649097442628, "step": 680 }, { "epoch": 0.06995710058234217, "grad_norm": 5.820873260498047, "learning_rate": 1.991686004009678e-05, "loss": 0.19141788482666017, "step": 690 }, { "epoch": 0.07097097160527466, "grad_norm": 4.116557598114014, "learning_rate": 1.991258142246917e-05, "loss": 0.19195983409881592, "step": 700 }, { "epoch": 0.07198484262820716, "grad_norm": 7.755215644836426, "learning_rate": 1.990819593779932e-05, "loss": 0.19151432514190675, "step": 710 }, { "epoch": 0.07299871365113965, "grad_norm": 5.39434814453125, "learning_rate": 1.9903703633366923e-05, "loss": 0.18523879051208497, "step": 720 }, { "epoch": 0.07401258467407215, "grad_norm": 7.998386859893799, "learning_rate": 1.9899104557603285e-05, "loss": 0.18002413511276244, "step": 730 }, { "epoch": 0.07502645569700464, "grad_norm": 7.916359901428223, "learning_rate": 1.9894398760090807e-05, "loss": 0.21493146419525147, "step": 740 }, { "epoch": 0.07604032671993714, "grad_norm": 4.1160078048706055, "learning_rate": 1.988958629156246e-05, "loss": 0.19023100137710572, "step": 750 }, { "epoch": 0.07705419774286963, "grad_norm": 3.414368152618408, "learning_rate": 1.988466720390123e-05, "loss": 0.19084513187408447, "step": 760 }, { "epoch": 0.07806806876580213, "grad_norm": 4.937281131744385, "learning_rate": 1.9879641550139545e-05, "loss": 0.18980729579925537, "step": 770 }, { "epoch": 0.07908193978873462, "grad_norm": 6.499246120452881, "learning_rate": 1.9874509384458726e-05, "loss": 0.18960732221603394, "step": 780 }, { "epoch": 0.08009581081166713, "grad_norm": 2.8017492294311523, "learning_rate": 1.9869270762188402e-05, "loss": 0.18859455585479737, "step": 790 }, { "epoch": 0.08110968183459961, "grad_norm": 5.848474025726318, "learning_rate": 1.986392573980589e-05, "loss": 0.1938597798347473, "step": 800 }, { "epoch": 0.08212355285753212, "grad_norm": 3.982879400253296, "learning_rate": 1.9858474374935606e-05, "loss": 0.18033983707427978, "step": 810 }, { "epoch": 0.0831374238804646, "grad_norm": 2.493093729019165, "learning_rate": 1.9852916726348446e-05, "loss": 0.18730685710906983, "step": 820 }, { "epoch": 0.0841512949033971, "grad_norm": 2.729903221130371, "learning_rate": 1.9847252853961136e-05, "loss": 0.18190314769744872, "step": 830 }, { "epoch": 0.0851651659263296, "grad_norm": 5.484076499938965, "learning_rate": 1.98414828188356e-05, "loss": 0.18336861133575438, "step": 840 }, { "epoch": 0.08617903694926209, "grad_norm": 3.006169080734253, "learning_rate": 1.98356066831783e-05, "loss": 0.1852172613143921, "step": 850 }, { "epoch": 0.08719290797219459, "grad_norm": 3.960447311401367, "learning_rate": 1.982962451033956e-05, "loss": 0.1833302140235901, "step": 860 }, { "epoch": 0.08820677899512708, "grad_norm": 4.232405662536621, "learning_rate": 1.9823536364812875e-05, "loss": 0.17448734045028685, "step": 870 }, { "epoch": 0.08922065001805958, "grad_norm": 3.6619720458984375, "learning_rate": 1.981734231223425e-05, "loss": 0.16705615520477296, "step": 880 }, { "epoch": 0.09023452104099207, "grad_norm": 9.439841270446777, "learning_rate": 1.9811042419381444e-05, "loss": 0.18462334871292113, "step": 890 }, { "epoch": 0.09124839206392457, "grad_norm": 5.641659259796143, "learning_rate": 1.980463675417329e-05, "loss": 0.17779160737991334, "step": 900 }, { "epoch": 0.09226226308685706, "grad_norm": 5.287451267242432, "learning_rate": 1.9798125385668942e-05, "loss": 0.193203866481781, "step": 910 }, { "epoch": 0.09327613410978956, "grad_norm": 3.2003333568573, "learning_rate": 1.9791508384067138e-05, "loss": 0.18196712732315062, "step": 920 }, { "epoch": 0.09429000513272205, "grad_norm": 4.201811790466309, "learning_rate": 1.9784785820705435e-05, "loss": 0.19191545248031616, "step": 930 }, { "epoch": 0.09530387615565455, "grad_norm": 6.79796838760376, "learning_rate": 1.9777957768059456e-05, "loss": 0.18216307163238527, "step": 940 }, { "epoch": 0.09631774717858704, "grad_norm": 11.196202278137207, "learning_rate": 1.977102429974209e-05, "loss": 0.18780003786087035, "step": 950 }, { "epoch": 0.09733161820151955, "grad_norm": 4.867665767669678, "learning_rate": 1.9763985490502714e-05, "loss": 0.1607222318649292, "step": 960 }, { "epoch": 0.09834548922445203, "grad_norm": 4.449387073516846, "learning_rate": 1.9756841416226372e-05, "loss": 0.1907544493675232, "step": 970 }, { "epoch": 0.09935936024738452, "grad_norm": 4.246815204620361, "learning_rate": 1.9749592153932974e-05, "loss": 0.1871699571609497, "step": 980 }, { "epoch": 0.10037323127031703, "grad_norm": 6.666019916534424, "learning_rate": 1.9742237781776455e-05, "loss": 0.1773092269897461, "step": 990 }, { "epoch": 0.10138710229324951, "grad_norm": 3.4716596603393555, "learning_rate": 1.9734778379043923e-05, "loss": 0.19829654693603516, "step": 1000 }, { "epoch": 0.10240097331618202, "grad_norm": 4.001105308532715, "learning_rate": 1.9727214026154827e-05, "loss": 0.172219181060791, "step": 1010 }, { "epoch": 0.1034148443391145, "grad_norm": 5.595200061798096, "learning_rate": 1.9719544804660084e-05, "loss": 0.19067714214324952, "step": 1020 }, { "epoch": 0.10442871536204701, "grad_norm": 8.75537395477295, "learning_rate": 1.9711770797241174e-05, "loss": 0.19879807233810426, "step": 1030 }, { "epoch": 0.1054425863849795, "grad_norm": 4.097433090209961, "learning_rate": 1.9703892087709287e-05, "loss": 0.16209633350372316, "step": 1040 }, { "epoch": 0.106456457407912, "grad_norm": 2.8113269805908203, "learning_rate": 1.9695908761004392e-05, "loss": 0.17149388790130615, "step": 1050 }, { "epoch": 0.10747032843084449, "grad_norm": 3.1849982738494873, "learning_rate": 1.9687820903194335e-05, "loss": 0.15203946828842163, "step": 1060 }, { "epoch": 0.10848419945377699, "grad_norm": 3.0330982208251953, "learning_rate": 1.9679628601473905e-05, "loss": 0.20001499652862548, "step": 1070 }, { "epoch": 0.10949807047670948, "grad_norm": 6.562714099884033, "learning_rate": 1.967133194416389e-05, "loss": 0.18244638442993164, "step": 1080 }, { "epoch": 0.11051194149964198, "grad_norm": 6.726948261260986, "learning_rate": 1.9662931020710138e-05, "loss": 0.18674607276916505, "step": 1090 }, { "epoch": 0.11152581252257447, "grad_norm": 2.490032911300659, "learning_rate": 1.965442592168259e-05, "loss": 0.20217299461364746, "step": 1100 }, { "epoch": 0.11253968354550696, "grad_norm": 3.9653773307800293, "learning_rate": 1.964581673877428e-05, "loss": 0.173240327835083, "step": 1110 }, { "epoch": 0.11355355456843946, "grad_norm": 1.3954994678497314, "learning_rate": 1.9637103564800384e-05, "loss": 0.1743401288986206, "step": 1120 }, { "epoch": 0.11456742559137195, "grad_norm": 3.965667486190796, "learning_rate": 1.962828649369719e-05, "loss": 0.18351821899414061, "step": 1130 }, { "epoch": 0.11558129661430445, "grad_norm": 5.7327494621276855, "learning_rate": 1.96193656205211e-05, "loss": 0.18304920196533203, "step": 1140 }, { "epoch": 0.11659516763723694, "grad_norm": 2.4191904067993164, "learning_rate": 1.9610341041447595e-05, "loss": 0.16946609020233155, "step": 1150 }, { "epoch": 0.11760903866016945, "grad_norm": 2.5790843963623047, "learning_rate": 1.9601212853770214e-05, "loss": 0.17085678577423097, "step": 1160 }, { "epoch": 0.11862290968310193, "grad_norm": 7.138026714324951, "learning_rate": 1.959198115589949e-05, "loss": 0.20687730312347413, "step": 1170 }, { "epoch": 0.11963678070603444, "grad_norm": 2.9101834297180176, "learning_rate": 1.9582646047361888e-05, "loss": 0.16963810920715333, "step": 1180 }, { "epoch": 0.12065065172896693, "grad_norm": 1.8580502271652222, "learning_rate": 1.9573207628798747e-05, "loss": 0.17606964111328124, "step": 1190 }, { "epoch": 0.12166452275189943, "grad_norm": 2.0669047832489014, "learning_rate": 1.956366600196519e-05, "loss": 0.19582138061523438, "step": 1200 }, { "epoch": 0.12267839377483192, "grad_norm": 2.3031439781188965, "learning_rate": 1.9554021269729003e-05, "loss": 0.16855788230895996, "step": 1210 }, { "epoch": 0.12369226479776442, "grad_norm": 4.095479965209961, "learning_rate": 1.9544273536069573e-05, "loss": 0.17147037982940674, "step": 1220 }, { "epoch": 0.12470613582069691, "grad_norm": 5.445440769195557, "learning_rate": 1.9534422906076714e-05, "loss": 0.18768423795700073, "step": 1230 }, { "epoch": 0.1257200068436294, "grad_norm": 2.476550579071045, "learning_rate": 1.9524469485949586e-05, "loss": 0.18541808128356935, "step": 1240 }, { "epoch": 0.1267338778665619, "grad_norm": 4.499939441680908, "learning_rate": 1.9514413382995498e-05, "loss": 0.19210604429244996, "step": 1250 }, { "epoch": 0.1277477488894944, "grad_norm": 5.683699607849121, "learning_rate": 1.9504254705628806e-05, "loss": 0.1786515474319458, "step": 1260 }, { "epoch": 0.12876161991242688, "grad_norm": 2.499145269393921, "learning_rate": 1.9493993563369688e-05, "loss": 0.1961538553237915, "step": 1270 }, { "epoch": 0.1297754909353594, "grad_norm": 6.258482933044434, "learning_rate": 1.9483630066843005e-05, "loss": 0.17282800674438475, "step": 1280 }, { "epoch": 0.13078936195829188, "grad_norm": 2.9660556316375732, "learning_rate": 1.9473164327777095e-05, "loss": 0.16082063913345337, "step": 1290 }, { "epoch": 0.13180323298122437, "grad_norm": 4.807501792907715, "learning_rate": 1.9462596459002565e-05, "loss": 0.1840299129486084, "step": 1300 }, { "epoch": 0.13281710400415686, "grad_norm": 1.713944435119629, "learning_rate": 1.9451926574451074e-05, "loss": 0.16494261026382445, "step": 1310 }, { "epoch": 0.13383097502708938, "grad_norm": 2.8573474884033203, "learning_rate": 1.944115478915412e-05, "loss": 0.17116280794143676, "step": 1320 }, { "epoch": 0.13484484605002187, "grad_norm": 4.584635257720947, "learning_rate": 1.9430281219241767e-05, "loss": 0.17726129293441772, "step": 1330 }, { "epoch": 0.13585871707295435, "grad_norm": 1.5950831174850464, "learning_rate": 1.9419305981941436e-05, "loss": 0.18369890451431276, "step": 1340 }, { "epoch": 0.13687258809588684, "grad_norm": 3.890930414199829, "learning_rate": 1.94082291955766e-05, "loss": 0.17165107727050782, "step": 1350 }, { "epoch": 0.13788645911881936, "grad_norm": 3.8331499099731445, "learning_rate": 1.939705097956554e-05, "loss": 0.1729375720024109, "step": 1360 }, { "epoch": 0.13890033014175185, "grad_norm": 2.6135668754577637, "learning_rate": 1.9385771454420048e-05, "loss": 0.1837218165397644, "step": 1370 }, { "epoch": 0.13991420116468434, "grad_norm": 5.500953197479248, "learning_rate": 1.9374390741744107e-05, "loss": 0.1717670440673828, "step": 1380 }, { "epoch": 0.14092807218761683, "grad_norm": 6.852078914642334, "learning_rate": 1.9362908964232616e-05, "loss": 0.19674603939056395, "step": 1390 }, { "epoch": 0.14194194321054932, "grad_norm": 2.0808866024017334, "learning_rate": 1.9351326245670038e-05, "loss": 0.18058934211730956, "step": 1400 }, { "epoch": 0.14295581423348183, "grad_norm": 3.591856002807617, "learning_rate": 1.933964271092908e-05, "loss": 0.16820857524871827, "step": 1410 }, { "epoch": 0.14396968525641432, "grad_norm": 2.17380428314209, "learning_rate": 1.932785848596934e-05, "loss": 0.19835982322692872, "step": 1420 }, { "epoch": 0.1449835562793468, "grad_norm": 3.26033353805542, "learning_rate": 1.9315973697835966e-05, "loss": 0.1854245185852051, "step": 1430 }, { "epoch": 0.1459974273022793, "grad_norm": 2.5539560317993164, "learning_rate": 1.930398847465825e-05, "loss": 0.17299385070800782, "step": 1440 }, { "epoch": 0.14701129832521181, "grad_norm": 2.6579883098602295, "learning_rate": 1.9291902945648283e-05, "loss": 0.16804063320159912, "step": 1450 }, { "epoch": 0.1480251693481443, "grad_norm": 3.420166492462158, "learning_rate": 1.9279717241099554e-05, "loss": 0.19274635314941407, "step": 1460 }, { "epoch": 0.1490390403710768, "grad_norm": 1.551734209060669, "learning_rate": 1.9267431492385524e-05, "loss": 0.18196936845779418, "step": 1470 }, { "epoch": 0.15005291139400928, "grad_norm": 2.8620002269744873, "learning_rate": 1.925504583195823e-05, "loss": 0.17625780105590821, "step": 1480 }, { "epoch": 0.1510667824169418, "grad_norm": 2.510690927505493, "learning_rate": 1.924256039334686e-05, "loss": 0.1830660104751587, "step": 1490 }, { "epoch": 0.15208065343987429, "grad_norm": 2.772343158721924, "learning_rate": 1.9229975311156305e-05, "loss": 0.18406553268432618, "step": 1500 }, { "epoch": 0.15309452446280677, "grad_norm": 3.0003373622894287, "learning_rate": 1.9217290721065693e-05, "loss": 0.18678648471832277, "step": 1510 }, { "epoch": 0.15410839548573926, "grad_norm": 5.895961284637451, "learning_rate": 1.9204506759826957e-05, "loss": 0.175705623626709, "step": 1520 }, { "epoch": 0.15512226650867175, "grad_norm": 1.4063879251480103, "learning_rate": 1.9191623565263342e-05, "loss": 0.17632969617843627, "step": 1530 }, { "epoch": 0.15613613753160427, "grad_norm": 2.5371170043945312, "learning_rate": 1.9178641276267922e-05, "loss": 0.17874865531921386, "step": 1540 }, { "epoch": 0.15715000855453676, "grad_norm": 2.096163749694824, "learning_rate": 1.91655600328021e-05, "loss": 0.1774620532989502, "step": 1550 }, { "epoch": 0.15816387957746925, "grad_norm": 5.8426361083984375, "learning_rate": 1.91523799758941e-05, "loss": 0.1691678285598755, "step": 1560 }, { "epoch": 0.15917775060040174, "grad_norm": 5.135700225830078, "learning_rate": 1.9139101247637465e-05, "loss": 0.1727163553237915, "step": 1570 }, { "epoch": 0.16019162162333425, "grad_norm": 4.097633361816406, "learning_rate": 1.912572399118949e-05, "loss": 0.1739732503890991, "step": 1580 }, { "epoch": 0.16120549264626674, "grad_norm": 5.218711853027344, "learning_rate": 1.9112248350769704e-05, "loss": 0.19398387670516967, "step": 1590 }, { "epoch": 0.16221936366919923, "grad_norm": 3.547726631164551, "learning_rate": 1.909867447165831e-05, "loss": 0.17006454467773438, "step": 1600 }, { "epoch": 0.16323323469213172, "grad_norm": 1.7929472923278809, "learning_rate": 1.908500250019462e-05, "loss": 0.1753736138343811, "step": 1610 }, { "epoch": 0.16424710571506423, "grad_norm": 5.1425275802612305, "learning_rate": 1.9071232583775465e-05, "loss": 0.17141422033309936, "step": 1620 }, { "epoch": 0.16526097673799672, "grad_norm": 3.8209145069122314, "learning_rate": 1.9057364870853628e-05, "loss": 0.1549139976501465, "step": 1630 }, { "epoch": 0.1662748477609292, "grad_norm": 3.196357011795044, "learning_rate": 1.904339951093622e-05, "loss": 0.16936087608337402, "step": 1640 }, { "epoch": 0.1672887187838617, "grad_norm": 3.1214442253112793, "learning_rate": 1.902933665458309e-05, "loss": 0.1723296284675598, "step": 1650 }, { "epoch": 0.1683025898067942, "grad_norm": 3.691730499267578, "learning_rate": 1.901517645340518e-05, "loss": 0.18743395805358887, "step": 1660 }, { "epoch": 0.1693164608297267, "grad_norm": 5.661662578582764, "learning_rate": 1.900091906006291e-05, "loss": 0.19337629079818724, "step": 1670 }, { "epoch": 0.1703303318526592, "grad_norm": 2.461442470550537, "learning_rate": 1.8986564628264527e-05, "loss": 0.18197574615478515, "step": 1680 }, { "epoch": 0.17134420287559168, "grad_norm": 1.965740442276001, "learning_rate": 1.8972113312764432e-05, "loss": 0.1684643507003784, "step": 1690 }, { "epoch": 0.17235807389852417, "grad_norm": 2.316579580307007, "learning_rate": 1.895756526936153e-05, "loss": 0.16924898624420165, "step": 1700 }, { "epoch": 0.1733719449214567, "grad_norm": 5.933597564697266, "learning_rate": 1.8942920654897553e-05, "loss": 0.17893342971801757, "step": 1710 }, { "epoch": 0.17438581594438918, "grad_norm": 1.4985255002975464, "learning_rate": 1.8928179627255347e-05, "loss": 0.18385090827941894, "step": 1720 }, { "epoch": 0.17539968696732167, "grad_norm": 2.8257546424865723, "learning_rate": 1.891334234535719e-05, "loss": 0.18000102043151855, "step": 1730 }, { "epoch": 0.17641355799025416, "grad_norm": 2.7296268939971924, "learning_rate": 1.8898408969163078e-05, "loss": 0.16033592224121093, "step": 1740 }, { "epoch": 0.17742742901318667, "grad_norm": 2.8006818294525146, "learning_rate": 1.8883379659668987e-05, "loss": 0.1778416395187378, "step": 1750 }, { "epoch": 0.17844130003611916, "grad_norm": 4.948977947235107, "learning_rate": 1.8868254578905147e-05, "loss": 0.1838975191116333, "step": 1760 }, { "epoch": 0.17945517105905165, "grad_norm": 3.669171094894409, "learning_rate": 1.8853033889934293e-05, "loss": 0.15434110164642334, "step": 1770 }, { "epoch": 0.18046904208198414, "grad_norm": 2.7602691650390625, "learning_rate": 1.883771775684991e-05, "loss": 0.1627889633178711, "step": 1780 }, { "epoch": 0.18148291310491665, "grad_norm": 4.734504699707031, "learning_rate": 1.882230634477446e-05, "loss": 0.1870139241218567, "step": 1790 }, { "epoch": 0.18249678412784914, "grad_norm": 5.433671951293945, "learning_rate": 1.8806799819857598e-05, "loss": 0.1914489150047302, "step": 1800 }, { "epoch": 0.18351065515078163, "grad_norm": 2.174558639526367, "learning_rate": 1.8791198349274393e-05, "loss": 0.16090764999389648, "step": 1810 }, { "epoch": 0.18452452617371412, "grad_norm": 4.33502197265625, "learning_rate": 1.8775502101223516e-05, "loss": 0.18112454414367676, "step": 1820 }, { "epoch": 0.1855383971966466, "grad_norm": 3.1700215339660645, "learning_rate": 1.8759711244925424e-05, "loss": 0.17715892791748047, "step": 1830 }, { "epoch": 0.18655226821957913, "grad_norm": 3.118669033050537, "learning_rate": 1.874382595062055e-05, "loss": 0.15066628456115722, "step": 1840 }, { "epoch": 0.18756613924251161, "grad_norm": 2.261730432510376, "learning_rate": 1.8727846389567457e-05, "loss": 0.17650190591812134, "step": 1850 }, { "epoch": 0.1885800102654441, "grad_norm": 4.170563697814941, "learning_rate": 1.871177273404098e-05, "loss": 0.18047792911529542, "step": 1860 }, { "epoch": 0.1895938812883766, "grad_norm": 3.864933490753174, "learning_rate": 1.8695605157330398e-05, "loss": 0.1607324719429016, "step": 1870 }, { "epoch": 0.1906077523113091, "grad_norm": 4.362032413482666, "learning_rate": 1.8679343833737546e-05, "loss": 0.18659234046936035, "step": 1880 }, { "epoch": 0.1916216233342416, "grad_norm": 3.2020859718322754, "learning_rate": 1.8662988938574926e-05, "loss": 0.1789344310760498, "step": 1890 }, { "epoch": 0.1926354943571741, "grad_norm": 2.256551742553711, "learning_rate": 1.8646540648163853e-05, "loss": 0.16743795871734618, "step": 1900 }, { "epoch": 0.19364936538010658, "grad_norm": 3.2936689853668213, "learning_rate": 1.862999913983251e-05, "loss": 0.18322941064834594, "step": 1910 }, { "epoch": 0.1946632364030391, "grad_norm": 3.723992109298706, "learning_rate": 1.8613364591914073e-05, "loss": 0.16167209148406983, "step": 1920 }, { "epoch": 0.19567710742597158, "grad_norm": 2.9982783794403076, "learning_rate": 1.8596637183744762e-05, "loss": 0.164739990234375, "step": 1930 }, { "epoch": 0.19669097844890407, "grad_norm": 4.473212718963623, "learning_rate": 1.857981709566193e-05, "loss": 0.1815632939338684, "step": 1940 }, { "epoch": 0.19770484947183656, "grad_norm": 4.265384674072266, "learning_rate": 1.85629045090021e-05, "loss": 0.17324402332305908, "step": 1950 }, { "epoch": 0.19871872049476905, "grad_norm": 2.1402785778045654, "learning_rate": 1.854589960609902e-05, "loss": 0.14822609424591066, "step": 1960 }, { "epoch": 0.19973259151770156, "grad_norm": 3.212965250015259, "learning_rate": 1.8528802570281686e-05, "loss": 0.1958602786064148, "step": 1970 }, { "epoch": 0.20074646254063405, "grad_norm": 6.423832893371582, "learning_rate": 1.851161358587239e-05, "loss": 0.17371766567230223, "step": 1980 }, { "epoch": 0.20176033356356654, "grad_norm": 4.056947708129883, "learning_rate": 1.8494332838184707e-05, "loss": 0.1845381736755371, "step": 1990 }, { "epoch": 0.20277420458649903, "grad_norm": 3.3405537605285645, "learning_rate": 1.847696051352151e-05, "loss": 0.162131929397583, "step": 2000 }, { "epoch": 0.20378807560943155, "grad_norm": 2.152820348739624, "learning_rate": 1.8459496799172957e-05, "loss": 0.1634583830833435, "step": 2010 }, { "epoch": 0.20480194663236403, "grad_norm": 6.523380756378174, "learning_rate": 1.8441941883414475e-05, "loss": 0.19309370517730712, "step": 2020 }, { "epoch": 0.20581581765529652, "grad_norm": 2.923640727996826, "learning_rate": 1.8424295955504727e-05, "loss": 0.1593304991722107, "step": 2030 }, { "epoch": 0.206829688678229, "grad_norm": 3.1888983249664307, "learning_rate": 1.840655920568358e-05, "loss": 0.18574296236038207, "step": 2040 }, { "epoch": 0.20784355970116153, "grad_norm": 3.792942762374878, "learning_rate": 1.838873182517004e-05, "loss": 0.17394421100616456, "step": 2050 }, { "epoch": 0.20885743072409402, "grad_norm": 2.950453042984009, "learning_rate": 1.83708140061602e-05, "loss": 0.17850914001464843, "step": 2060 }, { "epoch": 0.2098713017470265, "grad_norm": 3.823256492614746, "learning_rate": 1.835280594182517e-05, "loss": 0.17043533325195312, "step": 2070 }, { "epoch": 0.210885172769959, "grad_norm": 2.383899211883545, "learning_rate": 1.833470782630898e-05, "loss": 0.1765291690826416, "step": 2080 }, { "epoch": 0.21189904379289148, "grad_norm": 4.657973289489746, "learning_rate": 1.831651985472651e-05, "loss": 0.17014216184616088, "step": 2090 }, { "epoch": 0.212912914815824, "grad_norm": 5.516736030578613, "learning_rate": 1.8298242223161362e-05, "loss": 0.18471114635467528, "step": 2100 }, { "epoch": 0.2139267858387565, "grad_norm": 3.056934118270874, "learning_rate": 1.827987512866377e-05, "loss": 0.1617884159088135, "step": 2110 }, { "epoch": 0.21494065686168898, "grad_norm": 3.377586841583252, "learning_rate": 1.826141876924845e-05, "loss": 0.1630806803703308, "step": 2120 }, { "epoch": 0.21595452788462147, "grad_norm": 6.6159820556640625, "learning_rate": 1.8242873343892494e-05, "loss": 0.19185912609100342, "step": 2130 }, { "epoch": 0.21696839890755398, "grad_norm": 4.104115962982178, "learning_rate": 1.8224239052533194e-05, "loss": 0.17364728450775146, "step": 2140 }, { "epoch": 0.21798226993048647, "grad_norm": 4.700338363647461, "learning_rate": 1.820551609606591e-05, "loss": 0.1730794906616211, "step": 2150 }, { "epoch": 0.21899614095341896, "grad_norm": 1.7849842309951782, "learning_rate": 1.81867046763419e-05, "loss": 0.18294339179992675, "step": 2160 }, { "epoch": 0.22001001197635145, "grad_norm": 3.57377028465271, "learning_rate": 1.816780499616613e-05, "loss": 0.17579636573791504, "step": 2170 }, { "epoch": 0.22102388299928397, "grad_norm": 3.1869847774505615, "learning_rate": 1.81488172592951e-05, "loss": 0.1603633165359497, "step": 2180 }, { "epoch": 0.22203775402221645, "grad_norm": 1.9520888328552246, "learning_rate": 1.812974167043465e-05, "loss": 0.17120773792266847, "step": 2190 }, { "epoch": 0.22305162504514894, "grad_norm": 2.619166851043701, "learning_rate": 1.8110578435237748e-05, "loss": 0.1723056435585022, "step": 2200 }, { "epoch": 0.22406549606808143, "grad_norm": 3.154212474822998, "learning_rate": 1.8091327760302267e-05, "loss": 0.18496744632720946, "step": 2210 }, { "epoch": 0.22507936709101392, "grad_norm": 10.639167785644531, "learning_rate": 1.8071989853168765e-05, "loss": 0.2187610387802124, "step": 2220 }, { "epoch": 0.22609323811394644, "grad_norm": 1.5708106756210327, "learning_rate": 1.8052564922318247e-05, "loss": 0.18046164512634277, "step": 2230 }, { "epoch": 0.22710710913687893, "grad_norm": 6.631937503814697, "learning_rate": 1.803305317716992e-05, "loss": 0.18331143856048585, "step": 2240 }, { "epoch": 0.22812098015981142, "grad_norm": 4.499408721923828, "learning_rate": 1.8013454828078925e-05, "loss": 0.17058002948760986, "step": 2250 }, { "epoch": 0.2291348511827439, "grad_norm": 2.3769052028656006, "learning_rate": 1.7993770086334082e-05, "loss": 0.16242716312408448, "step": 2260 }, { "epoch": 0.23014872220567642, "grad_norm": 4.84720516204834, "learning_rate": 1.7973999164155597e-05, "loss": 0.15320740938186644, "step": 2270 }, { "epoch": 0.2311625932286089, "grad_norm": 4.615383148193359, "learning_rate": 1.795414227469279e-05, "loss": 0.15784790515899658, "step": 2280 }, { "epoch": 0.2321764642515414, "grad_norm": 4.024315357208252, "learning_rate": 1.7934199632021795e-05, "loss": 0.174176025390625, "step": 2290 }, { "epoch": 0.2331903352744739, "grad_norm": 2.5450239181518555, "learning_rate": 1.7914171451143235e-05, "loss": 0.1777829647064209, "step": 2300 }, { "epoch": 0.2342042062974064, "grad_norm": 2.331733226776123, "learning_rate": 1.7894057947979923e-05, "loss": 0.16839792728424072, "step": 2310 }, { "epoch": 0.2352180773203389, "grad_norm": 3.7677884101867676, "learning_rate": 1.7873859339374528e-05, "loss": 0.18251365423202515, "step": 2320 }, { "epoch": 0.23623194834327138, "grad_norm": 6.367522239685059, "learning_rate": 1.7853575843087227e-05, "loss": 0.16918504238128662, "step": 2330 }, { "epoch": 0.23724581936620387, "grad_norm": 2.7424275875091553, "learning_rate": 1.7833207677793382e-05, "loss": 0.1714447021484375, "step": 2340 }, { "epoch": 0.23825969038913636, "grad_norm": 1.6316560506820679, "learning_rate": 1.7812755063081156e-05, "loss": 0.16259571313858032, "step": 2350 }, { "epoch": 0.23927356141206887, "grad_norm": 3.2430737018585205, "learning_rate": 1.7792218219449165e-05, "loss": 0.1629849910736084, "step": 2360 }, { "epoch": 0.24028743243500136, "grad_norm": 4.058960914611816, "learning_rate": 1.777159736830408e-05, "loss": 0.16414337158203124, "step": 2370 }, { "epoch": 0.24130130345793385, "grad_norm": 3.348741054534912, "learning_rate": 1.7750892731958268e-05, "loss": 0.16303287744522094, "step": 2380 }, { "epoch": 0.24231517448086634, "grad_norm": 3.7765989303588867, "learning_rate": 1.773010453362737e-05, "loss": 0.16987354755401612, "step": 2390 }, { "epoch": 0.24332904550379886, "grad_norm": 2.9127395153045654, "learning_rate": 1.770923299742791e-05, "loss": 0.16712394952774048, "step": 2400 }, { "epoch": 0.24434291652673135, "grad_norm": 2.096036434173584, "learning_rate": 1.768827834837487e-05, "loss": 0.1650109052658081, "step": 2410 }, { "epoch": 0.24535678754966384, "grad_norm": 3.6143109798431396, "learning_rate": 1.7667240812379266e-05, "loss": 0.14948115348815919, "step": 2420 }, { "epoch": 0.24637065857259632, "grad_norm": 3.8175220489501953, "learning_rate": 1.7646120616245724e-05, "loss": 0.1708467960357666, "step": 2430 }, { "epoch": 0.24738452959552884, "grad_norm": 2.960667610168457, "learning_rate": 1.7624917987670006e-05, "loss": 0.17868982553482055, "step": 2440 }, { "epoch": 0.24839840061846133, "grad_norm": 3.4045045375823975, "learning_rate": 1.7603633155236595e-05, "loss": 0.16515703201293946, "step": 2450 }, { "epoch": 0.24941227164139382, "grad_norm": 3.7934482097625732, "learning_rate": 1.7582266348416194e-05, "loss": 0.17828478813171386, "step": 2460 }, { "epoch": 0.25042614266432633, "grad_norm": 1.66954505443573, "learning_rate": 1.7560817797563275e-05, "loss": 0.1673508405685425, "step": 2470 }, { "epoch": 0.2514400136872588, "grad_norm": 3.0442333221435547, "learning_rate": 1.7539287733913592e-05, "loss": 0.17552052736282348, "step": 2480 }, { "epoch": 0.2524538847101913, "grad_norm": 3.615107536315918, "learning_rate": 1.7517676389581675e-05, "loss": 0.16708381175994874, "step": 2490 }, { "epoch": 0.2534677557331238, "grad_norm": 4.291594505310059, "learning_rate": 1.7495983997558342e-05, "loss": 0.1658422589302063, "step": 2500 }, { "epoch": 0.2544816267560563, "grad_norm": 3.294996976852417, "learning_rate": 1.7474210791708177e-05, "loss": 0.17452149391174315, "step": 2510 }, { "epoch": 0.2554954977789888, "grad_norm": 4.1840620040893555, "learning_rate": 1.7452357006767026e-05, "loss": 0.15803751945495606, "step": 2520 }, { "epoch": 0.25650936880192127, "grad_norm": 2.280287504196167, "learning_rate": 1.7430422878339443e-05, "loss": 0.16659927368164062, "step": 2530 }, { "epoch": 0.25752323982485376, "grad_norm": 1.893286108970642, "learning_rate": 1.740840864289616e-05, "loss": 0.16525471210479736, "step": 2540 }, { "epoch": 0.2585371108477863, "grad_norm": 2.255012273788452, "learning_rate": 1.7386314537771553e-05, "loss": 0.1610265254974365, "step": 2550 }, { "epoch": 0.2595509818707188, "grad_norm": 3.2813899517059326, "learning_rate": 1.736414080116105e-05, "loss": 0.18437739610671997, "step": 2560 }, { "epoch": 0.2605648528936513, "grad_norm": 3.1449568271636963, "learning_rate": 1.7341887672118596e-05, "loss": 0.16621153354644774, "step": 2570 }, { "epoch": 0.26157872391658377, "grad_norm": 2.8474228382110596, "learning_rate": 1.7319555390554054e-05, "loss": 0.19002647399902345, "step": 2580 }, { "epoch": 0.26259259493951626, "grad_norm": 2.9551820755004883, "learning_rate": 1.7297144197230637e-05, "loss": 0.17045096158981324, "step": 2590 }, { "epoch": 0.26360646596244874, "grad_norm": 3.1648895740509033, "learning_rate": 1.7274654333762284e-05, "loss": 0.15646036863327026, "step": 2600 }, { "epoch": 0.26462033698538123, "grad_norm": 3.878000259399414, "learning_rate": 1.7252086042611086e-05, "loss": 0.18378331661224365, "step": 2610 }, { "epoch": 0.2656342080083137, "grad_norm": 1.824897050857544, "learning_rate": 1.722943956708466e-05, "loss": 0.1644439935684204, "step": 2620 }, { "epoch": 0.2666480790312462, "grad_norm": 2.7875611782073975, "learning_rate": 1.720671515133352e-05, "loss": 0.15994951725006104, "step": 2630 }, { "epoch": 0.26766195005417875, "grad_norm": 3.973095655441284, "learning_rate": 1.7183913040348447e-05, "loss": 0.17455931901931762, "step": 2640 }, { "epoch": 0.26867582107711124, "grad_norm": 3.7022650241851807, "learning_rate": 1.716103347995785e-05, "loss": 0.16791633367538453, "step": 2650 }, { "epoch": 0.26968969210004373, "grad_norm": 1.8909295797348022, "learning_rate": 1.713807671682513e-05, "loss": 0.1528566837310791, "step": 2660 }, { "epoch": 0.2707035631229762, "grad_norm": 2.9110567569732666, "learning_rate": 1.711504299844599e-05, "loss": 0.16480039358139037, "step": 2670 }, { "epoch": 0.2717174341459087, "grad_norm": 1.5039809942245483, "learning_rate": 1.7091932573145798e-05, "loss": 0.17736439704895018, "step": 2680 }, { "epoch": 0.2727313051688412, "grad_norm": 5.211136341094971, "learning_rate": 1.706874569007688e-05, "loss": 0.16089887619018556, "step": 2690 }, { "epoch": 0.2737451761917737, "grad_norm": 1.6614924669265747, "learning_rate": 1.7045482599215856e-05, "loss": 0.1808913230895996, "step": 2700 }, { "epoch": 0.2747590472147062, "grad_norm": 3.6266918182373047, "learning_rate": 1.7022143551360947e-05, "loss": 0.15850976705551148, "step": 2710 }, { "epoch": 0.2757729182376387, "grad_norm": 3.7560982704162598, "learning_rate": 1.699872879812925e-05, "loss": 0.17678102254867553, "step": 2720 }, { "epoch": 0.2767867892605712, "grad_norm": 4.494512557983398, "learning_rate": 1.6975238591954048e-05, "loss": 0.18644462823867797, "step": 2730 }, { "epoch": 0.2778006602835037, "grad_norm": 3.6960413455963135, "learning_rate": 1.695167318608206e-05, "loss": 0.1740654706954956, "step": 2740 }, { "epoch": 0.2788145313064362, "grad_norm": 2.3725805282592773, "learning_rate": 1.6928032834570767e-05, "loss": 0.16882944107055664, "step": 2750 }, { "epoch": 0.2798284023293687, "grad_norm": 3.1700241565704346, "learning_rate": 1.690431779228559e-05, "loss": 0.17133153676986695, "step": 2760 }, { "epoch": 0.28084227335230116, "grad_norm": 5.983316898345947, "learning_rate": 1.6880528314897212e-05, "loss": 0.17113537788391114, "step": 2770 }, { "epoch": 0.28185614437523365, "grad_norm": 3.767108678817749, "learning_rate": 1.6856664658878797e-05, "loss": 0.16650331020355225, "step": 2780 }, { "epoch": 0.28287001539816614, "grad_norm": 3.8107872009277344, "learning_rate": 1.6832727081503227e-05, "loss": 0.1670964002609253, "step": 2790 }, { "epoch": 0.28388388642109863, "grad_norm": 2.564277410507202, "learning_rate": 1.6808715840840308e-05, "loss": 0.15051751136779784, "step": 2800 }, { "epoch": 0.2848977574440312, "grad_norm": 3.18742299079895, "learning_rate": 1.6784631195754027e-05, "loss": 0.17719967365264894, "step": 2810 }, { "epoch": 0.28591162846696366, "grad_norm": 2.504634141921997, "learning_rate": 1.6760473405899733e-05, "loss": 0.15467846393585205, "step": 2820 }, { "epoch": 0.28692549948989615, "grad_norm": 4.1661858558654785, "learning_rate": 1.673624273172134e-05, "loss": 0.1684788703918457, "step": 2830 }, { "epoch": 0.28793937051282864, "grad_norm": 2.6700143814086914, "learning_rate": 1.6711939434448537e-05, "loss": 0.1614150285720825, "step": 2840 }, { "epoch": 0.28895324153576113, "grad_norm": 5.17772912979126, "learning_rate": 1.6687563776093943e-05, "loss": 0.18243277072906494, "step": 2850 }, { "epoch": 0.2899671125586936, "grad_norm": 2.1896145343780518, "learning_rate": 1.6663116019450306e-05, "loss": 0.15487515926361084, "step": 2860 }, { "epoch": 0.2909809835816261, "grad_norm": 2.190063714981079, "learning_rate": 1.6638596428087662e-05, "loss": 0.1819887638092041, "step": 2870 }, { "epoch": 0.2919948546045586, "grad_norm": 3.5239744186401367, "learning_rate": 1.66140052663505e-05, "loss": 0.16605134010314943, "step": 2880 }, { "epoch": 0.29300872562749114, "grad_norm": 3.027571439743042, "learning_rate": 1.6589342799354895e-05, "loss": 0.1647227883338928, "step": 2890 }, { "epoch": 0.29402259665042363, "grad_norm": 2.200685739517212, "learning_rate": 1.6564609292985663e-05, "loss": 0.1741114854812622, "step": 2900 }, { "epoch": 0.2950364676733561, "grad_norm": 3.953510046005249, "learning_rate": 1.6539805013893493e-05, "loss": 0.1795579671859741, "step": 2910 }, { "epoch": 0.2960503386962886, "grad_norm": 5.749588489532471, "learning_rate": 1.6514930229492073e-05, "loss": 0.17417149543762206, "step": 2920 }, { "epoch": 0.2970642097192211, "grad_norm": 4.477001190185547, "learning_rate": 1.6489985207955207e-05, "loss": 0.16855165958404542, "step": 2930 }, { "epoch": 0.2980780807421536, "grad_norm": 3.1740078926086426, "learning_rate": 1.6464970218213912e-05, "loss": 0.17368559837341307, "step": 2940 }, { "epoch": 0.2990919517650861, "grad_norm": 2.8511335849761963, "learning_rate": 1.643988552995354e-05, "loss": 0.17551398277282715, "step": 2950 }, { "epoch": 0.30010582278801856, "grad_norm": 4.697011947631836, "learning_rate": 1.6414731413610856e-05, "loss": 0.15562703609466552, "step": 2960 }, { "epoch": 0.30111969381095105, "grad_norm": 2.0237319469451904, "learning_rate": 1.638950814037112e-05, "loss": 0.15849627256393434, "step": 2970 }, { "epoch": 0.3021335648338836, "grad_norm": 3.426208257675171, "learning_rate": 1.6364215982165178e-05, "loss": 0.16725579500198365, "step": 2980 }, { "epoch": 0.3031474358568161, "grad_norm": 1.9791367053985596, "learning_rate": 1.633885521166651e-05, "loss": 0.15686841011047364, "step": 2990 }, { "epoch": 0.30416130687974857, "grad_norm": 2.168856620788574, "learning_rate": 1.6313426102288315e-05, "loss": 0.16359760761260986, "step": 3000 }, { "epoch": 0.30517517790268106, "grad_norm": 4.8279008865356445, "learning_rate": 1.6287928928180544e-05, "loss": 0.1829742431640625, "step": 3010 }, { "epoch": 0.30618904892561355, "grad_norm": 1.6717419624328613, "learning_rate": 1.6262363964226943e-05, "loss": 0.15336575508117675, "step": 3020 }, { "epoch": 0.30720291994854604, "grad_norm": 4.453526973724365, "learning_rate": 1.623673148604211e-05, "loss": 0.15211749076843262, "step": 3030 }, { "epoch": 0.3082167909714785, "grad_norm": 3.1263859272003174, "learning_rate": 1.6211031769968503e-05, "loss": 0.16396337747573853, "step": 3040 }, { "epoch": 0.309230661994411, "grad_norm": 4.314755916595459, "learning_rate": 1.6185265093073468e-05, "loss": 0.16026805639266967, "step": 3050 }, { "epoch": 0.3102445330173435, "grad_norm": 2.9118921756744385, "learning_rate": 1.6159431733146255e-05, "loss": 0.16558549404144288, "step": 3060 }, { "epoch": 0.31125840404027605, "grad_norm": 2.630174398422241, "learning_rate": 1.613353196869502e-05, "loss": 0.17114678621292115, "step": 3070 }, { "epoch": 0.31227227506320854, "grad_norm": 2.8074722290039062, "learning_rate": 1.6107566078943818e-05, "loss": 0.17385644912719728, "step": 3080 }, { "epoch": 0.313286146086141, "grad_norm": 2.6046977043151855, "learning_rate": 1.608153434382961e-05, "loss": 0.1747976064682007, "step": 3090 }, { "epoch": 0.3143000171090735, "grad_norm": 1.5635873079299927, "learning_rate": 1.6055437043999215e-05, "loss": 0.15061103105545043, "step": 3100 }, { "epoch": 0.315313888132006, "grad_norm": 2.0186190605163574, "learning_rate": 1.6029274460806318e-05, "loss": 0.16707242727279664, "step": 3110 }, { "epoch": 0.3163277591549385, "grad_norm": 2.9526009559631348, "learning_rate": 1.6003046876308413e-05, "loss": 0.17062506675720215, "step": 3120 }, { "epoch": 0.317341630177871, "grad_norm": 3.8352062702178955, "learning_rate": 1.5976754573263767e-05, "loss": 0.14680745601654052, "step": 3130 }, { "epoch": 0.31835550120080347, "grad_norm": 2.669579267501831, "learning_rate": 1.5950397835128378e-05, "loss": 0.16509473323822021, "step": 3140 }, { "epoch": 0.319369372223736, "grad_norm": 3.117079257965088, "learning_rate": 1.5923976946052918e-05, "loss": 0.14459657669067383, "step": 3150 }, { "epoch": 0.3203832432466685, "grad_norm": 3.4453272819519043, "learning_rate": 1.5897492190879667e-05, "loss": 0.1696108341217041, "step": 3160 }, { "epoch": 0.321397114269601, "grad_norm": 3.299166679382324, "learning_rate": 1.5870943855139437e-05, "loss": 0.16380412578582765, "step": 3170 }, { "epoch": 0.3224109852925335, "grad_norm": 3.252805233001709, "learning_rate": 1.5844332225048496e-05, "loss": 0.1515345811843872, "step": 3180 }, { "epoch": 0.32342485631546597, "grad_norm": 4.289857387542725, "learning_rate": 1.5817657587505503e-05, "loss": 0.15754903554916383, "step": 3190 }, { "epoch": 0.32443872733839846, "grad_norm": 3.814866304397583, "learning_rate": 1.5790920230088375e-05, "loss": 0.16420915126800537, "step": 3200 }, { "epoch": 0.32545259836133095, "grad_norm": 5.513790130615234, "learning_rate": 1.576412044105122e-05, "loss": 0.1583461880683899, "step": 3210 }, { "epoch": 0.32646646938426344, "grad_norm": 4.3734893798828125, "learning_rate": 1.5737258509321224e-05, "loss": 0.16023926734924315, "step": 3220 }, { "epoch": 0.3274803404071959, "grad_norm": 5.198915481567383, "learning_rate": 1.5710334724495514e-05, "loss": 0.16364346742630004, "step": 3230 }, { "epoch": 0.32849421143012847, "grad_norm": 1.9343093633651733, "learning_rate": 1.5683349376838067e-05, "loss": 0.1668004274368286, "step": 3240 }, { "epoch": 0.32950808245306096, "grad_norm": 3.5685009956359863, "learning_rate": 1.565630275727656e-05, "loss": 0.15513916015625, "step": 3250 }, { "epoch": 0.33052195347599345, "grad_norm": 3.150174617767334, "learning_rate": 1.5629195157399236e-05, "loss": 0.17704081535339355, "step": 3260 }, { "epoch": 0.33153582449892594, "grad_norm": 5.449197292327881, "learning_rate": 1.5602026869451773e-05, "loss": 0.16605228185653687, "step": 3270 }, { "epoch": 0.3325496955218584, "grad_norm": 2.994229555130005, "learning_rate": 1.5574798186334112e-05, "loss": 0.1611935615539551, "step": 3280 }, { "epoch": 0.3335635665447909, "grad_norm": 2.707587480545044, "learning_rate": 1.5547509401597322e-05, "loss": 0.16586792469024658, "step": 3290 }, { "epoch": 0.3345774375677234, "grad_norm": 1.6283924579620361, "learning_rate": 1.552016080944042e-05, "loss": 0.1552098035812378, "step": 3300 }, { "epoch": 0.3355913085906559, "grad_norm": 2.158595085144043, "learning_rate": 1.5492752704707198e-05, "loss": 0.16123635768890382, "step": 3310 }, { "epoch": 0.3366051796135884, "grad_norm": 3.895207643508911, "learning_rate": 1.5465285382883065e-05, "loss": 0.17130764722824096, "step": 3320 }, { "epoch": 0.3376190506365209, "grad_norm": 3.9018619060516357, "learning_rate": 1.5437759140091827e-05, "loss": 0.17065932750701904, "step": 3330 }, { "epoch": 0.3386329216594534, "grad_norm": 2.6603269577026367, "learning_rate": 1.541017427309254e-05, "loss": 0.16542216539382934, "step": 3340 }, { "epoch": 0.3396467926823859, "grad_norm": 3.028719663619995, "learning_rate": 1.538253107927625e-05, "loss": 0.1445623517036438, "step": 3350 }, { "epoch": 0.3406606637053184, "grad_norm": 3.360687494277954, "learning_rate": 1.535482985666285e-05, "loss": 0.15849270820617675, "step": 3360 }, { "epoch": 0.3416745347282509, "grad_norm": 4.967510223388672, "learning_rate": 1.5327070903897832e-05, "loss": 0.17102608680725098, "step": 3370 }, { "epoch": 0.34268840575118337, "grad_norm": 5.302033424377441, "learning_rate": 1.529925452024907e-05, "loss": 0.16842081546783447, "step": 3380 }, { "epoch": 0.34370227677411586, "grad_norm": 4.134098529815674, "learning_rate": 1.5271381005603593e-05, "loss": 0.16714918613433838, "step": 3390 }, { "epoch": 0.34471614779704834, "grad_norm": 4.1611857414245605, "learning_rate": 1.5243450660464368e-05, "loss": 0.14777036905288696, "step": 3400 }, { "epoch": 0.3457300188199809, "grad_norm": 3.727551221847534, "learning_rate": 1.5215463785947036e-05, "loss": 0.1692489743232727, "step": 3410 }, { "epoch": 0.3467438898429134, "grad_norm": 2.284158945083618, "learning_rate": 1.518742068377669e-05, "loss": 0.15674326419830323, "step": 3420 }, { "epoch": 0.34775776086584587, "grad_norm": 2.5479772090911865, "learning_rate": 1.5159321656284602e-05, "loss": 0.16180909872055055, "step": 3430 }, { "epoch": 0.34877163188877836, "grad_norm": 2.6171133518218994, "learning_rate": 1.5131167006404978e-05, "loss": 0.1712204933166504, "step": 3440 }, { "epoch": 0.34978550291171084, "grad_norm": 5.78970193862915, "learning_rate": 1.5102957037671689e-05, "loss": 0.15158032178878783, "step": 3450 }, { "epoch": 0.35079937393464333, "grad_norm": 2.1643099784851074, "learning_rate": 1.5074692054214977e-05, "loss": 0.16188063621520996, "step": 3460 }, { "epoch": 0.3518132449575758, "grad_norm": 2.289182186126709, "learning_rate": 1.504637236075822e-05, "loss": 0.1482093334197998, "step": 3470 }, { "epoch": 0.3528271159805083, "grad_norm": 2.8001837730407715, "learning_rate": 1.5017998262614609e-05, "loss": 0.1648741126060486, "step": 3480 }, { "epoch": 0.3538409870034408, "grad_norm": 1.7575448751449585, "learning_rate": 1.498957006568386e-05, "loss": 0.15495569705963136, "step": 3490 }, { "epoch": 0.35485485802637334, "grad_norm": 5.339682579040527, "learning_rate": 1.4961088076448947e-05, "loss": 0.15666577816009522, "step": 3500 }, { "epoch": 0.35586872904930583, "grad_norm": 2.778641700744629, "learning_rate": 1.4932552601972763e-05, "loss": 0.1729661226272583, "step": 3510 }, { "epoch": 0.3568826000722383, "grad_norm": 5.243635177612305, "learning_rate": 1.490396394989482e-05, "loss": 0.16724030971527098, "step": 3520 }, { "epoch": 0.3578964710951708, "grad_norm": 2.3540139198303223, "learning_rate": 1.4875322428427943e-05, "loss": 0.1518498182296753, "step": 3530 }, { "epoch": 0.3589103421181033, "grad_norm": 2.871760368347168, "learning_rate": 1.4846628346354934e-05, "loss": 0.1551913619041443, "step": 3540 }, { "epoch": 0.3599242131410358, "grad_norm": 4.326233386993408, "learning_rate": 1.4817882013025253e-05, "loss": 0.17081117630004883, "step": 3550 }, { "epoch": 0.3609380841639683, "grad_norm": 3.475688934326172, "learning_rate": 1.478908373835167e-05, "loss": 0.16411010026931763, "step": 3560 }, { "epoch": 0.36195195518690076, "grad_norm": 2.3227949142456055, "learning_rate": 1.476023383280694e-05, "loss": 0.16322510242462157, "step": 3570 }, { "epoch": 0.3629658262098333, "grad_norm": 3.9025697708129883, "learning_rate": 1.473133260742045e-05, "loss": 0.16093249320983888, "step": 3580 }, { "epoch": 0.3639796972327658, "grad_norm": 3.557671308517456, "learning_rate": 1.4702380373774852e-05, "loss": 0.16035478115081786, "step": 3590 }, { "epoch": 0.3649935682556983, "grad_norm": 4.1850152015686035, "learning_rate": 1.4673377444002724e-05, "loss": 0.14025766849517823, "step": 3600 }, { "epoch": 0.3660074392786308, "grad_norm": 5.60207462310791, "learning_rate": 1.4644324130783197e-05, "loss": 0.15384942293167114, "step": 3610 }, { "epoch": 0.36702131030156326, "grad_norm": 2.0321578979492188, "learning_rate": 1.4615220747338574e-05, "loss": 0.17537057399749756, "step": 3620 }, { "epoch": 0.36803518132449575, "grad_norm": 3.0883278846740723, "learning_rate": 1.4586067607430976e-05, "loss": 0.16596145629882814, "step": 3630 }, { "epoch": 0.36904905234742824, "grad_norm": 3.983988046646118, "learning_rate": 1.4556865025358942e-05, "loss": 0.17367626428604127, "step": 3640 }, { "epoch": 0.37006292337036073, "grad_norm": 3.1725988388061523, "learning_rate": 1.4527613315954035e-05, "loss": 0.16191341876983642, "step": 3650 }, { "epoch": 0.3710767943932932, "grad_norm": 3.5166831016540527, "learning_rate": 1.4498312794577465e-05, "loss": 0.1514730930328369, "step": 3660 }, { "epoch": 0.37209066541622576, "grad_norm": 2.1764700412750244, "learning_rate": 1.4468963777116686e-05, "loss": 0.18575730323791503, "step": 3670 }, { "epoch": 0.37310453643915825, "grad_norm": 3.7307302951812744, "learning_rate": 1.4439566579981979e-05, "loss": 0.172182297706604, "step": 3680 }, { "epoch": 0.37411840746209074, "grad_norm": 2.1338560581207275, "learning_rate": 1.4410121520103045e-05, "loss": 0.1528468370437622, "step": 3690 }, { "epoch": 0.37513227848502323, "grad_norm": 1.922220230102539, "learning_rate": 1.4380628914925597e-05, "loss": 0.14168074131011962, "step": 3700 }, { "epoch": 0.3761461495079557, "grad_norm": 4.436015605926514, "learning_rate": 1.4351089082407929e-05, "loss": 0.15495772361755372, "step": 3710 }, { "epoch": 0.3771600205308882, "grad_norm": 2.9600489139556885, "learning_rate": 1.4321502341017496e-05, "loss": 0.1647663116455078, "step": 3720 }, { "epoch": 0.3781738915538207, "grad_norm": 3.425632953643799, "learning_rate": 1.4291869009727463e-05, "loss": 0.15413867235183715, "step": 3730 }, { "epoch": 0.3791877625767532, "grad_norm": 3.6940057277679443, "learning_rate": 1.4262189408013294e-05, "loss": 0.15335288047790527, "step": 3740 }, { "epoch": 0.3802016335996857, "grad_norm": 3.9406473636627197, "learning_rate": 1.4232463855849275e-05, "loss": 0.17590076923370362, "step": 3750 }, { "epoch": 0.3812155046226182, "grad_norm": 1.737818717956543, "learning_rate": 1.4202692673705097e-05, "loss": 0.17051633596420288, "step": 3760 }, { "epoch": 0.3822293756455507, "grad_norm": 2.410871982574463, "learning_rate": 1.4172876182542372e-05, "loss": 0.15879977941513063, "step": 3770 }, { "epoch": 0.3832432466684832, "grad_norm": 3.0874032974243164, "learning_rate": 1.41430147038112e-05, "loss": 0.15428333282470702, "step": 3780 }, { "epoch": 0.3842571176914157, "grad_norm": 2.6549570560455322, "learning_rate": 1.411310855944668e-05, "loss": 0.1682439088821411, "step": 3790 }, { "epoch": 0.3852709887143482, "grad_norm": 2.574401617050171, "learning_rate": 1.4083158071865451e-05, "loss": 0.17337888479232788, "step": 3800 }, { "epoch": 0.38628485973728066, "grad_norm": 1.6368606090545654, "learning_rate": 1.4053163563962215e-05, "loss": 0.15535343885421754, "step": 3810 }, { "epoch": 0.38729873076021315, "grad_norm": 2.9492557048797607, "learning_rate": 1.4023125359106253e-05, "loss": 0.16198270320892333, "step": 3820 }, { "epoch": 0.38831260178314564, "grad_norm": 3.550856828689575, "learning_rate": 1.3993043781137945e-05, "loss": 0.1635347604751587, "step": 3830 }, { "epoch": 0.3893264728060782, "grad_norm": 1.8895564079284668, "learning_rate": 1.3962919154365273e-05, "loss": 0.17106428146362304, "step": 3840 }, { "epoch": 0.39034034382901067, "grad_norm": 2.0988729000091553, "learning_rate": 1.393275180356032e-05, "loss": 0.16662064790725709, "step": 3850 }, { "epoch": 0.39135421485194316, "grad_norm": 4.325247764587402, "learning_rate": 1.3902542053955781e-05, "loss": 0.16669061183929443, "step": 3860 }, { "epoch": 0.39236808587487565, "grad_norm": 2.293415069580078, "learning_rate": 1.387229023124145e-05, "loss": 0.1596634268760681, "step": 3870 }, { "epoch": 0.39338195689780814, "grad_norm": 3.042531728744507, "learning_rate": 1.3841996661560706e-05, "loss": 0.1546694278717041, "step": 3880 }, { "epoch": 0.3943958279207406, "grad_norm": 2.8624520301818848, "learning_rate": 1.3811661671507004e-05, "loss": 0.1437408447265625, "step": 3890 }, { "epoch": 0.3954096989436731, "grad_norm": 4.7996063232421875, "learning_rate": 1.3781285588120343e-05, "loss": 0.15341840982437133, "step": 3900 }, { "epoch": 0.3964235699666056, "grad_norm": 1.92435622215271, "learning_rate": 1.3750868738883755e-05, "loss": 0.15680136680603027, "step": 3910 }, { "epoch": 0.3974374409895381, "grad_norm": 4.228550910949707, "learning_rate": 1.3720411451719762e-05, "loss": 0.16492834091186523, "step": 3920 }, { "epoch": 0.39845131201247064, "grad_norm": 2.2239789962768555, "learning_rate": 1.3689914054986849e-05, "loss": 0.16755027770996095, "step": 3930 }, { "epoch": 0.3994651830354031, "grad_norm": 3.439840078353882, "learning_rate": 1.3659376877475916e-05, "loss": 0.16153541803359986, "step": 3940 }, { "epoch": 0.4004790540583356, "grad_norm": 5.044020652770996, "learning_rate": 1.3628800248406738e-05, "loss": 0.15570731163024903, "step": 3950 }, { "epoch": 0.4014929250812681, "grad_norm": 3.3132734298706055, "learning_rate": 1.3598184497424416e-05, "loss": 0.15284444093704225, "step": 3960 }, { "epoch": 0.4025067961042006, "grad_norm": 4.20509672164917, "learning_rate": 1.3567529954595826e-05, "loss": 0.16215853691101073, "step": 3970 }, { "epoch": 0.4035206671271331, "grad_norm": 2.8658134937286377, "learning_rate": 1.3536836950406057e-05, "loss": 0.14811460971832274, "step": 3980 }, { "epoch": 0.40453453815006557, "grad_norm": 3.4629766941070557, "learning_rate": 1.3506105815754836e-05, "loss": 0.15595074892044067, "step": 3990 }, { "epoch": 0.40554840917299806, "grad_norm": 5.029688835144043, "learning_rate": 1.3475336881952988e-05, "loss": 0.1867917537689209, "step": 4000 }, { "epoch": 0.40656228019593055, "grad_norm": 1.7216333150863647, "learning_rate": 1.3444530480718838e-05, "loss": 0.16517989635467528, "step": 4010 }, { "epoch": 0.4075761512188631, "grad_norm": 1.7058788537979126, "learning_rate": 1.3413686944174655e-05, "loss": 0.14283134937286376, "step": 4020 }, { "epoch": 0.4085900222417956, "grad_norm": 2.5572407245635986, "learning_rate": 1.3382806604843053e-05, "loss": 0.1676084280014038, "step": 4030 }, { "epoch": 0.40960389326472807, "grad_norm": 2.84143328666687, "learning_rate": 1.3351889795643423e-05, "loss": 0.14269261360168456, "step": 4040 }, { "epoch": 0.41061776428766056, "grad_norm": 5.240346908569336, "learning_rate": 1.3320936849888322e-05, "loss": 0.16012916564941407, "step": 4050 }, { "epoch": 0.41163163531059305, "grad_norm": 3.042839527130127, "learning_rate": 1.3289948101279912e-05, "loss": 0.16951757669448853, "step": 4060 }, { "epoch": 0.41264550633352554, "grad_norm": 4.746918678283691, "learning_rate": 1.3258923883906337e-05, "loss": 0.16574358940124512, "step": 4070 }, { "epoch": 0.413659377356458, "grad_norm": 16.666746139526367, "learning_rate": 1.3227864532238113e-05, "loss": 0.1630464553833008, "step": 4080 }, { "epoch": 0.4146732483793905, "grad_norm": 1.7099074125289917, "learning_rate": 1.3196770381124557e-05, "loss": 0.16200587749481202, "step": 4090 }, { "epoch": 0.41568711940232306, "grad_norm": 3.2498834133148193, "learning_rate": 1.3165641765790153e-05, "loss": 0.14905338287353515, "step": 4100 }, { "epoch": 0.41670099042525555, "grad_norm": 1.6342414617538452, "learning_rate": 1.3134479021830938e-05, "loss": 0.16522879600524903, "step": 4110 }, { "epoch": 0.41771486144818804, "grad_norm": 5.103591442108154, "learning_rate": 1.3103282485210882e-05, "loss": 0.1464191198348999, "step": 4120 }, { "epoch": 0.4187287324711205, "grad_norm": 2.021399736404419, "learning_rate": 1.3072052492258286e-05, "loss": 0.1474842071533203, "step": 4130 }, { "epoch": 0.419742603494053, "grad_norm": 4.256580829620361, "learning_rate": 1.3040789379662131e-05, "loss": 0.8005413055419922, "step": 4140 }, { "epoch": 0.4207564745169855, "grad_norm": 2.147343397140503, "learning_rate": 1.3009493484468464e-05, "loss": 0.220647931098938, "step": 4150 }, { "epoch": 0.421770345539918, "grad_norm": 2.797369956970215, "learning_rate": 1.2978165144076757e-05, "loss": 0.19730994701385499, "step": 4160 }, { "epoch": 0.4227842165628505, "grad_norm": 5.991499900817871, "learning_rate": 1.2946804696236277e-05, "loss": 0.1811044692993164, "step": 4170 }, { "epoch": 0.42379808758578297, "grad_norm": 2.705954074859619, "learning_rate": 1.2915412479042436e-05, "loss": 0.16742756366729736, "step": 4180 }, { "epoch": 0.4248119586087155, "grad_norm": 2.1189286708831787, "learning_rate": 1.2883988830933148e-05, "loss": 0.17728855609893798, "step": 4190 }, { "epoch": 0.425825829631648, "grad_norm": 2.882768392562866, "learning_rate": 1.2852534090685184e-05, "loss": 0.16739712953567504, "step": 4200 }, { "epoch": 0.4268397006545805, "grad_norm": 2.8499884605407715, "learning_rate": 1.282104859741052e-05, "loss": 0.179804790019989, "step": 4210 }, { "epoch": 0.427853571677513, "grad_norm": 3.890644073486328, "learning_rate": 1.2789532690552673e-05, "loss": 0.181143856048584, "step": 4220 }, { "epoch": 0.42886744270044547, "grad_norm": 7.017698764801025, "learning_rate": 1.2757986709883059e-05, "loss": 0.17041939496994019, "step": 4230 }, { "epoch": 0.42988131372337796, "grad_norm": 4.85646915435791, "learning_rate": 1.2726410995497304e-05, "loss": 0.17119736671447755, "step": 4240 }, { "epoch": 0.43089518474631044, "grad_norm": 3.541126251220703, "learning_rate": 1.2694805887811601e-05, "loss": 0.14441940784454346, "step": 4250 }, { "epoch": 0.43190905576924293, "grad_norm": 2.114220142364502, "learning_rate": 1.2663171727559025e-05, "loss": 0.16273953914642333, "step": 4260 }, { "epoch": 0.4329229267921755, "grad_norm": 2.0488624572753906, "learning_rate": 1.2631508855785877e-05, "loss": 0.16749272346496583, "step": 4270 }, { "epoch": 0.43393679781510797, "grad_norm": 3.8056087493896484, "learning_rate": 1.2599817613847973e-05, "loss": 0.1808352589607239, "step": 4280 }, { "epoch": 0.43495066883804046, "grad_norm": 2.6753997802734375, "learning_rate": 1.2568098343407007e-05, "loss": 0.15607202053070068, "step": 4290 }, { "epoch": 0.43596453986097294, "grad_norm": 4.669034481048584, "learning_rate": 1.2536351386426844e-05, "loss": 0.16458351612091066, "step": 4300 }, { "epoch": 0.43697841088390543, "grad_norm": 3.434441089630127, "learning_rate": 1.2504577085169826e-05, "loss": 0.17450275421142578, "step": 4310 }, { "epoch": 0.4379922819068379, "grad_norm": 3.5918631553649902, "learning_rate": 1.2472775782193099e-05, "loss": 0.1677042007446289, "step": 4320 }, { "epoch": 0.4390061529297704, "grad_norm": 3.2805838584899902, "learning_rate": 1.2440947820344916e-05, "loss": 0.16388581991195678, "step": 4330 }, { "epoch": 0.4400200239527029, "grad_norm": 2.3625571727752686, "learning_rate": 1.2409093542760925e-05, "loss": 0.16004600524902343, "step": 4340 }, { "epoch": 0.4410338949756354, "grad_norm": 5.255631446838379, "learning_rate": 1.2377213292860506e-05, "loss": 0.18639111518859863, "step": 4350 }, { "epoch": 0.44204776599856793, "grad_norm": 4.589694023132324, "learning_rate": 1.2345307414343021e-05, "loss": 0.15423507690429689, "step": 4360 }, { "epoch": 0.4430616370215004, "grad_norm": 3.5224647521972656, "learning_rate": 1.2313376251184148e-05, "loss": 0.15711262226104736, "step": 4370 }, { "epoch": 0.4440755080444329, "grad_norm": 2.493422269821167, "learning_rate": 1.2281420147632148e-05, "loss": 0.15215140581130981, "step": 4380 }, { "epoch": 0.4450893790673654, "grad_norm": 4.003855228424072, "learning_rate": 1.2249439448204172e-05, "loss": 0.14569275379180907, "step": 4390 }, { "epoch": 0.4461032500902979, "grad_norm": 2.374422311782837, "learning_rate": 1.2217434497682537e-05, "loss": 0.15659582614898682, "step": 4400 }, { "epoch": 0.4471171211132304, "grad_norm": 4.314223766326904, "learning_rate": 1.2185405641110997e-05, "loss": 0.16847187280654907, "step": 4410 }, { "epoch": 0.44813099213616286, "grad_norm": 3.2189884185791016, "learning_rate": 1.2153353223791049e-05, "loss": 0.15337512493133545, "step": 4420 }, { "epoch": 0.44914486315909535, "grad_norm": 4.424521446228027, "learning_rate": 1.2121277591278197e-05, "loss": 0.17151007652282715, "step": 4430 }, { "epoch": 0.45015873418202784, "grad_norm": 4.244558334350586, "learning_rate": 1.2089179089378222e-05, "loss": 0.16283468008041382, "step": 4440 }, { "epoch": 0.4511726052049604, "grad_norm": 4.890291690826416, "learning_rate": 1.2057058064143456e-05, "loss": 0.1505662202835083, "step": 4450 }, { "epoch": 0.4521864762278929, "grad_norm": 6.568395614624023, "learning_rate": 1.2024914861869064e-05, "loss": 0.16301509141921997, "step": 4460 }, { "epoch": 0.45320034725082536, "grad_norm": 2.213886022567749, "learning_rate": 1.199274982908929e-05, "loss": 0.1570921540260315, "step": 4470 }, { "epoch": 0.45421421827375785, "grad_norm": 3.4985079765319824, "learning_rate": 1.196056331257374e-05, "loss": 0.14683055877685547, "step": 4480 }, { "epoch": 0.45522808929669034, "grad_norm": 4.464450359344482, "learning_rate": 1.1928355659323627e-05, "loss": 0.15698071718215942, "step": 4490 }, { "epoch": 0.45624196031962283, "grad_norm": 2.735539197921753, "learning_rate": 1.1896127216568047e-05, "loss": 0.16567755937576295, "step": 4500 }, { "epoch": 0.4572558313425553, "grad_norm": 3.6638119220733643, "learning_rate": 1.1863878331760217e-05, "loss": 0.16200257539749147, "step": 4510 }, { "epoch": 0.4582697023654878, "grad_norm": 2.0567920207977295, "learning_rate": 1.183160935257375e-05, "loss": 0.1612597942352295, "step": 4520 }, { "epoch": 0.45928357338842035, "grad_norm": 2.721597194671631, "learning_rate": 1.1799320626898883e-05, "loss": 0.14253367185592652, "step": 4530 }, { "epoch": 0.46029744441135284, "grad_norm": 3.8951659202575684, "learning_rate": 1.1767012502838746e-05, "loss": 0.1533884048461914, "step": 4540 }, { "epoch": 0.46131131543428533, "grad_norm": 4.668922424316406, "learning_rate": 1.1734685328705604e-05, "loss": 0.16304969787597656, "step": 4550 }, { "epoch": 0.4623251864572178, "grad_norm": 1.9902985095977783, "learning_rate": 1.17023394530171e-05, "loss": 0.17659995555877686, "step": 4560 }, { "epoch": 0.4633390574801503, "grad_norm": 3.0388569831848145, "learning_rate": 1.1669975224492486e-05, "loss": 0.15591001510620117, "step": 4570 }, { "epoch": 0.4643529285030828, "grad_norm": 3.9241950511932373, "learning_rate": 1.1637592992048888e-05, "loss": 0.14760582447052, "step": 4580 }, { "epoch": 0.4653667995260153, "grad_norm": 4.700350284576416, "learning_rate": 1.160519310479753e-05, "loss": 0.1657216429710388, "step": 4590 }, { "epoch": 0.4663806705489478, "grad_norm": 1.5661981105804443, "learning_rate": 1.157277591203996e-05, "loss": 0.14892029762268066, "step": 4600 }, { "epoch": 0.46739454157188026, "grad_norm": 3.7274115085601807, "learning_rate": 1.1540341763264314e-05, "loss": 0.15452950000762938, "step": 4610 }, { "epoch": 0.4684084125948128, "grad_norm": 2.4442498683929443, "learning_rate": 1.1507891008141512e-05, "loss": 0.14732084274291993, "step": 4620 }, { "epoch": 0.4694222836177453, "grad_norm": 2.054442882537842, "learning_rate": 1.147542399652152e-05, "loss": 0.15829651355743407, "step": 4630 }, { "epoch": 0.4704361546406778, "grad_norm": 2.530618906021118, "learning_rate": 1.1442941078429554e-05, "loss": 0.14043886661529542, "step": 4640 }, { "epoch": 0.4714500256636103, "grad_norm": 2.979612350463867, "learning_rate": 1.141044260406233e-05, "loss": 0.14941320419311524, "step": 4650 }, { "epoch": 0.47246389668654276, "grad_norm": 5.417270183563232, "learning_rate": 1.1377928923784261e-05, "loss": 0.14762667417526246, "step": 4660 }, { "epoch": 0.47347776770947525, "grad_norm": 2.8944361209869385, "learning_rate": 1.1345400388123698e-05, "loss": 0.14285141229629517, "step": 4670 }, { "epoch": 0.47449163873240774, "grad_norm": 2.6330506801605225, "learning_rate": 1.1312857347769153e-05, "loss": 0.14520628452301027, "step": 4680 }, { "epoch": 0.4755055097553402, "grad_norm": 3.5171680450439453, "learning_rate": 1.128030015356551e-05, "loss": 0.15183353424072266, "step": 4690 }, { "epoch": 0.4765193807782727, "grad_norm": 2.504711866378784, "learning_rate": 1.1247729156510245e-05, "loss": 0.1480923891067505, "step": 4700 }, { "epoch": 0.47753325180120526, "grad_norm": 2.411503791809082, "learning_rate": 1.1215144707749635e-05, "loss": 0.15148638486862182, "step": 4710 }, { "epoch": 0.47854712282413775, "grad_norm": 2.9303362369537354, "learning_rate": 1.1182547158574988e-05, "loss": 0.13714178800582885, "step": 4720 }, { "epoch": 0.47956099384707024, "grad_norm": 2.6882307529449463, "learning_rate": 1.1149936860418846e-05, "loss": 0.15939137935638428, "step": 4730 }, { "epoch": 0.4805748648700027, "grad_norm": 1.568287968635559, "learning_rate": 1.1117314164851191e-05, "loss": 0.15600802898406982, "step": 4740 }, { "epoch": 0.4815887358929352, "grad_norm": 4.266833782196045, "learning_rate": 1.1084679423575666e-05, "loss": 0.1449056625366211, "step": 4750 }, { "epoch": 0.4826026069158677, "grad_norm": 2.4706196784973145, "learning_rate": 1.1052032988425778e-05, "loss": 0.13973610401153563, "step": 4760 }, { "epoch": 0.4836164779388002, "grad_norm": 5.350572109222412, "learning_rate": 1.1019375211361104e-05, "loss": 0.13630318641662598, "step": 4770 }, { "epoch": 0.4846303489617327, "grad_norm": 1.948779582977295, "learning_rate": 1.0986706444463496e-05, "loss": 0.1569026827812195, "step": 4780 }, { "epoch": 0.4856442199846652, "grad_norm": 3.5858521461486816, "learning_rate": 1.0954027039933288e-05, "loss": 0.13608676195144653, "step": 4790 }, { "epoch": 0.4866580910075977, "grad_norm": 5.797330379486084, "learning_rate": 1.09213373500855e-05, "loss": 0.15110974311828612, "step": 4800 }, { "epoch": 0.4876719620305302, "grad_norm": 3.1263742446899414, "learning_rate": 1.0888637727346032e-05, "loss": 0.16119924783706666, "step": 4810 }, { "epoch": 0.4886858330534627, "grad_norm": 5.44146728515625, "learning_rate": 1.0855928524247884e-05, "loss": 0.1551775813102722, "step": 4820 }, { "epoch": 0.4896997040763952, "grad_norm": 2.4344494342803955, "learning_rate": 1.0823210093427318e-05, "loss": 0.13722879886627198, "step": 4830 }, { "epoch": 0.49071357509932767, "grad_norm": 3.227388858795166, "learning_rate": 1.07904827876201e-05, "loss": 0.15810341835021974, "step": 4840 }, { "epoch": 0.49172744612226016, "grad_norm": 3.8198630809783936, "learning_rate": 1.0757746959657666e-05, "loss": 0.15472298860549927, "step": 4850 }, { "epoch": 0.49274131714519265, "grad_norm": 4.4296722412109375, "learning_rate": 1.072500296246334e-05, "loss": 0.14232156276702881, "step": 4860 }, { "epoch": 0.49375518816812514, "grad_norm": 4.410543441772461, "learning_rate": 1.06922511490485e-05, "loss": 0.1395261526107788, "step": 4870 }, { "epoch": 0.4947690591910577, "grad_norm": 2.991595506668091, "learning_rate": 1.0659491872508807e-05, "loss": 0.1488985538482666, "step": 4880 }, { "epoch": 0.49578293021399017, "grad_norm": 6.084048748016357, "learning_rate": 1.0626725486020374e-05, "loss": 0.14909031391143798, "step": 4890 }, { "epoch": 0.49679680123692266, "grad_norm": 3.5507917404174805, "learning_rate": 1.059395234283597e-05, "loss": 0.14481102228164672, "step": 4900 }, { "epoch": 0.49781067225985515, "grad_norm": 3.4617278575897217, "learning_rate": 1.0561172796281196e-05, "loss": 0.15721278190612792, "step": 4910 }, { "epoch": 0.49882454328278764, "grad_norm": 2.597158193588257, "learning_rate": 1.0528387199750706e-05, "loss": 0.155995512008667, "step": 4920 }, { "epoch": 0.4998384143057201, "grad_norm": 3.1649508476257324, "learning_rate": 1.0495595906704365e-05, "loss": 0.1395760416984558, "step": 4930 }, { "epoch": 0.5008522853286527, "grad_norm": 4.421586990356445, "learning_rate": 1.0462799270663457e-05, "loss": 0.1321110725402832, "step": 4940 }, { "epoch": 0.5018661563515852, "grad_norm": 2.7889621257781982, "learning_rate": 1.0429997645206865e-05, "loss": 0.1393531084060669, "step": 4950 }, { "epoch": 0.5028800273745176, "grad_norm": 2.6249351501464844, "learning_rate": 1.0397191383967267e-05, "loss": 0.13782973289489747, "step": 4960 }, { "epoch": 0.5038938983974501, "grad_norm": 4.488835334777832, "learning_rate": 1.0364380840627315e-05, "loss": 0.15089335441589355, "step": 4970 }, { "epoch": 0.5049077694203826, "grad_norm": 3.698000431060791, "learning_rate": 1.033156636891583e-05, "loss": 0.15579121112823485, "step": 4980 }, { "epoch": 0.5059216404433151, "grad_norm": 3.6457438468933105, "learning_rate": 1.0298748322603982e-05, "loss": 0.14652674198150634, "step": 4990 }, { "epoch": 0.5069355114662476, "grad_norm": 3.910425901412964, "learning_rate": 1.0265927055501476e-05, "loss": 0.15874855518341063, "step": 5000 }, { "epoch": 0.5079493824891801, "grad_norm": 1.9521701335906982, "learning_rate": 1.023310292145275e-05, "loss": 0.13689208030700684, "step": 5010 }, { "epoch": 0.5089632535121126, "grad_norm": 4.236190319061279, "learning_rate": 1.020027627433314e-05, "loss": 0.1461883306503296, "step": 5020 }, { "epoch": 0.5099771245350451, "grad_norm": 4.491451740264893, "learning_rate": 1.0167447468045083e-05, "loss": 0.14187023639678956, "step": 5030 }, { "epoch": 0.5109909955579776, "grad_norm": 3.9442343711853027, "learning_rate": 1.0134616856514282e-05, "loss": 0.15189744234085084, "step": 5040 }, { "epoch": 0.51200486658091, "grad_norm": 3.2438037395477295, "learning_rate": 1.0101784793685914e-05, "loss": 0.15441333055496215, "step": 5050 }, { "epoch": 0.5130187376038425, "grad_norm": 4.154975414276123, "learning_rate": 1.0068951633520802e-05, "loss": 0.13725154399871825, "step": 5060 }, { "epoch": 0.514032608626775, "grad_norm": 3.065091133117676, "learning_rate": 1.0036117729991595e-05, "loss": 0.14095354080200195, "step": 5070 }, { "epoch": 0.5150464796497075, "grad_norm": 4.373802185058594, "learning_rate": 1.0003283437078951e-05, "loss": 0.15148417949676513, "step": 5080 }, { "epoch": 0.5160603506726401, "grad_norm": 3.4716527462005615, "learning_rate": 9.970449108767742e-06, "loss": 0.14391247034072877, "step": 5090 }, { "epoch": 0.5170742216955726, "grad_norm": 4.481513023376465, "learning_rate": 9.937615099043206e-06, "loss": 0.1348968267440796, "step": 5100 }, { "epoch": 0.5180880927185051, "grad_norm": 4.418787002563477, "learning_rate": 9.904781761887147e-06, "loss": 0.15071940422058105, "step": 5110 }, { "epoch": 0.5191019637414376, "grad_norm": 3.084641218185425, "learning_rate": 9.871949451274137e-06, "loss": 0.1396837830543518, "step": 5120 }, { "epoch": 0.5201158347643701, "grad_norm": 2.188647508621216, "learning_rate": 9.839118521167656e-06, "loss": 0.1415063500404358, "step": 5130 }, { "epoch": 0.5211297057873026, "grad_norm": 3.328238010406494, "learning_rate": 9.80628932551631e-06, "loss": 0.14530320167541505, "step": 5140 }, { "epoch": 0.522143576810235, "grad_norm": 3.7415549755096436, "learning_rate": 9.773462218250014e-06, "loss": 0.13564271926879884, "step": 5150 }, { "epoch": 0.5231574478331675, "grad_norm": 4.298794269561768, "learning_rate": 9.740637553276162e-06, "loss": 0.15186307430267335, "step": 5160 }, { "epoch": 0.5241713188561, "grad_norm": 4.741273403167725, "learning_rate": 9.707815684475817e-06, "loss": 0.13670222759246825, "step": 5170 }, { "epoch": 0.5251851898790325, "grad_norm": 4.237489223480225, "learning_rate": 9.674996965699895e-06, "loss": 0.14122264385223388, "step": 5180 }, { "epoch": 0.526199060901965, "grad_norm": 4.871568202972412, "learning_rate": 9.642181750765354e-06, "loss": 0.1460057020187378, "step": 5190 }, { "epoch": 0.5272129319248975, "grad_norm": 2.8628692626953125, "learning_rate": 9.60937039345138e-06, "loss": 0.1560580015182495, "step": 5200 }, { "epoch": 0.52822680294783, "grad_norm": 2.6409449577331543, "learning_rate": 9.576563247495566e-06, "loss": 0.13821094036102294, "step": 5210 }, { "epoch": 0.5292406739707625, "grad_norm": 2.54032301902771, "learning_rate": 9.543760666590105e-06, "loss": 0.13847777843475342, "step": 5220 }, { "epoch": 0.530254544993695, "grad_norm": 4.0968756675720215, "learning_rate": 9.510963004377974e-06, "loss": 0.14252309799194335, "step": 5230 }, { "epoch": 0.5312684160166274, "grad_norm": 3.352979898452759, "learning_rate": 9.478170614449114e-06, "loss": 0.15437358617782593, "step": 5240 }, { "epoch": 0.5322822870395599, "grad_norm": 2.457838296890259, "learning_rate": 9.445383850336648e-06, "loss": 0.1365670680999756, "step": 5250 }, { "epoch": 0.5332961580624924, "grad_norm": 5.031740188598633, "learning_rate": 9.412603065513021e-06, "loss": 0.14756405353546143, "step": 5260 }, { "epoch": 0.534310029085425, "grad_norm": 2.9358203411102295, "learning_rate": 9.379828613386225e-06, "loss": 0.15488749742507935, "step": 5270 }, { "epoch": 0.5353239001083575, "grad_norm": 2.8792667388916016, "learning_rate": 9.347060847295991e-06, "loss": 0.1457419753074646, "step": 5280 }, { "epoch": 0.53633777113129, "grad_norm": 2.5209250450134277, "learning_rate": 9.314300120509952e-06, "loss": 0.1503441333770752, "step": 5290 }, { "epoch": 0.5373516421542225, "grad_norm": 2.267275094985962, "learning_rate": 9.281546786219861e-06, "loss": 0.14230962991714477, "step": 5300 }, { "epoch": 0.538365513177155, "grad_norm": 2.942389726638794, "learning_rate": 9.24880119753777e-06, "loss": 0.13648947477340698, "step": 5310 }, { "epoch": 0.5393793842000875, "grad_norm": 6.164488792419434, "learning_rate": 9.216063707492218e-06, "loss": 0.14450565576553345, "step": 5320 }, { "epoch": 0.54039325522302, "grad_norm": 3.196079969406128, "learning_rate": 9.183334669024449e-06, "loss": 0.1446017861366272, "step": 5330 }, { "epoch": 0.5414071262459524, "grad_norm": 3.482872724533081, "learning_rate": 9.150614434984578e-06, "loss": 0.14867767095565795, "step": 5340 }, { "epoch": 0.5424209972688849, "grad_norm": 3.8511879444122314, "learning_rate": 9.117903358127801e-06, "loss": 0.13554527759552001, "step": 5350 }, { "epoch": 0.5434348682918174, "grad_norm": 3.799161434173584, "learning_rate": 9.085201791110602e-06, "loss": 0.12787235975265504, "step": 5360 }, { "epoch": 0.5444487393147499, "grad_norm": 3.2492034435272217, "learning_rate": 9.052510086486922e-06, "loss": 0.14436739683151245, "step": 5370 }, { "epoch": 0.5454626103376824, "grad_norm": 2.5733280181884766, "learning_rate": 9.019828596704394e-06, "loss": 0.14406318664550782, "step": 5380 }, { "epoch": 0.5464764813606149, "grad_norm": 3.124138832092285, "learning_rate": 8.987157674100519e-06, "loss": 0.13797028064727784, "step": 5390 }, { "epoch": 0.5474903523835474, "grad_norm": 2.821145534515381, "learning_rate": 8.954497670898858e-06, "loss": 0.12771683931350708, "step": 5400 }, { "epoch": 0.5485042234064799, "grad_norm": 4.111342430114746, "learning_rate": 8.92184893920528e-06, "loss": 0.13545081615447999, "step": 5410 }, { "epoch": 0.5495180944294124, "grad_norm": 2.5815536975860596, "learning_rate": 8.889211831004112e-06, "loss": 0.14496612548828125, "step": 5420 }, { "epoch": 0.5505319654523448, "grad_norm": 3.7316558361053467, "learning_rate": 8.856586698154382e-06, "loss": 0.1404496908187866, "step": 5430 }, { "epoch": 0.5515458364752774, "grad_norm": 3.4450063705444336, "learning_rate": 8.823973892386007e-06, "loss": 0.1601710081100464, "step": 5440 }, { "epoch": 0.5525597074982099, "grad_norm": 3.6289408206939697, "learning_rate": 8.791373765296006e-06, "loss": 0.1428842306137085, "step": 5450 }, { "epoch": 0.5535735785211424, "grad_norm": 2.369802236557007, "learning_rate": 8.758786668344711e-06, "loss": 0.1454448699951172, "step": 5460 }, { "epoch": 0.5545874495440749, "grad_norm": 3.1093103885650635, "learning_rate": 8.726212952851978e-06, "loss": 0.15182974338531494, "step": 5470 }, { "epoch": 0.5556013205670074, "grad_norm": 2.7169063091278076, "learning_rate": 8.693652969993396e-06, "loss": 0.13570104837417601, "step": 5480 }, { "epoch": 0.5566151915899399, "grad_norm": 2.834397554397583, "learning_rate": 8.661107070796504e-06, "loss": 0.1441279411315918, "step": 5490 }, { "epoch": 0.5576290626128724, "grad_norm": 3.3638999462127686, "learning_rate": 8.628575606137005e-06, "loss": 0.15007853507995605, "step": 5500 }, { "epoch": 0.5586429336358049, "grad_norm": 4.294882297515869, "learning_rate": 8.59605892673499e-06, "loss": 0.14955049753189087, "step": 5510 }, { "epoch": 0.5596568046587374, "grad_norm": 3.9297008514404297, "learning_rate": 8.563557383151143e-06, "loss": 0.13754193782806395, "step": 5520 }, { "epoch": 0.5606706756816698, "grad_norm": 3.7196121215820312, "learning_rate": 8.531071325782965e-06, "loss": 0.14874330759048462, "step": 5530 }, { "epoch": 0.5616845467046023, "grad_norm": 2.6168320178985596, "learning_rate": 8.49860110486102e-06, "loss": 0.1275538444519043, "step": 5540 }, { "epoch": 0.5626984177275348, "grad_norm": 3.650357484817505, "learning_rate": 8.466147070445123e-06, "loss": 0.14097096920013427, "step": 5550 }, { "epoch": 0.5637122887504673, "grad_norm": 4.3712544441223145, "learning_rate": 8.433709572420586e-06, "loss": 0.13109488487243653, "step": 5560 }, { "epoch": 0.5647261597733998, "grad_norm": 3.4395973682403564, "learning_rate": 8.40128896049445e-06, "loss": 0.13488094806671141, "step": 5570 }, { "epoch": 0.5657400307963323, "grad_norm": 3.0373072624206543, "learning_rate": 8.368885584191698e-06, "loss": 0.12681009769439697, "step": 5580 }, { "epoch": 0.5667539018192648, "grad_norm": 2.564316511154175, "learning_rate": 8.336499792851505e-06, "loss": 0.1347282648086548, "step": 5590 }, { "epoch": 0.5677677728421973, "grad_norm": 3.0410120487213135, "learning_rate": 8.304131935623461e-06, "loss": 0.14376875162124633, "step": 5600 }, { "epoch": 0.5687816438651299, "grad_norm": 2.969306707382202, "learning_rate": 8.271782361463806e-06, "loss": 0.13774323463439941, "step": 5610 }, { "epoch": 0.5697955148880623, "grad_norm": 2.771578311920166, "learning_rate": 8.239451419131676e-06, "loss": 0.13872116804122925, "step": 5620 }, { "epoch": 0.5708093859109948, "grad_norm": 4.540144920349121, "learning_rate": 8.207139457185328e-06, "loss": 0.13571165800094603, "step": 5630 }, { "epoch": 0.5718232569339273, "grad_norm": 5.296921730041504, "learning_rate": 8.174846823978412e-06, "loss": 0.14394196271896362, "step": 5640 }, { "epoch": 0.5728371279568598, "grad_norm": 2.6158390045166016, "learning_rate": 8.142573867656182e-06, "loss": 0.126594078540802, "step": 5650 }, { "epoch": 0.5738509989797923, "grad_norm": 3.791353464126587, "learning_rate": 8.110320936151746e-06, "loss": 0.12088764905929565, "step": 5660 }, { "epoch": 0.5748648700027248, "grad_norm": 3.763542652130127, "learning_rate": 8.078088377182352e-06, "loss": 0.11011152267456055, "step": 5670 }, { "epoch": 0.5758787410256573, "grad_norm": 2.562742233276367, "learning_rate": 8.045876538245595e-06, "loss": 0.1275660753250122, "step": 5680 }, { "epoch": 0.5768926120485898, "grad_norm": 2.973264217376709, "learning_rate": 8.013685766615687e-06, "loss": 0.13500432968139647, "step": 5690 }, { "epoch": 0.5779064830715223, "grad_norm": 3.8001034259796143, "learning_rate": 7.981516409339726e-06, "loss": 0.14278759956359863, "step": 5700 }, { "epoch": 0.5789203540944547, "grad_norm": 2.986140251159668, "learning_rate": 7.94936881323393e-06, "loss": 0.13425228595733643, "step": 5710 }, { "epoch": 0.5799342251173872, "grad_norm": 4.187904357910156, "learning_rate": 7.917243324879924e-06, "loss": 0.14542546272277831, "step": 5720 }, { "epoch": 0.5809480961403197, "grad_norm": 2.965221405029297, "learning_rate": 7.88514029062098e-06, "loss": 0.13223426342010497, "step": 5730 }, { "epoch": 0.5819619671632522, "grad_norm": 2.9894657135009766, "learning_rate": 7.853060056558294e-06, "loss": 0.13083949089050292, "step": 5740 }, { "epoch": 0.5829758381861847, "grad_norm": 3.6800031661987305, "learning_rate": 7.821002968547266e-06, "loss": 0.14690288305282592, "step": 5750 }, { "epoch": 0.5839897092091172, "grad_norm": 2.6211352348327637, "learning_rate": 7.788969372193744e-06, "loss": 0.1286099672317505, "step": 5760 }, { "epoch": 0.5850035802320497, "grad_norm": 3.4995956420898438, "learning_rate": 7.75695961285032e-06, "loss": 0.11990203857421874, "step": 5770 }, { "epoch": 0.5860174512549823, "grad_norm": 2.8010613918304443, "learning_rate": 7.724974035612611e-06, "loss": 0.12358839511871338, "step": 5780 }, { "epoch": 0.5870313222779148, "grad_norm": 2.9989500045776367, "learning_rate": 7.693012985315503e-06, "loss": 0.1592903733253479, "step": 5790 }, { "epoch": 0.5880451933008473, "grad_norm": 4.760120868682861, "learning_rate": 7.661076806529486e-06, "loss": 0.12027475833892823, "step": 5800 }, { "epoch": 0.5890590643237797, "grad_norm": 2.7913382053375244, "learning_rate": 7.629165843556896e-06, "loss": 0.13846228122711182, "step": 5810 }, { "epoch": 0.5900729353467122, "grad_norm": 2.9448747634887695, "learning_rate": 7.597280440428216e-06, "loss": 0.13670837879180908, "step": 5820 }, { "epoch": 0.5910868063696447, "grad_norm": 3.403294086456299, "learning_rate": 7.565420940898381e-06, "loss": 0.11734638214111329, "step": 5830 }, { "epoch": 0.5921006773925772, "grad_norm": 4.822943687438965, "learning_rate": 7.5335876884430495e-06, "loss": 0.1402226448059082, "step": 5840 }, { "epoch": 0.5931145484155097, "grad_norm": 4.141275405883789, "learning_rate": 7.501781026254922e-06, "loss": 0.1380077362060547, "step": 5850 }, { "epoch": 0.5941284194384422, "grad_norm": 3.604555368423462, "learning_rate": 7.4700012972400224e-06, "loss": 0.1374759078025818, "step": 5860 }, { "epoch": 0.5951422904613747, "grad_norm": 3.7606914043426514, "learning_rate": 7.438248844014011e-06, "loss": 0.13837997913360595, "step": 5870 }, { "epoch": 0.5961561614843072, "grad_norm": 3.9170055389404297, "learning_rate": 7.4065240088984944e-06, "loss": 0.12297825813293457, "step": 5880 }, { "epoch": 0.5971700325072397, "grad_norm": 3.956040859222412, "learning_rate": 7.3748271339173224e-06, "loss": 0.1335007905960083, "step": 5890 }, { "epoch": 0.5981839035301721, "grad_norm": 4.96895694732666, "learning_rate": 7.34315856079291e-06, "loss": 0.14864261150360109, "step": 5900 }, { "epoch": 0.5991977745531046, "grad_norm": 3.3130221366882324, "learning_rate": 7.311518630942562e-06, "loss": 0.14004024267196655, "step": 5910 }, { "epoch": 0.6002116455760371, "grad_norm": 3.5170059204101562, "learning_rate": 7.279907685474759e-06, "loss": 0.1398717761039734, "step": 5920 }, { "epoch": 0.6012255165989696, "grad_norm": 3.654240846633911, "learning_rate": 7.248326065185527e-06, "loss": 0.14414597749710084, "step": 5930 }, { "epoch": 0.6022393876219021, "grad_norm": 2.9058890342712402, "learning_rate": 7.216774110554724e-06, "loss": 0.12478528022766114, "step": 5940 }, { "epoch": 0.6032532586448346, "grad_norm": 4.1255645751953125, "learning_rate": 7.185252161742385e-06, "loss": 0.13454605340957643, "step": 5950 }, { "epoch": 0.6042671296677672, "grad_norm": 3.821460247039795, "learning_rate": 7.153760558585059e-06, "loss": 0.11141924858093262, "step": 5960 }, { "epoch": 0.6052810006906997, "grad_norm": 3.8224868774414062, "learning_rate": 7.122299640592135e-06, "loss": 0.13664045333862304, "step": 5970 }, { "epoch": 0.6062948717136322, "grad_norm": 3.1847822666168213, "learning_rate": 7.090869746942191e-06, "loss": 0.12485500574111938, "step": 5980 }, { "epoch": 0.6073087427365647, "grad_norm": 3.8259971141815186, "learning_rate": 7.05947121647933e-06, "loss": 0.12685630321502686, "step": 5990 }, { "epoch": 0.6083226137594971, "grad_norm": 4.594860553741455, "learning_rate": 7.028104387709531e-06, "loss": 0.12300195693969726, "step": 6000 }, { "epoch": 0.6093364847824296, "grad_norm": 3.250913381576538, "learning_rate": 6.996769598797001e-06, "loss": 0.12160563468933105, "step": 6010 }, { "epoch": 0.6103503558053621, "grad_norm": 3.399765968322754, "learning_rate": 6.965467187560524e-06, "loss": 0.1239201545715332, "step": 6020 }, { "epoch": 0.6113642268282946, "grad_norm": 4.258700370788574, "learning_rate": 6.934197491469818e-06, "loss": 0.11449973583221436, "step": 6030 }, { "epoch": 0.6123780978512271, "grad_norm": 4.170248985290527, "learning_rate": 6.902960847641915e-06, "loss": 0.13275628089904784, "step": 6040 }, { "epoch": 0.6133919688741596, "grad_norm": 3.2121856212615967, "learning_rate": 6.8717575928374915e-06, "loss": 0.13948097229003906, "step": 6050 }, { "epoch": 0.6144058398970921, "grad_norm": 3.9944827556610107, "learning_rate": 6.840588063457278e-06, "loss": 0.12332876920700073, "step": 6060 }, { "epoch": 0.6154197109200246, "grad_norm": 2.638037919998169, "learning_rate": 6.809452595538403e-06, "loss": 0.12610797882080077, "step": 6070 }, { "epoch": 0.616433581942957, "grad_norm": 4.084270477294922, "learning_rate": 6.778351524750777e-06, "loss": 0.11982829570770263, "step": 6080 }, { "epoch": 0.6174474529658895, "grad_norm": 3.526817560195923, "learning_rate": 6.747285186393488e-06, "loss": 0.13258544206619263, "step": 6090 }, { "epoch": 0.618461323988822, "grad_norm": 6.293968200683594, "learning_rate": 6.716253915391167e-06, "loss": 0.14342122077941893, "step": 6100 }, { "epoch": 0.6194751950117545, "grad_norm": 3.05780029296875, "learning_rate": 6.685258046290381e-06, "loss": 0.12762250900268554, "step": 6110 }, { "epoch": 0.620489066034687, "grad_norm": 3.7242510318756104, "learning_rate": 6.654297913256047e-06, "loss": 0.14077589511871338, "step": 6120 }, { "epoch": 0.6215029370576196, "grad_norm": 3.328178644180298, "learning_rate": 6.623373850067794e-06, "loss": 0.14289050102233886, "step": 6130 }, { "epoch": 0.6225168080805521, "grad_norm": 6.281567573547363, "learning_rate": 6.592486190116405e-06, "loss": 0.13564225435256957, "step": 6140 }, { "epoch": 0.6235306791034846, "grad_norm": 4.925808429718018, "learning_rate": 6.561635266400181e-06, "loss": 0.11572608947753907, "step": 6150 }, { "epoch": 0.6245445501264171, "grad_norm": 4.832618236541748, "learning_rate": 6.5308214115213785e-06, "loss": 0.13204646110534668, "step": 6160 }, { "epoch": 0.6255584211493496, "grad_norm": 3.894721746444702, "learning_rate": 6.500044957682627e-06, "loss": 0.13178708553314208, "step": 6170 }, { "epoch": 0.626572292172282, "grad_norm": 3.004978895187378, "learning_rate": 6.469306236683324e-06, "loss": 0.1195718765258789, "step": 6180 }, { "epoch": 0.6275861631952145, "grad_norm": 3.0532383918762207, "learning_rate": 6.438605579916078e-06, "loss": 0.1321779251098633, "step": 6190 }, { "epoch": 0.628600034218147, "grad_norm": 4.953327655792236, "learning_rate": 6.4079433183631255e-06, "loss": 0.12331172227859497, "step": 6200 }, { "epoch": 0.6296139052410795, "grad_norm": 4.188135147094727, "learning_rate": 6.377319782592767e-06, "loss": 0.12372381687164306, "step": 6210 }, { "epoch": 0.630627776264012, "grad_norm": 3.8247809410095215, "learning_rate": 6.346735302755805e-06, "loss": 0.13184754848480223, "step": 6220 }, { "epoch": 0.6316416472869445, "grad_norm": 4.289982795715332, "learning_rate": 6.316190208581979e-06, "loss": 0.12009499073028565, "step": 6230 }, { "epoch": 0.632655518309877, "grad_norm": 3.1224775314331055, "learning_rate": 6.285684829376413e-06, "loss": 0.13072072267532348, "step": 6240 }, { "epoch": 0.6336693893328095, "grad_norm": 4.3607940673828125, "learning_rate": 6.25521949401607e-06, "loss": 0.12437069416046143, "step": 6250 }, { "epoch": 0.634683260355742, "grad_norm": 3.8495798110961914, "learning_rate": 6.2247945309461955e-06, "loss": 0.12434567213058471, "step": 6260 }, { "epoch": 0.6356971313786745, "grad_norm": 3.8541038036346436, "learning_rate": 6.194410268176796e-06, "loss": 0.12682929039001464, "step": 6270 }, { "epoch": 0.6367110024016069, "grad_norm": 3.505500078201294, "learning_rate": 6.164067033279073e-06, "loss": 0.12982414960861205, "step": 6280 }, { "epoch": 0.6377248734245394, "grad_norm": 2.8907277584075928, "learning_rate": 6.133765153381918e-06, "loss": 0.13704932928085328, "step": 6290 }, { "epoch": 0.638738744447472, "grad_norm": 3.957736015319824, "learning_rate": 6.103504955168382e-06, "loss": 0.11856443881988525, "step": 6300 }, { "epoch": 0.6397526154704045, "grad_norm": 5.244137763977051, "learning_rate": 6.07328676487214e-06, "loss": 0.13109784126281737, "step": 6310 }, { "epoch": 0.640766486493337, "grad_norm": 3.7115590572357178, "learning_rate": 6.043110908273973e-06, "loss": 0.12056677341461182, "step": 6320 }, { "epoch": 0.6417803575162695, "grad_norm": 7.7946953773498535, "learning_rate": 6.012977710698288e-06, "loss": 0.1168285608291626, "step": 6330 }, { "epoch": 0.642794228539202, "grad_norm": 4.533967971801758, "learning_rate": 5.982887497009566e-06, "loss": 0.12961047887802124, "step": 6340 }, { "epoch": 0.6438080995621345, "grad_norm": 4.069812297821045, "learning_rate": 5.9528405916088926e-06, "loss": 0.11906790733337402, "step": 6350 }, { "epoch": 0.644821970585067, "grad_norm": 5.429006576538086, "learning_rate": 5.9228373184304455e-06, "loss": 0.12392604351043701, "step": 6360 }, { "epoch": 0.6458358416079995, "grad_norm": 4.561014652252197, "learning_rate": 5.892878000938001e-06, "loss": 0.11974753141403198, "step": 6370 }, { "epoch": 0.6468497126309319, "grad_norm": 3.429579019546509, "learning_rate": 5.86296296212146e-06, "loss": 0.1196049690246582, "step": 6380 }, { "epoch": 0.6478635836538644, "grad_norm": 4.106597423553467, "learning_rate": 5.833092524493349e-06, "loss": 0.11336252689361573, "step": 6390 }, { "epoch": 0.6488774546767969, "grad_norm": 4.329062461853027, "learning_rate": 5.80326701008536e-06, "loss": 0.12404506206512451, "step": 6400 }, { "epoch": 0.6498913256997294, "grad_norm": 3.3768856525421143, "learning_rate": 5.773486740444862e-06, "loss": 0.11663469076156616, "step": 6410 }, { "epoch": 0.6509051967226619, "grad_norm": 3.3827834129333496, "learning_rate": 5.743752036631443e-06, "loss": 0.13179609775543213, "step": 6420 }, { "epoch": 0.6519190677455944, "grad_norm": 4.544255256652832, "learning_rate": 5.714063219213456e-06, "loss": 0.10733531713485718, "step": 6430 }, { "epoch": 0.6529329387685269, "grad_norm": 3.6513891220092773, "learning_rate": 5.684420608264549e-06, "loss": 0.13008267879486085, "step": 6440 }, { "epoch": 0.6539468097914594, "grad_norm": 3.53348445892334, "learning_rate": 5.654824523360219e-06, "loss": 0.11955926418304444, "step": 6450 }, { "epoch": 0.6549606808143918, "grad_norm": 3.4195852279663086, "learning_rate": 5.625275283574372e-06, "loss": 0.12314375638961791, "step": 6460 }, { "epoch": 0.6559745518373244, "grad_norm": 3.829285144805908, "learning_rate": 5.595773207475872e-06, "loss": 0.12133796215057373, "step": 6470 }, { "epoch": 0.6569884228602569, "grad_norm": 3.82688570022583, "learning_rate": 5.566318613125128e-06, "loss": 0.12166956663131714, "step": 6480 }, { "epoch": 0.6580022938831894, "grad_norm": 4.3651299476623535, "learning_rate": 5.536911818070636e-06, "loss": 0.12522552013397217, "step": 6490 }, { "epoch": 0.6590161649061219, "grad_norm": 3.7226948738098145, "learning_rate": 5.507553139345574e-06, "loss": 0.11598336696624756, "step": 6500 }, { "epoch": 0.6600300359290544, "grad_norm": 3.9972476959228516, "learning_rate": 5.478242893464389e-06, "loss": 0.11561784744262696, "step": 6510 }, { "epoch": 0.6610439069519869, "grad_norm": 4.571384906768799, "learning_rate": 5.448981396419366e-06, "loss": 0.11228375434875489, "step": 6520 }, { "epoch": 0.6620577779749194, "grad_norm": 3.7510361671447754, "learning_rate": 5.419768963677233e-06, "loss": 0.11499190330505371, "step": 6530 }, { "epoch": 0.6630716489978519, "grad_norm": 4.38587760925293, "learning_rate": 5.39060591017576e-06, "loss": 0.1292546033859253, "step": 6540 }, { "epoch": 0.6640855200207844, "grad_norm": 3.4060778617858887, "learning_rate": 5.3614925503203586e-06, "loss": 0.12483799457550049, "step": 6550 }, { "epoch": 0.6650993910437168, "grad_norm": 4.611334323883057, "learning_rate": 5.332429197980706e-06, "loss": 0.1144004225730896, "step": 6560 }, { "epoch": 0.6661132620666493, "grad_norm": 3.705246925354004, "learning_rate": 5.303416166487337e-06, "loss": 0.12463990449905396, "step": 6570 }, { "epoch": 0.6671271330895818, "grad_norm": 5.69264554977417, "learning_rate": 5.274453768628289e-06, "loss": 0.12295403480529785, "step": 6580 }, { "epoch": 0.6681410041125143, "grad_norm": 3.7814812660217285, "learning_rate": 5.245542316645718e-06, "loss": 0.11615349054336548, "step": 6590 }, { "epoch": 0.6691548751354468, "grad_norm": 6.564373970031738, "learning_rate": 5.2166821222325306e-06, "loss": 0.11338858604431153, "step": 6600 }, { "epoch": 0.6701687461583793, "grad_norm": 3.306744337081909, "learning_rate": 5.187873496529041e-06, "loss": 0.10835211277008057, "step": 6610 }, { "epoch": 0.6711826171813118, "grad_norm": 4.869850158691406, "learning_rate": 5.15911675011959e-06, "loss": 0.12774145603179932, "step": 6620 }, { "epoch": 0.6721964882042443, "grad_norm": 3.675657033920288, "learning_rate": 5.130412193029213e-06, "loss": 0.1112322449684143, "step": 6630 }, { "epoch": 0.6732103592271768, "grad_norm": 4.34423828125, "learning_rate": 5.101760134720306e-06, "loss": 0.11929440498352051, "step": 6640 }, { "epoch": 0.6742242302501094, "grad_norm": 3.9727461338043213, "learning_rate": 5.073160884089263e-06, "loss": 0.12310142517089843, "step": 6650 }, { "epoch": 0.6752381012730418, "grad_norm": 4.363874435424805, "learning_rate": 5.044614749463173e-06, "loss": 0.11071518659591675, "step": 6660 }, { "epoch": 0.6762519722959743, "grad_norm": 3.336449384689331, "learning_rate": 5.0161220385964745e-06, "loss": 0.11163054704666138, "step": 6670 }, { "epoch": 0.6772658433189068, "grad_norm": 3.901484489440918, "learning_rate": 4.987683058667651e-06, "loss": 0.11907176971435547, "step": 6680 }, { "epoch": 0.6782797143418393, "grad_norm": 5.88036584854126, "learning_rate": 4.9592981162759215e-06, "loss": 0.128798246383667, "step": 6690 }, { "epoch": 0.6792935853647718, "grad_norm": 3.423100471496582, "learning_rate": 4.930967517437922e-06, "loss": 0.10864698886871338, "step": 6700 }, { "epoch": 0.6803074563877043, "grad_norm": 5.441021919250488, "learning_rate": 4.902691567584412e-06, "loss": 0.12306756973266601, "step": 6710 }, { "epoch": 0.6813213274106368, "grad_norm": 4.3981032371521, "learning_rate": 4.87447057155699e-06, "loss": 0.10503174066543579, "step": 6720 }, { "epoch": 0.6823351984335693, "grad_norm": 3.3175535202026367, "learning_rate": 4.846304833604792e-06, "loss": 0.11194050312042236, "step": 6730 }, { "epoch": 0.6833490694565018, "grad_norm": 6.594106197357178, "learning_rate": 4.8181946573812236e-06, "loss": 0.13289908170700074, "step": 6740 }, { "epoch": 0.6843629404794342, "grad_norm": 2.959491014480591, "learning_rate": 4.790140345940688e-06, "loss": 0.1031903624534607, "step": 6750 }, { "epoch": 0.6853768115023667, "grad_norm": 5.476659297943115, "learning_rate": 4.762142201735299e-06, "loss": 0.11533935070037842, "step": 6760 }, { "epoch": 0.6863906825252992, "grad_norm": 4.635532855987549, "learning_rate": 4.734200526611652e-06, "loss": 0.1102502703666687, "step": 6770 }, { "epoch": 0.6874045535482317, "grad_norm": 3.565369129180908, "learning_rate": 4.706315621807537e-06, "loss": 0.10698442459106446, "step": 6780 }, { "epoch": 0.6884184245711642, "grad_norm": 3.906066656112671, "learning_rate": 4.678487787948711e-06, "loss": 0.11416656970977783, "step": 6790 }, { "epoch": 0.6894322955940967, "grad_norm": 5.572487831115723, "learning_rate": 4.650717325045655e-06, "loss": 0.11687943935394288, "step": 6800 }, { "epoch": 0.6904461666170292, "grad_norm": 4.496267318725586, "learning_rate": 4.623004532490328e-06, "loss": 0.11642987728118896, "step": 6810 }, { "epoch": 0.6914600376399618, "grad_norm": 4.719959735870361, "learning_rate": 4.595349709052964e-06, "loss": 0.10449960231781005, "step": 6820 }, { "epoch": 0.6924739086628943, "grad_norm": 4.657838821411133, "learning_rate": 4.5677531528788196e-06, "loss": 0.10199984312057495, "step": 6830 }, { "epoch": 0.6934877796858268, "grad_norm": 3.8813729286193848, "learning_rate": 4.54021516148498e-06, "loss": 0.11608996391296386, "step": 6840 }, { "epoch": 0.6945016507087592, "grad_norm": 4.931285381317139, "learning_rate": 4.5127360317571475e-06, "loss": 0.11226991415023804, "step": 6850 }, { "epoch": 0.6955155217316917, "grad_norm": 4.785773754119873, "learning_rate": 4.485316059946438e-06, "loss": 0.09994369745254517, "step": 6860 }, { "epoch": 0.6965293927546242, "grad_norm": 6.203670978546143, "learning_rate": 4.457955541666188e-06, "loss": 0.11624548435211182, "step": 6870 }, { "epoch": 0.6975432637775567, "grad_norm": 5.032005786895752, "learning_rate": 4.430654771888776e-06, "loss": 0.09974044561386108, "step": 6880 }, { "epoch": 0.6985571348004892, "grad_norm": 4.610232830047607, "learning_rate": 4.403414044942422e-06, "loss": 0.10959720611572266, "step": 6890 }, { "epoch": 0.6995710058234217, "grad_norm": 5.267967700958252, "learning_rate": 4.376233654508042e-06, "loss": 0.09943661689758301, "step": 6900 }, { "epoch": 0.7005848768463542, "grad_norm": 4.623991966247559, "learning_rate": 4.349113893616056e-06, "loss": 0.10182205438613892, "step": 6910 }, { "epoch": 0.7015987478692867, "grad_norm": 6.415874481201172, "learning_rate": 4.322055054643244e-06, "loss": 0.10073331594467164, "step": 6920 }, { "epoch": 0.7026126188922192, "grad_norm": 5.15396785736084, "learning_rate": 4.295057429309589e-06, "loss": 0.10898244380950928, "step": 6930 }, { "epoch": 0.7036264899151516, "grad_norm": 4.617178440093994, "learning_rate": 4.268121308675132e-06, "loss": 0.1035955548286438, "step": 6940 }, { "epoch": 0.7046403609380841, "grad_norm": 3.763751268386841, "learning_rate": 4.241246983136834e-06, "loss": 0.1022830605506897, "step": 6950 }, { "epoch": 0.7056542319610166, "grad_norm": 3.4903979301452637, "learning_rate": 4.214434742425455e-06, "loss": 0.10237841606140137, "step": 6960 }, { "epoch": 0.7066681029839491, "grad_norm": 4.06130838394165, "learning_rate": 4.1876848756024116e-06, "loss": 0.1067464828491211, "step": 6970 }, { "epoch": 0.7076819740068816, "grad_norm": 3.887772798538208, "learning_rate": 4.1609976710566735e-06, "loss": 0.12693111896514891, "step": 6980 }, { "epoch": 0.7086958450298142, "grad_norm": 2.8780038356781006, "learning_rate": 4.134373416501652e-06, "loss": 0.0991293728351593, "step": 6990 }, { "epoch": 0.7097097160527467, "grad_norm": 4.41875696182251, "learning_rate": 4.107812398972093e-06, "loss": 0.11864647865295411, "step": 7000 }, { "epoch": 0.7107235870756792, "grad_norm": 3.7676761150360107, "learning_rate": 4.081314904821001e-06, "loss": 0.10184986591339111, "step": 7010 }, { "epoch": 0.7117374580986117, "grad_norm": 4.858131408691406, "learning_rate": 4.054881219716521e-06, "loss": 0.1123092532157898, "step": 7020 }, { "epoch": 0.7127513291215442, "grad_norm": 5.325002670288086, "learning_rate": 4.0285116286388914e-06, "loss": 0.09597529768943787, "step": 7030 }, { "epoch": 0.7137652001444766, "grad_norm": 5.566653251647949, "learning_rate": 4.0022064158773445e-06, "loss": 0.11914772987365722, "step": 7040 }, { "epoch": 0.7147790711674091, "grad_norm": 3.6714675426483154, "learning_rate": 3.9759658650270575e-06, "loss": 0.11739552021026611, "step": 7050 }, { "epoch": 0.7157929421903416, "grad_norm": 5.075488567352295, "learning_rate": 3.94979025898609e-06, "loss": 0.10595519542694092, "step": 7060 }, { "epoch": 0.7168068132132741, "grad_norm": 4.974448204040527, "learning_rate": 3.9236798799523375e-06, "loss": 0.10856907367706299, "step": 7070 }, { "epoch": 0.7178206842362066, "grad_norm": 4.546585559844971, "learning_rate": 3.89763500942048e-06, "loss": 0.12504260540008544, "step": 7080 }, { "epoch": 0.7188345552591391, "grad_norm": 4.110910892486572, "learning_rate": 3.871655928178962e-06, "loss": 0.1036729097366333, "step": 7090 }, { "epoch": 0.7198484262820716, "grad_norm": 4.180790901184082, "learning_rate": 3.8457429163069534e-06, "loss": 0.11692248582839966, "step": 7100 }, { "epoch": 0.7208622973050041, "grad_norm": 3.8821749687194824, "learning_rate": 3.819896253171332e-06, "loss": 0.11592633724212646, "step": 7110 }, { "epoch": 0.7218761683279366, "grad_norm": 3.5592424869537354, "learning_rate": 3.7941162174236745e-06, "loss": 0.10237376689910889, "step": 7120 }, { "epoch": 0.722890039350869, "grad_norm": 4.686851978302002, "learning_rate": 3.7684030869972464e-06, "loss": 0.09550986289978028, "step": 7130 }, { "epoch": 0.7239039103738015, "grad_norm": 5.058285713195801, "learning_rate": 3.742757139104023e-06, "loss": 0.12144012451171875, "step": 7140 }, { "epoch": 0.724917781396734, "grad_norm": 3.904869794845581, "learning_rate": 3.7171786502316767e-06, "loss": 0.11412193775177001, "step": 7150 }, { "epoch": 0.7259316524196666, "grad_norm": 2.748364210128784, "learning_rate": 3.691667896140605e-06, "loss": 0.1008143663406372, "step": 7160 }, { "epoch": 0.7269455234425991, "grad_norm": 4.379690647125244, "learning_rate": 3.6662251518609747e-06, "loss": 0.1099550485610962, "step": 7170 }, { "epoch": 0.7279593944655316, "grad_norm": 4.316267490386963, "learning_rate": 3.64085069168973e-06, "loss": 0.10962003469467163, "step": 7180 }, { "epoch": 0.7289732654884641, "grad_norm": 3.9741435050964355, "learning_rate": 3.6155447891876518e-06, "loss": 0.09216449856758117, "step": 7190 }, { "epoch": 0.7299871365113966, "grad_norm": 3.734102964401245, "learning_rate": 3.590307717176401e-06, "loss": 0.1006998062133789, "step": 7200 }, { "epoch": 0.7310010075343291, "grad_norm": 6.133769989013672, "learning_rate": 3.565139747735581e-06, "loss": 0.10065001249313354, "step": 7210 }, { "epoch": 0.7320148785572616, "grad_norm": 4.566039562225342, "learning_rate": 3.5400411521998123e-06, "loss": 0.0780746579170227, "step": 7220 }, { "epoch": 0.733028749580194, "grad_norm": 4.790506839752197, "learning_rate": 3.5150122011557888e-06, "loss": 0.10489886999130249, "step": 7230 }, { "epoch": 0.7340426206031265, "grad_norm": 3.5307323932647705, "learning_rate": 3.4900531644393744e-06, "loss": 0.09241369366645813, "step": 7240 }, { "epoch": 0.735056491626059, "grad_norm": 5.288381576538086, "learning_rate": 3.4651643111326895e-06, "loss": 0.11200971603393554, "step": 7250 }, { "epoch": 0.7360703626489915, "grad_norm": 2.8507535457611084, "learning_rate": 3.440345909561208e-06, "loss": 0.09021645188331603, "step": 7260 }, { "epoch": 0.737084233671924, "grad_norm": 3.1646201610565186, "learning_rate": 3.415598227290877e-06, "loss": 0.0947993516921997, "step": 7270 }, { "epoch": 0.7380981046948565, "grad_norm": 4.599608421325684, "learning_rate": 3.390921531125211e-06, "loss": 0.09816359281539917, "step": 7280 }, { "epoch": 0.739111975717789, "grad_norm": 5.637341022491455, "learning_rate": 3.366316087102429e-06, "loss": 0.08803806304931641, "step": 7290 }, { "epoch": 0.7401258467407215, "grad_norm": 3.5424907207489014, "learning_rate": 3.3417821604925937e-06, "loss": 0.09935276508331299, "step": 7300 }, { "epoch": 0.741139717763654, "grad_norm": 4.974106311798096, "learning_rate": 3.3173200157947315e-06, "loss": 0.10940626859664918, "step": 7310 }, { "epoch": 0.7421535887865864, "grad_norm": 4.41220760345459, "learning_rate": 3.2929299167339955e-06, "loss": 0.10175122022628784, "step": 7320 }, { "epoch": 0.7431674598095189, "grad_norm": 3.8045525550842285, "learning_rate": 3.2686121262588165e-06, "loss": 0.09857631921768188, "step": 7330 }, { "epoch": 0.7441813308324515, "grad_norm": 5.400123596191406, "learning_rate": 3.244366906538071e-06, "loss": 0.09939402341842651, "step": 7340 }, { "epoch": 0.745195201855384, "grad_norm": 4.235897064208984, "learning_rate": 3.2201945189582597e-06, "loss": 0.0995379388332367, "step": 7350 }, { "epoch": 0.7462090728783165, "grad_norm": 4.877383708953857, "learning_rate": 3.1960952241206745e-06, "loss": 0.09899389743804932, "step": 7360 }, { "epoch": 0.747222943901249, "grad_norm": 6.720852375030518, "learning_rate": 3.172069281838603e-06, "loss": 0.09987670779228211, "step": 7370 }, { "epoch": 0.7482368149241815, "grad_norm": 6.211799621582031, "learning_rate": 3.148116951134522e-06, "loss": 0.09357274174690247, "step": 7380 }, { "epoch": 0.749250685947114, "grad_norm": 2.486097574234009, "learning_rate": 3.1242384902373024e-06, "loss": 0.10118416547775269, "step": 7390 }, { "epoch": 0.7502645569700465, "grad_norm": 4.066234588623047, "learning_rate": 3.1004341565794373e-06, "loss": 0.1019406795501709, "step": 7400 }, { "epoch": 0.751278427992979, "grad_norm": 4.16953182220459, "learning_rate": 3.0767042067942475e-06, "loss": 0.10167169570922852, "step": 7410 }, { "epoch": 0.7522922990159114, "grad_norm": 5.76350736618042, "learning_rate": 3.0530488967131265e-06, "loss": 0.09561743736267089, "step": 7420 }, { "epoch": 0.7533061700388439, "grad_norm": 3.7936747074127197, "learning_rate": 3.0294684813627917e-06, "loss": 0.08844194412231446, "step": 7430 }, { "epoch": 0.7543200410617764, "grad_norm": 5.28712797164917, "learning_rate": 3.0059632149625118e-06, "loss": 0.09058210253715515, "step": 7440 }, { "epoch": 0.7553339120847089, "grad_norm": 4.342914581298828, "learning_rate": 2.982533350921383e-06, "loss": 0.10027762651443481, "step": 7450 }, { "epoch": 0.7563477831076414, "grad_norm": 2.9940621852874756, "learning_rate": 2.959179141835591e-06, "loss": 0.0893632173538208, "step": 7460 }, { "epoch": 0.7573616541305739, "grad_norm": 3.274364471435547, "learning_rate": 2.935900839485688e-06, "loss": 0.09944291114807129, "step": 7470 }, { "epoch": 0.7583755251535064, "grad_norm": 5.007838726043701, "learning_rate": 2.9126986948338898e-06, "loss": 0.07947916984558105, "step": 7480 }, { "epoch": 0.7593893961764389, "grad_norm": 3.3942065238952637, "learning_rate": 2.889572958021347e-06, "loss": 0.10128275156021119, "step": 7490 }, { "epoch": 0.7604032671993713, "grad_norm": 4.05620002746582, "learning_rate": 2.866523878365468e-06, "loss": 0.09129643440246582, "step": 7500 }, { "epoch": 0.761417138222304, "grad_norm": 3.859697103500366, "learning_rate": 2.8435517043572204e-06, "loss": 0.08813599348068238, "step": 7510 }, { "epoch": 0.7624310092452364, "grad_norm": 5.2373151779174805, "learning_rate": 2.820656683658456e-06, "loss": 0.10122092962265014, "step": 7520 }, { "epoch": 0.7634448802681689, "grad_norm": 5.711012840270996, "learning_rate": 2.797839063099249e-06, "loss": 0.09346293210983277, "step": 7530 }, { "epoch": 0.7644587512911014, "grad_norm": 3.5013835430145264, "learning_rate": 2.775099088675216e-06, "loss": 0.10620670318603516, "step": 7540 }, { "epoch": 0.7654726223140339, "grad_norm": 5.915644645690918, "learning_rate": 2.7524370055448755e-06, "loss": 0.09730988144874572, "step": 7550 }, { "epoch": 0.7664864933369664, "grad_norm": 3.8528103828430176, "learning_rate": 2.7298530580270154e-06, "loss": 0.08746033906936646, "step": 7560 }, { "epoch": 0.7675003643598989, "grad_norm": 4.142298221588135, "learning_rate": 2.7073474895980333e-06, "loss": 0.08797315359115601, "step": 7570 }, { "epoch": 0.7685142353828314, "grad_norm": 4.597126483917236, "learning_rate": 2.6849205428893334e-06, "loss": 0.09730020761489869, "step": 7580 }, { "epoch": 0.7695281064057639, "grad_norm": 4.061728477478027, "learning_rate": 2.662572459684699e-06, "loss": 0.08910443186759949, "step": 7590 }, { "epoch": 0.7705419774286963, "grad_norm": 4.217514991760254, "learning_rate": 2.640303480917693e-06, "loss": 0.09037652015686035, "step": 7600 }, { "epoch": 0.7715558484516288, "grad_norm": 4.958043575286865, "learning_rate": 2.618113846669059e-06, "loss": 0.10221297740936279, "step": 7610 }, { "epoch": 0.7725697194745613, "grad_norm": 5.3961181640625, "learning_rate": 2.596003796164127e-06, "loss": 0.08964524865150451, "step": 7620 }, { "epoch": 0.7735835904974938, "grad_norm": 5.202049732208252, "learning_rate": 2.5739735677702416e-06, "loss": 0.09016172289848327, "step": 7630 }, { "epoch": 0.7745974615204263, "grad_norm": 4.970019340515137, "learning_rate": 2.552023398994188e-06, "loss": 0.09237334728240967, "step": 7640 }, { "epoch": 0.7756113325433588, "grad_norm": 4.460151672363281, "learning_rate": 2.5301535264796274e-06, "loss": 0.09495210647583008, "step": 7650 }, { "epoch": 0.7766252035662913, "grad_norm": 5.019233703613281, "learning_rate": 2.508364186004566e-06, "loss": 0.09691332578659058, "step": 7660 }, { "epoch": 0.7776390745892238, "grad_norm": 6.3407182693481445, "learning_rate": 2.486655612478782e-06, "loss": 0.09180307984352112, "step": 7670 }, { "epoch": 0.7786529456121564, "grad_norm": 4.483320713043213, "learning_rate": 2.465028039941316e-06, "loss": 0.07932631373405456, "step": 7680 }, { "epoch": 0.7796668166350889, "grad_norm": 4.975465774536133, "learning_rate": 2.443481701557946e-06, "loss": 0.08428882956504821, "step": 7690 }, { "epoch": 0.7806806876580213, "grad_norm": 4.534189701080322, "learning_rate": 2.4220168296186587e-06, "loss": 0.0774091362953186, "step": 7700 }, { "epoch": 0.7816945586809538, "grad_norm": 4.683703899383545, "learning_rate": 2.4006336555351615e-06, "loss": 0.09106833338737488, "step": 7710 }, { "epoch": 0.7827084297038863, "grad_norm": 4.836935997009277, "learning_rate": 2.3793324098383796e-06, "loss": 0.09796152710914612, "step": 7720 }, { "epoch": 0.7837223007268188, "grad_norm": 7.7593183517456055, "learning_rate": 2.35811332217597e-06, "loss": 0.07632666826248169, "step": 7730 }, { "epoch": 0.7847361717497513, "grad_norm": 4.0806756019592285, "learning_rate": 2.3369766213098553e-06, "loss": 0.08270615935325623, "step": 7740 }, { "epoch": 0.7857500427726838, "grad_norm": 3.8709774017333984, "learning_rate": 2.315922535113743e-06, "loss": 0.08345532417297363, "step": 7750 }, { "epoch": 0.7867639137956163, "grad_norm": 4.506741523742676, "learning_rate": 2.2949512905706793e-06, "loss": 0.08291237354278565, "step": 7760 }, { "epoch": 0.7877777848185488, "grad_norm": 6.220364093780518, "learning_rate": 2.274063113770597e-06, "loss": 0.08606305122375488, "step": 7770 }, { "epoch": 0.7887916558414813, "grad_norm": 3.7870330810546875, "learning_rate": 2.2532582299078775e-06, "loss": 0.09340934753417969, "step": 7780 }, { "epoch": 0.7898055268644137, "grad_norm": 5.073027610778809, "learning_rate": 2.2325368632789345e-06, "loss": 0.08656355142593383, "step": 7790 }, { "epoch": 0.7908193978873462, "grad_norm": 4.130858898162842, "learning_rate": 2.211899237279779e-06, "loss": 0.09168598651885987, "step": 7800 }, { "epoch": 0.7918332689102787, "grad_norm": 4.221619129180908, "learning_rate": 2.1913455744036138e-06, "loss": 0.10724952220916747, "step": 7810 }, { "epoch": 0.7928471399332112, "grad_norm": 5.0216064453125, "learning_rate": 2.1708760962384545e-06, "loss": 0.09740132093429565, "step": 7820 }, { "epoch": 0.7938610109561437, "grad_norm": 4.177464008331299, "learning_rate": 2.1504910234647112e-06, "loss": 0.0834004044532776, "step": 7830 }, { "epoch": 0.7948748819790762, "grad_norm": 4.253190994262695, "learning_rate": 2.130190575852832e-06, "loss": 0.08391332626342773, "step": 7840 }, { "epoch": 0.7958887530020088, "grad_norm": 4.773930549621582, "learning_rate": 2.109974972260921e-06, "loss": 0.0817363977432251, "step": 7850 }, { "epoch": 0.7969026240249413, "grad_norm": 4.6458563804626465, "learning_rate": 2.0898444306323807e-06, "loss": 0.07273721098899841, "step": 7860 }, { "epoch": 0.7979164950478738, "grad_norm": 3.639235734939575, "learning_rate": 2.069799167993577e-06, "loss": 0.08109580278396607, "step": 7870 }, { "epoch": 0.7989303660708063, "grad_norm": 7.6358113288879395, "learning_rate": 2.0498394004514745e-06, "loss": 0.08337472081184387, "step": 7880 }, { "epoch": 0.7999442370937387, "grad_norm": 4.963197708129883, "learning_rate": 2.029965343191326e-06, "loss": 0.0956379532814026, "step": 7890 }, { "epoch": 0.8009581081166712, "grad_norm": 7.849239826202393, "learning_rate": 2.0101772104743422e-06, "loss": 0.10055131912231445, "step": 7900 }, { "epoch": 0.8019719791396037, "grad_norm": 4.876297950744629, "learning_rate": 1.990475215635388e-06, "loss": 0.08398588895797729, "step": 7910 }, { "epoch": 0.8029858501625362, "grad_norm": 4.562499523162842, "learning_rate": 1.9708595710806787e-06, "loss": 0.07735443115234375, "step": 7920 }, { "epoch": 0.8039997211854687, "grad_norm": 4.5146660804748535, "learning_rate": 1.9513304882854966e-06, "loss": 0.07882379293441773, "step": 7930 }, { "epoch": 0.8050135922084012, "grad_norm": 4.275259017944336, "learning_rate": 1.9318881777918973e-06, "loss": 0.07733672857284546, "step": 7940 }, { "epoch": 0.8060274632313337, "grad_norm": 5.276503086090088, "learning_rate": 1.9125328492064575e-06, "loss": 0.07831760644912719, "step": 7950 }, { "epoch": 0.8070413342542662, "grad_norm": 5.065098762512207, "learning_rate": 1.8932647111980007e-06, "loss": 0.0843509316444397, "step": 7960 }, { "epoch": 0.8080552052771987, "grad_norm": 4.887883186340332, "learning_rate": 1.8740839714953552e-06, "loss": 0.08201159238815307, "step": 7970 }, { "epoch": 0.8090690763001311, "grad_norm": 5.504922389984131, "learning_rate": 1.8549908368851099e-06, "loss": 0.08893084526062012, "step": 7980 }, { "epoch": 0.8100829473230636, "grad_norm": 4.823802947998047, "learning_rate": 1.8359855132093884e-06, "loss": 0.07049165964126587, "step": 7990 }, { "epoch": 0.8110968183459961, "grad_norm": 4.539687156677246, "learning_rate": 1.8170682053636358e-06, "loss": 0.08722858428955078, "step": 8000 }, { "epoch": 0.8121106893689286, "grad_norm": 6.281988620758057, "learning_rate": 1.7982391172943936e-06, "loss": 0.09367263317108154, "step": 8010 }, { "epoch": 0.8131245603918611, "grad_norm": 6.986349105834961, "learning_rate": 1.7794984519971126e-06, "loss": 0.09466084241867065, "step": 8020 }, { "epoch": 0.8141384314147937, "grad_norm": 4.470920562744141, "learning_rate": 1.7608464115139712e-06, "loss": 0.07877894639968872, "step": 8030 }, { "epoch": 0.8151523024377262, "grad_norm": 4.17576265335083, "learning_rate": 1.7422831969316724e-06, "loss": 0.09320245981216431, "step": 8040 }, { "epoch": 0.8161661734606587, "grad_norm": 5.327627182006836, "learning_rate": 1.7238090083793003e-06, "loss": 0.08330129981040954, "step": 8050 }, { "epoch": 0.8171800444835912, "grad_norm": 4.673901081085205, "learning_rate": 1.7054240450261594e-06, "loss": 0.07770236730575561, "step": 8060 }, { "epoch": 0.8181939155065237, "grad_norm": 5.1785101890563965, "learning_rate": 1.6871285050796093e-06, "loss": 0.09054569005966187, "step": 8070 }, { "epoch": 0.8192077865294561, "grad_norm": 5.154356956481934, "learning_rate": 1.6689225857829527e-06, "loss": 0.0824481189250946, "step": 8080 }, { "epoch": 0.8202216575523886, "grad_norm": 4.349667549133301, "learning_rate": 1.6508064834132875e-06, "loss": 0.09376422166824341, "step": 8090 }, { "epoch": 0.8212355285753211, "grad_norm": 6.0271100997924805, "learning_rate": 1.632780393279404e-06, "loss": 0.08163780570030213, "step": 8100 }, { "epoch": 0.8222493995982536, "grad_norm": 3.621938705444336, "learning_rate": 1.614844509719674e-06, "loss": 0.07117488384246826, "step": 8110 }, { "epoch": 0.8232632706211861, "grad_norm": 4.708275318145752, "learning_rate": 1.5969990260999569e-06, "loss": 0.08912086486816406, "step": 8120 }, { "epoch": 0.8242771416441186, "grad_norm": 4.474498748779297, "learning_rate": 1.5792441348115116e-06, "loss": 0.07504209280014038, "step": 8130 }, { "epoch": 0.8252910126670511, "grad_norm": 5.949587345123291, "learning_rate": 1.5615800272689352e-06, "loss": 0.06669926047325134, "step": 8140 }, { "epoch": 0.8263048836899836, "grad_norm": 3.7174272537231445, "learning_rate": 1.5440068939080776e-06, "loss": 0.0678774893283844, "step": 8150 }, { "epoch": 0.827318754712916, "grad_norm": 4.99799108505249, "learning_rate": 1.5265249241840153e-06, "loss": 0.07570796012878418, "step": 8160 }, { "epoch": 0.8283326257358485, "grad_norm": 4.445627212524414, "learning_rate": 1.5091343065689756e-06, "loss": 0.0791064977645874, "step": 8170 }, { "epoch": 0.829346496758781, "grad_norm": 4.844067096710205, "learning_rate": 1.4918352285503357e-06, "loss": 0.07499915361404419, "step": 8180 }, { "epoch": 0.8303603677817135, "grad_norm": 5.108837127685547, "learning_rate": 1.4746278766285905e-06, "loss": 0.07426892518997193, "step": 8190 }, { "epoch": 0.8313742388046461, "grad_norm": 5.938630104064941, "learning_rate": 1.4575124363153315e-06, "loss": 0.08731330633163452, "step": 8200 }, { "epoch": 0.8323881098275786, "grad_norm": 4.797246932983398, "learning_rate": 1.4404890921312654e-06, "loss": 0.08274707794189454, "step": 8210 }, { "epoch": 0.8334019808505111, "grad_norm": 5.858916282653809, "learning_rate": 1.4235580276042071e-06, "loss": 0.06896687746047973, "step": 8220 }, { "epoch": 0.8344158518734436, "grad_norm": 3.583987236022949, "learning_rate": 1.4067194252671157e-06, "loss": 0.07374770641326904, "step": 8230 }, { "epoch": 0.8354297228963761, "grad_norm": 4.494335174560547, "learning_rate": 1.3899734666561138e-06, "loss": 0.07876806259155274, "step": 8240 }, { "epoch": 0.8364435939193086, "grad_norm": 4.918553352355957, "learning_rate": 1.373320332308541e-06, "loss": 0.0790461003780365, "step": 8250 }, { "epoch": 0.837457464942241, "grad_norm": 4.133692264556885, "learning_rate": 1.3567602017609981e-06, "loss": 0.06747585535049438, "step": 8260 }, { "epoch": 0.8384713359651735, "grad_norm": 3.8353757858276367, "learning_rate": 1.3402932535474277e-06, "loss": 0.06970171332359314, "step": 8270 }, { "epoch": 0.839485206988106, "grad_norm": 6.360500335693359, "learning_rate": 1.3239196651971654e-06, "loss": 0.08912325501441956, "step": 8280 }, { "epoch": 0.8404990780110385, "grad_norm": 3.324700355529785, "learning_rate": 1.3076396132330516e-06, "loss": 0.0652248740196228, "step": 8290 }, { "epoch": 0.841512949033971, "grad_norm": 3.6326732635498047, "learning_rate": 1.2914532731694996e-06, "loss": 0.07003127336502075, "step": 8300 }, { "epoch": 0.8425268200569035, "grad_norm": 4.563235282897949, "learning_rate": 1.2753608195106314e-06, "loss": 0.06879711151123047, "step": 8310 }, { "epoch": 0.843540691079836, "grad_norm": 5.484338283538818, "learning_rate": 1.2593624257483838e-06, "loss": 0.061539262533187866, "step": 8320 }, { "epoch": 0.8445545621027685, "grad_norm": 6.228531360626221, "learning_rate": 1.243458264360634e-06, "loss": 0.07752963304519653, "step": 8330 }, { "epoch": 0.845568433125701, "grad_norm": 6.124917984008789, "learning_rate": 1.2276485068093447e-06, "loss": 0.07129353284835815, "step": 8340 }, { "epoch": 0.8465823041486334, "grad_norm": 5.815363883972168, "learning_rate": 1.2119333235387232e-06, "loss": 0.06360725164413453, "step": 8350 }, { "epoch": 0.8475961751715659, "grad_norm": 5.0116286277771, "learning_rate": 1.1963128839733674e-06, "loss": 0.0643109917640686, "step": 8360 }, { "epoch": 0.8486100461944985, "grad_norm": 4.6302947998046875, "learning_rate": 1.1807873565164507e-06, "loss": 0.06914657354354858, "step": 8370 }, { "epoch": 0.849623917217431, "grad_norm": 5.133659362792969, "learning_rate": 1.1653569085479067e-06, "loss": 0.07831198573112488, "step": 8380 }, { "epoch": 0.8506377882403635, "grad_norm": 5.711822509765625, "learning_rate": 1.150021706422615e-06, "loss": 0.0840286672115326, "step": 8390 }, { "epoch": 0.851651659263296, "grad_norm": 5.892103672027588, "learning_rate": 1.1347819154686246e-06, "loss": 0.07551345229148865, "step": 8400 }, { "epoch": 0.8526655302862285, "grad_norm": 5.697546005249023, "learning_rate": 1.1196376999853531e-06, "loss": 0.06512370109558105, "step": 8410 }, { "epoch": 0.853679401309161, "grad_norm": 4.115391254425049, "learning_rate": 1.104589223241831e-06, "loss": 0.07958337664604187, "step": 8420 }, { "epoch": 0.8546932723320935, "grad_norm": 4.224241256713867, "learning_rate": 1.089636647474923e-06, "loss": 0.07118669748306275, "step": 8430 }, { "epoch": 0.855707143355026, "grad_norm": 3.619410991668701, "learning_rate": 1.0747801338876006e-06, "loss": 0.06367869973182679, "step": 8440 }, { "epoch": 0.8567210143779584, "grad_norm": 5.33629846572876, "learning_rate": 1.0600198426471908e-06, "loss": 0.06862658262252808, "step": 8450 }, { "epoch": 0.8577348854008909, "grad_norm": 4.377651691436768, "learning_rate": 1.0453559328836517e-06, "loss": 0.07210018634796142, "step": 8460 }, { "epoch": 0.8587487564238234, "grad_norm": 5.1786322593688965, "learning_rate": 1.0307885626878555e-06, "loss": 0.06370820999145507, "step": 8470 }, { "epoch": 0.8597626274467559, "grad_norm": 4.209073543548584, "learning_rate": 1.0163178891098912e-06, "loss": 0.058979594707489015, "step": 8480 }, { "epoch": 0.8607764984696884, "grad_norm": 5.77325439453125, "learning_rate": 1.0019440681573633e-06, "loss": 0.060262471437454224, "step": 8490 }, { "epoch": 0.8617903694926209, "grad_norm": 4.921428203582764, "learning_rate": 9.876672547937117e-07, "loss": 0.06716686487197876, "step": 8500 }, { "epoch": 0.8628042405155534, "grad_norm": 5.240196704864502, "learning_rate": 9.734876029365448e-07, "loss": 0.061546307802200315, "step": 8510 }, { "epoch": 0.8638181115384859, "grad_norm": 6.601016998291016, "learning_rate": 9.594052654559737e-07, "loss": 0.05916718244552612, "step": 8520 }, { "epoch": 0.8648319825614184, "grad_norm": 4.37329626083374, "learning_rate": 9.454203941729767e-07, "loss": 0.06357216835021973, "step": 8530 }, { "epoch": 0.865845853584351, "grad_norm": 3.963998556137085, "learning_rate": 9.315331398577454e-07, "loss": 0.0680131196975708, "step": 8540 }, { "epoch": 0.8668597246072834, "grad_norm": 5.682548999786377, "learning_rate": 9.177436522280714e-07, "loss": 0.06892768144607545, "step": 8550 }, { "epoch": 0.8678735956302159, "grad_norm": 5.12714958190918, "learning_rate": 9.04052079947727e-07, "loss": 0.0730743169784546, "step": 8560 }, { "epoch": 0.8688874666531484, "grad_norm": 4.491752624511719, "learning_rate": 8.904585706248637e-07, "loss": 0.06435039043426513, "step": 8570 }, { "epoch": 0.8699013376760809, "grad_norm": 4.151668071746826, "learning_rate": 8.76963270810427e-07, "loss": 0.06860342025756835, "step": 8580 }, { "epoch": 0.8709152086990134, "grad_norm": 4.716901779174805, "learning_rate": 8.635663259965632e-07, "loss": 0.07604730129241943, "step": 8590 }, { "epoch": 0.8719290797219459, "grad_norm": 3.2747366428375244, "learning_rate": 8.502678806150588e-07, "loss": 0.05681849122047424, "step": 8600 }, { "epoch": 0.8729429507448784, "grad_norm": 3.5171210765838623, "learning_rate": 8.370680780357909e-07, "loss": 0.06516213417053222, "step": 8610 }, { "epoch": 0.8739568217678109, "grad_norm": 3.8131790161132812, "learning_rate": 8.23967060565164e-07, "loss": 0.061232781410217284, "step": 8620 }, { "epoch": 0.8749706927907434, "grad_norm": 3.0722405910491943, "learning_rate": 8.109649694445898e-07, "loss": 0.05991050601005554, "step": 8630 }, { "epoch": 0.8759845638136758, "grad_norm": 4.461371898651123, "learning_rate": 7.980619448489601e-07, "loss": 0.06417039036750793, "step": 8640 }, { "epoch": 0.8769984348366083, "grad_norm": 3.214142084121704, "learning_rate": 7.852581258851333e-07, "loss": 0.05304415822029114, "step": 8650 }, { "epoch": 0.8780123058595408, "grad_norm": 4.948453903198242, "learning_rate": 7.725536505904396e-07, "loss": 0.04496611058712006, "step": 8660 }, { "epoch": 0.8790261768824733, "grad_norm": 4.847232341766357, "learning_rate": 7.599486559311887e-07, "loss": 0.07105047702789306, "step": 8670 }, { "epoch": 0.8800400479054058, "grad_norm": 5.020716667175293, "learning_rate": 7.474432778011953e-07, "loss": 0.06621414422988892, "step": 8680 }, { "epoch": 0.8810539189283383, "grad_norm": 5.306026458740234, "learning_rate": 7.350376510203105e-07, "loss": 0.06517731547355651, "step": 8690 }, { "epoch": 0.8820677899512708, "grad_norm": 4.0302252769470215, "learning_rate": 7.227319093329732e-07, "loss": 0.0666893482208252, "step": 8700 }, { "epoch": 0.8830816609742033, "grad_norm": 4.732696533203125, "learning_rate": 7.105261854067691e-07, "loss": 0.06089327335357666, "step": 8710 }, { "epoch": 0.8840955319971359, "grad_norm": 5.188896179199219, "learning_rate": 6.984206108309932e-07, "loss": 0.059158319234848024, "step": 8720 }, { "epoch": 0.8851094030200684, "grad_norm": 3.7922396659851074, "learning_rate": 6.864153161152354e-07, "loss": 0.047634834051132204, "step": 8730 }, { "epoch": 0.8861232740430008, "grad_norm": 5.181560516357422, "learning_rate": 6.745104306879769e-07, "loss": 0.07083773612976074, "step": 8740 }, { "epoch": 0.8871371450659333, "grad_norm": 4.9345526695251465, "learning_rate": 6.627060828951881e-07, "loss": 0.061925995349884036, "step": 8750 }, { "epoch": 0.8881510160888658, "grad_norm": 5.475928783416748, "learning_rate": 6.510023999989501e-07, "loss": 0.06808217763900756, "step": 8760 }, { "epoch": 0.8891648871117983, "grad_norm": 4.580986499786377, "learning_rate": 6.393995081760795e-07, "loss": 0.06025439500808716, "step": 8770 }, { "epoch": 0.8901787581347308, "grad_norm": 4.831587314605713, "learning_rate": 6.278975325167691e-07, "loss": 0.06854138374328614, "step": 8780 }, { "epoch": 0.8911926291576633, "grad_norm": 10.326428413391113, "learning_rate": 6.164965970232417e-07, "loss": 0.08820582032203675, "step": 8790 }, { "epoch": 0.8922065001805958, "grad_norm": 4.944916248321533, "learning_rate": 6.051968246084117e-07, "loss": 0.0629104197025299, "step": 8800 }, { "epoch": 0.8932203712035283, "grad_norm": 5.334218502044678, "learning_rate": 5.939983370945535e-07, "loss": 0.06887788772583008, "step": 8810 }, { "epoch": 0.8942342422264608, "grad_norm": 4.3452277183532715, "learning_rate": 5.829012552120039e-07, "loss": 0.06265774965286255, "step": 8820 }, { "epoch": 0.8952481132493932, "grad_norm": 3.814781904220581, "learning_rate": 5.719056985978388e-07, "loss": 0.06355304121971131, "step": 8830 }, { "epoch": 0.8962619842723257, "grad_norm": 5.958459854125977, "learning_rate": 5.610117857946062e-07, "loss": 0.0565993070602417, "step": 8840 }, { "epoch": 0.8972758552952582, "grad_norm": 3.6568236351013184, "learning_rate": 5.502196342490318e-07, "loss": 0.06544533967971802, "step": 8850 }, { "epoch": 0.8982897263181907, "grad_norm": 4.1614580154418945, "learning_rate": 5.395293603107566e-07, "loss": 0.050055968761444095, "step": 8860 }, { "epoch": 0.8993035973411232, "grad_norm": 2.9660284519195557, "learning_rate": 5.2894107923109e-07, "loss": 0.06726775765419006, "step": 8870 }, { "epoch": 0.9003174683640557, "grad_norm": 4.464524745941162, "learning_rate": 5.184549051617571e-07, "loss": 0.0682625412940979, "step": 8880 }, { "epoch": 0.9013313393869883, "grad_norm": 4.249090671539307, "learning_rate": 5.08070951153673e-07, "loss": 0.05337014198303223, "step": 8890 }, { "epoch": 0.9023452104099208, "grad_norm": 3.241093397140503, "learning_rate": 4.977893291557256e-07, "loss": 0.0526625394821167, "step": 8900 }, { "epoch": 0.9033590814328533, "grad_norm": 3.7543373107910156, "learning_rate": 4.876101500135621e-07, "loss": 0.06358504295349121, "step": 8910 }, { "epoch": 0.9043729524557858, "grad_norm": 5.70884895324707, "learning_rate": 4.775335234684042e-07, "loss": 0.05813519954681397, "step": 8920 }, { "epoch": 0.9053868234787182, "grad_norm": 4.940177917480469, "learning_rate": 4.675595581558556e-07, "loss": 0.06051092147827149, "step": 8930 }, { "epoch": 0.9064006945016507, "grad_norm": 6.463301658630371, "learning_rate": 4.576883616047345e-07, "loss": 0.08148432970046997, "step": 8940 }, { "epoch": 0.9074145655245832, "grad_norm": 4.565691947937012, "learning_rate": 4.479200402359174e-07, "loss": 0.05534660220146179, "step": 8950 }, { "epoch": 0.9084284365475157, "grad_norm": 4.9108357429504395, "learning_rate": 4.382546993611836e-07, "loss": 0.06004546880722046, "step": 8960 }, { "epoch": 0.9094423075704482, "grad_norm": 6.026642322540283, "learning_rate": 4.28692443182086e-07, "loss": 0.06637172102928161, "step": 8970 }, { "epoch": 0.9104561785933807, "grad_norm": 3.55735445022583, "learning_rate": 4.192333747888311e-07, "loss": 0.05333456993103027, "step": 8980 }, { "epoch": 0.9114700496163132, "grad_norm": 2.8055026531219482, "learning_rate": 4.0987759615915837e-07, "loss": 0.058899986743927005, "step": 8990 }, { "epoch": 0.9124839206392457, "grad_norm": 6.616962432861328, "learning_rate": 4.0062520815724816e-07, "loss": 0.06216345429420471, "step": 9000 }, { "epoch": 0.9134977916621781, "grad_norm": 5.246631622314453, "learning_rate": 3.9147631053263027e-07, "loss": 0.0539068341255188, "step": 9010 }, { "epoch": 0.9145116626851106, "grad_norm": 6.24096155166626, "learning_rate": 3.824310019191102e-07, "loss": 0.06231405735015869, "step": 9020 }, { "epoch": 0.9155255337080431, "grad_norm": 4.590670108795166, "learning_rate": 3.734893798337058e-07, "loss": 0.05769467353820801, "step": 9030 }, { "epoch": 0.9165394047309756, "grad_norm": 3.3333728313446045, "learning_rate": 3.646515406755946e-07, "loss": 0.05494285225868225, "step": 9040 }, { "epoch": 0.9175532757539081, "grad_norm": 5.564886093139648, "learning_rate": 3.559175797250769e-07, "loss": 0.06190871000289917, "step": 9050 }, { "epoch": 0.9185671467768407, "grad_norm": 3.935804843902588, "learning_rate": 3.4728759114254774e-07, "loss": 0.04948931932449341, "step": 9060 }, { "epoch": 0.9195810177997732, "grad_norm": 4.101546287536621, "learning_rate": 3.3876166796747877e-07, "loss": 0.059813350439071655, "step": 9070 }, { "epoch": 0.9205948888227057, "grad_norm": 3.637817859649658, "learning_rate": 3.303399021174214e-07, "loss": 0.057499855756759644, "step": 9080 }, { "epoch": 0.9216087598456382, "grad_norm": 4.832284450531006, "learning_rate": 3.220223843870096e-07, "loss": 0.04635609686374664, "step": 9090 }, { "epoch": 0.9226226308685707, "grad_norm": 7.6659722328186035, "learning_rate": 3.1380920444698093e-07, "loss": 0.06449834108352662, "step": 9100 }, { "epoch": 0.9236365018915031, "grad_norm": 4.712719440460205, "learning_rate": 3.057004508432193e-07, "loss": 0.04793646335601807, "step": 9110 }, { "epoch": 0.9246503729144356, "grad_norm": 4.0972065925598145, "learning_rate": 2.976962109957882e-07, "loss": 0.05987362265586853, "step": 9120 }, { "epoch": 0.9256642439373681, "grad_norm": 3.846667766571045, "learning_rate": 2.8979657119799667e-07, "loss": 0.05216259956359863, "step": 9130 }, { "epoch": 0.9266781149603006, "grad_norm": 4.752377986907959, "learning_rate": 2.8200161661546377e-07, "loss": 0.054792702198028564, "step": 9140 }, { "epoch": 0.9276919859832331, "grad_norm": 5.170145034790039, "learning_rate": 2.7431143128520243e-07, "loss": 0.05780558586120606, "step": 9150 }, { "epoch": 0.9287058570061656, "grad_norm": 5.853137969970703, "learning_rate": 2.667260981147157e-07, "loss": 0.053895843029022214, "step": 9160 }, { "epoch": 0.9297197280290981, "grad_norm": 8.281099319458008, "learning_rate": 2.5924569888109654e-07, "loss": 0.06144669055938721, "step": 9170 }, { "epoch": 0.9307335990520306, "grad_norm": 6.1465630531311035, "learning_rate": 2.5187031423015597e-07, "loss": 0.05397428274154663, "step": 9180 }, { "epoch": 0.9317474700749631, "grad_norm": 4.0532941818237305, "learning_rate": 2.4460002367554523e-07, "loss": 0.04843437969684601, "step": 9190 }, { "epoch": 0.9327613410978955, "grad_norm": 5.181836128234863, "learning_rate": 2.3743490559789973e-07, "loss": 0.0638721227645874, "step": 9200 }, { "epoch": 0.933775212120828, "grad_norm": 4.037086009979248, "learning_rate": 2.3037503724399946e-07, "loss": 0.043375921249389646, "step": 9210 }, { "epoch": 0.9347890831437605, "grad_norm": 5.292807102203369, "learning_rate": 2.2342049472592996e-07, "loss": 0.0504015862941742, "step": 9220 }, { "epoch": 0.9358029541666931, "grad_norm": 6.241759777069092, "learning_rate": 2.1657135302026177e-07, "loss": 0.05315278768539429, "step": 9230 }, { "epoch": 0.9368168251896256, "grad_norm": 4.746480941772461, "learning_rate": 2.09827685967251e-07, "loss": 0.04525644779205322, "step": 9240 }, { "epoch": 0.9378306962125581, "grad_norm": 3.4479005336761475, "learning_rate": 2.0318956627003227e-07, "loss": 0.047617995738983156, "step": 9250 }, { "epoch": 0.9388445672354906, "grad_norm": 5.817080020904541, "learning_rate": 1.9665706549384044e-07, "loss": 0.053697168827056885, "step": 9260 }, { "epoch": 0.9398584382584231, "grad_norm": 5.849475383758545, "learning_rate": 1.9023025406523787e-07, "loss": 0.06545135974884034, "step": 9270 }, { "epoch": 0.9408723092813556, "grad_norm": 4.62653923034668, "learning_rate": 1.8390920127135613e-07, "loss": 0.05728898048400879, "step": 9280 }, { "epoch": 0.9418861803042881, "grad_norm": 6.1696038246154785, "learning_rate": 1.7769397525914668e-07, "loss": 0.05313742756843567, "step": 9290 }, { "epoch": 0.9429000513272205, "grad_norm": 3.82340145111084, "learning_rate": 1.7158464303465017e-07, "loss": 0.054454505443573, "step": 9300 }, { "epoch": 0.943913922350153, "grad_norm": 6.341670036315918, "learning_rate": 1.6558127046226945e-07, "loss": 0.0567773699760437, "step": 9310 }, { "epoch": 0.9449277933730855, "grad_norm": 4.672585964202881, "learning_rate": 1.5968392226406337e-07, "loss": 0.050523436069488524, "step": 9320 }, { "epoch": 0.945941664396018, "grad_norm": 7.10723876953125, "learning_rate": 1.5389266201904506e-07, "loss": 0.045911183953285216, "step": 9330 }, { "epoch": 0.9469555354189505, "grad_norm": 3.1012203693389893, "learning_rate": 1.482075521625026e-07, "loss": 0.050934404134750366, "step": 9340 }, { "epoch": 0.947969406441883, "grad_norm": 2.5665082931518555, "learning_rate": 1.4262865398531834e-07, "loss": 0.04892100393772125, "step": 9350 }, { "epoch": 0.9489832774648155, "grad_norm": 4.231151580810547, "learning_rate": 1.3715602763331172e-07, "loss": 0.05368692874908447, "step": 9360 }, { "epoch": 0.949997148487748, "grad_norm": 4.845627307891846, "learning_rate": 1.3178973210659528e-07, "loss": 0.051189303398132324, "step": 9370 }, { "epoch": 0.9510110195106805, "grad_norm": 3.556556224822998, "learning_rate": 1.2652982525892975e-07, "loss": 0.052664971351623534, "step": 9380 }, { "epoch": 0.9520248905336129, "grad_norm": 8.750890731811523, "learning_rate": 1.213763637971066e-07, "loss": 0.05586069226264954, "step": 9390 }, { "epoch": 0.9530387615565454, "grad_norm": 4.104826927185059, "learning_rate": 1.1632940328033526e-07, "loss": 0.04904595315456391, "step": 9400 }, { "epoch": 0.954052632579478, "grad_norm": 5.830951690673828, "learning_rate": 1.1138899811964477e-07, "loss": 0.04796171188354492, "step": 9410 }, { "epoch": 0.9550665036024105, "grad_norm": 4.369207859039307, "learning_rate": 1.0655520157729194e-07, "loss": 0.05262248516082764, "step": 9420 }, { "epoch": 0.956080374625343, "grad_norm": 2.2920260429382324, "learning_rate": 1.0182806576619742e-07, "loss": 0.05363759994506836, "step": 9430 }, { "epoch": 0.9570942456482755, "grad_norm": 5.0525970458984375, "learning_rate": 9.72076416493728e-08, "loss": 0.04086320102214813, "step": 9440 }, { "epoch": 0.958108116671208, "grad_norm": 5.655333995819092, "learning_rate": 9.269397903937883e-08, "loss": 0.0578920304775238, "step": 9450 }, { "epoch": 0.9591219876941405, "grad_norm": 4.696969985961914, "learning_rate": 8.828712659778471e-08, "loss": 0.0535239577293396, "step": 9460 }, { "epoch": 0.960135858717073, "grad_norm": 5.703117847442627, "learning_rate": 8.398713183464857e-08, "loss": 0.04438081383705139, "step": 9470 }, { "epoch": 0.9611497297400055, "grad_norm": 8.498617172241211, "learning_rate": 7.979404110799338e-08, "loss": 0.05438788533210755, "step": 9480 }, { "epoch": 0.9621636007629379, "grad_norm": 2.829289436340332, "learning_rate": 7.570789962332181e-08, "loss": 0.04603458046913147, "step": 9490 }, { "epoch": 0.9631774717858704, "grad_norm": 4.522730350494385, "learning_rate": 7.172875143311996e-08, "loss": 0.05448850393295288, "step": 9500 }, { "epoch": 0.9641913428088029, "grad_norm": 6.869065284729004, "learning_rate": 6.785663943638333e-08, "loss": 0.06823081970214843, "step": 9510 }, { "epoch": 0.9652052138317354, "grad_norm": 4.94692325592041, "learning_rate": 6.409160537815818e-08, "loss": 0.051534605026245114, "step": 9520 }, { "epoch": 0.9662190848546679, "grad_norm": 5.636471748352051, "learning_rate": 6.043368984908759e-08, "loss": 0.051368117332458496, "step": 9530 }, { "epoch": 0.9672329558776004, "grad_norm": 4.431375026702881, "learning_rate": 5.688293228497399e-08, "loss": 0.05590658187866211, "step": 9540 }, { "epoch": 0.9682468269005329, "grad_norm": 3.6254162788391113, "learning_rate": 5.34393709663561e-08, "loss": 0.053951942920684816, "step": 9550 }, { "epoch": 0.9692606979234654, "grad_norm": 4.701842308044434, "learning_rate": 5.0103043018097096e-08, "loss": 0.05751445293426514, "step": 9560 }, { "epoch": 0.9702745689463979, "grad_norm": 4.468296051025391, "learning_rate": 4.687398440897828e-08, "loss": 0.051804614067077634, "step": 9570 }, { "epoch": 0.9712884399693305, "grad_norm": 3.603551149368286, "learning_rate": 4.3752229951321553e-08, "loss": 0.04880141913890838, "step": 9580 }, { "epoch": 0.9723023109922629, "grad_norm": 3.6143252849578857, "learning_rate": 4.0737813300602e-08, "loss": 0.05306161642074585, "step": 9590 }, { "epoch": 0.9733161820151954, "grad_norm": 4.152408599853516, "learning_rate": 3.783076695509702e-08, "loss": 0.05450977683067322, "step": 9600 }, { "epoch": 0.9743300530381279, "grad_norm": 4.092566013336182, "learning_rate": 3.5031122255524406e-08, "loss": 0.04853144288063049, "step": 9610 }, { "epoch": 0.9753439240610604, "grad_norm": 4.105499744415283, "learning_rate": 3.233890938471373e-08, "loss": 0.06039822697639465, "step": 9620 }, { "epoch": 0.9763577950839929, "grad_norm": 3.5629465579986572, "learning_rate": 2.9754157367277715e-08, "loss": 0.05258353352546692, "step": 9630 }, { "epoch": 0.9773716661069254, "grad_norm": 6.203003406524658, "learning_rate": 2.72768940692969e-08, "loss": 0.04388065934181214, "step": 9640 }, { "epoch": 0.9783855371298579, "grad_norm": 7.822943687438965, "learning_rate": 2.4907146198023256e-08, "loss": 0.05769015550613403, "step": 9650 }, { "epoch": 0.9793994081527904, "grad_norm": 4.313169002532959, "learning_rate": 2.2644939301588174e-08, "loss": 0.04913476407527924, "step": 9660 }, { "epoch": 0.9804132791757229, "grad_norm": 5.097107410430908, "learning_rate": 2.049029776873268e-08, "loss": 0.04284180402755737, "step": 9670 }, { "epoch": 0.9814271501986553, "grad_norm": 1.6582667827606201, "learning_rate": 1.8443244828536544e-08, "loss": 0.05603996515274048, "step": 9680 }, { "epoch": 0.9824410212215878, "grad_norm": 4.571530818939209, "learning_rate": 1.650380255017625e-08, "loss": 0.05413894653320313, "step": 9690 }, { "epoch": 0.9834548922445203, "grad_norm": 4.475245952606201, "learning_rate": 1.4671991842680756e-08, "loss": 0.040913155674934386, "step": 9700 }, { "epoch": 0.9844687632674528, "grad_norm": 4.526188850402832, "learning_rate": 1.294783245470943e-08, "loss": 0.05015727877616882, "step": 9710 }, { "epoch": 0.9854826342903853, "grad_norm": 5.866358280181885, "learning_rate": 1.13313429743378e-08, "loss": 0.05000307559967041, "step": 9720 }, { "epoch": 0.9864965053133178, "grad_norm": 3.7328734397888184, "learning_rate": 9.822540828858807e-09, "loss": 0.05562148094177246, "step": 9730 }, { "epoch": 0.9875103763362503, "grad_norm": 5.492976188659668, "learning_rate": 8.421442284591852e-09, "loss": 0.05504986643791199, "step": 9740 }, { "epoch": 0.9885242473591829, "grad_norm": 5.216894149780273, "learning_rate": 7.128062446709605e-09, "loss": 0.04994580447673798, "step": 9750 }, { "epoch": 0.9895381183821154, "grad_norm": 5.341288089752197, "learning_rate": 5.942415259074796e-09, "loss": 0.05473965406417847, "step": 9760 }, { "epoch": 0.9905519894050479, "grad_norm": 4.76381778717041, "learning_rate": 4.86451350409145e-09, "loss": 0.044488373398780826, "step": 9770 }, { "epoch": 0.9915658604279803, "grad_norm": 4.680641174316406, "learning_rate": 3.894368802563886e-09, "loss": 0.047656279802322385, "step": 9780 }, { "epoch": 0.9925797314509128, "grad_norm": 3.3582489490509033, "learning_rate": 3.0319916135723713e-09, "loss": 0.05701117515563965, "step": 9790 }, { "epoch": 0.9935936024738453, "grad_norm": 5.76708459854126, "learning_rate": 2.277391234363213e-09, "loss": 0.043110010027885434, "step": 9800 }, { "epoch": 0.9946074734967778, "grad_norm": 4.109799385070801, "learning_rate": 1.6305758002443939e-09, "loss": 0.049923932552337645, "step": 9810 }, { "epoch": 0.9956213445197103, "grad_norm": 5.104488372802734, "learning_rate": 1.091552284500086e-09, "loss": 0.058217406272888184, "step": 9820 }, { "epoch": 0.9966352155426428, "grad_norm": 6.099133014678955, "learning_rate": 6.603264983173762e-10, "loss": 0.054376769065856936, "step": 9830 }, { "epoch": 0.9976490865655753, "grad_norm": 2.6326494216918945, "learning_rate": 3.3690309071965355e-10, "loss": 0.047551578283309935, "step": 9840 }, { "epoch": 0.9986629575885078, "grad_norm": 5.558837413787842, "learning_rate": 1.2128554851664754e-10, "loss": 0.04187522530555725, "step": 9850 }, { "epoch": 0.9996768286114402, "grad_norm": 3.578449010848999, "learning_rate": 1.3476196272232955e-11, "loss": 0.042344897985458374, "step": 9860 }, { "epoch": 1.0, "step": 9864, "total_flos": 5.070703459485876e+19, "train_loss": 0.13711818100375464, "train_runtime": 223750.6593, "train_samples_per_second": 2.821, "train_steps_per_second": 0.044 } ], "logging_steps": 10, "max_steps": 9864, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 1000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 5.070703459485876e+19, "train_batch_size": 1, "trial_name": null, "trial_params": null }