{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0094382476152022, "eval_steps": 500, "global_step": 20000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.000504719123807601, "grad_norm": 13.60463809967041, "learning_rate": 4.542013626040879e-08, "loss": 2.5717, "step": 10 }, { "epoch": 0.001009438247615202, "grad_norm": 13.106037139892578, "learning_rate": 9.588695432752966e-08, "loss": 2.5732, "step": 20 }, { "epoch": 0.0015141573714228032, "grad_norm": 13.530716896057129, "learning_rate": 1.4635377239465053e-07, "loss": 2.5295, "step": 30 }, { "epoch": 0.002018876495230404, "grad_norm": 14.077570915222168, "learning_rate": 1.9682059046177143e-07, "loss": 2.5395, "step": 40 }, { "epoch": 0.0025235956190380053, "grad_norm": 15.561798095703125, "learning_rate": 2.472874085288923e-07, "loss": 2.5872, "step": 50 }, { "epoch": 0.0030283147428456065, "grad_norm": 17.170623779296875, "learning_rate": 2.9775422659601315e-07, "loss": 2.4167, "step": 60 }, { "epoch": 0.0035330338666532076, "grad_norm": 11.311697959899902, "learning_rate": 3.48221044663134e-07, "loss": 2.3179, "step": 70 }, { "epoch": 0.004037752990460808, "grad_norm": 8.047669410705566, "learning_rate": 3.986878627302549e-07, "loss": 2.1541, "step": 80 }, { "epoch": 0.0045424721142684095, "grad_norm": 5.208219051361084, "learning_rate": 4.4915468079737575e-07, "loss": 2.1151, "step": 90 }, { "epoch": 0.005047191238076011, "grad_norm": 5.202821254730225, "learning_rate": 4.996214988644967e-07, "loss": 2.0509, "step": 100 }, { "epoch": 0.005551910361883612, "grad_norm": 3.4649884700775146, "learning_rate": 5.500883169316174e-07, "loss": 1.7731, "step": 110 }, { "epoch": 0.006056629485691213, "grad_norm": 2.5928854942321777, "learning_rate": 6.005551349987384e-07, "loss": 1.6927, "step": 120 }, { "epoch": 0.006561348609498814, "grad_norm": 2.219893217086792, "learning_rate": 6.510219530658593e-07, "loss": 1.6752, "step": 130 }, { "epoch": 0.007066067733306415, "grad_norm": 2.344254732131958, "learning_rate": 7.014887711329802e-07, "loss": 1.4725, "step": 140 }, { "epoch": 0.007570786857114016, "grad_norm": 4.898065567016602, "learning_rate": 7.51955589200101e-07, "loss": 1.3596, "step": 150 }, { "epoch": 0.008075505980921617, "grad_norm": 7.858865261077881, "learning_rate": 8.024224072672219e-07, "loss": 1.1521, "step": 160 }, { "epoch": 0.008580225104729219, "grad_norm": 4.452445983886719, "learning_rate": 8.528892253343428e-07, "loss": 0.852, "step": 170 }, { "epoch": 0.009084944228536819, "grad_norm": 2.8811142444610596, "learning_rate": 9.033560434014637e-07, "loss": 0.5835, "step": 180 }, { "epoch": 0.009589663352344421, "grad_norm": 1.8620843887329102, "learning_rate": 9.538228614685845e-07, "loss": 0.4718, "step": 190 }, { "epoch": 0.010094382476152021, "grad_norm": 1.3505512475967407, "learning_rate": 1.0042896795357054e-06, "loss": 0.3571, "step": 200 }, { "epoch": 0.010599101599959623, "grad_norm": 1.15274977684021, "learning_rate": 1.0547564976028263e-06, "loss": 0.3255, "step": 210 }, { "epoch": 0.011103820723767224, "grad_norm": 1.1440281867980957, "learning_rate": 1.1052233156699472e-06, "loss": 0.3012, "step": 220 }, { "epoch": 0.011608539847574824, "grad_norm": 0.9628319144248962, "learning_rate": 1.155690133737068e-06, "loss": 0.2912, "step": 230 }, { "epoch": 0.012113258971382426, "grad_norm": 1.3185631036758423, "learning_rate": 1.2061569518041887e-06, "loss": 0.2762, "step": 240 }, { "epoch": 0.012617978095190026, "grad_norm": 1.1212304830551147, "learning_rate": 1.2566237698713097e-06, "loss": 0.2684, "step": 250 }, { "epoch": 0.013122697218997628, "grad_norm": 1.2404594421386719, "learning_rate": 1.3070905879384306e-06, "loss": 0.2719, "step": 260 }, { "epoch": 0.013627416342805228, "grad_norm": 1.154213309288025, "learning_rate": 1.3575574060055517e-06, "loss": 0.2639, "step": 270 }, { "epoch": 0.01413213546661283, "grad_norm": 1.249667763710022, "learning_rate": 1.4080242240726724e-06, "loss": 0.2634, "step": 280 }, { "epoch": 0.01463685459042043, "grad_norm": 1.0084279775619507, "learning_rate": 1.4584910421397933e-06, "loss": 0.2515, "step": 290 }, { "epoch": 0.015141573714228033, "grad_norm": 1.0564252138137817, "learning_rate": 1.5089578602069142e-06, "loss": 0.2551, "step": 300 }, { "epoch": 0.015646292838035633, "grad_norm": 0.9480035901069641, "learning_rate": 1.5594246782740349e-06, "loss": 0.256, "step": 310 }, { "epoch": 0.016151011961843233, "grad_norm": 1.013540506362915, "learning_rate": 1.6098914963411558e-06, "loss": 0.2528, "step": 320 }, { "epoch": 0.016655731085650834, "grad_norm": 0.9483206868171692, "learning_rate": 1.6603583144082767e-06, "loss": 0.2439, "step": 330 }, { "epoch": 0.017160450209458437, "grad_norm": 1.1123472452163696, "learning_rate": 1.7108251324753973e-06, "loss": 0.2444, "step": 340 }, { "epoch": 0.017665169333266038, "grad_norm": 1.0798614025115967, "learning_rate": 1.7612919505425185e-06, "loss": 0.2468, "step": 350 }, { "epoch": 0.018169888457073638, "grad_norm": 1.1317782402038574, "learning_rate": 1.8117587686096394e-06, "loss": 0.2399, "step": 360 }, { "epoch": 0.018674607580881238, "grad_norm": 0.9075382351875305, "learning_rate": 1.8622255866767603e-06, "loss": 0.2384, "step": 370 }, { "epoch": 0.019179326704688842, "grad_norm": 1.131590485572815, "learning_rate": 1.912692404743881e-06, "loss": 0.2411, "step": 380 }, { "epoch": 0.019684045828496442, "grad_norm": 0.9107761979103088, "learning_rate": 1.963159222811002e-06, "loss": 0.2459, "step": 390 }, { "epoch": 0.020188764952304043, "grad_norm": 0.9174781441688538, "learning_rate": 2.0136260408781225e-06, "loss": 0.2324, "step": 400 }, { "epoch": 0.020693484076111643, "grad_norm": 0.9846957325935364, "learning_rate": 2.0640928589452434e-06, "loss": 0.2423, "step": 410 }, { "epoch": 0.021198203199919247, "grad_norm": 1.0217281579971313, "learning_rate": 2.1145596770123643e-06, "loss": 0.2366, "step": 420 }, { "epoch": 0.021702922323726847, "grad_norm": 0.8702396750450134, "learning_rate": 2.1650264950794857e-06, "loss": 0.2372, "step": 430 }, { "epoch": 0.022207641447534447, "grad_norm": 1.0318386554718018, "learning_rate": 2.2154933131466066e-06, "loss": 0.2385, "step": 440 }, { "epoch": 0.022712360571342047, "grad_norm": 1.035325527191162, "learning_rate": 2.265960131213727e-06, "loss": 0.2364, "step": 450 }, { "epoch": 0.023217079695149648, "grad_norm": 0.8677272200584412, "learning_rate": 2.316426949280848e-06, "loss": 0.2255, "step": 460 }, { "epoch": 0.02372179881895725, "grad_norm": 0.8766999244689941, "learning_rate": 2.366893767347969e-06, "loss": 0.2336, "step": 470 }, { "epoch": 0.024226517942764852, "grad_norm": 1.010567545890808, "learning_rate": 2.4173605854150898e-06, "loss": 0.2289, "step": 480 }, { "epoch": 0.024731237066572452, "grad_norm": 0.8621071577072144, "learning_rate": 2.4678274034822107e-06, "loss": 0.2394, "step": 490 }, { "epoch": 0.025235956190380052, "grad_norm": 1.1157803535461426, "learning_rate": 2.5182942215493316e-06, "loss": 0.2283, "step": 500 }, { "epoch": 0.025740675314187656, "grad_norm": 0.9231483340263367, "learning_rate": 2.5687610396164525e-06, "loss": 0.2328, "step": 510 }, { "epoch": 0.026245394437995256, "grad_norm": 0.8060536980628967, "learning_rate": 2.6192278576835734e-06, "loss": 0.2274, "step": 520 }, { "epoch": 0.026750113561802857, "grad_norm": 0.9141907691955566, "learning_rate": 2.6696946757506943e-06, "loss": 0.2276, "step": 530 }, { "epoch": 0.027254832685610457, "grad_norm": 0.9911260604858398, "learning_rate": 2.720161493817815e-06, "loss": 0.2348, "step": 540 }, { "epoch": 0.027759551809418057, "grad_norm": 0.8503599762916565, "learning_rate": 2.770628311884936e-06, "loss": 0.2276, "step": 550 }, { "epoch": 0.02826427093322566, "grad_norm": 0.8563116192817688, "learning_rate": 2.8210951299520566e-06, "loss": 0.2218, "step": 560 }, { "epoch": 0.02876899005703326, "grad_norm": 0.8135624527931213, "learning_rate": 2.8715619480191775e-06, "loss": 0.2245, "step": 570 }, { "epoch": 0.02927370918084086, "grad_norm": 0.8141925930976868, "learning_rate": 2.9220287660862984e-06, "loss": 0.2236, "step": 580 }, { "epoch": 0.029778428304648462, "grad_norm": 0.8813909888267517, "learning_rate": 2.9724955841534193e-06, "loss": 0.2221, "step": 590 }, { "epoch": 0.030283147428456066, "grad_norm": 0.7687870264053345, "learning_rate": 3.02296240222054e-06, "loss": 0.223, "step": 600 }, { "epoch": 0.030787866552263666, "grad_norm": 0.8352845907211304, "learning_rate": 3.073429220287661e-06, "loss": 0.2286, "step": 610 }, { "epoch": 0.031292585676071266, "grad_norm": 0.8227149844169617, "learning_rate": 3.1238960383547815e-06, "loss": 0.2276, "step": 620 }, { "epoch": 0.03179730479987887, "grad_norm": 0.810450553894043, "learning_rate": 3.1743628564219033e-06, "loss": 0.2206, "step": 630 }, { "epoch": 0.03230202392368647, "grad_norm": 0.7927150726318359, "learning_rate": 3.2248296744890238e-06, "loss": 0.2253, "step": 640 }, { "epoch": 0.03280674304749407, "grad_norm": 0.8559219241142273, "learning_rate": 3.2752964925561447e-06, "loss": 0.2228, "step": 650 }, { "epoch": 0.03331146217130167, "grad_norm": 0.8136037588119507, "learning_rate": 3.3257633106232656e-06, "loss": 0.2269, "step": 660 }, { "epoch": 0.03381618129510927, "grad_norm": 0.7821820378303528, "learning_rate": 3.3762301286903865e-06, "loss": 0.2177, "step": 670 }, { "epoch": 0.034320900418916875, "grad_norm": 0.7286434173583984, "learning_rate": 3.4266969467575074e-06, "loss": 0.2193, "step": 680 }, { "epoch": 0.03482561954272447, "grad_norm": 0.7875818014144897, "learning_rate": 3.4771637648246283e-06, "loss": 0.2154, "step": 690 }, { "epoch": 0.035330338666532075, "grad_norm": 0.7284175753593445, "learning_rate": 3.527630582891749e-06, "loss": 0.2222, "step": 700 }, { "epoch": 0.03583505779033968, "grad_norm": 0.7832701206207275, "learning_rate": 3.5780974009588697e-06, "loss": 0.2181, "step": 710 }, { "epoch": 0.036339776914147276, "grad_norm": 0.6910974979400635, "learning_rate": 3.6285642190259906e-06, "loss": 0.2209, "step": 720 }, { "epoch": 0.03684449603795488, "grad_norm": 0.7531803250312805, "learning_rate": 3.6790310370931115e-06, "loss": 0.2172, "step": 730 }, { "epoch": 0.037349215161762477, "grad_norm": 0.7840366363525391, "learning_rate": 3.7294978551602324e-06, "loss": 0.2254, "step": 740 }, { "epoch": 0.03785393428557008, "grad_norm": 0.8185635209083557, "learning_rate": 3.7799646732273533e-06, "loss": 0.218, "step": 750 }, { "epoch": 0.038358653409377684, "grad_norm": 0.699073076248169, "learning_rate": 3.830431491294474e-06, "loss": 0.2201, "step": 760 }, { "epoch": 0.03886337253318528, "grad_norm": 0.7522355318069458, "learning_rate": 3.880898309361595e-06, "loss": 0.2163, "step": 770 }, { "epoch": 0.039368091656992885, "grad_norm": 0.7708520293235779, "learning_rate": 3.931365127428716e-06, "loss": 0.2249, "step": 780 }, { "epoch": 0.03987281078080048, "grad_norm": 0.8467464447021484, "learning_rate": 3.981831945495837e-06, "loss": 0.2172, "step": 790 }, { "epoch": 0.040377529904608085, "grad_norm": 0.6811386942863464, "learning_rate": 4.032298763562958e-06, "loss": 0.2186, "step": 800 }, { "epoch": 0.04088224902841569, "grad_norm": 0.8693949580192566, "learning_rate": 4.082765581630079e-06, "loss": 0.2248, "step": 810 }, { "epoch": 0.041386968152223286, "grad_norm": 0.6656254529953003, "learning_rate": 4.1332323996971996e-06, "loss": 0.2234, "step": 820 }, { "epoch": 0.04189168727603089, "grad_norm": 0.8368794918060303, "learning_rate": 4.1836992177643205e-06, "loss": 0.2162, "step": 830 }, { "epoch": 0.04239640639983849, "grad_norm": 0.6947387456893921, "learning_rate": 4.234166035831441e-06, "loss": 0.2139, "step": 840 }, { "epoch": 0.04290112552364609, "grad_norm": 0.7174718379974365, "learning_rate": 4.284632853898562e-06, "loss": 0.2155, "step": 850 }, { "epoch": 0.043405844647453694, "grad_norm": 0.7197349071502686, "learning_rate": 4.335099671965683e-06, "loss": 0.2118, "step": 860 }, { "epoch": 0.04391056377126129, "grad_norm": 0.7465193271636963, "learning_rate": 4.385566490032804e-06, "loss": 0.2158, "step": 870 }, { "epoch": 0.044415282895068894, "grad_norm": 0.7318498492240906, "learning_rate": 4.436033308099925e-06, "loss": 0.2225, "step": 880 }, { "epoch": 0.0449200020188765, "grad_norm": 0.751470685005188, "learning_rate": 4.486500126167045e-06, "loss": 0.2116, "step": 890 }, { "epoch": 0.045424721142684095, "grad_norm": 0.6552090048789978, "learning_rate": 4.536966944234166e-06, "loss": 0.21, "step": 900 }, { "epoch": 0.0459294402664917, "grad_norm": 0.8061506152153015, "learning_rate": 4.587433762301287e-06, "loss": 0.2175, "step": 910 }, { "epoch": 0.046434159390299296, "grad_norm": 0.7149888873100281, "learning_rate": 4.637900580368408e-06, "loss": 0.2152, "step": 920 }, { "epoch": 0.0469388785141069, "grad_norm": 0.6820036768913269, "learning_rate": 4.688367398435529e-06, "loss": 0.2181, "step": 930 }, { "epoch": 0.0474435976379145, "grad_norm": 0.7252848744392395, "learning_rate": 4.7388342165026496e-06, "loss": 0.2108, "step": 940 }, { "epoch": 0.0479483167617221, "grad_norm": 0.7742591500282288, "learning_rate": 4.789301034569771e-06, "loss": 0.2107, "step": 950 }, { "epoch": 0.048453035885529704, "grad_norm": 0.7993348836898804, "learning_rate": 4.839767852636892e-06, "loss": 0.2201, "step": 960 }, { "epoch": 0.0489577550093373, "grad_norm": 0.6789315938949585, "learning_rate": 4.890234670704013e-06, "loss": 0.2134, "step": 970 }, { "epoch": 0.049462474133144904, "grad_norm": 0.7064614295959473, "learning_rate": 4.940701488771133e-06, "loss": 0.212, "step": 980 }, { "epoch": 0.04996719325695251, "grad_norm": 0.6817086935043335, "learning_rate": 4.991168306838254e-06, "loss": 0.2141, "step": 990 }, { "epoch": 0.050471912380760105, "grad_norm": 0.6135743260383606, "learning_rate": 5.041635124905375e-06, "loss": 0.2141, "step": 1000 }, { "epoch": 0.05097663150456771, "grad_norm": 0.7486844658851624, "learning_rate": 5.092101942972496e-06, "loss": 0.2111, "step": 1010 }, { "epoch": 0.05148135062837531, "grad_norm": 0.6590331792831421, "learning_rate": 5.142568761039617e-06, "loss": 0.2091, "step": 1020 }, { "epoch": 0.05198606975218291, "grad_norm": 0.7175525426864624, "learning_rate": 5.193035579106738e-06, "loss": 0.2176, "step": 1030 }, { "epoch": 0.05249078887599051, "grad_norm": 0.7034561038017273, "learning_rate": 5.2435023971738586e-06, "loss": 0.2104, "step": 1040 }, { "epoch": 0.05299550799979811, "grad_norm": 0.7325619459152222, "learning_rate": 5.2939692152409795e-06, "loss": 0.2161, "step": 1050 }, { "epoch": 0.05350022712360571, "grad_norm": 0.6911323070526123, "learning_rate": 5.3444360333081e-06, "loss": 0.2115, "step": 1060 }, { "epoch": 0.05400494624741332, "grad_norm": 0.6810673475265503, "learning_rate": 5.394902851375221e-06, "loss": 0.2164, "step": 1070 }, { "epoch": 0.054509665371220914, "grad_norm": 0.7306351661682129, "learning_rate": 5.445369669442342e-06, "loss": 0.2177, "step": 1080 }, { "epoch": 0.05501438449502852, "grad_norm": 0.662295401096344, "learning_rate": 5.495836487509463e-06, "loss": 0.212, "step": 1090 }, { "epoch": 0.055519103618836114, "grad_norm": 0.7090970873832703, "learning_rate": 5.546303305576584e-06, "loss": 0.214, "step": 1100 }, { "epoch": 0.05602382274264372, "grad_norm": 0.6260803937911987, "learning_rate": 5.596770123643704e-06, "loss": 0.2109, "step": 1110 }, { "epoch": 0.05652854186645132, "grad_norm": 0.6673741340637207, "learning_rate": 5.647236941710825e-06, "loss": 0.2102, "step": 1120 }, { "epoch": 0.05703326099025892, "grad_norm": 0.6217586994171143, "learning_rate": 5.697703759777946e-06, "loss": 0.2114, "step": 1130 }, { "epoch": 0.05753798011406652, "grad_norm": 0.6669089794158936, "learning_rate": 5.748170577845067e-06, "loss": 0.2168, "step": 1140 }, { "epoch": 0.058042699237874126, "grad_norm": 0.6872769594192505, "learning_rate": 5.798637395912188e-06, "loss": 0.2085, "step": 1150 }, { "epoch": 0.05854741836168172, "grad_norm": 0.6450240015983582, "learning_rate": 5.8491042139793085e-06, "loss": 0.2139, "step": 1160 }, { "epoch": 0.05905213748548933, "grad_norm": 0.6934195160865784, "learning_rate": 5.8995710320464294e-06, "loss": 0.216, "step": 1170 }, { "epoch": 0.059556856609296924, "grad_norm": 0.650347113609314, "learning_rate": 5.95003785011355e-06, "loss": 0.2129, "step": 1180 }, { "epoch": 0.06006157573310453, "grad_norm": 0.6073017716407776, "learning_rate": 6.000504668180672e-06, "loss": 0.2113, "step": 1190 }, { "epoch": 0.06056629485691213, "grad_norm": 0.6289875507354736, "learning_rate": 6.050971486247793e-06, "loss": 0.2078, "step": 1200 }, { "epoch": 0.06107101398071973, "grad_norm": 0.6105359792709351, "learning_rate": 6.101438304314914e-06, "loss": 0.2108, "step": 1210 }, { "epoch": 0.06157573310452733, "grad_norm": 0.6120012998580933, "learning_rate": 6.151905122382035e-06, "loss": 0.2121, "step": 1220 }, { "epoch": 0.06208045222833493, "grad_norm": 0.6814672946929932, "learning_rate": 6.202371940449156e-06, "loss": 0.2079, "step": 1230 }, { "epoch": 0.06258517135214253, "grad_norm": 0.6240723729133606, "learning_rate": 6.252838758516277e-06, "loss": 0.2067, "step": 1240 }, { "epoch": 0.06308989047595014, "grad_norm": 0.5940879583358765, "learning_rate": 6.3033055765833975e-06, "loss": 0.2102, "step": 1250 }, { "epoch": 0.06359460959975774, "grad_norm": 0.5910018682479858, "learning_rate": 6.353772394650518e-06, "loss": 0.2099, "step": 1260 }, { "epoch": 0.06409932872356533, "grad_norm": 0.6340048909187317, "learning_rate": 6.404239212717639e-06, "loss": 0.2058, "step": 1270 }, { "epoch": 0.06460404784737293, "grad_norm": 0.6318060755729675, "learning_rate": 6.454706030784759e-06, "loss": 0.2102, "step": 1280 }, { "epoch": 0.06510876697118054, "grad_norm": 0.6777286529541016, "learning_rate": 6.50517284885188e-06, "loss": 0.2058, "step": 1290 }, { "epoch": 0.06561348609498814, "grad_norm": 0.5975624918937683, "learning_rate": 6.555639666919001e-06, "loss": 0.2081, "step": 1300 }, { "epoch": 0.06611820521879574, "grad_norm": 0.6808609366416931, "learning_rate": 6.606106484986122e-06, "loss": 0.2139, "step": 1310 }, { "epoch": 0.06662292434260333, "grad_norm": 0.6233915090560913, "learning_rate": 6.656573303053243e-06, "loss": 0.2064, "step": 1320 }, { "epoch": 0.06712764346641094, "grad_norm": 0.6113154888153076, "learning_rate": 6.707040121120364e-06, "loss": 0.2016, "step": 1330 }, { "epoch": 0.06763236259021854, "grad_norm": 0.6894047856330872, "learning_rate": 6.757506939187485e-06, "loss": 0.2131, "step": 1340 }, { "epoch": 0.06813708171402615, "grad_norm": 0.6559394001960754, "learning_rate": 6.807973757254606e-06, "loss": 0.2138, "step": 1350 }, { "epoch": 0.06864180083783375, "grad_norm": 0.6041450500488281, "learning_rate": 6.858440575321727e-06, "loss": 0.2069, "step": 1360 }, { "epoch": 0.06914651996164135, "grad_norm": 0.5984525680541992, "learning_rate": 6.9089073933888475e-06, "loss": 0.2075, "step": 1370 }, { "epoch": 0.06965123908544894, "grad_norm": 0.6031705737113953, "learning_rate": 6.959374211455968e-06, "loss": 0.2043, "step": 1380 }, { "epoch": 0.07015595820925655, "grad_norm": 0.6178134679794312, "learning_rate": 7.009841029523089e-06, "loss": 0.2029, "step": 1390 }, { "epoch": 0.07066067733306415, "grad_norm": 0.6558049917221069, "learning_rate": 7.06030784759021e-06, "loss": 0.21, "step": 1400 }, { "epoch": 0.07116539645687175, "grad_norm": 0.6221516728401184, "learning_rate": 7.11077466565733e-06, "loss": 0.2085, "step": 1410 }, { "epoch": 0.07167011558067936, "grad_norm": 0.5956682562828064, "learning_rate": 7.161241483724451e-06, "loss": 0.2126, "step": 1420 }, { "epoch": 0.07217483470448695, "grad_norm": 0.719821035861969, "learning_rate": 7.211708301791572e-06, "loss": 0.2092, "step": 1430 }, { "epoch": 0.07267955382829455, "grad_norm": 0.5889129042625427, "learning_rate": 7.262175119858693e-06, "loss": 0.2048, "step": 1440 }, { "epoch": 0.07318427295210216, "grad_norm": 0.6264426112174988, "learning_rate": 7.312641937925814e-06, "loss": 0.2072, "step": 1450 }, { "epoch": 0.07368899207590976, "grad_norm": 0.6397431492805481, "learning_rate": 7.363108755992935e-06, "loss": 0.2086, "step": 1460 }, { "epoch": 0.07419371119971736, "grad_norm": 0.6320244073867798, "learning_rate": 7.413575574060056e-06, "loss": 0.2119, "step": 1470 }, { "epoch": 0.07469843032352495, "grad_norm": 0.62810879945755, "learning_rate": 7.4640423921271766e-06, "loss": 0.2074, "step": 1480 }, { "epoch": 0.07520314944733256, "grad_norm": 0.5991032123565674, "learning_rate": 7.5145092101942975e-06, "loss": 0.21, "step": 1490 }, { "epoch": 0.07570786857114016, "grad_norm": 0.6474929451942444, "learning_rate": 7.564976028261418e-06, "loss": 0.2028, "step": 1500 }, { "epoch": 0.07621258769494776, "grad_norm": 0.6450440883636475, "learning_rate": 7.61544284632854e-06, "loss": 0.2091, "step": 1510 }, { "epoch": 0.07671730681875537, "grad_norm": 0.6348863244056702, "learning_rate": 7.665909664395661e-06, "loss": 0.2076, "step": 1520 }, { "epoch": 0.07722202594256296, "grad_norm": 0.5891790986061096, "learning_rate": 7.716376482462781e-06, "loss": 0.2043, "step": 1530 }, { "epoch": 0.07772674506637056, "grad_norm": 0.6226921677589417, "learning_rate": 7.766843300529903e-06, "loss": 0.2103, "step": 1540 }, { "epoch": 0.07823146419017817, "grad_norm": 0.5896533131599426, "learning_rate": 7.817310118597023e-06, "loss": 0.2043, "step": 1550 }, { "epoch": 0.07873618331398577, "grad_norm": 0.6020935773849487, "learning_rate": 7.867776936664145e-06, "loss": 0.2054, "step": 1560 }, { "epoch": 0.07924090243779337, "grad_norm": 0.6630162000656128, "learning_rate": 7.918243754731265e-06, "loss": 0.2095, "step": 1570 }, { "epoch": 0.07974562156160096, "grad_norm": 0.5960749983787537, "learning_rate": 7.968710572798386e-06, "loss": 0.2035, "step": 1580 }, { "epoch": 0.08025034068540857, "grad_norm": 0.6002117991447449, "learning_rate": 8.019177390865506e-06, "loss": 0.2124, "step": 1590 }, { "epoch": 0.08075505980921617, "grad_norm": 0.5932050347328186, "learning_rate": 8.069644208932628e-06, "loss": 0.2012, "step": 1600 }, { "epoch": 0.08125977893302377, "grad_norm": 0.6021419763565063, "learning_rate": 8.120111026999748e-06, "loss": 0.2015, "step": 1610 }, { "epoch": 0.08176449805683138, "grad_norm": 0.5997337698936462, "learning_rate": 8.17057784506687e-06, "loss": 0.2097, "step": 1620 }, { "epoch": 0.08226921718063897, "grad_norm": 0.5498554110527039, "learning_rate": 8.22104466313399e-06, "loss": 0.2005, "step": 1630 }, { "epoch": 0.08277393630444657, "grad_norm": 0.6537087559700012, "learning_rate": 8.271511481201112e-06, "loss": 0.2035, "step": 1640 }, { "epoch": 0.08327865542825418, "grad_norm": 0.6217123866081238, "learning_rate": 8.321978299268232e-06, "loss": 0.205, "step": 1650 }, { "epoch": 0.08378337455206178, "grad_norm": 0.5982206463813782, "learning_rate": 8.372445117335352e-06, "loss": 0.2059, "step": 1660 }, { "epoch": 0.08428809367586938, "grad_norm": 0.5786901712417603, "learning_rate": 8.422911935402474e-06, "loss": 0.2015, "step": 1670 }, { "epoch": 0.08479281279967699, "grad_norm": 0.577913761138916, "learning_rate": 8.473378753469594e-06, "loss": 0.2053, "step": 1680 }, { "epoch": 0.08529753192348458, "grad_norm": 0.5637945532798767, "learning_rate": 8.523845571536715e-06, "loss": 0.2038, "step": 1690 }, { "epoch": 0.08580225104729218, "grad_norm": 0.5863056182861328, "learning_rate": 8.574312389603836e-06, "loss": 0.2074, "step": 1700 }, { "epoch": 0.08630697017109978, "grad_norm": 0.6190007925033569, "learning_rate": 8.624779207670957e-06, "loss": 0.203, "step": 1710 }, { "epoch": 0.08681168929490739, "grad_norm": 0.5714817643165588, "learning_rate": 8.675246025738077e-06, "loss": 0.2096, "step": 1720 }, { "epoch": 0.08731640841871499, "grad_norm": 0.56711745262146, "learning_rate": 8.725712843805199e-06, "loss": 0.2015, "step": 1730 }, { "epoch": 0.08782112754252258, "grad_norm": 0.5756425261497498, "learning_rate": 8.77617966187232e-06, "loss": 0.207, "step": 1740 }, { "epoch": 0.08832584666633018, "grad_norm": 0.5967185497283936, "learning_rate": 8.826646479939441e-06, "loss": 0.2076, "step": 1750 }, { "epoch": 0.08883056579013779, "grad_norm": 0.5538885593414307, "learning_rate": 8.877113298006561e-06, "loss": 0.2012, "step": 1760 }, { "epoch": 0.08933528491394539, "grad_norm": 0.5975233912467957, "learning_rate": 8.927580116073683e-06, "loss": 0.2086, "step": 1770 }, { "epoch": 0.089840004037753, "grad_norm": 0.5774773955345154, "learning_rate": 8.978046934140803e-06, "loss": 0.2087, "step": 1780 }, { "epoch": 0.09034472316156059, "grad_norm": 0.5733230710029602, "learning_rate": 9.028513752207923e-06, "loss": 0.2023, "step": 1790 }, { "epoch": 0.09084944228536819, "grad_norm": 0.6751763820648193, "learning_rate": 9.078980570275045e-06, "loss": 0.2065, "step": 1800 }, { "epoch": 0.0913541614091758, "grad_norm": 0.5938685536384583, "learning_rate": 9.129447388342165e-06, "loss": 0.1959, "step": 1810 }, { "epoch": 0.0918588805329834, "grad_norm": 0.5863669514656067, "learning_rate": 9.179914206409286e-06, "loss": 0.2057, "step": 1820 }, { "epoch": 0.092363599656791, "grad_norm": 0.5345251560211182, "learning_rate": 9.230381024476408e-06, "loss": 0.2054, "step": 1830 }, { "epoch": 0.09286831878059859, "grad_norm": 0.5751822590827942, "learning_rate": 9.280847842543528e-06, "loss": 0.2048, "step": 1840 }, { "epoch": 0.0933730379044062, "grad_norm": 0.5309717655181885, "learning_rate": 9.33131466061065e-06, "loss": 0.2041, "step": 1850 }, { "epoch": 0.0938777570282138, "grad_norm": 0.5853695869445801, "learning_rate": 9.38178147867777e-06, "loss": 0.2058, "step": 1860 }, { "epoch": 0.0943824761520214, "grad_norm": 0.5337305665016174, "learning_rate": 9.432248296744892e-06, "loss": 0.2065, "step": 1870 }, { "epoch": 0.094887195275829, "grad_norm": 0.6002751588821411, "learning_rate": 9.482715114812012e-06, "loss": 0.2004, "step": 1880 }, { "epoch": 0.0953919143996366, "grad_norm": 0.5918161273002625, "learning_rate": 9.533181932879134e-06, "loss": 0.2048, "step": 1890 }, { "epoch": 0.0958966335234442, "grad_norm": 0.5987269282341003, "learning_rate": 9.583648750946254e-06, "loss": 0.2062, "step": 1900 }, { "epoch": 0.0964013526472518, "grad_norm": 0.5298378467559814, "learning_rate": 9.634115569013375e-06, "loss": 0.2077, "step": 1910 }, { "epoch": 0.09690607177105941, "grad_norm": 0.601384162902832, "learning_rate": 9.684582387080495e-06, "loss": 0.2087, "step": 1920 }, { "epoch": 0.09741079089486701, "grad_norm": 0.5613410472869873, "learning_rate": 9.735049205147617e-06, "loss": 0.2109, "step": 1930 }, { "epoch": 0.0979155100186746, "grad_norm": 0.5484994053840637, "learning_rate": 9.785516023214737e-06, "loss": 0.2018, "step": 1940 }, { "epoch": 0.0984202291424822, "grad_norm": 0.5879421830177307, "learning_rate": 9.835982841281857e-06, "loss": 0.2043, "step": 1950 }, { "epoch": 0.09892494826628981, "grad_norm": 0.5307125449180603, "learning_rate": 9.886449659348979e-06, "loss": 0.203, "step": 1960 }, { "epoch": 0.09942966739009741, "grad_norm": 0.604020893573761, "learning_rate": 9.936916477416099e-06, "loss": 0.2118, "step": 1970 }, { "epoch": 0.09993438651390502, "grad_norm": 0.49037832021713257, "learning_rate": 9.98738329548322e-06, "loss": 0.2042, "step": 1980 }, { "epoch": 0.10043910563771262, "grad_norm": 0.5946449041366577, "learning_rate": 1.0037850113550343e-05, "loss": 0.2008, "step": 1990 }, { "epoch": 0.10094382476152021, "grad_norm": 0.5766437649726868, "learning_rate": 1.0088316931617463e-05, "loss": 0.2033, "step": 2000 }, { "epoch": 0.10144854388532781, "grad_norm": 0.5545073747634888, "learning_rate": 1.0138783749684584e-05, "loss": 0.2086, "step": 2010 }, { "epoch": 0.10195326300913542, "grad_norm": 0.55591881275177, "learning_rate": 1.0189250567751704e-05, "loss": 0.2038, "step": 2020 }, { "epoch": 0.10245798213294302, "grad_norm": 0.5176115036010742, "learning_rate": 1.0239717385818826e-05, "loss": 0.2067, "step": 2030 }, { "epoch": 0.10296270125675062, "grad_norm": 0.5575576424598694, "learning_rate": 1.0290184203885946e-05, "loss": 0.1999, "step": 2040 }, { "epoch": 0.10346742038055821, "grad_norm": 0.5232179164886475, "learning_rate": 1.0340651021953068e-05, "loss": 0.2094, "step": 2050 }, { "epoch": 0.10397213950436582, "grad_norm": 0.5789377093315125, "learning_rate": 1.0391117840020188e-05, "loss": 0.2014, "step": 2060 }, { "epoch": 0.10447685862817342, "grad_norm": 0.5562260746955872, "learning_rate": 1.044158465808731e-05, "loss": 0.2084, "step": 2070 }, { "epoch": 0.10498157775198103, "grad_norm": 0.5855028629302979, "learning_rate": 1.049205147615443e-05, "loss": 0.2111, "step": 2080 }, { "epoch": 0.10548629687578863, "grad_norm": 0.5580106973648071, "learning_rate": 1.0542518294221552e-05, "loss": 0.2124, "step": 2090 }, { "epoch": 0.10599101599959622, "grad_norm": 0.5740782022476196, "learning_rate": 1.0592985112288672e-05, "loss": 0.1988, "step": 2100 }, { "epoch": 0.10649573512340382, "grad_norm": 0.5421823859214783, "learning_rate": 1.0643451930355793e-05, "loss": 0.2074, "step": 2110 }, { "epoch": 0.10700045424721143, "grad_norm": 0.5478121042251587, "learning_rate": 1.0693918748422913e-05, "loss": 0.2045, "step": 2120 }, { "epoch": 0.10750517337101903, "grad_norm": 0.6460627317428589, "learning_rate": 1.0744385566490033e-05, "loss": 0.2031, "step": 2130 }, { "epoch": 0.10800989249482663, "grad_norm": 0.5555402636528015, "learning_rate": 1.0794852384557155e-05, "loss": 0.2009, "step": 2140 }, { "epoch": 0.10851461161863422, "grad_norm": 0.5407416820526123, "learning_rate": 1.0845319202624275e-05, "loss": 0.2062, "step": 2150 }, { "epoch": 0.10901933074244183, "grad_norm": 0.527349054813385, "learning_rate": 1.0895786020691397e-05, "loss": 0.2121, "step": 2160 }, { "epoch": 0.10952404986624943, "grad_norm": 0.5303550362586975, "learning_rate": 1.0946252838758517e-05, "loss": 0.201, "step": 2170 }, { "epoch": 0.11002876899005704, "grad_norm": 0.5750499963760376, "learning_rate": 1.0996719656825639e-05, "loss": 0.2088, "step": 2180 }, { "epoch": 0.11053348811386464, "grad_norm": 0.5124275088310242, "learning_rate": 1.1047186474892759e-05, "loss": 0.2029, "step": 2190 }, { "epoch": 0.11103820723767223, "grad_norm": 0.5102079510688782, "learning_rate": 1.109765329295988e-05, "loss": 0.2018, "step": 2200 }, { "epoch": 0.11154292636147983, "grad_norm": 0.5555093884468079, "learning_rate": 1.1148120111027e-05, "loss": 0.2, "step": 2210 }, { "epoch": 0.11204764548528744, "grad_norm": 0.5269559025764465, "learning_rate": 1.1198586929094122e-05, "loss": 0.2008, "step": 2220 }, { "epoch": 0.11255236460909504, "grad_norm": 0.5200217962265015, "learning_rate": 1.1249053747161243e-05, "loss": 0.2012, "step": 2230 }, { "epoch": 0.11305708373290264, "grad_norm": 0.5588811635971069, "learning_rate": 1.1299520565228364e-05, "loss": 0.2045, "step": 2240 }, { "epoch": 0.11356180285671023, "grad_norm": 0.5830052495002747, "learning_rate": 1.1349987383295484e-05, "loss": 0.2025, "step": 2250 }, { "epoch": 0.11406652198051784, "grad_norm": 0.5431234836578369, "learning_rate": 1.1400454201362604e-05, "loss": 0.2052, "step": 2260 }, { "epoch": 0.11457124110432544, "grad_norm": 0.5214938521385193, "learning_rate": 1.1450921019429726e-05, "loss": 0.2033, "step": 2270 }, { "epoch": 0.11507596022813305, "grad_norm": 0.5378023386001587, "learning_rate": 1.1501387837496846e-05, "loss": 0.2026, "step": 2280 }, { "epoch": 0.11558067935194065, "grad_norm": 0.6039928793907166, "learning_rate": 1.1551854655563968e-05, "loss": 0.2066, "step": 2290 }, { "epoch": 0.11608539847574825, "grad_norm": 0.575427770614624, "learning_rate": 1.1602321473631088e-05, "loss": 0.2094, "step": 2300 }, { "epoch": 0.11659011759955584, "grad_norm": 0.5340985655784607, "learning_rate": 1.165278829169821e-05, "loss": 0.2026, "step": 2310 }, { "epoch": 0.11709483672336345, "grad_norm": 0.5241402387619019, "learning_rate": 1.170325510976533e-05, "loss": 0.2086, "step": 2320 }, { "epoch": 0.11759955584717105, "grad_norm": 0.5186008810997009, "learning_rate": 1.1753721927832452e-05, "loss": 0.2056, "step": 2330 }, { "epoch": 0.11810427497097865, "grad_norm": 0.5805855989456177, "learning_rate": 1.1804188745899572e-05, "loss": 0.2013, "step": 2340 }, { "epoch": 0.11860899409478626, "grad_norm": 0.5305898785591125, "learning_rate": 1.1854655563966693e-05, "loss": 0.2022, "step": 2350 }, { "epoch": 0.11911371321859385, "grad_norm": 0.5241792798042297, "learning_rate": 1.1905122382033813e-05, "loss": 0.2059, "step": 2360 }, { "epoch": 0.11961843234240145, "grad_norm": 0.5495730042457581, "learning_rate": 1.1955589200100935e-05, "loss": 0.204, "step": 2370 }, { "epoch": 0.12012315146620905, "grad_norm": 0.5762546062469482, "learning_rate": 1.2006056018168055e-05, "loss": 0.205, "step": 2380 }, { "epoch": 0.12062787059001666, "grad_norm": 0.582310676574707, "learning_rate": 1.2056522836235175e-05, "loss": 0.2077, "step": 2390 }, { "epoch": 0.12113258971382426, "grad_norm": 0.5618459582328796, "learning_rate": 1.2106989654302297e-05, "loss": 0.2114, "step": 2400 }, { "epoch": 0.12163730883763185, "grad_norm": 0.5692446231842041, "learning_rate": 1.2157456472369417e-05, "loss": 0.2069, "step": 2410 }, { "epoch": 0.12214202796143946, "grad_norm": 0.5451514720916748, "learning_rate": 1.2207923290436539e-05, "loss": 0.2061, "step": 2420 }, { "epoch": 0.12264674708524706, "grad_norm": 0.5205888748168945, "learning_rate": 1.2258390108503659e-05, "loss": 0.2121, "step": 2430 }, { "epoch": 0.12315146620905466, "grad_norm": 0.5541833639144897, "learning_rate": 1.230885692657078e-05, "loss": 0.2057, "step": 2440 }, { "epoch": 0.12365618533286227, "grad_norm": 0.5493166446685791, "learning_rate": 1.23593237446379e-05, "loss": 0.2073, "step": 2450 }, { "epoch": 0.12416090445666986, "grad_norm": 0.48053088784217834, "learning_rate": 1.2409790562705022e-05, "loss": 0.1988, "step": 2460 }, { "epoch": 0.12466562358047746, "grad_norm": 0.5019202828407288, "learning_rate": 1.2460257380772142e-05, "loss": 0.2013, "step": 2470 }, { "epoch": 0.12517034270428506, "grad_norm": 0.5050928592681885, "learning_rate": 1.2510724198839264e-05, "loss": 0.1997, "step": 2480 }, { "epoch": 0.12567506182809265, "grad_norm": 0.5156263709068298, "learning_rate": 1.2561191016906384e-05, "loss": 0.2014, "step": 2490 }, { "epoch": 0.12617978095190027, "grad_norm": 0.49331608414649963, "learning_rate": 1.2611657834973506e-05, "loss": 0.2101, "step": 2500 }, { "epoch": 0.12668450007570786, "grad_norm": 0.5257033705711365, "learning_rate": 1.2662124653040626e-05, "loss": 0.2003, "step": 2510 }, { "epoch": 0.12718921919951548, "grad_norm": 0.5659562945365906, "learning_rate": 1.2712591471107746e-05, "loss": 0.2088, "step": 2520 }, { "epoch": 0.12769393832332307, "grad_norm": 0.5572566390037537, "learning_rate": 1.2763058289174868e-05, "loss": 0.2048, "step": 2530 }, { "epoch": 0.12819865744713066, "grad_norm": 0.5570494532585144, "learning_rate": 1.2813525107241988e-05, "loss": 0.2068, "step": 2540 }, { "epoch": 0.12870337657093828, "grad_norm": 0.5042135715484619, "learning_rate": 1.286399192530911e-05, "loss": 0.2035, "step": 2550 }, { "epoch": 0.12920809569474587, "grad_norm": 0.5362774729728699, "learning_rate": 1.291445874337623e-05, "loss": 0.2011, "step": 2560 }, { "epoch": 0.12971281481855348, "grad_norm": 0.5633722543716431, "learning_rate": 1.2964925561443351e-05, "loss": 0.2036, "step": 2570 }, { "epoch": 0.13021753394236107, "grad_norm": 0.5761681199073792, "learning_rate": 1.3015392379510472e-05, "loss": 0.2031, "step": 2580 }, { "epoch": 0.13072225306616866, "grad_norm": 0.4851507246494293, "learning_rate": 1.3065859197577593e-05, "loss": 0.205, "step": 2590 }, { "epoch": 0.13122697218997628, "grad_norm": 0.49152272939682007, "learning_rate": 1.3116326015644713e-05, "loss": 0.1997, "step": 2600 }, { "epoch": 0.13173169131378387, "grad_norm": 0.5188784003257751, "learning_rate": 1.3166792833711835e-05, "loss": 0.2103, "step": 2610 }, { "epoch": 0.1322364104375915, "grad_norm": 0.49195101857185364, "learning_rate": 1.3217259651778955e-05, "loss": 0.2063, "step": 2620 }, { "epoch": 0.13274112956139908, "grad_norm": 0.5160151720046997, "learning_rate": 1.3267726469846079e-05, "loss": 0.2066, "step": 2630 }, { "epoch": 0.13324584868520667, "grad_norm": 0.5125986933708191, "learning_rate": 1.3318193287913199e-05, "loss": 0.2049, "step": 2640 }, { "epoch": 0.1337505678090143, "grad_norm": 0.4767388701438904, "learning_rate": 1.336866010598032e-05, "loss": 0.2056, "step": 2650 }, { "epoch": 0.13425528693282188, "grad_norm": 0.5120488405227661, "learning_rate": 1.341912692404744e-05, "loss": 0.2051, "step": 2660 }, { "epoch": 0.1347600060566295, "grad_norm": 0.5037410259246826, "learning_rate": 1.3469593742114562e-05, "loss": 0.2067, "step": 2670 }, { "epoch": 0.13526472518043708, "grad_norm": 0.5058390498161316, "learning_rate": 1.3520060560181682e-05, "loss": 0.2094, "step": 2680 }, { "epoch": 0.13576944430424467, "grad_norm": 0.46480345726013184, "learning_rate": 1.3570527378248804e-05, "loss": 0.2087, "step": 2690 }, { "epoch": 0.1362741634280523, "grad_norm": 0.5122387409210205, "learning_rate": 1.3620994196315924e-05, "loss": 0.2033, "step": 2700 }, { "epoch": 0.13677888255185988, "grad_norm": 0.4942021071910858, "learning_rate": 1.3671461014383046e-05, "loss": 0.2014, "step": 2710 }, { "epoch": 0.1372836016756675, "grad_norm": 0.5033432841300964, "learning_rate": 1.3721927832450166e-05, "loss": 0.2093, "step": 2720 }, { "epoch": 0.1377883207994751, "grad_norm": 0.4836193025112152, "learning_rate": 1.3772394650517286e-05, "loss": 0.2076, "step": 2730 }, { "epoch": 0.1382930399232827, "grad_norm": 0.51753830909729, "learning_rate": 1.3822861468584408e-05, "loss": 0.2097, "step": 2740 }, { "epoch": 0.1387977590470903, "grad_norm": 0.4928639531135559, "learning_rate": 1.3873328286651528e-05, "loss": 0.2047, "step": 2750 }, { "epoch": 0.1393024781708979, "grad_norm": 0.5241543054580688, "learning_rate": 1.392379510471865e-05, "loss": 0.2052, "step": 2760 }, { "epoch": 0.1398071972947055, "grad_norm": 0.5354957580566406, "learning_rate": 1.397426192278577e-05, "loss": 0.2081, "step": 2770 }, { "epoch": 0.1403119164185131, "grad_norm": 0.4901171028614044, "learning_rate": 1.4024728740852891e-05, "loss": 0.2021, "step": 2780 }, { "epoch": 0.1408166355423207, "grad_norm": 0.5066599249839783, "learning_rate": 1.4075195558920011e-05, "loss": 0.2092, "step": 2790 }, { "epoch": 0.1413213546661283, "grad_norm": 0.5887558460235596, "learning_rate": 1.4125662376987133e-05, "loss": 0.2051, "step": 2800 }, { "epoch": 0.1418260737899359, "grad_norm": 0.49662190675735474, "learning_rate": 1.4176129195054253e-05, "loss": 0.2057, "step": 2810 }, { "epoch": 0.1423307929137435, "grad_norm": 0.5539114475250244, "learning_rate": 1.4226596013121375e-05, "loss": 0.2074, "step": 2820 }, { "epoch": 0.1428355120375511, "grad_norm": 0.4961530566215515, "learning_rate": 1.4277062831188495e-05, "loss": 0.2053, "step": 2830 }, { "epoch": 0.14334023116135872, "grad_norm": 0.5377898812294006, "learning_rate": 1.4327529649255617e-05, "loss": 0.2079, "step": 2840 }, { "epoch": 0.1438449502851663, "grad_norm": 0.5557325482368469, "learning_rate": 1.4377996467322737e-05, "loss": 0.2038, "step": 2850 }, { "epoch": 0.1443496694089739, "grad_norm": 0.5314593315124512, "learning_rate": 1.4428463285389858e-05, "loss": 0.2061, "step": 2860 }, { "epoch": 0.14485438853278151, "grad_norm": 0.5089156627655029, "learning_rate": 1.4478930103456979e-05, "loss": 0.2045, "step": 2870 }, { "epoch": 0.1453591076565891, "grad_norm": 0.5253519415855408, "learning_rate": 1.4529396921524099e-05, "loss": 0.2062, "step": 2880 }, { "epoch": 0.14586382678039672, "grad_norm": 0.527683675289154, "learning_rate": 1.457986373959122e-05, "loss": 0.2045, "step": 2890 }, { "epoch": 0.1463685459042043, "grad_norm": 0.5471828579902649, "learning_rate": 1.463033055765834e-05, "loss": 0.2069, "step": 2900 }, { "epoch": 0.1468732650280119, "grad_norm": 0.4928535223007202, "learning_rate": 1.4680797375725462e-05, "loss": 0.2034, "step": 2910 }, { "epoch": 0.14737798415181952, "grad_norm": 0.6011394262313843, "learning_rate": 1.4731264193792582e-05, "loss": 0.2094, "step": 2920 }, { "epoch": 0.1478827032756271, "grad_norm": 0.5474486351013184, "learning_rate": 1.4781731011859704e-05, "loss": 0.2071, "step": 2930 }, { "epoch": 0.14838742239943473, "grad_norm": 0.5326178073883057, "learning_rate": 1.4832197829926824e-05, "loss": 0.2053, "step": 2940 }, { "epoch": 0.14889214152324232, "grad_norm": 0.5644922256469727, "learning_rate": 1.4882664647993946e-05, "loss": 0.2118, "step": 2950 }, { "epoch": 0.1493968606470499, "grad_norm": 0.5063136219978333, "learning_rate": 1.4933131466061066e-05, "loss": 0.2046, "step": 2960 }, { "epoch": 0.14990157977085752, "grad_norm": 0.46589791774749756, "learning_rate": 1.4983598284128188e-05, "loss": 0.2015, "step": 2970 }, { "epoch": 0.1504062988946651, "grad_norm": 0.5082399249076843, "learning_rate": 1.5034065102195308e-05, "loss": 0.207, "step": 2980 }, { "epoch": 0.15091101801847273, "grad_norm": 0.5655195713043213, "learning_rate": 1.508453192026243e-05, "loss": 0.2102, "step": 2990 }, { "epoch": 0.15141573714228032, "grad_norm": 0.5005980134010315, "learning_rate": 1.513499873832955e-05, "loss": 0.2081, "step": 3000 }, { "epoch": 0.1519204562660879, "grad_norm": 0.5262600183486938, "learning_rate": 1.518546555639667e-05, "loss": 0.2046, "step": 3010 }, { "epoch": 0.15242517538989553, "grad_norm": 0.4845588803291321, "learning_rate": 1.5235932374463791e-05, "loss": 0.2036, "step": 3020 }, { "epoch": 0.15292989451370312, "grad_norm": 0.4828517735004425, "learning_rate": 1.528639919253091e-05, "loss": 0.2084, "step": 3030 }, { "epoch": 0.15343461363751074, "grad_norm": 0.4961801767349243, "learning_rate": 1.533686601059803e-05, "loss": 0.2119, "step": 3040 }, { "epoch": 0.15393933276131833, "grad_norm": 0.5301594734191895, "learning_rate": 1.5387332828665155e-05, "loss": 0.2098, "step": 3050 }, { "epoch": 0.15444405188512592, "grad_norm": 0.5543929934501648, "learning_rate": 1.5437799646732275e-05, "loss": 0.1997, "step": 3060 }, { "epoch": 0.15494877100893353, "grad_norm": 0.4859484136104584, "learning_rate": 1.5488266464799395e-05, "loss": 0.2101, "step": 3070 }, { "epoch": 0.15545349013274112, "grad_norm": 0.4913060665130615, "learning_rate": 1.5538733282866515e-05, "loss": 0.2063, "step": 3080 }, { "epoch": 0.15595820925654874, "grad_norm": 0.4876630902290344, "learning_rate": 1.558920010093364e-05, "loss": 0.2093, "step": 3090 }, { "epoch": 0.15646292838035633, "grad_norm": 0.4703383147716522, "learning_rate": 1.563966691900076e-05, "loss": 0.2016, "step": 3100 }, { "epoch": 0.15696764750416392, "grad_norm": 0.5342310070991516, "learning_rate": 1.569013373706788e-05, "loss": 0.2071, "step": 3110 }, { "epoch": 0.15747236662797154, "grad_norm": 0.4855271577835083, "learning_rate": 1.5740600555135e-05, "loss": 0.2074, "step": 3120 }, { "epoch": 0.15797708575177913, "grad_norm": 0.490731805562973, "learning_rate": 1.579106737320212e-05, "loss": 0.2071, "step": 3130 }, { "epoch": 0.15848180487558675, "grad_norm": 0.48338964581489563, "learning_rate": 1.5841534191269242e-05, "loss": 0.2029, "step": 3140 }, { "epoch": 0.15898652399939434, "grad_norm": 0.4918305277824402, "learning_rate": 1.5892001009336362e-05, "loss": 0.2056, "step": 3150 }, { "epoch": 0.15949124312320193, "grad_norm": 0.5193613171577454, "learning_rate": 1.5942467827403482e-05, "loss": 0.2063, "step": 3160 }, { "epoch": 0.15999596224700954, "grad_norm": 0.4969571828842163, "learning_rate": 1.5992934645470602e-05, "loss": 0.2072, "step": 3170 }, { "epoch": 0.16050068137081713, "grad_norm": 0.4870218336582184, "learning_rate": 1.6043401463537726e-05, "loss": 0.1998, "step": 3180 }, { "epoch": 0.16100540049462475, "grad_norm": 0.46504756808280945, "learning_rate": 1.6093868281604846e-05, "loss": 0.211, "step": 3190 }, { "epoch": 0.16151011961843234, "grad_norm": 0.4723342955112457, "learning_rate": 1.6144335099671966e-05, "loss": 0.2115, "step": 3200 }, { "epoch": 0.16201483874223993, "grad_norm": 0.4949096143245697, "learning_rate": 1.6194801917739086e-05, "loss": 0.2055, "step": 3210 }, { "epoch": 0.16251955786604755, "grad_norm": 0.4994921386241913, "learning_rate": 1.624526873580621e-05, "loss": 0.2102, "step": 3220 }, { "epoch": 0.16302427698985514, "grad_norm": 0.5186566114425659, "learning_rate": 1.629573555387333e-05, "loss": 0.2106, "step": 3230 }, { "epoch": 0.16352899611366276, "grad_norm": 0.4731649160385132, "learning_rate": 1.634620237194045e-05, "loss": 0.2025, "step": 3240 }, { "epoch": 0.16403371523747035, "grad_norm": 0.4779031574726105, "learning_rate": 1.639666919000757e-05, "loss": 0.2027, "step": 3250 }, { "epoch": 0.16453843436127794, "grad_norm": 0.4834672510623932, "learning_rate": 1.644713600807469e-05, "loss": 0.2057, "step": 3260 }, { "epoch": 0.16504315348508555, "grad_norm": 0.4884241223335266, "learning_rate": 1.6497602826141813e-05, "loss": 0.2096, "step": 3270 }, { "epoch": 0.16554787260889314, "grad_norm": 0.5092395544052124, "learning_rate": 1.6548069644208936e-05, "loss": 0.205, "step": 3280 }, { "epoch": 0.16605259173270076, "grad_norm": 0.5025358200073242, "learning_rate": 1.6598536462276056e-05, "loss": 0.2038, "step": 3290 }, { "epoch": 0.16655731085650835, "grad_norm": 0.47842273116111755, "learning_rate": 1.6649003280343176e-05, "loss": 0.2066, "step": 3300 }, { "epoch": 0.16706202998031594, "grad_norm": 0.4668811559677124, "learning_rate": 1.6699470098410297e-05, "loss": 0.2065, "step": 3310 }, { "epoch": 0.16756674910412356, "grad_norm": 0.48619693517684937, "learning_rate": 1.674993691647742e-05, "loss": 0.2039, "step": 3320 }, { "epoch": 0.16807146822793115, "grad_norm": 0.5014223456382751, "learning_rate": 1.680040373454454e-05, "loss": 0.2129, "step": 3330 }, { "epoch": 0.16857618735173877, "grad_norm": 0.48916780948638916, "learning_rate": 1.685087055261166e-05, "loss": 0.2121, "step": 3340 }, { "epoch": 0.16908090647554636, "grad_norm": 0.484353631734848, "learning_rate": 1.690133737067878e-05, "loss": 0.2128, "step": 3350 }, { "epoch": 0.16958562559935397, "grad_norm": 0.5127568244934082, "learning_rate": 1.69518041887459e-05, "loss": 0.2029, "step": 3360 }, { "epoch": 0.17009034472316156, "grad_norm": 0.5266575217247009, "learning_rate": 1.7002271006813024e-05, "loss": 0.207, "step": 3370 }, { "epoch": 0.17059506384696915, "grad_norm": 0.46694424748420715, "learning_rate": 1.7052737824880144e-05, "loss": 0.2133, "step": 3380 }, { "epoch": 0.17109978297077677, "grad_norm": 0.47989538311958313, "learning_rate": 1.7103204642947264e-05, "loss": 0.2065, "step": 3390 }, { "epoch": 0.17160450209458436, "grad_norm": 0.4943184554576874, "learning_rate": 1.7153671461014384e-05, "loss": 0.2084, "step": 3400 }, { "epoch": 0.17210922121839198, "grad_norm": 0.46200627088546753, "learning_rate": 1.7204138279081507e-05, "loss": 0.2062, "step": 3410 }, { "epoch": 0.17261394034219957, "grad_norm": 0.49327176809310913, "learning_rate": 1.7254605097148627e-05, "loss": 0.204, "step": 3420 }, { "epoch": 0.17311865946600716, "grad_norm": 0.4550900161266327, "learning_rate": 1.7305071915215747e-05, "loss": 0.2048, "step": 3430 }, { "epoch": 0.17362337858981478, "grad_norm": 0.4996788799762726, "learning_rate": 1.7355538733282867e-05, "loss": 0.2066, "step": 3440 }, { "epoch": 0.17412809771362237, "grad_norm": 0.4984946548938751, "learning_rate": 1.740600555134999e-05, "loss": 0.2092, "step": 3450 }, { "epoch": 0.17463281683742998, "grad_norm": 0.49960917234420776, "learning_rate": 1.745647236941711e-05, "loss": 0.2119, "step": 3460 }, { "epoch": 0.17513753596123757, "grad_norm": 0.46433204412460327, "learning_rate": 1.750693918748423e-05, "loss": 0.2033, "step": 3470 }, { "epoch": 0.17564225508504516, "grad_norm": 0.4587175250053406, "learning_rate": 1.755740600555135e-05, "loss": 0.207, "step": 3480 }, { "epoch": 0.17614697420885278, "grad_norm": 0.4598322808742523, "learning_rate": 1.760787282361847e-05, "loss": 0.2064, "step": 3490 }, { "epoch": 0.17665169333266037, "grad_norm": 0.48385360836982727, "learning_rate": 1.7658339641685594e-05, "loss": 0.2064, "step": 3500 }, { "epoch": 0.177156412456468, "grad_norm": 0.47701433300971985, "learning_rate": 1.7708806459752715e-05, "loss": 0.2102, "step": 3510 }, { "epoch": 0.17766113158027558, "grad_norm": 0.47555553913116455, "learning_rate": 1.7759273277819835e-05, "loss": 0.2155, "step": 3520 }, { "epoch": 0.17816585070408317, "grad_norm": 0.4453350305557251, "learning_rate": 1.7809740095886955e-05, "loss": 0.2101, "step": 3530 }, { "epoch": 0.17867056982789079, "grad_norm": 0.46237778663635254, "learning_rate": 1.7860206913954078e-05, "loss": 0.2082, "step": 3540 }, { "epoch": 0.17917528895169837, "grad_norm": 0.47256776690483093, "learning_rate": 1.7910673732021198e-05, "loss": 0.2176, "step": 3550 }, { "epoch": 0.179680008075506, "grad_norm": 0.5074901580810547, "learning_rate": 1.7961140550088318e-05, "loss": 0.2067, "step": 3560 }, { "epoch": 0.18018472719931358, "grad_norm": 0.47876206040382385, "learning_rate": 1.8011607368155438e-05, "loss": 0.2108, "step": 3570 }, { "epoch": 0.18068944632312117, "grad_norm": 0.49246981739997864, "learning_rate": 1.8062074186222562e-05, "loss": 0.2104, "step": 3580 }, { "epoch": 0.1811941654469288, "grad_norm": 0.46744489669799805, "learning_rate": 1.8112541004289682e-05, "loss": 0.2101, "step": 3590 }, { "epoch": 0.18169888457073638, "grad_norm": 0.46315091848373413, "learning_rate": 1.8163007822356802e-05, "loss": 0.211, "step": 3600 }, { "epoch": 0.182203603694544, "grad_norm": 0.47723183035850525, "learning_rate": 1.8213474640423922e-05, "loss": 0.2083, "step": 3610 }, { "epoch": 0.1827083228183516, "grad_norm": 0.4837911128997803, "learning_rate": 1.8263941458491042e-05, "loss": 0.2082, "step": 3620 }, { "epoch": 0.18321304194215918, "grad_norm": 0.4494918882846832, "learning_rate": 1.8314408276558165e-05, "loss": 0.2097, "step": 3630 }, { "epoch": 0.1837177610659668, "grad_norm": 0.4382678270339966, "learning_rate": 1.8364875094625285e-05, "loss": 0.2053, "step": 3640 }, { "epoch": 0.18422248018977438, "grad_norm": 0.5080766677856445, "learning_rate": 1.8415341912692405e-05, "loss": 0.2072, "step": 3650 }, { "epoch": 0.184727199313582, "grad_norm": 0.46133163571357727, "learning_rate": 1.8465808730759526e-05, "loss": 0.2065, "step": 3660 }, { "epoch": 0.1852319184373896, "grad_norm": 0.4453032612800598, "learning_rate": 1.851627554882665e-05, "loss": 0.2109, "step": 3670 }, { "epoch": 0.18573663756119718, "grad_norm": 0.4881640374660492, "learning_rate": 1.856674236689377e-05, "loss": 0.2064, "step": 3680 }, { "epoch": 0.1862413566850048, "grad_norm": 0.44903120398521423, "learning_rate": 1.861720918496089e-05, "loss": 0.2094, "step": 3690 }, { "epoch": 0.1867460758088124, "grad_norm": 0.5004118084907532, "learning_rate": 1.866767600302801e-05, "loss": 0.2108, "step": 3700 }, { "epoch": 0.18725079493262, "grad_norm": 0.456538587808609, "learning_rate": 1.8718142821095133e-05, "loss": 0.2097, "step": 3710 }, { "epoch": 0.1877555140564276, "grad_norm": 0.4323200583457947, "learning_rate": 1.8768609639162253e-05, "loss": 0.211, "step": 3720 }, { "epoch": 0.1882602331802352, "grad_norm": 0.44577351212501526, "learning_rate": 1.8819076457229373e-05, "loss": 0.2053, "step": 3730 }, { "epoch": 0.1887649523040428, "grad_norm": 0.4906276762485504, "learning_rate": 1.8869543275296493e-05, "loss": 0.2084, "step": 3740 }, { "epoch": 0.1892696714278504, "grad_norm": 0.47778740525245667, "learning_rate": 1.8920010093363613e-05, "loss": 0.2093, "step": 3750 }, { "epoch": 0.189774390551658, "grad_norm": 0.47851407527923584, "learning_rate": 1.8970476911430736e-05, "loss": 0.2126, "step": 3760 }, { "epoch": 0.1902791096754656, "grad_norm": 0.47555801272392273, "learning_rate": 1.9020943729497856e-05, "loss": 0.2138, "step": 3770 }, { "epoch": 0.1907838287992732, "grad_norm": 0.4747466742992401, "learning_rate": 1.9071410547564976e-05, "loss": 0.2134, "step": 3780 }, { "epoch": 0.1912885479230808, "grad_norm": 0.4366407096385956, "learning_rate": 1.9121877365632096e-05, "loss": 0.2048, "step": 3790 }, { "epoch": 0.1917932670468884, "grad_norm": 0.47420045733451843, "learning_rate": 1.917234418369922e-05, "loss": 0.2124, "step": 3800 }, { "epoch": 0.19229798617069602, "grad_norm": 0.47648707032203674, "learning_rate": 1.922281100176634e-05, "loss": 0.2082, "step": 3810 }, { "epoch": 0.1928027052945036, "grad_norm": 0.4899962544441223, "learning_rate": 1.927327781983346e-05, "loss": 0.2092, "step": 3820 }, { "epoch": 0.1933074244183112, "grad_norm": 0.45395606756210327, "learning_rate": 1.932374463790058e-05, "loss": 0.2108, "step": 3830 }, { "epoch": 0.19381214354211881, "grad_norm": 0.4671913683414459, "learning_rate": 1.9374211455967703e-05, "loss": 0.2097, "step": 3840 }, { "epoch": 0.1943168626659264, "grad_norm": 0.48714789748191833, "learning_rate": 1.9424678274034824e-05, "loss": 0.2104, "step": 3850 }, { "epoch": 0.19482158178973402, "grad_norm": 0.46096110343933105, "learning_rate": 1.9475145092101944e-05, "loss": 0.214, "step": 3860 }, { "epoch": 0.1953263009135416, "grad_norm": 0.473842978477478, "learning_rate": 1.9525611910169064e-05, "loss": 0.2106, "step": 3870 }, { "epoch": 0.1958310200373492, "grad_norm": 0.4506091773509979, "learning_rate": 1.9576078728236184e-05, "loss": 0.2064, "step": 3880 }, { "epoch": 0.19633573916115682, "grad_norm": 0.4985959529876709, "learning_rate": 1.9626545546303307e-05, "loss": 0.2074, "step": 3890 }, { "epoch": 0.1968404582849644, "grad_norm": 0.4573221504688263, "learning_rate": 1.9677012364370427e-05, "loss": 0.2114, "step": 3900 }, { "epoch": 0.19734517740877203, "grad_norm": 0.4832017123699188, "learning_rate": 1.972747918243755e-05, "loss": 0.2069, "step": 3910 }, { "epoch": 0.19784989653257962, "grad_norm": 0.4062134027481079, "learning_rate": 1.977794600050467e-05, "loss": 0.2149, "step": 3920 }, { "epoch": 0.19835461565638723, "grad_norm": 0.4573279619216919, "learning_rate": 1.982841281857179e-05, "loss": 0.2074, "step": 3930 }, { "epoch": 0.19885933478019482, "grad_norm": 0.48879367113113403, "learning_rate": 1.9878879636638914e-05, "loss": 0.2131, "step": 3940 }, { "epoch": 0.19936405390400241, "grad_norm": 0.47412362694740295, "learning_rate": 1.9929346454706034e-05, "loss": 0.2108, "step": 3950 }, { "epoch": 0.19986877302781003, "grad_norm": 0.4407310485839844, "learning_rate": 1.9979813272773154e-05, "loss": 0.2054, "step": 3960 }, { "epoch": 0.20037349215161762, "grad_norm": 0.4495188295841217, "learning_rate": 1.999999860319271e-05, "loss": 0.2123, "step": 3970 }, { "epoch": 0.20087821127542524, "grad_norm": 0.4630189538002014, "learning_rate": 1.9999990067149568e-05, "loss": 0.2071, "step": 3980 }, { "epoch": 0.20138293039923283, "grad_norm": 0.4396592080593109, "learning_rate": 1.999997377107395e-05, "loss": 0.2162, "step": 3990 }, { "epoch": 0.20188764952304042, "grad_norm": 0.4609256982803345, "learning_rate": 1.9999949714978504e-05, "loss": 0.2104, "step": 4000 }, { "epoch": 0.20239236864684804, "grad_norm": 0.45663967728614807, "learning_rate": 1.9999917898881892e-05, "loss": 0.2076, "step": 4010 }, { "epoch": 0.20289708777065563, "grad_norm": 0.4687517285346985, "learning_rate": 1.999987832280881e-05, "loss": 0.2051, "step": 4020 }, { "epoch": 0.20340180689446324, "grad_norm": 0.4855906665325165, "learning_rate": 1.9999830986789968e-05, "loss": 0.2121, "step": 4030 }, { "epoch": 0.20390652601827083, "grad_norm": 0.4439662992954254, "learning_rate": 1.9999775890862097e-05, "loss": 0.2128, "step": 4040 }, { "epoch": 0.20441124514207842, "grad_norm": 0.5356059074401855, "learning_rate": 1.999971303506795e-05, "loss": 0.2138, "step": 4050 }, { "epoch": 0.20491596426588604, "grad_norm": 0.44190514087677, "learning_rate": 1.9999642419456308e-05, "loss": 0.2068, "step": 4060 }, { "epoch": 0.20542068338969363, "grad_norm": 0.46819841861724854, "learning_rate": 1.9999564044081962e-05, "loss": 0.212, "step": 4070 }, { "epoch": 0.20592540251350125, "grad_norm": 0.43184694647789, "learning_rate": 1.9999477909005738e-05, "loss": 0.2085, "step": 4080 }, { "epoch": 0.20643012163730884, "grad_norm": 0.4735959768295288, "learning_rate": 1.9999384014294474e-05, "loss": 0.216, "step": 4090 }, { "epoch": 0.20693484076111643, "grad_norm": 0.431597501039505, "learning_rate": 1.9999282360021035e-05, "loss": 0.2026, "step": 4100 }, { "epoch": 0.20743955988492405, "grad_norm": 0.4696648120880127, "learning_rate": 1.9999172946264304e-05, "loss": 0.2118, "step": 4110 }, { "epoch": 0.20794427900873164, "grad_norm": 0.4368724822998047, "learning_rate": 1.9999055773109187e-05, "loss": 0.215, "step": 4120 }, { "epoch": 0.20844899813253925, "grad_norm": 0.4657285511493683, "learning_rate": 1.999893084064661e-05, "loss": 0.2036, "step": 4130 }, { "epoch": 0.20895371725634684, "grad_norm": 0.4232470393180847, "learning_rate": 1.9998798148973522e-05, "loss": 0.2052, "step": 4140 }, { "epoch": 0.20945843638015443, "grad_norm": 0.4144943654537201, "learning_rate": 1.999865769819289e-05, "loss": 0.2031, "step": 4150 }, { "epoch": 0.20996315550396205, "grad_norm": 0.44187450408935547, "learning_rate": 1.9998509488413712e-05, "loss": 0.2078, "step": 4160 }, { "epoch": 0.21046787462776964, "grad_norm": 0.42849841713905334, "learning_rate": 1.9998353519750986e-05, "loss": 0.2082, "step": 4170 }, { "epoch": 0.21097259375157726, "grad_norm": 0.410536527633667, "learning_rate": 1.9998189792325757e-05, "loss": 0.208, "step": 4180 }, { "epoch": 0.21147731287538485, "grad_norm": 0.46338728070259094, "learning_rate": 1.999801830626507e-05, "loss": 0.2082, "step": 4190 }, { "epoch": 0.21198203199919244, "grad_norm": 0.4344061315059662, "learning_rate": 1.9997839061702003e-05, "loss": 0.2068, "step": 4200 }, { "epoch": 0.21248675112300006, "grad_norm": 0.42914628982543945, "learning_rate": 1.999765205877565e-05, "loss": 0.2056, "step": 4210 }, { "epoch": 0.21299147024680765, "grad_norm": 0.4740099310874939, "learning_rate": 1.9997457297631123e-05, "loss": 0.207, "step": 4220 }, { "epoch": 0.21349618937061526, "grad_norm": 0.4434734880924225, "learning_rate": 1.999725477841956e-05, "loss": 0.2098, "step": 4230 }, { "epoch": 0.21400090849442285, "grad_norm": 0.41909220814704895, "learning_rate": 1.9997044501298115e-05, "loss": 0.213, "step": 4240 }, { "epoch": 0.21450562761823044, "grad_norm": 0.4443434774875641, "learning_rate": 1.9996826466429967e-05, "loss": 0.2068, "step": 4250 }, { "epoch": 0.21501034674203806, "grad_norm": 0.46440449357032776, "learning_rate": 1.999660067398431e-05, "loss": 0.213, "step": 4260 }, { "epoch": 0.21551506586584565, "grad_norm": 0.44428780674934387, "learning_rate": 1.999636712413636e-05, "loss": 0.2067, "step": 4270 }, { "epoch": 0.21601978498965327, "grad_norm": 0.44897201657295227, "learning_rate": 1.9996125817067356e-05, "loss": 0.2123, "step": 4280 }, { "epoch": 0.21652450411346086, "grad_norm": 0.4407517910003662, "learning_rate": 1.999587675296455e-05, "loss": 0.2086, "step": 4290 }, { "epoch": 0.21702922323726845, "grad_norm": 0.4416534900665283, "learning_rate": 1.9995619932021212e-05, "loss": 0.2093, "step": 4300 }, { "epoch": 0.21753394236107607, "grad_norm": 0.47025397419929504, "learning_rate": 1.999535535443664e-05, "loss": 0.2158, "step": 4310 }, { "epoch": 0.21803866148488366, "grad_norm": 0.42740362882614136, "learning_rate": 1.999508302041615e-05, "loss": 0.2109, "step": 4320 }, { "epoch": 0.21854338060869127, "grad_norm": 0.44681379199028015, "learning_rate": 1.9994802930171077e-05, "loss": 0.2116, "step": 4330 }, { "epoch": 0.21904809973249886, "grad_norm": 0.4711915850639343, "learning_rate": 1.9994515083918763e-05, "loss": 0.21, "step": 4340 }, { "epoch": 0.21955281885630645, "grad_norm": 0.4454067647457123, "learning_rate": 1.9994219481882584e-05, "loss": 0.2056, "step": 4350 }, { "epoch": 0.22005753798011407, "grad_norm": 0.4321040213108063, "learning_rate": 1.9993916124291926e-05, "loss": 0.2096, "step": 4360 }, { "epoch": 0.22056225710392166, "grad_norm": 0.44907715916633606, "learning_rate": 1.9993605011382196e-05, "loss": 0.2079, "step": 4370 }, { "epoch": 0.22106697622772928, "grad_norm": 0.4888754189014435, "learning_rate": 1.999328614339482e-05, "loss": 0.213, "step": 4380 }, { "epoch": 0.22157169535153687, "grad_norm": 0.4669919013977051, "learning_rate": 1.9992959520577238e-05, "loss": 0.2081, "step": 4390 }, { "epoch": 0.22207641447534446, "grad_norm": 0.4628717601299286, "learning_rate": 1.9992625143182914e-05, "loss": 0.2087, "step": 4400 }, { "epoch": 0.22258113359915208, "grad_norm": 0.4592908024787903, "learning_rate": 1.999228301147133e-05, "loss": 0.2105, "step": 4410 }, { "epoch": 0.22308585272295967, "grad_norm": 0.42841342091560364, "learning_rate": 1.999193312570797e-05, "loss": 0.2139, "step": 4420 }, { "epoch": 0.22359057184676728, "grad_norm": 0.443726509809494, "learning_rate": 1.9991575486164357e-05, "loss": 0.2052, "step": 4430 }, { "epoch": 0.22409529097057487, "grad_norm": 0.42919921875, "learning_rate": 1.9991210093118015e-05, "loss": 0.2086, "step": 4440 }, { "epoch": 0.22460001009438246, "grad_norm": 0.5065860748291016, "learning_rate": 1.9990836946852494e-05, "loss": 0.2086, "step": 4450 }, { "epoch": 0.22510472921819008, "grad_norm": 0.444206178188324, "learning_rate": 1.9990456047657357e-05, "loss": 0.2097, "step": 4460 }, { "epoch": 0.22560944834199767, "grad_norm": 0.42514482140541077, "learning_rate": 1.999006739582818e-05, "loss": 0.2153, "step": 4470 }, { "epoch": 0.2261141674658053, "grad_norm": 0.4584311246871948, "learning_rate": 1.9989670991666558e-05, "loss": 0.2081, "step": 4480 }, { "epoch": 0.22661888658961288, "grad_norm": 0.45617085695266724, "learning_rate": 1.9989266835480104e-05, "loss": 0.2078, "step": 4490 }, { "epoch": 0.22712360571342047, "grad_norm": 0.4982506036758423, "learning_rate": 1.9988854927582452e-05, "loss": 0.207, "step": 4500 }, { "epoch": 0.22762832483722809, "grad_norm": 0.42006564140319824, "learning_rate": 1.998843526829323e-05, "loss": 0.2072, "step": 4510 }, { "epoch": 0.22813304396103568, "grad_norm": 0.4090621769428253, "learning_rate": 1.998800785793811e-05, "loss": 0.208, "step": 4520 }, { "epoch": 0.2286377630848433, "grad_norm": 0.45028218626976013, "learning_rate": 1.998757269684875e-05, "loss": 0.2056, "step": 4530 }, { "epoch": 0.22914248220865088, "grad_norm": 0.43163150548934937, "learning_rate": 1.9987129785362843e-05, "loss": 0.2096, "step": 4540 }, { "epoch": 0.2296472013324585, "grad_norm": 0.44366002082824707, "learning_rate": 1.9986679123824096e-05, "loss": 0.2102, "step": 4550 }, { "epoch": 0.2301519204562661, "grad_norm": 0.4207097887992859, "learning_rate": 1.9986220712582218e-05, "loss": 0.2137, "step": 4560 }, { "epoch": 0.23065663958007368, "grad_norm": 0.46169212460517883, "learning_rate": 1.998575455199294e-05, "loss": 0.2043, "step": 4570 }, { "epoch": 0.2311613587038813, "grad_norm": 0.44540101289749146, "learning_rate": 1.9985280642418e-05, "loss": 0.2078, "step": 4580 }, { "epoch": 0.2316660778276889, "grad_norm": 0.45593440532684326, "learning_rate": 1.998479898422516e-05, "loss": 0.2116, "step": 4590 }, { "epoch": 0.2321707969514965, "grad_norm": 0.4587077796459198, "learning_rate": 1.9984309577788183e-05, "loss": 0.2113, "step": 4600 }, { "epoch": 0.2326755160753041, "grad_norm": 0.4238251745700836, "learning_rate": 1.998381242348685e-05, "loss": 0.2083, "step": 4610 }, { "epoch": 0.23318023519911169, "grad_norm": 0.47338321805000305, "learning_rate": 1.9983307521706964e-05, "loss": 0.2114, "step": 4620 }, { "epoch": 0.2336849543229193, "grad_norm": 0.45549440383911133, "learning_rate": 1.9982794872840325e-05, "loss": 0.2065, "step": 4630 }, { "epoch": 0.2341896734467269, "grad_norm": 0.41257891058921814, "learning_rate": 1.9982274477284745e-05, "loss": 0.2061, "step": 4640 }, { "epoch": 0.2346943925705345, "grad_norm": 0.40934988856315613, "learning_rate": 1.9981746335444063e-05, "loss": 0.2071, "step": 4650 }, { "epoch": 0.2351991116943421, "grad_norm": 0.4533693492412567, "learning_rate": 1.9981210447728113e-05, "loss": 0.2091, "step": 4660 }, { "epoch": 0.2357038308181497, "grad_norm": 0.4373621642589569, "learning_rate": 1.9980666814552748e-05, "loss": 0.2061, "step": 4670 }, { "epoch": 0.2362085499419573, "grad_norm": 0.43047308921813965, "learning_rate": 1.9980115436339827e-05, "loss": 0.2112, "step": 4680 }, { "epoch": 0.2367132690657649, "grad_norm": 0.4146009087562561, "learning_rate": 1.9979556313517225e-05, "loss": 0.2064, "step": 4690 }, { "epoch": 0.23721798818957252, "grad_norm": 0.43192046880722046, "learning_rate": 1.9978989446518825e-05, "loss": 0.2068, "step": 4700 }, { "epoch": 0.2377227073133801, "grad_norm": 0.4342500567436218, "learning_rate": 1.997841483578451e-05, "loss": 0.2075, "step": 4710 }, { "epoch": 0.2382274264371877, "grad_norm": 0.41722989082336426, "learning_rate": 1.997783248176019e-05, "loss": 0.2069, "step": 4720 }, { "epoch": 0.2387321455609953, "grad_norm": 0.3955322504043579, "learning_rate": 1.997724238489777e-05, "loss": 0.2083, "step": 4730 }, { "epoch": 0.2392368646848029, "grad_norm": 0.4160379469394684, "learning_rate": 1.9976644545655163e-05, "loss": 0.2075, "step": 4740 }, { "epoch": 0.23974158380861052, "grad_norm": 0.43674159049987793, "learning_rate": 1.99760389644963e-05, "loss": 0.2062, "step": 4750 }, { "epoch": 0.2402463029324181, "grad_norm": 0.4491446316242218, "learning_rate": 1.997542564189112e-05, "loss": 0.2103, "step": 4760 }, { "epoch": 0.2407510220562257, "grad_norm": 0.44447171688079834, "learning_rate": 1.997480457831555e-05, "loss": 0.2134, "step": 4770 }, { "epoch": 0.24125574118003332, "grad_norm": 0.43392515182495117, "learning_rate": 1.9974175774251544e-05, "loss": 0.2103, "step": 4780 }, { "epoch": 0.2417604603038409, "grad_norm": 0.44160422682762146, "learning_rate": 1.997353923018706e-05, "loss": 0.214, "step": 4790 }, { "epoch": 0.24226517942764852, "grad_norm": 0.4248678386211395, "learning_rate": 1.997289494661606e-05, "loss": 0.2104, "step": 4800 }, { "epoch": 0.24276989855145611, "grad_norm": 0.45019054412841797, "learning_rate": 1.99722429240385e-05, "loss": 0.2091, "step": 4810 }, { "epoch": 0.2432746176752637, "grad_norm": 0.4370255470275879, "learning_rate": 1.9971583162960364e-05, "loss": 0.2117, "step": 4820 }, { "epoch": 0.24377933679907132, "grad_norm": 0.4528055787086487, "learning_rate": 1.9970915663893623e-05, "loss": 0.2133, "step": 4830 }, { "epoch": 0.2442840559228789, "grad_norm": 0.43560346961021423, "learning_rate": 1.9970240427356257e-05, "loss": 0.2122, "step": 4840 }, { "epoch": 0.24478877504668653, "grad_norm": 0.4284495711326599, "learning_rate": 1.996955745387226e-05, "loss": 0.2123, "step": 4850 }, { "epoch": 0.24529349417049412, "grad_norm": 0.4030678868293762, "learning_rate": 1.9968866743971614e-05, "loss": 0.2038, "step": 4860 }, { "epoch": 0.2457982132943017, "grad_norm": 0.4090377390384674, "learning_rate": 1.9968168298190318e-05, "loss": 0.2113, "step": 4870 }, { "epoch": 0.24630293241810933, "grad_norm": 0.4348921477794647, "learning_rate": 1.9967462117070366e-05, "loss": 0.2118, "step": 4880 }, { "epoch": 0.24680765154191692, "grad_norm": 0.43023329973220825, "learning_rate": 1.9966748201159762e-05, "loss": 0.2076, "step": 4890 }, { "epoch": 0.24731237066572453, "grad_norm": 0.4445458650588989, "learning_rate": 1.99660265510125e-05, "loss": 0.204, "step": 4900 }, { "epoch": 0.24781708978953212, "grad_norm": 0.4400614798069, "learning_rate": 1.9965297167188588e-05, "loss": 0.2174, "step": 4910 }, { "epoch": 0.24832180891333971, "grad_norm": 0.41057854890823364, "learning_rate": 1.996456005025403e-05, "loss": 0.2134, "step": 4920 }, { "epoch": 0.24882652803714733, "grad_norm": 0.4448695480823517, "learning_rate": 1.9963815200780833e-05, "loss": 0.2148, "step": 4930 }, { "epoch": 0.24933124716095492, "grad_norm": 0.4160345494747162, "learning_rate": 1.9963062619347e-05, "loss": 0.2117, "step": 4940 }, { "epoch": 0.24983596628476254, "grad_norm": 0.4251341223716736, "learning_rate": 1.9962302306536544e-05, "loss": 0.2014, "step": 4950 }, { "epoch": 0.25034068540857013, "grad_norm": 0.4156761169433594, "learning_rate": 1.9961534262939462e-05, "loss": 0.2074, "step": 4960 }, { "epoch": 0.25084540453237775, "grad_norm": 0.41890910267829895, "learning_rate": 1.9960758489151765e-05, "loss": 0.2067, "step": 4970 }, { "epoch": 0.2513501236561853, "grad_norm": 0.44092434644699097, "learning_rate": 1.995997498577545e-05, "loss": 0.2099, "step": 4980 }, { "epoch": 0.2518548427799929, "grad_norm": 0.4364526569843292, "learning_rate": 1.995918375341853e-05, "loss": 0.2107, "step": 4990 }, { "epoch": 0.25235956190380054, "grad_norm": 0.4292025566101074, "learning_rate": 1.9958384792694992e-05, "loss": 0.2069, "step": 5000 }, { "epoch": 0.25286428102760816, "grad_norm": 0.4423369765281677, "learning_rate": 1.9957578104224843e-05, "loss": 0.2122, "step": 5010 }, { "epoch": 0.2533690001514157, "grad_norm": 0.4413395822048187, "learning_rate": 1.995676368863407e-05, "loss": 0.2072, "step": 5020 }, { "epoch": 0.25387371927522334, "grad_norm": 0.43734773993492126, "learning_rate": 1.9955941546554666e-05, "loss": 0.214, "step": 5030 }, { "epoch": 0.25437843839903096, "grad_norm": 0.44729700684547424, "learning_rate": 1.9955111678624615e-05, "loss": 0.2082, "step": 5040 }, { "epoch": 0.2548831575228385, "grad_norm": 0.43439602851867676, "learning_rate": 1.9954274085487893e-05, "loss": 0.2095, "step": 5050 }, { "epoch": 0.25538787664664614, "grad_norm": 0.40715253353118896, "learning_rate": 1.9953428767794487e-05, "loss": 0.2067, "step": 5060 }, { "epoch": 0.25589259577045376, "grad_norm": 0.4260392487049103, "learning_rate": 1.995257572620036e-05, "loss": 0.2088, "step": 5070 }, { "epoch": 0.2563973148942613, "grad_norm": 0.423867791891098, "learning_rate": 1.9951714961367476e-05, "loss": 0.206, "step": 5080 }, { "epoch": 0.25690203401806894, "grad_norm": 0.4600396156311035, "learning_rate": 1.9950846473963792e-05, "loss": 0.2053, "step": 5090 }, { "epoch": 0.25740675314187655, "grad_norm": 0.42651209235191345, "learning_rate": 1.994997026466326e-05, "loss": 0.2078, "step": 5100 }, { "epoch": 0.25791147226568417, "grad_norm": 0.39605095982551575, "learning_rate": 1.994908633414582e-05, "loss": 0.2075, "step": 5110 }, { "epoch": 0.25841619138949173, "grad_norm": 0.4656001329421997, "learning_rate": 1.99481946830974e-05, "loss": 0.208, "step": 5120 }, { "epoch": 0.25892091051329935, "grad_norm": 0.4509201943874359, "learning_rate": 1.994729531220994e-05, "loss": 0.2087, "step": 5130 }, { "epoch": 0.25942562963710697, "grad_norm": 0.45018404722213745, "learning_rate": 1.994638822218134e-05, "loss": 0.209, "step": 5140 }, { "epoch": 0.25993034876091453, "grad_norm": 0.4501037895679474, "learning_rate": 1.994547341371551e-05, "loss": 0.2085, "step": 5150 }, { "epoch": 0.26043506788472215, "grad_norm": 0.4430723190307617, "learning_rate": 1.994455088752235e-05, "loss": 0.207, "step": 5160 }, { "epoch": 0.26093978700852977, "grad_norm": 0.41028741002082825, "learning_rate": 1.994362064431774e-05, "loss": 0.2085, "step": 5170 }, { "epoch": 0.26144450613233733, "grad_norm": 0.3991943597793579, "learning_rate": 1.994268268482355e-05, "loss": 0.2098, "step": 5180 }, { "epoch": 0.26194922525614495, "grad_norm": 0.4641764760017395, "learning_rate": 1.994173700976765e-05, "loss": 0.2108, "step": 5190 }, { "epoch": 0.26245394437995256, "grad_norm": 0.416415810585022, "learning_rate": 1.9940783619883875e-05, "loss": 0.212, "step": 5200 }, { "epoch": 0.2629586635037602, "grad_norm": 0.419129878282547, "learning_rate": 1.9939822515912066e-05, "loss": 0.2065, "step": 5210 }, { "epoch": 0.26346338262756774, "grad_norm": 0.4185030460357666, "learning_rate": 1.9938853698598044e-05, "loss": 0.2083, "step": 5220 }, { "epoch": 0.26396810175137536, "grad_norm": 0.4453229308128357, "learning_rate": 1.9937877168693616e-05, "loss": 0.2073, "step": 5230 }, { "epoch": 0.264472820875183, "grad_norm": 0.4194733798503876, "learning_rate": 1.993689292695657e-05, "loss": 0.2105, "step": 5240 }, { "epoch": 0.26497753999899054, "grad_norm": 0.41537266969680786, "learning_rate": 1.993590097415068e-05, "loss": 0.2084, "step": 5250 }, { "epoch": 0.26548225912279816, "grad_norm": 0.42537128925323486, "learning_rate": 1.993490131104571e-05, "loss": 0.2068, "step": 5260 }, { "epoch": 0.2659869782466058, "grad_norm": 0.42887747287750244, "learning_rate": 1.9933893938417404e-05, "loss": 0.2082, "step": 5270 }, { "epoch": 0.26649169737041334, "grad_norm": 0.44657662510871887, "learning_rate": 1.993287885704748e-05, "loss": 0.2039, "step": 5280 }, { "epoch": 0.26699641649422096, "grad_norm": 0.4399039149284363, "learning_rate": 1.993185606772365e-05, "loss": 0.2101, "step": 5290 }, { "epoch": 0.2675011356180286, "grad_norm": 0.4244379997253418, "learning_rate": 1.9930825571239603e-05, "loss": 0.2066, "step": 5300 }, { "epoch": 0.2680058547418362, "grad_norm": 0.4329201281070709, "learning_rate": 1.9929787368395003e-05, "loss": 0.2138, "step": 5310 }, { "epoch": 0.26851057386564375, "grad_norm": 0.4212918281555176, "learning_rate": 1.992874145999551e-05, "loss": 0.2098, "step": 5320 }, { "epoch": 0.26901529298945137, "grad_norm": 0.4777679443359375, "learning_rate": 1.9927687846852743e-05, "loss": 0.2154, "step": 5330 }, { "epoch": 0.269520012113259, "grad_norm": 0.4291732907295227, "learning_rate": 1.9926626529784313e-05, "loss": 0.2114, "step": 5340 }, { "epoch": 0.27002473123706655, "grad_norm": 0.4233384430408478, "learning_rate": 1.9925557509613805e-05, "loss": 0.2072, "step": 5350 }, { "epoch": 0.27052945036087417, "grad_norm": 0.4097965955734253, "learning_rate": 1.9924480787170792e-05, "loss": 0.207, "step": 5360 }, { "epoch": 0.2710341694846818, "grad_norm": 0.4130129814147949, "learning_rate": 1.9923396363290807e-05, "loss": 0.2055, "step": 5370 }, { "epoch": 0.27153888860848935, "grad_norm": 0.44088903069496155, "learning_rate": 1.9922304238815364e-05, "loss": 0.2038, "step": 5380 }, { "epoch": 0.27204360773229697, "grad_norm": 0.3887929618358612, "learning_rate": 1.9921204414591964e-05, "loss": 0.2098, "step": 5390 }, { "epoch": 0.2725483268561046, "grad_norm": 0.40305423736572266, "learning_rate": 1.9920096891474067e-05, "loss": 0.2089, "step": 5400 }, { "epoch": 0.2730530459799122, "grad_norm": 0.4090634286403656, "learning_rate": 1.9918981670321124e-05, "loss": 0.2081, "step": 5410 }, { "epoch": 0.27355776510371976, "grad_norm": 0.4016440808773041, "learning_rate": 1.9917858751998547e-05, "loss": 0.2103, "step": 5420 }, { "epoch": 0.2740624842275274, "grad_norm": 0.3911189138889313, "learning_rate": 1.9916728137377724e-05, "loss": 0.2128, "step": 5430 }, { "epoch": 0.274567203351335, "grad_norm": 0.4302690923213959, "learning_rate": 1.9915589827336015e-05, "loss": 0.2141, "step": 5440 }, { "epoch": 0.27507192247514256, "grad_norm": 0.39874517917633057, "learning_rate": 1.9914443822756757e-05, "loss": 0.2097, "step": 5450 }, { "epoch": 0.2755766415989502, "grad_norm": 0.4208013713359833, "learning_rate": 1.9913290124529253e-05, "loss": 0.211, "step": 5460 }, { "epoch": 0.2760813607227578, "grad_norm": 0.3907218873500824, "learning_rate": 1.991212873354878e-05, "loss": 0.2091, "step": 5470 }, { "epoch": 0.2765860798465654, "grad_norm": 0.3849351704120636, "learning_rate": 1.9910959650716576e-05, "loss": 0.2055, "step": 5480 }, { "epoch": 0.277090798970373, "grad_norm": 0.4441866874694824, "learning_rate": 1.990978287693986e-05, "loss": 0.2124, "step": 5490 }, { "epoch": 0.2775955180941806, "grad_norm": 0.40791434049606323, "learning_rate": 1.9908598413131805e-05, "loss": 0.2111, "step": 5500 }, { "epoch": 0.2781002372179882, "grad_norm": 0.4549468457698822, "learning_rate": 1.990740626021157e-05, "loss": 0.2132, "step": 5510 }, { "epoch": 0.2786049563417958, "grad_norm": 0.427784264087677, "learning_rate": 1.9906206419104264e-05, "loss": 0.2044, "step": 5520 }, { "epoch": 0.2791096754656034, "grad_norm": 0.46978235244750977, "learning_rate": 1.9904998890740973e-05, "loss": 0.2095, "step": 5530 }, { "epoch": 0.279614394589411, "grad_norm": 0.42245644330978394, "learning_rate": 1.9903783676058738e-05, "loss": 0.2119, "step": 5540 }, { "epoch": 0.28011911371321857, "grad_norm": 0.42393338680267334, "learning_rate": 1.9902560776000573e-05, "loss": 0.2129, "step": 5550 }, { "epoch": 0.2806238328370262, "grad_norm": 0.41817086935043335, "learning_rate": 1.9901330191515455e-05, "loss": 0.2104, "step": 5560 }, { "epoch": 0.2811285519608338, "grad_norm": 0.4182088375091553, "learning_rate": 1.990009192355832e-05, "loss": 0.2109, "step": 5570 }, { "epoch": 0.2816332710846414, "grad_norm": 0.41876691579818726, "learning_rate": 1.9898845973090074e-05, "loss": 0.2022, "step": 5580 }, { "epoch": 0.282137990208449, "grad_norm": 0.4053371250629425, "learning_rate": 1.989759234107757e-05, "loss": 0.2073, "step": 5590 }, { "epoch": 0.2826427093322566, "grad_norm": 0.41588065028190613, "learning_rate": 1.9896331028493642e-05, "loss": 0.2121, "step": 5600 }, { "epoch": 0.2831474284560642, "grad_norm": 0.3771092891693115, "learning_rate": 1.9895062036317068e-05, "loss": 0.2085, "step": 5610 }, { "epoch": 0.2836521475798718, "grad_norm": 0.39868807792663574, "learning_rate": 1.989378536553259e-05, "loss": 0.2084, "step": 5620 }, { "epoch": 0.2841568667036794, "grad_norm": 0.43951281905174255, "learning_rate": 1.9892501017130915e-05, "loss": 0.2124, "step": 5630 }, { "epoch": 0.284661585827487, "grad_norm": 0.42283257842063904, "learning_rate": 1.9891208992108697e-05, "loss": 0.2069, "step": 5640 }, { "epoch": 0.2851663049512946, "grad_norm": 0.3722674548625946, "learning_rate": 1.9889909291468556e-05, "loss": 0.2051, "step": 5650 }, { "epoch": 0.2856710240751022, "grad_norm": 0.39864447712898254, "learning_rate": 1.9888601916219063e-05, "loss": 0.2111, "step": 5660 }, { "epoch": 0.2861757431989098, "grad_norm": 0.4220223128795624, "learning_rate": 1.9887286867374745e-05, "loss": 0.2119, "step": 5670 }, { "epoch": 0.28668046232271743, "grad_norm": 0.45008954405784607, "learning_rate": 1.988596414595609e-05, "loss": 0.2096, "step": 5680 }, { "epoch": 0.287185181446525, "grad_norm": 0.393761545419693, "learning_rate": 1.988463375298953e-05, "loss": 0.2067, "step": 5690 }, { "epoch": 0.2876899005703326, "grad_norm": 0.3759346306324005, "learning_rate": 1.988329568950746e-05, "loss": 0.2071, "step": 5700 }, { "epoch": 0.28819461969414023, "grad_norm": 0.3997967541217804, "learning_rate": 1.988194995654822e-05, "loss": 0.2016, "step": 5710 }, { "epoch": 0.2886993388179478, "grad_norm": 0.40321558713912964, "learning_rate": 1.9880596555156107e-05, "loss": 0.2077, "step": 5720 }, { "epoch": 0.2892040579417554, "grad_norm": 0.40369144082069397, "learning_rate": 1.987923548638136e-05, "loss": 0.2026, "step": 5730 }, { "epoch": 0.28970877706556303, "grad_norm": 0.415730744600296, "learning_rate": 1.9877866751280177e-05, "loss": 0.203, "step": 5740 }, { "epoch": 0.2902134961893706, "grad_norm": 0.40590837597846985, "learning_rate": 1.9876490350914703e-05, "loss": 0.2009, "step": 5750 }, { "epoch": 0.2907182153131782, "grad_norm": 0.42671629786491394, "learning_rate": 1.987510628635303e-05, "loss": 0.2098, "step": 5760 }, { "epoch": 0.2912229344369858, "grad_norm": 0.3944723606109619, "learning_rate": 1.9873714558669197e-05, "loss": 0.204, "step": 5770 }, { "epoch": 0.29172765356079344, "grad_norm": 0.4174182415008545, "learning_rate": 1.9872315168943192e-05, "loss": 0.2088, "step": 5780 }, { "epoch": 0.292232372684601, "grad_norm": 0.4163215160369873, "learning_rate": 1.9870908118260943e-05, "loss": 0.2021, "step": 5790 }, { "epoch": 0.2927370918084086, "grad_norm": 0.4151400327682495, "learning_rate": 1.986949340771433e-05, "loss": 0.2075, "step": 5800 }, { "epoch": 0.29324181093221624, "grad_norm": 0.44372260570526123, "learning_rate": 1.9868071038401175e-05, "loss": 0.2092, "step": 5810 }, { "epoch": 0.2937465300560238, "grad_norm": 0.4433077573776245, "learning_rate": 1.9866641011425237e-05, "loss": 0.2095, "step": 5820 }, { "epoch": 0.2942512491798314, "grad_norm": 0.412314772605896, "learning_rate": 1.986520332789623e-05, "loss": 0.2096, "step": 5830 }, { "epoch": 0.29475596830363904, "grad_norm": 0.41241535544395447, "learning_rate": 1.9863757988929797e-05, "loss": 0.2071, "step": 5840 }, { "epoch": 0.2952606874274466, "grad_norm": 0.41660410165786743, "learning_rate": 1.9862304995647526e-05, "loss": 0.2107, "step": 5850 }, { "epoch": 0.2957654065512542, "grad_norm": 0.4263871908187866, "learning_rate": 1.9860844349176954e-05, "loss": 0.2113, "step": 5860 }, { "epoch": 0.29627012567506184, "grad_norm": 0.38611581921577454, "learning_rate": 1.985937605065154e-05, "loss": 0.2133, "step": 5870 }, { "epoch": 0.29677484479886945, "grad_norm": 0.4042183756828308, "learning_rate": 1.985790010121069e-05, "loss": 0.2032, "step": 5880 }, { "epoch": 0.297279563922677, "grad_norm": 0.4147700369358063, "learning_rate": 1.9856416501999754e-05, "loss": 0.2025, "step": 5890 }, { "epoch": 0.29778428304648463, "grad_norm": 0.423336386680603, "learning_rate": 1.9854925254170004e-05, "loss": 0.2113, "step": 5900 }, { "epoch": 0.29828900217029225, "grad_norm": 0.4082251191139221, "learning_rate": 1.9853426358878654e-05, "loss": 0.2093, "step": 5910 }, { "epoch": 0.2987937212940998, "grad_norm": 0.4519009590148926, "learning_rate": 1.9851919817288858e-05, "loss": 0.2103, "step": 5920 }, { "epoch": 0.29929844041790743, "grad_norm": 0.386529803276062, "learning_rate": 1.9850405630569692e-05, "loss": 0.2095, "step": 5930 }, { "epoch": 0.29980315954171505, "grad_norm": 0.4266643226146698, "learning_rate": 1.9848883799896176e-05, "loss": 0.2124, "step": 5940 }, { "epoch": 0.3003078786655226, "grad_norm": 0.4103555977344513, "learning_rate": 1.9847354326449256e-05, "loss": 0.2126, "step": 5950 }, { "epoch": 0.3008125977893302, "grad_norm": 0.38030311465263367, "learning_rate": 1.9845817211415804e-05, "loss": 0.2065, "step": 5960 }, { "epoch": 0.30131731691313784, "grad_norm": 0.4409065544605255, "learning_rate": 1.984427245598864e-05, "loss": 0.2176, "step": 5970 }, { "epoch": 0.30182203603694546, "grad_norm": 0.41631922125816345, "learning_rate": 1.9842720061366484e-05, "loss": 0.2131, "step": 5980 }, { "epoch": 0.302326755160753, "grad_norm": 0.4635816216468811, "learning_rate": 1.984116002875401e-05, "loss": 0.2164, "step": 5990 }, { "epoch": 0.30283147428456064, "grad_norm": 0.4287009835243225, "learning_rate": 1.9839592359361816e-05, "loss": 0.211, "step": 6000 }, { "epoch": 0.30333619340836826, "grad_norm": 0.39588597416877747, "learning_rate": 1.9838017054406405e-05, "loss": 0.2073, "step": 6010 }, { "epoch": 0.3038409125321758, "grad_norm": 0.4438442885875702, "learning_rate": 1.983643411511023e-05, "loss": 0.2031, "step": 6020 }, { "epoch": 0.30434563165598344, "grad_norm": 0.43027395009994507, "learning_rate": 1.9834843542701652e-05, "loss": 0.2104, "step": 6030 }, { "epoch": 0.30485035077979106, "grad_norm": 0.5001382231712341, "learning_rate": 1.983324533841497e-05, "loss": 0.2078, "step": 6040 }, { "epoch": 0.3053550699035987, "grad_norm": 0.41776421666145325, "learning_rate": 1.983163950349039e-05, "loss": 0.2099, "step": 6050 }, { "epoch": 0.30585978902740624, "grad_norm": 0.42034173011779785, "learning_rate": 1.9830026039174047e-05, "loss": 0.2092, "step": 6060 }, { "epoch": 0.30636450815121385, "grad_norm": 0.44205567240715027, "learning_rate": 1.9828404946717997e-05, "loss": 0.2118, "step": 6070 }, { "epoch": 0.30686922727502147, "grad_norm": 0.42176687717437744, "learning_rate": 1.9826776227380217e-05, "loss": 0.2081, "step": 6080 }, { "epoch": 0.30737394639882903, "grad_norm": 0.39319849014282227, "learning_rate": 1.9825139882424594e-05, "loss": 0.2037, "step": 6090 }, { "epoch": 0.30787866552263665, "grad_norm": 0.4079185724258423, "learning_rate": 1.9823495913120942e-05, "loss": 0.2154, "step": 6100 }, { "epoch": 0.30838338464644427, "grad_norm": 0.39221206307411194, "learning_rate": 1.9821844320744988e-05, "loss": 0.202, "step": 6110 }, { "epoch": 0.30888810377025183, "grad_norm": 0.394840806722641, "learning_rate": 1.9820185106578374e-05, "loss": 0.2079, "step": 6120 }, { "epoch": 0.30939282289405945, "grad_norm": 0.4356917440891266, "learning_rate": 1.9818518271908655e-05, "loss": 0.2046, "step": 6130 }, { "epoch": 0.30989754201786707, "grad_norm": 0.3984021842479706, "learning_rate": 1.9816843818029303e-05, "loss": 0.2085, "step": 6140 }, { "epoch": 0.3104022611416747, "grad_norm": 0.4020964503288269, "learning_rate": 1.9815161746239702e-05, "loss": 0.2078, "step": 6150 }, { "epoch": 0.31090698026548225, "grad_norm": 0.3983485996723175, "learning_rate": 1.9813472057845143e-05, "loss": 0.2075, "step": 6160 }, { "epoch": 0.31141169938928986, "grad_norm": 0.43550729751586914, "learning_rate": 1.9811774754156836e-05, "loss": 0.2065, "step": 6170 }, { "epoch": 0.3119164185130975, "grad_norm": 0.42853283882141113, "learning_rate": 1.981006983649189e-05, "loss": 0.2082, "step": 6180 }, { "epoch": 0.31242113763690504, "grad_norm": 0.3858283758163452, "learning_rate": 1.980835730617333e-05, "loss": 0.2047, "step": 6190 }, { "epoch": 0.31292585676071266, "grad_norm": 0.41216278076171875, "learning_rate": 1.9806637164530088e-05, "loss": 0.207, "step": 6200 }, { "epoch": 0.3134305758845203, "grad_norm": 0.4008423686027527, "learning_rate": 1.9804909412897003e-05, "loss": 0.2092, "step": 6210 }, { "epoch": 0.31393529500832784, "grad_norm": 0.41772013902664185, "learning_rate": 1.980317405261481e-05, "loss": 0.2065, "step": 6220 }, { "epoch": 0.31444001413213546, "grad_norm": 0.41248050332069397, "learning_rate": 1.980143108503016e-05, "loss": 0.2084, "step": 6230 }, { "epoch": 0.3149447332559431, "grad_norm": 0.4062042534351349, "learning_rate": 1.9799680511495602e-05, "loss": 0.2032, "step": 6240 }, { "epoch": 0.3154494523797507, "grad_norm": 0.4108707308769226, "learning_rate": 1.979792233336959e-05, "loss": 0.2061, "step": 6250 }, { "epoch": 0.31595417150355826, "grad_norm": 0.4284683167934418, "learning_rate": 1.9796156552016476e-05, "loss": 0.2079, "step": 6260 }, { "epoch": 0.3164588906273659, "grad_norm": 0.4208002984523773, "learning_rate": 1.9794383168806512e-05, "loss": 0.2135, "step": 6270 }, { "epoch": 0.3169636097511735, "grad_norm": 0.44342759251594543, "learning_rate": 1.9792602185115855e-05, "loss": 0.2064, "step": 6280 }, { "epoch": 0.31746832887498105, "grad_norm": 0.4113001823425293, "learning_rate": 1.9790813602326548e-05, "loss": 0.2045, "step": 6290 }, { "epoch": 0.31797304799878867, "grad_norm": 0.38857993483543396, "learning_rate": 1.978901742182654e-05, "loss": 0.2078, "step": 6300 }, { "epoch": 0.3184777671225963, "grad_norm": 0.4491465091705322, "learning_rate": 1.9787213645009685e-05, "loss": 0.21, "step": 6310 }, { "epoch": 0.31898248624640385, "grad_norm": 0.3899092674255371, "learning_rate": 1.978540227327571e-05, "loss": 0.2062, "step": 6320 }, { "epoch": 0.31948720537021147, "grad_norm": 0.4059198498725891, "learning_rate": 1.9783583308030248e-05, "loss": 0.2142, "step": 6330 }, { "epoch": 0.3199919244940191, "grad_norm": 0.41340652108192444, "learning_rate": 1.9781756750684824e-05, "loss": 0.2055, "step": 6340 }, { "epoch": 0.3204966436178267, "grad_norm": 0.41715288162231445, "learning_rate": 1.9779922602656858e-05, "loss": 0.2064, "step": 6350 }, { "epoch": 0.32100136274163427, "grad_norm": 0.4375815689563751, "learning_rate": 1.9778080865369654e-05, "loss": 0.2155, "step": 6360 }, { "epoch": 0.3215060818654419, "grad_norm": 0.41439878940582275, "learning_rate": 1.9776231540252403e-05, "loss": 0.2065, "step": 6370 }, { "epoch": 0.3220108009892495, "grad_norm": 0.38811203837394714, "learning_rate": 1.9774374628740194e-05, "loss": 0.2015, "step": 6380 }, { "epoch": 0.32251552011305706, "grad_norm": 0.4033221900463104, "learning_rate": 1.9772510132273998e-05, "loss": 0.2127, "step": 6390 }, { "epoch": 0.3230202392368647, "grad_norm": 0.41507217288017273, "learning_rate": 1.9770638052300667e-05, "loss": 0.2055, "step": 6400 }, { "epoch": 0.3235249583606723, "grad_norm": 0.3831386864185333, "learning_rate": 1.9768758390272946e-05, "loss": 0.2086, "step": 6410 }, { "epoch": 0.32402967748447986, "grad_norm": 0.415081650018692, "learning_rate": 1.976687114764946e-05, "loss": 0.213, "step": 6420 }, { "epoch": 0.3245343966082875, "grad_norm": 0.4058787524700165, "learning_rate": 1.976497632589472e-05, "loss": 0.203, "step": 6430 }, { "epoch": 0.3250391157320951, "grad_norm": 0.4149510860443115, "learning_rate": 1.9763073926479105e-05, "loss": 0.2115, "step": 6440 }, { "epoch": 0.3255438348559027, "grad_norm": 0.3906279504299164, "learning_rate": 1.9761163950878897e-05, "loss": 0.2004, "step": 6450 }, { "epoch": 0.3260485539797103, "grad_norm": 0.43657800555229187, "learning_rate": 1.975924640057624e-05, "loss": 0.2065, "step": 6460 }, { "epoch": 0.3265532731035179, "grad_norm": 0.3803505003452301, "learning_rate": 1.9757321277059156e-05, "loss": 0.2129, "step": 6470 }, { "epoch": 0.3270579922273255, "grad_norm": 0.39368507266044617, "learning_rate": 1.9755388581821556e-05, "loss": 0.2077, "step": 6480 }, { "epoch": 0.3275627113511331, "grad_norm": 0.41575753688812256, "learning_rate": 1.9753448316363215e-05, "loss": 0.2101, "step": 6490 }, { "epoch": 0.3280674304749407, "grad_norm": 0.4082091152667999, "learning_rate": 1.9751500482189787e-05, "loss": 0.2044, "step": 6500 }, { "epoch": 0.3285721495987483, "grad_norm": 0.3808952867984772, "learning_rate": 1.97495450808128e-05, "loss": 0.2127, "step": 6510 }, { "epoch": 0.32907686872255587, "grad_norm": 0.41712161898612976, "learning_rate": 1.974758211374965e-05, "loss": 0.2073, "step": 6520 }, { "epoch": 0.3295815878463635, "grad_norm": 0.3919859826564789, "learning_rate": 1.9745611582523616e-05, "loss": 0.2051, "step": 6530 }, { "epoch": 0.3300863069701711, "grad_norm": 0.47025394439697266, "learning_rate": 1.9743633488663833e-05, "loss": 0.213, "step": 6540 }, { "epoch": 0.3305910260939787, "grad_norm": 0.44702544808387756, "learning_rate": 1.9741647833705303e-05, "loss": 0.2043, "step": 6550 }, { "epoch": 0.3310957452177863, "grad_norm": 0.3706350326538086, "learning_rate": 1.9739654619188915e-05, "loss": 0.205, "step": 6560 }, { "epoch": 0.3316004643415939, "grad_norm": 0.46079081296920776, "learning_rate": 1.9737653846661402e-05, "loss": 0.2053, "step": 6570 }, { "epoch": 0.3321051834654015, "grad_norm": 0.413225382566452, "learning_rate": 1.9735645517675378e-05, "loss": 0.2088, "step": 6580 }, { "epoch": 0.3326099025892091, "grad_norm": 0.36785048246383667, "learning_rate": 1.973362963378931e-05, "loss": 0.1967, "step": 6590 }, { "epoch": 0.3331146217130167, "grad_norm": 0.42024168372154236, "learning_rate": 1.9731606196567527e-05, "loss": 0.2087, "step": 6600 }, { "epoch": 0.3336193408368243, "grad_norm": 0.416878879070282, "learning_rate": 1.9729575207580237e-05, "loss": 0.205, "step": 6610 }, { "epoch": 0.3341240599606319, "grad_norm": 0.3891215920448303, "learning_rate": 1.9727536668403486e-05, "loss": 0.2105, "step": 6620 }, { "epoch": 0.3346287790844395, "grad_norm": 0.3856225609779358, "learning_rate": 1.9725490580619193e-05, "loss": 0.2057, "step": 6630 }, { "epoch": 0.3351334982082471, "grad_norm": 0.40319544076919556, "learning_rate": 1.972343694581513e-05, "loss": 0.2164, "step": 6640 }, { "epoch": 0.33563821733205473, "grad_norm": 0.39841437339782715, "learning_rate": 1.972137576558492e-05, "loss": 0.2083, "step": 6650 }, { "epoch": 0.3361429364558623, "grad_norm": 0.4119560718536377, "learning_rate": 1.971930704152806e-05, "loss": 0.2056, "step": 6660 }, { "epoch": 0.3366476555796699, "grad_norm": 0.39955729246139526, "learning_rate": 1.9717230775249873e-05, "loss": 0.2056, "step": 6670 }, { "epoch": 0.33715237470347753, "grad_norm": 0.4089430570602417, "learning_rate": 1.971514696836156e-05, "loss": 0.2032, "step": 6680 }, { "epoch": 0.3376570938272851, "grad_norm": 0.3785223364830017, "learning_rate": 1.971305562248016e-05, "loss": 0.2075, "step": 6690 }, { "epoch": 0.3381618129510927, "grad_norm": 0.3994757831096649, "learning_rate": 1.9710956739228565e-05, "loss": 0.2117, "step": 6700 }, { "epoch": 0.33866653207490033, "grad_norm": 0.4081379771232605, "learning_rate": 1.970885032023552e-05, "loss": 0.2105, "step": 6710 }, { "epoch": 0.33917125119870795, "grad_norm": 0.40712255239486694, "learning_rate": 1.9706736367135613e-05, "loss": 0.2, "step": 6720 }, { "epoch": 0.3396759703225155, "grad_norm": 0.41339489817619324, "learning_rate": 1.9704614881569282e-05, "loss": 0.2141, "step": 6730 }, { "epoch": 0.3401806894463231, "grad_norm": 0.4159870147705078, "learning_rate": 1.9702485865182805e-05, "loss": 0.2087, "step": 6740 }, { "epoch": 0.34068540857013074, "grad_norm": 0.39818209409713745, "learning_rate": 1.9700349319628305e-05, "loss": 0.2004, "step": 6750 }, { "epoch": 0.3411901276939383, "grad_norm": 0.43601059913635254, "learning_rate": 1.9698205246563757e-05, "loss": 0.2071, "step": 6760 }, { "epoch": 0.3416948468177459, "grad_norm": 0.39479944109916687, "learning_rate": 1.969605364765297e-05, "loss": 0.202, "step": 6770 }, { "epoch": 0.34219956594155354, "grad_norm": 0.41283515095710754, "learning_rate": 1.9693894524565585e-05, "loss": 0.2113, "step": 6780 }, { "epoch": 0.3427042850653611, "grad_norm": 0.42678365111351013, "learning_rate": 1.9691727878977094e-05, "loss": 0.2089, "step": 6790 }, { "epoch": 0.3432090041891687, "grad_norm": 0.3861899673938751, "learning_rate": 1.968955371256883e-05, "loss": 0.2061, "step": 6800 }, { "epoch": 0.34371372331297634, "grad_norm": 0.41596877574920654, "learning_rate": 1.9687372027027948e-05, "loss": 0.2066, "step": 6810 }, { "epoch": 0.34421844243678396, "grad_norm": 0.38345086574554443, "learning_rate": 1.968518282404744e-05, "loss": 0.1991, "step": 6820 }, { "epoch": 0.3447231615605915, "grad_norm": 0.4169529378414154, "learning_rate": 1.9682986105326148e-05, "loss": 0.2103, "step": 6830 }, { "epoch": 0.34522788068439914, "grad_norm": 0.3927992880344391, "learning_rate": 1.9680781872568725e-05, "loss": 0.2084, "step": 6840 }, { "epoch": 0.34573259980820675, "grad_norm": 0.42318835854530334, "learning_rate": 1.967857012748567e-05, "loss": 0.2069, "step": 6850 }, { "epoch": 0.3462373189320143, "grad_norm": 0.38372209668159485, "learning_rate": 1.9676350871793303e-05, "loss": 0.2042, "step": 6860 }, { "epoch": 0.34674203805582193, "grad_norm": 0.43242713809013367, "learning_rate": 1.967412410721378e-05, "loss": 0.2098, "step": 6870 }, { "epoch": 0.34724675717962955, "grad_norm": 0.3919036388397217, "learning_rate": 1.9671889835475075e-05, "loss": 0.2115, "step": 6880 }, { "epoch": 0.3477514763034371, "grad_norm": 0.3822705149650574, "learning_rate": 1.966964805831099e-05, "loss": 0.2103, "step": 6890 }, { "epoch": 0.34825619542724473, "grad_norm": 0.41578924655914307, "learning_rate": 1.9667398777461153e-05, "loss": 0.2098, "step": 6900 }, { "epoch": 0.34876091455105235, "grad_norm": 0.41378557682037354, "learning_rate": 1.966514199467102e-05, "loss": 0.2124, "step": 6910 }, { "epoch": 0.34926563367485997, "grad_norm": 0.4057765603065491, "learning_rate": 1.9662877711691863e-05, "loss": 0.2043, "step": 6920 }, { "epoch": 0.3497703527986675, "grad_norm": 0.4015139639377594, "learning_rate": 1.966060593028077e-05, "loss": 0.2089, "step": 6930 }, { "epoch": 0.35027507192247515, "grad_norm": 0.3479464650154114, "learning_rate": 1.965832665220066e-05, "loss": 0.1983, "step": 6940 }, { "epoch": 0.35077979104628276, "grad_norm": 0.3926767110824585, "learning_rate": 1.9656039879220253e-05, "loss": 0.2062, "step": 6950 }, { "epoch": 0.3512845101700903, "grad_norm": 0.4035007953643799, "learning_rate": 1.96537456131141e-05, "loss": 0.2044, "step": 6960 }, { "epoch": 0.35178922929389794, "grad_norm": 0.3953687250614166, "learning_rate": 1.965144385566256e-05, "loss": 0.2055, "step": 6970 }, { "epoch": 0.35229394841770556, "grad_norm": 0.41460809111595154, "learning_rate": 1.9649134608651805e-05, "loss": 0.2104, "step": 6980 }, { "epoch": 0.3527986675415131, "grad_norm": 0.38975444436073303, "learning_rate": 1.9646817873873818e-05, "loss": 0.2089, "step": 6990 }, { "epoch": 0.35330338666532074, "grad_norm": 0.38710498809814453, "learning_rate": 1.96444936531264e-05, "loss": 0.2048, "step": 7000 }, { "epoch": 0.35380810578912836, "grad_norm": 0.38204658031463623, "learning_rate": 1.9642161948213147e-05, "loss": 0.2013, "step": 7010 }, { "epoch": 0.354312824912936, "grad_norm": 0.4161977171897888, "learning_rate": 1.963982276094348e-05, "loss": 0.2079, "step": 7020 }, { "epoch": 0.35481754403674354, "grad_norm": 0.39030978083610535, "learning_rate": 1.9637476093132615e-05, "loss": 0.2046, "step": 7030 }, { "epoch": 0.35532226316055116, "grad_norm": 0.40646493434906006, "learning_rate": 1.9635121946601574e-05, "loss": 0.2076, "step": 7040 }, { "epoch": 0.3558269822843588, "grad_norm": 0.4005410671234131, "learning_rate": 1.9632760323177185e-05, "loss": 0.204, "step": 7050 }, { "epoch": 0.35633170140816633, "grad_norm": 0.41471466422080994, "learning_rate": 1.9630391224692077e-05, "loss": 0.2083, "step": 7060 }, { "epoch": 0.35683642053197395, "grad_norm": 0.40808790922164917, "learning_rate": 1.9628014652984683e-05, "loss": 0.2047, "step": 7070 }, { "epoch": 0.35734113965578157, "grad_norm": 0.38818976283073425, "learning_rate": 1.9625630609899226e-05, "loss": 0.2039, "step": 7080 }, { "epoch": 0.35784585877958913, "grad_norm": 0.5258064866065979, "learning_rate": 1.9623239097285734e-05, "loss": 0.2022, "step": 7090 }, { "epoch": 0.35835057790339675, "grad_norm": 0.41228073835372925, "learning_rate": 1.962084011700004e-05, "loss": 0.2041, "step": 7100 }, { "epoch": 0.35885529702720437, "grad_norm": 0.3778305947780609, "learning_rate": 1.961843367090375e-05, "loss": 0.1981, "step": 7110 }, { "epoch": 0.359360016151012, "grad_norm": 0.3965858221054077, "learning_rate": 1.9616019760864284e-05, "loss": 0.2042, "step": 7120 }, { "epoch": 0.35986473527481955, "grad_norm": 0.3994516432285309, "learning_rate": 1.961359838875484e-05, "loss": 0.2063, "step": 7130 }, { "epoch": 0.36036945439862716, "grad_norm": 0.4078081548213959, "learning_rate": 1.961116955645442e-05, "loss": 0.2074, "step": 7140 }, { "epoch": 0.3608741735224348, "grad_norm": 0.39783546328544617, "learning_rate": 1.96087332658478e-05, "loss": 0.2058, "step": 7150 }, { "epoch": 0.36137889264624234, "grad_norm": 0.41310301423072815, "learning_rate": 1.9606289518825555e-05, "loss": 0.2022, "step": 7160 }, { "epoch": 0.36188361177004996, "grad_norm": 0.3897462785243988, "learning_rate": 1.9603838317284042e-05, "loss": 0.2095, "step": 7170 }, { "epoch": 0.3623883308938576, "grad_norm": 0.459762841463089, "learning_rate": 1.9601379663125405e-05, "loss": 0.2039, "step": 7180 }, { "epoch": 0.36289305001766514, "grad_norm": 0.4271124005317688, "learning_rate": 1.9598913558257564e-05, "loss": 0.2092, "step": 7190 }, { "epoch": 0.36339776914147276, "grad_norm": 0.42241042852401733, "learning_rate": 1.9596440004594233e-05, "loss": 0.2048, "step": 7200 }, { "epoch": 0.3639024882652804, "grad_norm": 0.39565253257751465, "learning_rate": 1.9593959004054893e-05, "loss": 0.2091, "step": 7210 }, { "epoch": 0.364407207389088, "grad_norm": 0.427129328250885, "learning_rate": 1.9591470558564816e-05, "loss": 0.2103, "step": 7220 }, { "epoch": 0.36491192651289556, "grad_norm": 0.3694396913051605, "learning_rate": 1.9588974670055046e-05, "loss": 0.2084, "step": 7230 }, { "epoch": 0.3654166456367032, "grad_norm": 0.4052709639072418, "learning_rate": 1.9586471340462396e-05, "loss": 0.2045, "step": 7240 }, { "epoch": 0.3659213647605108, "grad_norm": 0.42015960812568665, "learning_rate": 1.9583960571729467e-05, "loss": 0.2046, "step": 7250 }, { "epoch": 0.36642608388431835, "grad_norm": 0.42557698488235474, "learning_rate": 1.9581442365804623e-05, "loss": 0.2094, "step": 7260 }, { "epoch": 0.36693080300812597, "grad_norm": 0.41774365305900574, "learning_rate": 1.9578916724642e-05, "loss": 0.2079, "step": 7270 }, { "epoch": 0.3674355221319336, "grad_norm": 0.38158556818962097, "learning_rate": 1.9576383650201506e-05, "loss": 0.2051, "step": 7280 }, { "epoch": 0.3679402412557412, "grad_norm": 0.42440083622932434, "learning_rate": 1.957384314444882e-05, "loss": 0.2123, "step": 7290 }, { "epoch": 0.36844496037954877, "grad_norm": 0.3999404013156891, "learning_rate": 1.957129520935538e-05, "loss": 0.2076, "step": 7300 }, { "epoch": 0.3689496795033564, "grad_norm": 0.39880621433258057, "learning_rate": 1.9568739846898402e-05, "loss": 0.2111, "step": 7310 }, { "epoch": 0.369454398627164, "grad_norm": 0.418241024017334, "learning_rate": 1.956617705906085e-05, "loss": 0.2098, "step": 7320 }, { "epoch": 0.36995911775097157, "grad_norm": 0.38861551880836487, "learning_rate": 1.9563606847831455e-05, "loss": 0.2042, "step": 7330 }, { "epoch": 0.3704638368747792, "grad_norm": 0.4121749699115753, "learning_rate": 1.956102921520472e-05, "loss": 0.212, "step": 7340 }, { "epoch": 0.3709685559985868, "grad_norm": 0.4041878581047058, "learning_rate": 1.9558444163180897e-05, "loss": 0.2091, "step": 7350 }, { "epoch": 0.37147327512239436, "grad_norm": 0.4128355383872986, "learning_rate": 1.9555851693765994e-05, "loss": 0.2106, "step": 7360 }, { "epoch": 0.371977994246202, "grad_norm": 0.38102713227272034, "learning_rate": 1.9553251808971773e-05, "loss": 0.2009, "step": 7370 }, { "epoch": 0.3724827133700096, "grad_norm": 0.4190948009490967, "learning_rate": 1.9550644510815764e-05, "loss": 0.202, "step": 7380 }, { "epoch": 0.3729874324938172, "grad_norm": 0.4004126489162445, "learning_rate": 1.9548029801321235e-05, "loss": 0.2058, "step": 7390 }, { "epoch": 0.3734921516176248, "grad_norm": 0.4466496706008911, "learning_rate": 1.954540768251721e-05, "loss": 0.2075, "step": 7400 }, { "epoch": 0.3739968707414324, "grad_norm": 0.4149305820465088, "learning_rate": 1.954277815643847e-05, "loss": 0.2036, "step": 7410 }, { "epoch": 0.37450158986524, "grad_norm": 0.40400826930999756, "learning_rate": 1.9540141225125536e-05, "loss": 0.2038, "step": 7420 }, { "epoch": 0.3750063089890476, "grad_norm": 0.4136577844619751, "learning_rate": 1.9537496890624674e-05, "loss": 0.2069, "step": 7430 }, { "epoch": 0.3755110281128552, "grad_norm": 0.4099649488925934, "learning_rate": 1.9534845154987898e-05, "loss": 0.2071, "step": 7440 }, { "epoch": 0.3760157472366628, "grad_norm": 0.3781002461910248, "learning_rate": 1.953218602027297e-05, "loss": 0.2021, "step": 7450 }, { "epoch": 0.3765204663604704, "grad_norm": 0.40136510133743286, "learning_rate": 1.9529519488543385e-05, "loss": 0.2073, "step": 7460 }, { "epoch": 0.377025185484278, "grad_norm": 0.4042928218841553, "learning_rate": 1.9526845561868383e-05, "loss": 0.2102, "step": 7470 }, { "epoch": 0.3775299046080856, "grad_norm": 0.3834425210952759, "learning_rate": 1.9524164242322946e-05, "loss": 0.2053, "step": 7480 }, { "epoch": 0.3780346237318932, "grad_norm": 0.39187344908714294, "learning_rate": 1.952147553198778e-05, "loss": 0.2053, "step": 7490 }, { "epoch": 0.3785393428557008, "grad_norm": 0.4059430658817291, "learning_rate": 1.9518779432949347e-05, "loss": 0.2037, "step": 7500 }, { "epoch": 0.3790440619795084, "grad_norm": 0.37832382321357727, "learning_rate": 1.951607594729982e-05, "loss": 0.2065, "step": 7510 }, { "epoch": 0.379548781103316, "grad_norm": 0.389780730009079, "learning_rate": 1.951336507713712e-05, "loss": 0.2032, "step": 7520 }, { "epoch": 0.3800535002271236, "grad_norm": 0.42029881477355957, "learning_rate": 1.9510646824564895e-05, "loss": 0.2016, "step": 7530 }, { "epoch": 0.3805582193509312, "grad_norm": 0.433145672082901, "learning_rate": 1.9507921191692515e-05, "loss": 0.2141, "step": 7540 }, { "epoch": 0.3810629384747388, "grad_norm": 0.41278716921806335, "learning_rate": 1.950518818063508e-05, "loss": 0.2073, "step": 7550 }, { "epoch": 0.3815676575985464, "grad_norm": 0.3960997462272644, "learning_rate": 1.9502447793513425e-05, "loss": 0.2122, "step": 7560 }, { "epoch": 0.382072376722354, "grad_norm": 0.3841581344604492, "learning_rate": 1.94997000324541e-05, "loss": 0.2175, "step": 7570 }, { "epoch": 0.3825770958461616, "grad_norm": 0.4116559326648712, "learning_rate": 1.9496944899589373e-05, "loss": 0.2062, "step": 7580 }, { "epoch": 0.38308181496996924, "grad_norm": 0.38816478848457336, "learning_rate": 1.9494182397057243e-05, "loss": 0.2039, "step": 7590 }, { "epoch": 0.3835865340937768, "grad_norm": 0.40836450457572937, "learning_rate": 1.9491412527001424e-05, "loss": 0.204, "step": 7600 }, { "epoch": 0.3840912532175844, "grad_norm": 0.38004180788993835, "learning_rate": 1.9488635291571343e-05, "loss": 0.2076, "step": 7610 }, { "epoch": 0.38459597234139203, "grad_norm": 0.38514116406440735, "learning_rate": 1.9485850692922146e-05, "loss": 0.2008, "step": 7620 }, { "epoch": 0.3851006914651996, "grad_norm": 0.39999067783355713, "learning_rate": 1.9483058733214696e-05, "loss": 0.2031, "step": 7630 }, { "epoch": 0.3856054105890072, "grad_norm": 0.4089111089706421, "learning_rate": 1.948025941461556e-05, "loss": 0.2085, "step": 7640 }, { "epoch": 0.38611012971281483, "grad_norm": 0.4247584044933319, "learning_rate": 1.9477452739297024e-05, "loss": 0.2058, "step": 7650 }, { "epoch": 0.3866148488366224, "grad_norm": 0.4129102826118469, "learning_rate": 1.947463870943708e-05, "loss": 0.2056, "step": 7660 }, { "epoch": 0.38711956796043, "grad_norm": 0.4200417399406433, "learning_rate": 1.9471817327219424e-05, "loss": 0.2043, "step": 7670 }, { "epoch": 0.38762428708423763, "grad_norm": 0.41104769706726074, "learning_rate": 1.946898859483346e-05, "loss": 0.2054, "step": 7680 }, { "epoch": 0.38812900620804525, "grad_norm": 0.4127444922924042, "learning_rate": 1.9466152514474296e-05, "loss": 0.2145, "step": 7690 }, { "epoch": 0.3886337253318528, "grad_norm": 0.389413982629776, "learning_rate": 1.9463309088342746e-05, "loss": 0.1984, "step": 7700 }, { "epoch": 0.3891384444556604, "grad_norm": 0.3793945014476776, "learning_rate": 1.9460458318645314e-05, "loss": 0.2102, "step": 7710 }, { "epoch": 0.38964316357946804, "grad_norm": 0.3802949786186218, "learning_rate": 1.945760020759421e-05, "loss": 0.2133, "step": 7720 }, { "epoch": 0.3901478827032756, "grad_norm": 0.45480239391326904, "learning_rate": 1.9454734757407342e-05, "loss": 0.2002, "step": 7730 }, { "epoch": 0.3906526018270832, "grad_norm": 0.38292738795280457, "learning_rate": 1.9451861970308316e-05, "loss": 0.2102, "step": 7740 }, { "epoch": 0.39115732095089084, "grad_norm": 0.41002869606018066, "learning_rate": 1.9448981848526413e-05, "loss": 0.2068, "step": 7750 }, { "epoch": 0.3916620400746984, "grad_norm": 0.40191933512687683, "learning_rate": 1.9446094394296626e-05, "loss": 0.2049, "step": 7760 }, { "epoch": 0.392166759198506, "grad_norm": 0.4180382490158081, "learning_rate": 1.9443199609859634e-05, "loss": 0.2014, "step": 7770 }, { "epoch": 0.39267147832231364, "grad_norm": 0.39724284410476685, "learning_rate": 1.94402974974618e-05, "loss": 0.2108, "step": 7780 }, { "epoch": 0.39317619744612126, "grad_norm": 0.36111047863960266, "learning_rate": 1.9437388059355168e-05, "loss": 0.2065, "step": 7790 }, { "epoch": 0.3936809165699288, "grad_norm": 0.42821329832077026, "learning_rate": 1.9434471297797484e-05, "loss": 0.2114, "step": 7800 }, { "epoch": 0.39418563569373644, "grad_norm": 0.3763152062892914, "learning_rate": 1.943154721505216e-05, "loss": 0.2087, "step": 7810 }, { "epoch": 0.39469035481754405, "grad_norm": 0.39144444465637207, "learning_rate": 1.9428615813388297e-05, "loss": 0.2078, "step": 7820 }, { "epoch": 0.3951950739413516, "grad_norm": 0.42041778564453125, "learning_rate": 1.9425677095080678e-05, "loss": 0.2029, "step": 7830 }, { "epoch": 0.39569979306515923, "grad_norm": 0.38172173500061035, "learning_rate": 1.9422731062409755e-05, "loss": 0.2055, "step": 7840 }, { "epoch": 0.39620451218896685, "grad_norm": 0.40780210494995117, "learning_rate": 1.9419777717661662e-05, "loss": 0.2079, "step": 7850 }, { "epoch": 0.39670923131277447, "grad_norm": 0.3793182671070099, "learning_rate": 1.9416817063128214e-05, "loss": 0.2033, "step": 7860 }, { "epoch": 0.39721395043658203, "grad_norm": 0.43219003081321716, "learning_rate": 1.941384910110688e-05, "loss": 0.2067, "step": 7870 }, { "epoch": 0.39771866956038965, "grad_norm": 0.3826935887336731, "learning_rate": 1.941087383390082e-05, "loss": 0.2044, "step": 7880 }, { "epoch": 0.39822338868419727, "grad_norm": 0.3746674954891205, "learning_rate": 1.9407891263818843e-05, "loss": 0.212, "step": 7890 }, { "epoch": 0.39872810780800483, "grad_norm": 0.3994777798652649, "learning_rate": 1.9404901393175442e-05, "loss": 0.2065, "step": 7900 }, { "epoch": 0.39923282693181245, "grad_norm": 0.38579386472702026, "learning_rate": 1.940190422429077e-05, "loss": 0.2049, "step": 7910 }, { "epoch": 0.39973754605562006, "grad_norm": 0.38713276386260986, "learning_rate": 1.939889975949064e-05, "loss": 0.2063, "step": 7920 }, { "epoch": 0.4002422651794276, "grad_norm": 0.4004268944263458, "learning_rate": 1.9395888001106532e-05, "loss": 0.2091, "step": 7930 }, { "epoch": 0.40074698430323524, "grad_norm": 0.41367191076278687, "learning_rate": 1.9392868951475573e-05, "loss": 0.2061, "step": 7940 }, { "epoch": 0.40125170342704286, "grad_norm": 0.389457106590271, "learning_rate": 1.9389842612940563e-05, "loss": 0.2059, "step": 7950 }, { "epoch": 0.4017564225508505, "grad_norm": 0.45216983556747437, "learning_rate": 1.9386808987849956e-05, "loss": 0.2049, "step": 7960 }, { "epoch": 0.40226114167465804, "grad_norm": 0.40425655245780945, "learning_rate": 1.938376807855786e-05, "loss": 0.2049, "step": 7970 }, { "epoch": 0.40276586079846566, "grad_norm": 0.4268009662628174, "learning_rate": 1.938071988742402e-05, "loss": 0.2048, "step": 7980 }, { "epoch": 0.4032705799222733, "grad_norm": 0.38915547728538513, "learning_rate": 1.937766441681386e-05, "loss": 0.2035, "step": 7990 }, { "epoch": 0.40377529904608084, "grad_norm": 0.3786913752555847, "learning_rate": 1.9374601669098422e-05, "loss": 0.2091, "step": 8000 }, { "epoch": 0.40428001816988846, "grad_norm": 0.4033719599246979, "learning_rate": 1.937153164665442e-05, "loss": 0.2074, "step": 8010 }, { "epoch": 0.4047847372936961, "grad_norm": 0.38390615582466125, "learning_rate": 1.9368454351864202e-05, "loss": 0.2081, "step": 8020 }, { "epoch": 0.40528945641750364, "grad_norm": 0.3759255111217499, "learning_rate": 1.9365369787115766e-05, "loss": 0.2093, "step": 8030 }, { "epoch": 0.40579417554131125, "grad_norm": 0.4238349199295044, "learning_rate": 1.9362277954802738e-05, "loss": 0.2074, "step": 8040 }, { "epoch": 0.40629889466511887, "grad_norm": 0.39572450518608093, "learning_rate": 1.9359178857324393e-05, "loss": 0.2001, "step": 8050 }, { "epoch": 0.4068036137889265, "grad_norm": 0.39443671703338623, "learning_rate": 1.935607249708565e-05, "loss": 0.2018, "step": 8060 }, { "epoch": 0.40730833291273405, "grad_norm": 0.38588353991508484, "learning_rate": 1.9352958876497054e-05, "loss": 0.204, "step": 8070 }, { "epoch": 0.40781305203654167, "grad_norm": 0.40837380290031433, "learning_rate": 1.9349837997974788e-05, "loss": 0.2025, "step": 8080 }, { "epoch": 0.4083177711603493, "grad_norm": 0.4147998094558716, "learning_rate": 1.9346709863940664e-05, "loss": 0.2037, "step": 8090 }, { "epoch": 0.40882249028415685, "grad_norm": 0.4256783723831177, "learning_rate": 1.934357447682212e-05, "loss": 0.2094, "step": 8100 }, { "epoch": 0.40932720940796447, "grad_norm": 0.38599008321762085, "learning_rate": 1.9340431839052244e-05, "loss": 0.2092, "step": 8110 }, { "epoch": 0.4098319285317721, "grad_norm": 0.3755679726600647, "learning_rate": 1.9337281953069726e-05, "loss": 0.2071, "step": 8120 }, { "epoch": 0.41033664765557964, "grad_norm": 0.3688192069530487, "learning_rate": 1.9334124821318888e-05, "loss": 0.203, "step": 8130 }, { "epoch": 0.41084136677938726, "grad_norm": 0.3933801054954529, "learning_rate": 1.933096044624969e-05, "loss": 0.2044, "step": 8140 }, { "epoch": 0.4113460859031949, "grad_norm": 0.40221431851387024, "learning_rate": 1.9327788830317682e-05, "loss": 0.213, "step": 8150 }, { "epoch": 0.4118508050270025, "grad_norm": 0.4060612618923187, "learning_rate": 1.932460997598406e-05, "loss": 0.2036, "step": 8160 }, { "epoch": 0.41235552415081006, "grad_norm": 0.4644846022129059, "learning_rate": 1.9321423885715628e-05, "loss": 0.203, "step": 8170 }, { "epoch": 0.4128602432746177, "grad_norm": 0.38242819905281067, "learning_rate": 1.9318230561984808e-05, "loss": 0.2055, "step": 8180 }, { "epoch": 0.4133649623984253, "grad_norm": 0.39508551359176636, "learning_rate": 1.9315030007269622e-05, "loss": 0.204, "step": 8190 }, { "epoch": 0.41386968152223286, "grad_norm": 0.36735671758651733, "learning_rate": 1.9311822224053724e-05, "loss": 0.2057, "step": 8200 }, { "epoch": 0.4143744006460405, "grad_norm": 0.3767877221107483, "learning_rate": 1.930860721482636e-05, "loss": 0.2063, "step": 8210 }, { "epoch": 0.4148791197698481, "grad_norm": 0.4019070863723755, "learning_rate": 1.9305384982082392e-05, "loss": 0.2034, "step": 8220 }, { "epoch": 0.41538383889365565, "grad_norm": 0.39172878861427307, "learning_rate": 1.9302155528322286e-05, "loss": 0.2077, "step": 8230 }, { "epoch": 0.4158885580174633, "grad_norm": 0.4190254807472229, "learning_rate": 1.929891885605211e-05, "loss": 0.2048, "step": 8240 }, { "epoch": 0.4163932771412709, "grad_norm": 0.38926592469215393, "learning_rate": 1.9295674967783536e-05, "loss": 0.2084, "step": 8250 }, { "epoch": 0.4168979962650785, "grad_norm": 0.3967519998550415, "learning_rate": 1.9292423866033832e-05, "loss": 0.207, "step": 8260 }, { "epoch": 0.41740271538888607, "grad_norm": 0.40327543020248413, "learning_rate": 1.9289165553325868e-05, "loss": 0.2078, "step": 8270 }, { "epoch": 0.4179074345126937, "grad_norm": 0.37681883573532104, "learning_rate": 1.928590003218811e-05, "loss": 0.2018, "step": 8280 }, { "epoch": 0.4184121536365013, "grad_norm": 0.40885376930236816, "learning_rate": 1.928262730515461e-05, "loss": 0.1982, "step": 8290 }, { "epoch": 0.41891687276030887, "grad_norm": 0.4730125665664673, "learning_rate": 1.9279347374765024e-05, "loss": 0.2075, "step": 8300 }, { "epoch": 0.4194215918841165, "grad_norm": 0.3920527398586273, "learning_rate": 1.9276060243564585e-05, "loss": 0.2124, "step": 8310 }, { "epoch": 0.4199263110079241, "grad_norm": 0.412396103143692, "learning_rate": 1.9272765914104123e-05, "loss": 0.1994, "step": 8320 }, { "epoch": 0.42043103013173166, "grad_norm": 0.3784191906452179, "learning_rate": 1.926946438894005e-05, "loss": 0.201, "step": 8330 }, { "epoch": 0.4209357492555393, "grad_norm": 0.3999391496181488, "learning_rate": 1.9266155670634364e-05, "loss": 0.2037, "step": 8340 }, { "epoch": 0.4214404683793469, "grad_norm": 0.38616886734962463, "learning_rate": 1.926283976175464e-05, "loss": 0.2034, "step": 8350 }, { "epoch": 0.4219451875031545, "grad_norm": 0.36696118116378784, "learning_rate": 1.9259516664874044e-05, "loss": 0.2031, "step": 8360 }, { "epoch": 0.4224499066269621, "grad_norm": 0.41070589423179626, "learning_rate": 1.9256186382571306e-05, "loss": 0.2054, "step": 8370 }, { "epoch": 0.4229546257507697, "grad_norm": 0.3783276379108429, "learning_rate": 1.925284891743074e-05, "loss": 0.2041, "step": 8380 }, { "epoch": 0.4234593448745773, "grad_norm": 0.3996153473854065, "learning_rate": 1.9249504272042233e-05, "loss": 0.2094, "step": 8390 }, { "epoch": 0.4239640639983849, "grad_norm": 0.3872492015361786, "learning_rate": 1.9246152449001246e-05, "loss": 0.2072, "step": 8400 }, { "epoch": 0.4244687831221925, "grad_norm": 0.41536667943000793, "learning_rate": 1.92427934509088e-05, "loss": 0.2072, "step": 8410 }, { "epoch": 0.4249735022460001, "grad_norm": 0.48226529359817505, "learning_rate": 1.9239427280371495e-05, "loss": 0.2051, "step": 8420 }, { "epoch": 0.4254782213698077, "grad_norm": 0.3886622190475464, "learning_rate": 1.9236053940001496e-05, "loss": 0.202, "step": 8430 }, { "epoch": 0.4259829404936153, "grad_norm": 0.3822025954723358, "learning_rate": 1.9232673432416526e-05, "loss": 0.2089, "step": 8440 }, { "epoch": 0.4264876596174229, "grad_norm": 0.37891459465026855, "learning_rate": 1.922928576023987e-05, "loss": 0.2078, "step": 8450 }, { "epoch": 0.4269923787412305, "grad_norm": 0.39177405834198, "learning_rate": 1.922589092610038e-05, "loss": 0.2069, "step": 8460 }, { "epoch": 0.4274970978650381, "grad_norm": 0.4225703775882721, "learning_rate": 1.9222488932632455e-05, "loss": 0.2033, "step": 8470 }, { "epoch": 0.4280018169888457, "grad_norm": 0.3983403146266937, "learning_rate": 1.9219079782476063e-05, "loss": 0.2107, "step": 8480 }, { "epoch": 0.4285065361126533, "grad_norm": 0.41266676783561707, "learning_rate": 1.921566347827671e-05, "loss": 0.202, "step": 8490 }, { "epoch": 0.4290112552364609, "grad_norm": 0.40439867973327637, "learning_rate": 1.9212240022685472e-05, "loss": 0.2012, "step": 8500 }, { "epoch": 0.4295159743602685, "grad_norm": 0.4001920521259308, "learning_rate": 1.9208809418358954e-05, "loss": 0.2018, "step": 8510 }, { "epoch": 0.4300206934840761, "grad_norm": 0.418304443359375, "learning_rate": 1.920537166795932e-05, "loss": 0.2026, "step": 8520 }, { "epoch": 0.43052541260788374, "grad_norm": 0.3936491906642914, "learning_rate": 1.9201926774154288e-05, "loss": 0.2076, "step": 8530 }, { "epoch": 0.4310301317316913, "grad_norm": 0.3910875916481018, "learning_rate": 1.9198474739617102e-05, "loss": 0.2026, "step": 8540 }, { "epoch": 0.4315348508554989, "grad_norm": 0.4275718033313751, "learning_rate": 1.919501556702655e-05, "loss": 0.2057, "step": 8550 }, { "epoch": 0.43203956997930654, "grad_norm": 0.45599114894866943, "learning_rate": 1.9191549259066977e-05, "loss": 0.2021, "step": 8560 }, { "epoch": 0.4325442891031141, "grad_norm": 0.4135439395904541, "learning_rate": 1.9188075818428236e-05, "loss": 0.2087, "step": 8570 }, { "epoch": 0.4330490082269217, "grad_norm": 0.37159863114356995, "learning_rate": 1.9184595247805742e-05, "loss": 0.2009, "step": 8580 }, { "epoch": 0.43355372735072933, "grad_norm": 0.3828233480453491, "learning_rate": 1.918110754990043e-05, "loss": 0.2059, "step": 8590 }, { "epoch": 0.4340584464745369, "grad_norm": 0.44772619009017944, "learning_rate": 1.9177612727418766e-05, "loss": 0.1998, "step": 8600 }, { "epoch": 0.4345631655983445, "grad_norm": 0.36972683668136597, "learning_rate": 1.9174110783072745e-05, "loss": 0.2061, "step": 8610 }, { "epoch": 0.43506788472215213, "grad_norm": 0.41674354672431946, "learning_rate": 1.9170601719579895e-05, "loss": 0.2046, "step": 8620 }, { "epoch": 0.43557260384595975, "grad_norm": 0.39545294642448425, "learning_rate": 1.9167085539663258e-05, "loss": 0.2057, "step": 8630 }, { "epoch": 0.4360773229697673, "grad_norm": 0.3691506087779999, "learning_rate": 1.9163562246051402e-05, "loss": 0.205, "step": 8640 }, { "epoch": 0.43658204209357493, "grad_norm": 0.3994152843952179, "learning_rate": 1.9160031841478425e-05, "loss": 0.207, "step": 8650 }, { "epoch": 0.43708676121738255, "grad_norm": 0.3888298571109772, "learning_rate": 1.915649432868393e-05, "loss": 0.2045, "step": 8660 }, { "epoch": 0.4375914803411901, "grad_norm": 0.4081946313381195, "learning_rate": 1.9152949710413043e-05, "loss": 0.2039, "step": 8670 }, { "epoch": 0.4380961994649977, "grad_norm": 0.38510993123054504, "learning_rate": 1.91493979894164e-05, "loss": 0.2003, "step": 8680 }, { "epoch": 0.43860091858880534, "grad_norm": 0.39869043231010437, "learning_rate": 1.9145839168450153e-05, "loss": 0.2103, "step": 8690 }, { "epoch": 0.4391056377126129, "grad_norm": 0.39642101526260376, "learning_rate": 1.9142273250275956e-05, "loss": 0.2031, "step": 8700 }, { "epoch": 0.4396103568364205, "grad_norm": 0.4236326515674591, "learning_rate": 1.9138700237660982e-05, "loss": 0.2055, "step": 8710 }, { "epoch": 0.44011507596022814, "grad_norm": 0.38142406940460205, "learning_rate": 1.91351201333779e-05, "loss": 0.2063, "step": 8720 }, { "epoch": 0.44061979508403576, "grad_norm": 0.39191731810569763, "learning_rate": 1.913153294020489e-05, "loss": 0.2091, "step": 8730 }, { "epoch": 0.4411245142078433, "grad_norm": 0.3744587302207947, "learning_rate": 1.912793866092562e-05, "loss": 0.2024, "step": 8740 }, { "epoch": 0.44162923333165094, "grad_norm": 0.3846729099750519, "learning_rate": 1.9124337298329273e-05, "loss": 0.2048, "step": 8750 }, { "epoch": 0.44213395245545856, "grad_norm": 0.4181509017944336, "learning_rate": 1.9120728855210516e-05, "loss": 0.2073, "step": 8760 }, { "epoch": 0.4426386715792661, "grad_norm": 0.39247962832450867, "learning_rate": 1.9117113334369518e-05, "loss": 0.2035, "step": 8770 }, { "epoch": 0.44314339070307374, "grad_norm": 0.39907535910606384, "learning_rate": 1.9113490738611936e-05, "loss": 0.2082, "step": 8780 }, { "epoch": 0.44364810982688135, "grad_norm": 0.4037775993347168, "learning_rate": 1.910986107074892e-05, "loss": 0.2051, "step": 8790 }, { "epoch": 0.4441528289506889, "grad_norm": 0.398607075214386, "learning_rate": 1.9106224333597105e-05, "loss": 0.203, "step": 8800 }, { "epoch": 0.44465754807449653, "grad_norm": 0.43546563386917114, "learning_rate": 1.910258052997862e-05, "loss": 0.1984, "step": 8810 }, { "epoch": 0.44516226719830415, "grad_norm": 0.37100470066070557, "learning_rate": 1.9098929662721062e-05, "loss": 0.2021, "step": 8820 }, { "epoch": 0.44566698632211177, "grad_norm": 0.38905686140060425, "learning_rate": 1.9095271734657524e-05, "loss": 0.2049, "step": 8830 }, { "epoch": 0.44617170544591933, "grad_norm": 0.49843448400497437, "learning_rate": 1.909160674862657e-05, "loss": 0.2029, "step": 8840 }, { "epoch": 0.44667642456972695, "grad_norm": 0.3714364171028137, "learning_rate": 1.908793470747225e-05, "loss": 0.2031, "step": 8850 }, { "epoch": 0.44718114369353457, "grad_norm": 0.4098736345767975, "learning_rate": 1.9084255614044073e-05, "loss": 0.2127, "step": 8860 }, { "epoch": 0.44768586281734213, "grad_norm": 0.4381491243839264, "learning_rate": 1.9080569471197043e-05, "loss": 0.2026, "step": 8870 }, { "epoch": 0.44819058194114975, "grad_norm": 0.3967340290546417, "learning_rate": 1.907687628179161e-05, "loss": 0.2103, "step": 8880 }, { "epoch": 0.44869530106495736, "grad_norm": 0.3644460439682007, "learning_rate": 1.9073176048693708e-05, "loss": 0.2071, "step": 8890 }, { "epoch": 0.4492000201887649, "grad_norm": 0.41402724385261536, "learning_rate": 1.906946877477473e-05, "loss": 0.2096, "step": 8900 }, { "epoch": 0.44970473931257254, "grad_norm": 0.3982716202735901, "learning_rate": 1.9065754462911546e-05, "loss": 0.2057, "step": 8910 }, { "epoch": 0.45020945843638016, "grad_norm": 0.3908991515636444, "learning_rate": 1.9062033115986463e-05, "loss": 0.2044, "step": 8920 }, { "epoch": 0.4507141775601878, "grad_norm": 0.39306896924972534, "learning_rate": 1.905830473688727e-05, "loss": 0.197, "step": 8930 }, { "epoch": 0.45121889668399534, "grad_norm": 0.4064842760562897, "learning_rate": 1.9054569328507204e-05, "loss": 0.2053, "step": 8940 }, { "epoch": 0.45172361580780296, "grad_norm": 0.42026376724243164, "learning_rate": 1.9050826893744953e-05, "loss": 0.2072, "step": 8950 }, { "epoch": 0.4522283349316106, "grad_norm": 0.40060895681381226, "learning_rate": 1.904707743550466e-05, "loss": 0.2047, "step": 8960 }, { "epoch": 0.45273305405541814, "grad_norm": 0.4095679521560669, "learning_rate": 1.9043320956695927e-05, "loss": 0.2005, "step": 8970 }, { "epoch": 0.45323777317922576, "grad_norm": 0.4284416735172272, "learning_rate": 1.903955746023379e-05, "loss": 0.2061, "step": 8980 }, { "epoch": 0.4537424923030334, "grad_norm": 0.40786415338516235, "learning_rate": 1.9035786949038736e-05, "loss": 0.2036, "step": 8990 }, { "epoch": 0.45424721142684094, "grad_norm": 0.38453125953674316, "learning_rate": 1.903200942603671e-05, "loss": 0.2021, "step": 9000 }, { "epoch": 0.45475193055064855, "grad_norm": 0.38962501287460327, "learning_rate": 1.9028224894159066e-05, "loss": 0.2029, "step": 9010 }, { "epoch": 0.45525664967445617, "grad_norm": 0.40023374557495117, "learning_rate": 1.902443335634263e-05, "loss": 0.2087, "step": 9020 }, { "epoch": 0.4557613687982638, "grad_norm": 0.3782180845737457, "learning_rate": 1.9020634815529646e-05, "loss": 0.211, "step": 9030 }, { "epoch": 0.45626608792207135, "grad_norm": 0.37544599175453186, "learning_rate": 1.9016829274667797e-05, "loss": 0.2064, "step": 9040 }, { "epoch": 0.45677080704587897, "grad_norm": 0.3761289715766907, "learning_rate": 1.90130167367102e-05, "loss": 0.2044, "step": 9050 }, { "epoch": 0.4572755261696866, "grad_norm": 0.38967007398605347, "learning_rate": 1.9009197204615394e-05, "loss": 0.2031, "step": 9060 }, { "epoch": 0.45778024529349415, "grad_norm": 0.41389700770378113, "learning_rate": 1.9005370681347357e-05, "loss": 0.2035, "step": 9070 }, { "epoch": 0.45828496441730177, "grad_norm": 0.3774156868457794, "learning_rate": 1.9001537169875485e-05, "loss": 0.2034, "step": 9080 }, { "epoch": 0.4587896835411094, "grad_norm": 0.4000142514705658, "learning_rate": 1.89976966731746e-05, "loss": 0.2139, "step": 9090 }, { "epoch": 0.459294402664917, "grad_norm": 0.4163024425506592, "learning_rate": 1.8993849194224934e-05, "loss": 0.1965, "step": 9100 }, { "epoch": 0.45979912178872456, "grad_norm": 0.39134812355041504, "learning_rate": 1.8989994736012156e-05, "loss": 0.2021, "step": 9110 }, { "epoch": 0.4603038409125322, "grad_norm": 0.3848602771759033, "learning_rate": 1.898613330152734e-05, "loss": 0.2026, "step": 9120 }, { "epoch": 0.4608085600363398, "grad_norm": 0.4389389157295227, "learning_rate": 1.898226489376697e-05, "loss": 0.2053, "step": 9130 }, { "epoch": 0.46131327916014736, "grad_norm": 0.39440467953681946, "learning_rate": 1.897838951573295e-05, "loss": 0.2042, "step": 9140 }, { "epoch": 0.461817998283955, "grad_norm": 0.3784294128417969, "learning_rate": 1.897450717043259e-05, "loss": 0.1974, "step": 9150 }, { "epoch": 0.4623227174077626, "grad_norm": 0.39914289116859436, "learning_rate": 1.8970617860878596e-05, "loss": 0.2032, "step": 9160 }, { "epoch": 0.46282743653157016, "grad_norm": 0.39829057455062866, "learning_rate": 1.8966721590089097e-05, "loss": 0.2005, "step": 9170 }, { "epoch": 0.4633321556553778, "grad_norm": 0.40047967433929443, "learning_rate": 1.8962818361087618e-05, "loss": 0.2001, "step": 9180 }, { "epoch": 0.4638368747791854, "grad_norm": 0.39740699529647827, "learning_rate": 1.8958908176903073e-05, "loss": 0.2022, "step": 9190 }, { "epoch": 0.464341593902993, "grad_norm": 0.3922129273414612, "learning_rate": 1.8954991040569777e-05, "loss": 0.2033, "step": 9200 }, { "epoch": 0.4648463130268006, "grad_norm": 0.4136725962162018, "learning_rate": 1.8951066955127456e-05, "loss": 0.2029, "step": 9210 }, { "epoch": 0.4653510321506082, "grad_norm": 0.3752077519893646, "learning_rate": 1.8947135923621208e-05, "loss": 0.2046, "step": 9220 }, { "epoch": 0.4658557512744158, "grad_norm": 0.37377792596817017, "learning_rate": 1.894319794910153e-05, "loss": 0.2024, "step": 9230 }, { "epoch": 0.46636047039822337, "grad_norm": 0.3743211328983307, "learning_rate": 1.8939253034624303e-05, "loss": 0.2017, "step": 9240 }, { "epoch": 0.466865189522031, "grad_norm": 0.3567100167274475, "learning_rate": 1.8935301183250802e-05, "loss": 0.2082, "step": 9250 }, { "epoch": 0.4673699086458386, "grad_norm": 0.4325428605079651, "learning_rate": 1.893134239804768e-05, "loss": 0.2021, "step": 9260 }, { "epoch": 0.46787462776964617, "grad_norm": 0.39428356289863586, "learning_rate": 1.8927376682086968e-05, "loss": 0.205, "step": 9270 }, { "epoch": 0.4683793468934538, "grad_norm": 0.3995846211910248, "learning_rate": 1.8923404038446073e-05, "loss": 0.2062, "step": 9280 }, { "epoch": 0.4688840660172614, "grad_norm": 0.3832608759403229, "learning_rate": 1.891942447020779e-05, "loss": 0.2058, "step": 9290 }, { "epoch": 0.469388785141069, "grad_norm": 0.4071822464466095, "learning_rate": 1.8915437980460277e-05, "loss": 0.2041, "step": 9300 }, { "epoch": 0.4698935042648766, "grad_norm": 0.43110477924346924, "learning_rate": 1.8911444572297066e-05, "loss": 0.2067, "step": 9310 }, { "epoch": 0.4703982233886842, "grad_norm": 0.37988990545272827, "learning_rate": 1.8907444248817055e-05, "loss": 0.209, "step": 9320 }, { "epoch": 0.4709029425124918, "grad_norm": 0.36598843336105347, "learning_rate": 1.8903437013124515e-05, "loss": 0.2049, "step": 9330 }, { "epoch": 0.4714076616362994, "grad_norm": 0.4369811415672302, "learning_rate": 1.8899422868329078e-05, "loss": 0.2063, "step": 9340 }, { "epoch": 0.471912380760107, "grad_norm": 0.4093732237815857, "learning_rate": 1.889540181754573e-05, "loss": 0.2002, "step": 9350 }, { "epoch": 0.4724170998839146, "grad_norm": 0.40535488724708557, "learning_rate": 1.8891373863894828e-05, "loss": 0.2098, "step": 9360 }, { "epoch": 0.4729218190077222, "grad_norm": 0.37018147110939026, "learning_rate": 1.8887339010502078e-05, "loss": 0.2009, "step": 9370 }, { "epoch": 0.4734265381315298, "grad_norm": 0.36854809522628784, "learning_rate": 1.8883297260498547e-05, "loss": 0.2029, "step": 9380 }, { "epoch": 0.4739312572553374, "grad_norm": 0.38829296827316284, "learning_rate": 1.8879248617020644e-05, "loss": 0.2041, "step": 9390 }, { "epoch": 0.47443597637914503, "grad_norm": 0.37410488724708557, "learning_rate": 1.8875193083210134e-05, "loss": 0.2071, "step": 9400 }, { "epoch": 0.4749406955029526, "grad_norm": 0.40239956974983215, "learning_rate": 1.8871130662214127e-05, "loss": 0.2114, "step": 9410 }, { "epoch": 0.4754454146267602, "grad_norm": 0.40627485513687134, "learning_rate": 1.886706135718508e-05, "loss": 0.2088, "step": 9420 }, { "epoch": 0.4759501337505678, "grad_norm": 0.418685644865036, "learning_rate": 1.8862985171280787e-05, "loss": 0.2073, "step": 9430 }, { "epoch": 0.4764548528743754, "grad_norm": 0.41880112886428833, "learning_rate": 1.8858902107664388e-05, "loss": 0.2069, "step": 9440 }, { "epoch": 0.476959571998183, "grad_norm": 0.36286643147468567, "learning_rate": 1.8854812169504355e-05, "loss": 0.2099, "step": 9450 }, { "epoch": 0.4774642911219906, "grad_norm": 0.4063674211502075, "learning_rate": 1.8850715359974498e-05, "loss": 0.2017, "step": 9460 }, { "epoch": 0.4779690102457982, "grad_norm": 0.43370112776756287, "learning_rate": 1.8846611682253953e-05, "loss": 0.2015, "step": 9470 }, { "epoch": 0.4784737293696058, "grad_norm": 0.37671422958374023, "learning_rate": 1.8842501139527195e-05, "loss": 0.2068, "step": 9480 }, { "epoch": 0.4789784484934134, "grad_norm": 0.4265560507774353, "learning_rate": 1.8838383734984023e-05, "loss": 0.2021, "step": 9490 }, { "epoch": 0.47948316761722104, "grad_norm": 0.40119296312332153, "learning_rate": 1.8834259471819552e-05, "loss": 0.205, "step": 9500 }, { "epoch": 0.4799878867410286, "grad_norm": 0.41625097393989563, "learning_rate": 1.8830128353234238e-05, "loss": 0.204, "step": 9510 }, { "epoch": 0.4804926058648362, "grad_norm": 0.40846097469329834, "learning_rate": 1.8825990382433836e-05, "loss": 0.2027, "step": 9520 }, { "epoch": 0.48099732498864384, "grad_norm": 0.38621267676353455, "learning_rate": 1.882184556262943e-05, "loss": 0.1997, "step": 9530 }, { "epoch": 0.4815020441124514, "grad_norm": 0.4072802662849426, "learning_rate": 1.881769389703742e-05, "loss": 0.199, "step": 9540 }, { "epoch": 0.482006763236259, "grad_norm": 0.38016727566719055, "learning_rate": 1.8813535388879512e-05, "loss": 0.2049, "step": 9550 }, { "epoch": 0.48251148236006663, "grad_norm": 0.39268413186073303, "learning_rate": 1.8809370041382728e-05, "loss": 0.2165, "step": 9560 }, { "epoch": 0.4830162014838742, "grad_norm": 0.3851618468761444, "learning_rate": 1.8805197857779392e-05, "loss": 0.2012, "step": 9570 }, { "epoch": 0.4835209206076818, "grad_norm": 0.3664343059062958, "learning_rate": 1.8801018841307134e-05, "loss": 0.205, "step": 9580 }, { "epoch": 0.48402563973148943, "grad_norm": 0.4345386028289795, "learning_rate": 1.879683299520889e-05, "loss": 0.2012, "step": 9590 }, { "epoch": 0.48453035885529705, "grad_norm": 0.39762023091316223, "learning_rate": 1.8792640322732895e-05, "loss": 0.1989, "step": 9600 }, { "epoch": 0.4850350779791046, "grad_norm": 0.3345952033996582, "learning_rate": 1.8788440827132678e-05, "loss": 0.2048, "step": 9610 }, { "epoch": 0.48553979710291223, "grad_norm": 0.4148552119731903, "learning_rate": 1.8784234511667062e-05, "loss": 0.2034, "step": 9620 }, { "epoch": 0.48604451622671985, "grad_norm": 0.39140069484710693, "learning_rate": 1.8780021379600167e-05, "loss": 0.2043, "step": 9630 }, { "epoch": 0.4865492353505274, "grad_norm": 0.37049537897109985, "learning_rate": 1.8775801434201405e-05, "loss": 0.201, "step": 9640 }, { "epoch": 0.487053954474335, "grad_norm": 0.3984649181365967, "learning_rate": 1.8771574678745458e-05, "loss": 0.1997, "step": 9650 }, { "epoch": 0.48755867359814264, "grad_norm": 0.3972446918487549, "learning_rate": 1.8767341116512317e-05, "loss": 0.2048, "step": 9660 }, { "epoch": 0.48806339272195026, "grad_norm": 0.4101347327232361, "learning_rate": 1.876310075078724e-05, "loss": 0.2036, "step": 9670 }, { "epoch": 0.4885681118457578, "grad_norm": 0.39462989568710327, "learning_rate": 1.875885358486077e-05, "loss": 0.199, "step": 9680 }, { "epoch": 0.48907283096956544, "grad_norm": 0.3914542496204376, "learning_rate": 1.8754599622028717e-05, "loss": 0.2038, "step": 9690 }, { "epoch": 0.48957755009337306, "grad_norm": 0.3947005271911621, "learning_rate": 1.875033886559218e-05, "loss": 0.2058, "step": 9700 }, { "epoch": 0.4900822692171806, "grad_norm": 0.41873449087142944, "learning_rate": 1.874607131885752e-05, "loss": 0.2074, "step": 9710 }, { "epoch": 0.49058698834098824, "grad_norm": 0.41425102949142456, "learning_rate": 1.874179698513637e-05, "loss": 0.2027, "step": 9720 }, { "epoch": 0.49109170746479586, "grad_norm": 0.3735681474208832, "learning_rate": 1.8737515867745636e-05, "loss": 0.2009, "step": 9730 }, { "epoch": 0.4915964265886034, "grad_norm": 0.3874130845069885, "learning_rate": 1.8733227970007477e-05, "loss": 0.2043, "step": 9740 }, { "epoch": 0.49210114571241104, "grad_norm": 0.40142571926116943, "learning_rate": 1.872893329524932e-05, "loss": 0.199, "step": 9750 }, { "epoch": 0.49260586483621865, "grad_norm": 0.4082174599170685, "learning_rate": 1.8724631846803847e-05, "loss": 0.2075, "step": 9760 }, { "epoch": 0.49311058396002627, "grad_norm": 0.3918592929840088, "learning_rate": 1.8720323628009005e-05, "loss": 0.2014, "step": 9770 }, { "epoch": 0.49361530308383383, "grad_norm": 0.3654271960258484, "learning_rate": 1.8716008642207987e-05, "loss": 0.2065, "step": 9780 }, { "epoch": 0.49412002220764145, "grad_norm": 0.4195430278778076, "learning_rate": 1.871168689274924e-05, "loss": 0.2003, "step": 9790 }, { "epoch": 0.49462474133144907, "grad_norm": 0.37709110975265503, "learning_rate": 1.870735838298645e-05, "loss": 0.203, "step": 9800 }, { "epoch": 0.49512946045525663, "grad_norm": 0.3876439929008484, "learning_rate": 1.8703023116278575e-05, "loss": 0.2021, "step": 9810 }, { "epoch": 0.49563417957906425, "grad_norm": 0.3941469192504883, "learning_rate": 1.8698681095989784e-05, "loss": 0.1979, "step": 9820 }, { "epoch": 0.49613889870287187, "grad_norm": 0.3648691177368164, "learning_rate": 1.8694332325489512e-05, "loss": 0.1976, "step": 9830 }, { "epoch": 0.49664361782667943, "grad_norm": 0.3665609359741211, "learning_rate": 1.8689976808152414e-05, "loss": 0.1998, "step": 9840 }, { "epoch": 0.49714833695048705, "grad_norm": 0.4103701114654541, "learning_rate": 1.86856145473584e-05, "loss": 0.1981, "step": 9850 }, { "epoch": 0.49765305607429466, "grad_norm": 0.36568301916122437, "learning_rate": 1.868124554649259e-05, "loss": 0.207, "step": 9860 }, { "epoch": 0.4981577751981023, "grad_norm": 0.3623066246509552, "learning_rate": 1.867686980894535e-05, "loss": 0.2041, "step": 9870 }, { "epoch": 0.49866249432190984, "grad_norm": 0.3851739764213562, "learning_rate": 1.867248733811228e-05, "loss": 0.2017, "step": 9880 }, { "epoch": 0.49916721344571746, "grad_norm": 0.39143890142440796, "learning_rate": 1.8668098137394178e-05, "loss": 0.2014, "step": 9890 }, { "epoch": 0.4996719325695251, "grad_norm": 0.36800166964530945, "learning_rate": 1.8663702210197092e-05, "loss": 0.2039, "step": 9900 }, { "epoch": 0.5001766516933327, "grad_norm": 0.400608092546463, "learning_rate": 1.865929955993228e-05, "loss": 0.2053, "step": 9910 }, { "epoch": 0.5006813708171403, "grad_norm": 0.3732556104660034, "learning_rate": 1.865489019001621e-05, "loss": 0.2036, "step": 9920 }, { "epoch": 0.5011860899409478, "grad_norm": 0.372669517993927, "learning_rate": 1.8650474103870576e-05, "loss": 0.2058, "step": 9930 }, { "epoch": 0.5016908090647555, "grad_norm": 0.36902669072151184, "learning_rate": 1.8646051304922276e-05, "loss": 0.2076, "step": 9940 }, { "epoch": 0.5021955281885631, "grad_norm": 0.365439772605896, "learning_rate": 1.8641621796603423e-05, "loss": 0.202, "step": 9950 }, { "epoch": 0.5027002473123706, "grad_norm": 0.3705258071422577, "learning_rate": 1.8637185582351323e-05, "loss": 0.1956, "step": 9960 }, { "epoch": 0.5032049664361783, "grad_norm": 0.371537446975708, "learning_rate": 1.8632742665608516e-05, "loss": 0.1962, "step": 9970 }, { "epoch": 0.5037096855599859, "grad_norm": 0.39395010471343994, "learning_rate": 1.86282930498227e-05, "loss": 0.2011, "step": 9980 }, { "epoch": 0.5042144046837934, "grad_norm": 0.37659838795661926, "learning_rate": 1.862383673844681e-05, "loss": 0.1989, "step": 9990 }, { "epoch": 0.5047191238076011, "grad_norm": 0.4044819474220276, "learning_rate": 1.8619373734938958e-05, "loss": 0.2043, "step": 10000 }, { "epoch": 0.5052238429314087, "grad_norm": 0.3683159649372101, "learning_rate": 1.8614904042762453e-05, "loss": 0.2087, "step": 10010 }, { "epoch": 0.5057285620552163, "grad_norm": 0.3975251615047455, "learning_rate": 1.861042766538579e-05, "loss": 0.2001, "step": 10020 }, { "epoch": 0.5062332811790239, "grad_norm": 0.37469029426574707, "learning_rate": 1.860594460628266e-05, "loss": 0.2068, "step": 10030 }, { "epoch": 0.5067380003028314, "grad_norm": 0.3667330741882324, "learning_rate": 1.8601454868931936e-05, "loss": 0.2013, "step": 10040 }, { "epoch": 0.5072427194266391, "grad_norm": 0.41870278120040894, "learning_rate": 1.859695845681767e-05, "loss": 0.2042, "step": 10050 }, { "epoch": 0.5077474385504467, "grad_norm": 0.39825090765953064, "learning_rate": 1.8592455373429093e-05, "loss": 0.2067, "step": 10060 }, { "epoch": 0.5082521576742542, "grad_norm": 0.3795827627182007, "learning_rate": 1.858794562226062e-05, "loss": 0.2068, "step": 10070 }, { "epoch": 0.5087568767980619, "grad_norm": 0.3556322753429413, "learning_rate": 1.8583429206811834e-05, "loss": 0.2035, "step": 10080 }, { "epoch": 0.5092615959218695, "grad_norm": 0.3829616904258728, "learning_rate": 1.8578906130587492e-05, "loss": 0.2014, "step": 10090 }, { "epoch": 0.509766315045677, "grad_norm": 0.37458744645118713, "learning_rate": 1.8574376397097523e-05, "loss": 0.2011, "step": 10100 }, { "epoch": 0.5102710341694847, "grad_norm": 0.3717310130596161, "learning_rate": 1.8569840009857013e-05, "loss": 0.2127, "step": 10110 }, { "epoch": 0.5107757532932923, "grad_norm": 0.3764341175556183, "learning_rate": 1.8565296972386216e-05, "loss": 0.1961, "step": 10120 }, { "epoch": 0.5112804724170998, "grad_norm": 0.3787286877632141, "learning_rate": 1.856074728821055e-05, "loss": 0.2015, "step": 10130 }, { "epoch": 0.5117851915409075, "grad_norm": 0.40645572543144226, "learning_rate": 1.8556190960860595e-05, "loss": 0.2057, "step": 10140 }, { "epoch": 0.5122899106647151, "grad_norm": 0.41215336322784424, "learning_rate": 1.855162799387207e-05, "loss": 0.2067, "step": 10150 }, { "epoch": 0.5127946297885226, "grad_norm": 0.3868434727191925, "learning_rate": 1.8547058390785852e-05, "loss": 0.2018, "step": 10160 }, { "epoch": 0.5132993489123303, "grad_norm": 0.38569343090057373, "learning_rate": 1.8542482155147984e-05, "loss": 0.2003, "step": 10170 }, { "epoch": 0.5138040680361379, "grad_norm": 0.3978995978832245, "learning_rate": 1.8537899290509632e-05, "loss": 0.2075, "step": 10180 }, { "epoch": 0.5143087871599454, "grad_norm": 0.3826935589313507, "learning_rate": 1.8533309800427127e-05, "loss": 0.2052, "step": 10190 }, { "epoch": 0.5148135062837531, "grad_norm": 0.3969276547431946, "learning_rate": 1.8528713688461925e-05, "loss": 0.2023, "step": 10200 }, { "epoch": 0.5153182254075607, "grad_norm": 0.3864808678627014, "learning_rate": 1.852411095818063e-05, "loss": 0.2017, "step": 10210 }, { "epoch": 0.5158229445313683, "grad_norm": 0.35776060819625854, "learning_rate": 1.8519501613154978e-05, "loss": 0.2004, "step": 10220 }, { "epoch": 0.5163276636551759, "grad_norm": 0.3918339014053345, "learning_rate": 1.851488565696184e-05, "loss": 0.2032, "step": 10230 }, { "epoch": 0.5168323827789835, "grad_norm": 0.37810128927230835, "learning_rate": 1.8510263093183216e-05, "loss": 0.1978, "step": 10240 }, { "epoch": 0.5173371019027911, "grad_norm": 0.3825649619102478, "learning_rate": 1.8505633925406234e-05, "loss": 0.2078, "step": 10250 }, { "epoch": 0.5178418210265987, "grad_norm": 0.38997209072113037, "learning_rate": 1.8500998157223148e-05, "loss": 0.1996, "step": 10260 }, { "epoch": 0.5183465401504063, "grad_norm": 0.39847061038017273, "learning_rate": 1.8496355792231333e-05, "loss": 0.1997, "step": 10270 }, { "epoch": 0.5188512592742139, "grad_norm": 0.4106511175632477, "learning_rate": 1.849170683403328e-05, "loss": 0.2021, "step": 10280 }, { "epoch": 0.5193559783980215, "grad_norm": 0.37418898940086365, "learning_rate": 1.84870512862366e-05, "loss": 0.2053, "step": 10290 }, { "epoch": 0.5198606975218291, "grad_norm": 0.4157654643058777, "learning_rate": 1.8482389152454022e-05, "loss": 0.2044, "step": 10300 }, { "epoch": 0.5203654166456367, "grad_norm": 0.38720905780792236, "learning_rate": 1.8477720436303373e-05, "loss": 0.2013, "step": 10310 }, { "epoch": 0.5208701357694443, "grad_norm": 0.3907393515110016, "learning_rate": 1.84730451414076e-05, "loss": 0.2045, "step": 10320 }, { "epoch": 0.5213748548932519, "grad_norm": 0.390533983707428, "learning_rate": 1.846836327139475e-05, "loss": 0.1976, "step": 10330 }, { "epoch": 0.5218795740170595, "grad_norm": 0.3749466836452484, "learning_rate": 1.8463674829897975e-05, "loss": 0.1979, "step": 10340 }, { "epoch": 0.5223842931408671, "grad_norm": 0.43039828538894653, "learning_rate": 1.8458979820555517e-05, "loss": 0.2009, "step": 10350 }, { "epoch": 0.5228890122646747, "grad_norm": 0.4118586480617523, "learning_rate": 1.8454278247010732e-05, "loss": 0.2091, "step": 10360 }, { "epoch": 0.5233937313884823, "grad_norm": 0.38007211685180664, "learning_rate": 1.8449570112912048e-05, "loss": 0.2117, "step": 10370 }, { "epoch": 0.5238984505122899, "grad_norm": 0.37855833768844604, "learning_rate": 1.844485542191301e-05, "loss": 0.2043, "step": 10380 }, { "epoch": 0.5244031696360976, "grad_norm": 0.3918007016181946, "learning_rate": 1.8440134177672228e-05, "loss": 0.2034, "step": 10390 }, { "epoch": 0.5249078887599051, "grad_norm": 0.40334776043891907, "learning_rate": 1.8435406383853407e-05, "loss": 0.2022, "step": 10400 }, { "epoch": 0.5254126078837127, "grad_norm": 0.37950173020362854, "learning_rate": 1.843067204412534e-05, "loss": 0.2015, "step": 10410 }, { "epoch": 0.5259173270075204, "grad_norm": 0.3836900293827057, "learning_rate": 1.8425931162161887e-05, "loss": 0.206, "step": 10420 }, { "epoch": 0.5264220461313279, "grad_norm": 0.4270097315311432, "learning_rate": 1.842118374164199e-05, "loss": 0.2072, "step": 10430 }, { "epoch": 0.5269267652551355, "grad_norm": 0.4038906693458557, "learning_rate": 1.8416429786249675e-05, "loss": 0.2023, "step": 10440 }, { "epoch": 0.5274314843789432, "grad_norm": 0.37887027859687805, "learning_rate": 1.8411669299674023e-05, "loss": 0.2052, "step": 10450 }, { "epoch": 0.5279362035027507, "grad_norm": 0.4389133155345917, "learning_rate": 1.8406902285609197e-05, "loss": 0.2043, "step": 10460 }, { "epoch": 0.5284409226265583, "grad_norm": 0.4199444651603699, "learning_rate": 1.8402128747754412e-05, "loss": 0.2025, "step": 10470 }, { "epoch": 0.528945641750366, "grad_norm": 0.3710445463657379, "learning_rate": 1.8397348689813958e-05, "loss": 0.2068, "step": 10480 }, { "epoch": 0.5294503608741735, "grad_norm": 0.3669309616088867, "learning_rate": 1.839256211549717e-05, "loss": 0.1999, "step": 10490 }, { "epoch": 0.5299550799979811, "grad_norm": 0.40174925327301025, "learning_rate": 1.8387769028518467e-05, "loss": 0.204, "step": 10500 }, { "epoch": 0.5304597991217888, "grad_norm": 0.41097989678382874, "learning_rate": 1.8382969432597285e-05, "loss": 0.2019, "step": 10510 }, { "epoch": 0.5309645182455963, "grad_norm": 0.4006945788860321, "learning_rate": 1.8378163331458143e-05, "loss": 0.2023, "step": 10520 }, { "epoch": 0.5314692373694039, "grad_norm": 0.38123708963394165, "learning_rate": 1.8373350728830586e-05, "loss": 0.2027, "step": 10530 }, { "epoch": 0.5319739564932116, "grad_norm": 0.388837605714798, "learning_rate": 1.8368531628449218e-05, "loss": 0.1998, "step": 10540 }, { "epoch": 0.5324786756170191, "grad_norm": 0.3879856467247009, "learning_rate": 1.8363706034053677e-05, "loss": 0.2041, "step": 10550 }, { "epoch": 0.5329833947408267, "grad_norm": 0.39001527428627014, "learning_rate": 1.8358873949388647e-05, "loss": 0.2016, "step": 10560 }, { "epoch": 0.5334881138646344, "grad_norm": 0.3819146156311035, "learning_rate": 1.8354035378203843e-05, "loss": 0.2028, "step": 10570 }, { "epoch": 0.5339928329884419, "grad_norm": 0.3892366588115692, "learning_rate": 1.8349190324254014e-05, "loss": 0.2011, "step": 10580 }, { "epoch": 0.5344975521122496, "grad_norm": 0.4114999771118164, "learning_rate": 1.8344338791298946e-05, "loss": 0.203, "step": 10590 }, { "epoch": 0.5350022712360571, "grad_norm": 0.4151875078678131, "learning_rate": 1.8339480783103445e-05, "loss": 0.2042, "step": 10600 }, { "epoch": 0.5355069903598647, "grad_norm": 0.382701575756073, "learning_rate": 1.8334616303437345e-05, "loss": 0.2003, "step": 10610 }, { "epoch": 0.5360117094836724, "grad_norm": 0.39572301506996155, "learning_rate": 1.8329745356075502e-05, "loss": 0.206, "step": 10620 }, { "epoch": 0.53651642860748, "grad_norm": 0.39479056000709534, "learning_rate": 1.832486794479779e-05, "loss": 0.2037, "step": 10630 }, { "epoch": 0.5370211477312875, "grad_norm": 0.400800883769989, "learning_rate": 1.83199840733891e-05, "loss": 0.2053, "step": 10640 }, { "epoch": 0.5375258668550952, "grad_norm": 0.4275124669075012, "learning_rate": 1.8315093745639337e-05, "loss": 0.198, "step": 10650 }, { "epoch": 0.5380305859789027, "grad_norm": 0.3905058205127716, "learning_rate": 1.8310196965343418e-05, "loss": 0.2017, "step": 10660 }, { "epoch": 0.5385353051027103, "grad_norm": 0.37394940853118896, "learning_rate": 1.8305293736301255e-05, "loss": 0.2018, "step": 10670 }, { "epoch": 0.539040024226518, "grad_norm": 0.3599688708782196, "learning_rate": 1.830038406231778e-05, "loss": 0.1989, "step": 10680 }, { "epoch": 0.5395447433503255, "grad_norm": 0.390587717294693, "learning_rate": 1.8295467947202922e-05, "loss": 0.1994, "step": 10690 }, { "epoch": 0.5400494624741331, "grad_norm": 0.38423457741737366, "learning_rate": 1.82905453947716e-05, "loss": 0.2027, "step": 10700 }, { "epoch": 0.5405541815979408, "grad_norm": 0.38596031069755554, "learning_rate": 1.828561640884374e-05, "loss": 0.1989, "step": 10710 }, { "epoch": 0.5410589007217483, "grad_norm": 0.41214585304260254, "learning_rate": 1.8280680993244252e-05, "loss": 0.1975, "step": 10720 }, { "epoch": 0.5415636198455559, "grad_norm": 0.37058907747268677, "learning_rate": 1.8275739151803038e-05, "loss": 0.2035, "step": 10730 }, { "epoch": 0.5420683389693636, "grad_norm": 0.38389307260513306, "learning_rate": 1.8270790888354986e-05, "loss": 0.1979, "step": 10740 }, { "epoch": 0.5425730580931711, "grad_norm": 0.3965015411376953, "learning_rate": 1.8265836206739972e-05, "loss": 0.2004, "step": 10750 }, { "epoch": 0.5430777772169787, "grad_norm": 0.40257513523101807, "learning_rate": 1.826087511080284e-05, "loss": 0.2053, "step": 10760 }, { "epoch": 0.5435824963407864, "grad_norm": 0.3750956654548645, "learning_rate": 1.8255907604393436e-05, "loss": 0.2025, "step": 10770 }, { "epoch": 0.5440872154645939, "grad_norm": 0.35990533232688904, "learning_rate": 1.825093369136655e-05, "loss": 0.2025, "step": 10780 }, { "epoch": 0.5445919345884016, "grad_norm": 0.4312472343444824, "learning_rate": 1.8245953375581967e-05, "loss": 0.2022, "step": 10790 }, { "epoch": 0.5450966537122092, "grad_norm": 0.40499332547187805, "learning_rate": 1.824096666090443e-05, "loss": 0.2, "step": 10800 }, { "epoch": 0.5456013728360167, "grad_norm": 0.3883630335330963, "learning_rate": 1.8235973551203644e-05, "loss": 0.1989, "step": 10810 }, { "epoch": 0.5461060919598244, "grad_norm": 0.3942257761955261, "learning_rate": 1.823097405035429e-05, "loss": 0.204, "step": 10820 }, { "epoch": 0.546610811083632, "grad_norm": 0.38020947575569153, "learning_rate": 1.8225968162236002e-05, "loss": 0.2047, "step": 10830 }, { "epoch": 0.5471155302074395, "grad_norm": 0.3638669550418854, "learning_rate": 1.822095589073336e-05, "loss": 0.2048, "step": 10840 }, { "epoch": 0.5476202493312472, "grad_norm": 0.41253650188446045, "learning_rate": 1.8215937239735915e-05, "loss": 0.2016, "step": 10850 }, { "epoch": 0.5481249684550548, "grad_norm": 0.3950449228286743, "learning_rate": 1.8210912213138153e-05, "loss": 0.2033, "step": 10860 }, { "epoch": 0.5486296875788623, "grad_norm": 0.40623238682746887, "learning_rate": 1.8205880814839525e-05, "loss": 0.2037, "step": 10870 }, { "epoch": 0.54913440670267, "grad_norm": 0.3869873285293579, "learning_rate": 1.8200843048744406e-05, "loss": 0.2038, "step": 10880 }, { "epoch": 0.5496391258264776, "grad_norm": 0.3886772394180298, "learning_rate": 1.819579891876213e-05, "loss": 0.2021, "step": 10890 }, { "epoch": 0.5501438449502851, "grad_norm": 0.38156023621559143, "learning_rate": 1.819074842880696e-05, "loss": 0.1997, "step": 10900 }, { "epoch": 0.5506485640740928, "grad_norm": 0.3554256856441498, "learning_rate": 1.8185691582798095e-05, "loss": 0.2073, "step": 10910 }, { "epoch": 0.5511532831979004, "grad_norm": 0.3768918812274933, "learning_rate": 1.8180628384659667e-05, "loss": 0.2007, "step": 10920 }, { "epoch": 0.5516580023217079, "grad_norm": 0.3710586428642273, "learning_rate": 1.8175558838320743e-05, "loss": 0.2078, "step": 10930 }, { "epoch": 0.5521627214455156, "grad_norm": 0.3829667270183563, "learning_rate": 1.8170482947715307e-05, "loss": 0.2017, "step": 10940 }, { "epoch": 0.5526674405693232, "grad_norm": 0.4542217254638672, "learning_rate": 1.816540071678227e-05, "loss": 0.2064, "step": 10950 }, { "epoch": 0.5531721596931308, "grad_norm": 0.37953147292137146, "learning_rate": 1.8160312149465468e-05, "loss": 0.1927, "step": 10960 }, { "epoch": 0.5536768788169384, "grad_norm": 0.39591094851493835, "learning_rate": 1.8155217249713643e-05, "loss": 0.2065, "step": 10970 }, { "epoch": 0.554181597940746, "grad_norm": 0.37706032395362854, "learning_rate": 1.8150116021480466e-05, "loss": 0.2067, "step": 10980 }, { "epoch": 0.5546863170645536, "grad_norm": 0.35152387619018555, "learning_rate": 1.8145008468724504e-05, "loss": 0.2021, "step": 10990 }, { "epoch": 0.5551910361883612, "grad_norm": 0.37381699681282043, "learning_rate": 1.813989459540924e-05, "loss": 0.2042, "step": 11000 }, { "epoch": 0.5556957553121687, "grad_norm": 0.37255996465682983, "learning_rate": 1.8134774405503065e-05, "loss": 0.1973, "step": 11010 }, { "epoch": 0.5562004744359764, "grad_norm": 0.38796907663345337, "learning_rate": 1.812964790297926e-05, "loss": 0.1965, "step": 11020 }, { "epoch": 0.556705193559784, "grad_norm": 0.4013110399246216, "learning_rate": 1.8124515091816013e-05, "loss": 0.2054, "step": 11030 }, { "epoch": 0.5572099126835915, "grad_norm": 0.37320786714553833, "learning_rate": 1.811937597599641e-05, "loss": 0.2049, "step": 11040 }, { "epoch": 0.5577146318073992, "grad_norm": 0.3693302273750305, "learning_rate": 1.8114230559508422e-05, "loss": 0.2045, "step": 11050 }, { "epoch": 0.5582193509312068, "grad_norm": 0.3564622104167938, "learning_rate": 1.8109078846344915e-05, "loss": 0.1965, "step": 11060 }, { "epoch": 0.5587240700550143, "grad_norm": 0.39271607995033264, "learning_rate": 1.8103920840503634e-05, "loss": 0.2036, "step": 11070 }, { "epoch": 0.559228789178822, "grad_norm": 0.37395143508911133, "learning_rate": 1.8098756545987222e-05, "loss": 0.2, "step": 11080 }, { "epoch": 0.5597335083026296, "grad_norm": 0.3947660028934479, "learning_rate": 1.8093585966803184e-05, "loss": 0.2011, "step": 11090 }, { "epoch": 0.5602382274264371, "grad_norm": 0.37211912870407104, "learning_rate": 1.8088409106963913e-05, "loss": 0.1971, "step": 11100 }, { "epoch": 0.5607429465502448, "grad_norm": 0.39325466752052307, "learning_rate": 1.8083225970486673e-05, "loss": 0.203, "step": 11110 }, { "epoch": 0.5612476656740524, "grad_norm": 0.40715140104293823, "learning_rate": 1.80780365613936e-05, "loss": 0.1998, "step": 11120 }, { "epoch": 0.5617523847978599, "grad_norm": 0.3809134066104889, "learning_rate": 1.8072840883711693e-05, "loss": 0.2008, "step": 11130 }, { "epoch": 0.5622571039216676, "grad_norm": 0.4207008481025696, "learning_rate": 1.806763894147282e-05, "loss": 0.2033, "step": 11140 }, { "epoch": 0.5627618230454752, "grad_norm": 0.416278600692749, "learning_rate": 1.8062430738713714e-05, "loss": 0.2065, "step": 11150 }, { "epoch": 0.5632665421692828, "grad_norm": 0.41072267293930054, "learning_rate": 1.8057216279475954e-05, "loss": 0.1977, "step": 11160 }, { "epoch": 0.5637712612930904, "grad_norm": 0.37965571880340576, "learning_rate": 1.8051995567805984e-05, "loss": 0.2026, "step": 11170 }, { "epoch": 0.564275980416898, "grad_norm": 0.3644537627696991, "learning_rate": 1.80467686077551e-05, "loss": 0.1983, "step": 11180 }, { "epoch": 0.5647806995407056, "grad_norm": 0.37633323669433594, "learning_rate": 1.8041535403379437e-05, "loss": 0.2007, "step": 11190 }, { "epoch": 0.5652854186645132, "grad_norm": 0.3770269751548767, "learning_rate": 1.803629595873999e-05, "loss": 0.1999, "step": 11200 }, { "epoch": 0.5657901377883208, "grad_norm": 0.38815274834632874, "learning_rate": 1.8031050277902586e-05, "loss": 0.2007, "step": 11210 }, { "epoch": 0.5662948569121284, "grad_norm": 0.3711063265800476, "learning_rate": 1.8025798364937895e-05, "loss": 0.1925, "step": 11220 }, { "epoch": 0.566799576035936, "grad_norm": 0.3847515881061554, "learning_rate": 1.8020540223921424e-05, "loss": 0.2002, "step": 11230 }, { "epoch": 0.5673042951597436, "grad_norm": 0.4080047309398651, "learning_rate": 1.801527585893351e-05, "loss": 0.2046, "step": 11240 }, { "epoch": 0.5678090142835512, "grad_norm": 0.4060002267360687, "learning_rate": 1.801000527405932e-05, "loss": 0.2025, "step": 11250 }, { "epoch": 0.5683137334073588, "grad_norm": 0.3975309431552887, "learning_rate": 1.800472847338885e-05, "loss": 0.2, "step": 11260 }, { "epoch": 0.5688184525311664, "grad_norm": 0.3938188850879669, "learning_rate": 1.7999445461016915e-05, "loss": 0.2128, "step": 11270 }, { "epoch": 0.569323171654974, "grad_norm": 0.3705352544784546, "learning_rate": 1.7994156241043165e-05, "loss": 0.1965, "step": 11280 }, { "epoch": 0.5698278907787816, "grad_norm": 0.36212560534477234, "learning_rate": 1.7988860817572044e-05, "loss": 0.1956, "step": 11290 }, { "epoch": 0.5703326099025892, "grad_norm": 0.3973407745361328, "learning_rate": 1.7983559194712827e-05, "loss": 0.1969, "step": 11300 }, { "epoch": 0.5708373290263968, "grad_norm": 0.40104198455810547, "learning_rate": 1.7978251376579593e-05, "loss": 0.1969, "step": 11310 }, { "epoch": 0.5713420481502044, "grad_norm": 0.38570693135261536, "learning_rate": 1.7972937367291233e-05, "loss": 0.1979, "step": 11320 }, { "epoch": 0.571846767274012, "grad_norm": 0.4392693340778351, "learning_rate": 1.7967617170971443e-05, "loss": 0.2019, "step": 11330 }, { "epoch": 0.5723514863978196, "grad_norm": 0.3742884695529938, "learning_rate": 1.79622907917487e-05, "loss": 0.1993, "step": 11340 }, { "epoch": 0.5728562055216272, "grad_norm": 0.37207651138305664, "learning_rate": 1.7956958233756315e-05, "loss": 0.2065, "step": 11350 }, { "epoch": 0.5733609246454349, "grad_norm": 0.3949874937534332, "learning_rate": 1.795161950113237e-05, "loss": 0.1993, "step": 11360 }, { "epoch": 0.5738656437692424, "grad_norm": 0.35773733258247375, "learning_rate": 1.794627459801973e-05, "loss": 0.197, "step": 11370 }, { "epoch": 0.57437036289305, "grad_norm": 0.3528626263141632, "learning_rate": 1.7940923528566082e-05, "loss": 0.2011, "step": 11380 }, { "epoch": 0.5748750820168577, "grad_norm": 0.366789311170578, "learning_rate": 1.7935566296923858e-05, "loss": 0.2017, "step": 11390 }, { "epoch": 0.5753798011406652, "grad_norm": 0.37556684017181396, "learning_rate": 1.7930202907250304e-05, "loss": 0.2015, "step": 11400 }, { "epoch": 0.5758845202644728, "grad_norm": 0.4032560884952545, "learning_rate": 1.7924833363707425e-05, "loss": 0.2051, "step": 11410 }, { "epoch": 0.5763892393882805, "grad_norm": 0.3806757926940918, "learning_rate": 1.791945767046201e-05, "loss": 0.2026, "step": 11420 }, { "epoch": 0.576893958512088, "grad_norm": 0.3679375946521759, "learning_rate": 1.7914075831685625e-05, "loss": 0.2006, "step": 11430 }, { "epoch": 0.5773986776358956, "grad_norm": 0.37518128752708435, "learning_rate": 1.7908687851554587e-05, "loss": 0.2, "step": 11440 }, { "epoch": 0.5779033967597033, "grad_norm": 0.3771637976169586, "learning_rate": 1.790329373425e-05, "loss": 0.2003, "step": 11450 }, { "epoch": 0.5784081158835108, "grad_norm": 0.36271998286247253, "learning_rate": 1.7897893483957717e-05, "loss": 0.1981, "step": 11460 }, { "epoch": 0.5789128350073184, "grad_norm": 0.4105806350708008, "learning_rate": 1.789248710486835e-05, "loss": 0.1972, "step": 11470 }, { "epoch": 0.5794175541311261, "grad_norm": 0.4346831142902374, "learning_rate": 1.788707460117728e-05, "loss": 0.2004, "step": 11480 }, { "epoch": 0.5799222732549336, "grad_norm": 0.39782822132110596, "learning_rate": 1.7881655977084623e-05, "loss": 0.1985, "step": 11490 }, { "epoch": 0.5804269923787412, "grad_norm": 0.3827611804008484, "learning_rate": 1.787623123679526e-05, "loss": 0.2029, "step": 11500 }, { "epoch": 0.5809317115025489, "grad_norm": 0.3728889524936676, "learning_rate": 1.7870800384518804e-05, "loss": 0.2016, "step": 11510 }, { "epoch": 0.5814364306263564, "grad_norm": 0.3599525988101959, "learning_rate": 1.7865363424469622e-05, "loss": 0.2027, "step": 11520 }, { "epoch": 0.5819411497501641, "grad_norm": 0.423088401556015, "learning_rate": 1.7859920360866816e-05, "loss": 0.2014, "step": 11530 }, { "epoch": 0.5824458688739717, "grad_norm": 0.35874050855636597, "learning_rate": 1.785447119793423e-05, "loss": 0.204, "step": 11540 }, { "epoch": 0.5829505879977792, "grad_norm": 0.3682592511177063, "learning_rate": 1.7849015939900432e-05, "loss": 0.1948, "step": 11550 }, { "epoch": 0.5834553071215869, "grad_norm": 0.37663495540618896, "learning_rate": 1.7843554590998723e-05, "loss": 0.2017, "step": 11560 }, { "epoch": 0.5839600262453944, "grad_norm": 0.4028005301952362, "learning_rate": 1.7838087155467133e-05, "loss": 0.2022, "step": 11570 }, { "epoch": 0.584464745369202, "grad_norm": 0.353716105222702, "learning_rate": 1.7832613637548413e-05, "loss": 0.204, "step": 11580 }, { "epoch": 0.5849694644930097, "grad_norm": 0.4014138877391815, "learning_rate": 1.7827134041490036e-05, "loss": 0.1987, "step": 11590 }, { "epoch": 0.5854741836168172, "grad_norm": 0.369448721408844, "learning_rate": 1.7821648371544192e-05, "loss": 0.1974, "step": 11600 }, { "epoch": 0.5859789027406248, "grad_norm": 0.37600019574165344, "learning_rate": 1.7816156631967782e-05, "loss": 0.2017, "step": 11610 }, { "epoch": 0.5864836218644325, "grad_norm": 0.4023212790489197, "learning_rate": 1.7810658827022414e-05, "loss": 0.206, "step": 11620 }, { "epoch": 0.58698834098824, "grad_norm": 0.4584110975265503, "learning_rate": 1.7805154960974418e-05, "loss": 0.2024, "step": 11630 }, { "epoch": 0.5874930601120476, "grad_norm": 0.3865315616130829, "learning_rate": 1.7799645038094803e-05, "loss": 0.2047, "step": 11640 }, { "epoch": 0.5879977792358553, "grad_norm": 0.38099750876426697, "learning_rate": 1.77941290626593e-05, "loss": 0.2019, "step": 11650 }, { "epoch": 0.5885024983596628, "grad_norm": 0.3519286811351776, "learning_rate": 1.7788607038948317e-05, "loss": 0.1953, "step": 11660 }, { "epoch": 0.5890072174834704, "grad_norm": 0.3987323045730591, "learning_rate": 1.778307897124698e-05, "loss": 0.2, "step": 11670 }, { "epoch": 0.5895119366072781, "grad_norm": 0.3673013150691986, "learning_rate": 1.7777544863845085e-05, "loss": 0.2055, "step": 11680 }, { "epoch": 0.5900166557310856, "grad_norm": 0.3869536817073822, "learning_rate": 1.7772004721037125e-05, "loss": 0.1978, "step": 11690 }, { "epoch": 0.5905213748548932, "grad_norm": 0.3834979236125946, "learning_rate": 1.7766458547122272e-05, "loss": 0.1996, "step": 11700 }, { "epoch": 0.5910260939787009, "grad_norm": 0.4139108657836914, "learning_rate": 1.7760906346404374e-05, "loss": 0.2082, "step": 11710 }, { "epoch": 0.5915308131025084, "grad_norm": 0.35232701897621155, "learning_rate": 1.7755348123191968e-05, "loss": 0.1963, "step": 11720 }, { "epoch": 0.5920355322263161, "grad_norm": 0.364030122756958, "learning_rate": 1.7749783881798253e-05, "loss": 0.197, "step": 11730 }, { "epoch": 0.5925402513501237, "grad_norm": 0.43412619829177856, "learning_rate": 1.7744213626541104e-05, "loss": 0.1969, "step": 11740 }, { "epoch": 0.5930449704739312, "grad_norm": 0.40217188000679016, "learning_rate": 1.773863736174306e-05, "loss": 0.1933, "step": 11750 }, { "epoch": 0.5935496895977389, "grad_norm": 0.3734113574028015, "learning_rate": 1.7733055091731332e-05, "loss": 0.1989, "step": 11760 }, { "epoch": 0.5940544087215465, "grad_norm": 0.4069409668445587, "learning_rate": 1.7727466820837772e-05, "loss": 0.2007, "step": 11770 }, { "epoch": 0.594559127845354, "grad_norm": 0.38047051429748535, "learning_rate": 1.7721872553398914e-05, "loss": 0.1964, "step": 11780 }, { "epoch": 0.5950638469691617, "grad_norm": 0.3625827431678772, "learning_rate": 1.771627229375592e-05, "loss": 0.1963, "step": 11790 }, { "epoch": 0.5955685660929693, "grad_norm": 0.36244070529937744, "learning_rate": 1.7710666046254623e-05, "loss": 0.1982, "step": 11800 }, { "epoch": 0.5960732852167768, "grad_norm": 0.4101755917072296, "learning_rate": 1.770505381524549e-05, "loss": 0.2007, "step": 11810 }, { "epoch": 0.5965780043405845, "grad_norm": 0.41657382249832153, "learning_rate": 1.769943560508363e-05, "loss": 0.1986, "step": 11820 }, { "epoch": 0.5970827234643921, "grad_norm": 0.41567012667655945, "learning_rate": 1.769381142012881e-05, "loss": 0.1861, "step": 11830 }, { "epoch": 0.5975874425881996, "grad_norm": 0.4253331124782562, "learning_rate": 1.7688181264745402e-05, "loss": 0.1987, "step": 11840 }, { "epoch": 0.5980921617120073, "grad_norm": 0.3822976052761078, "learning_rate": 1.7682545143302445e-05, "loss": 0.2067, "step": 11850 }, { "epoch": 0.5985968808358149, "grad_norm": 0.4388420879840851, "learning_rate": 1.767690306017358e-05, "loss": 0.2008, "step": 11860 }, { "epoch": 0.5991015999596224, "grad_norm": 0.39134496450424194, "learning_rate": 1.76712550197371e-05, "loss": 0.1957, "step": 11870 }, { "epoch": 0.5996063190834301, "grad_norm": 0.3856163024902344, "learning_rate": 1.7665601026375893e-05, "loss": 0.2011, "step": 11880 }, { "epoch": 0.6001110382072377, "grad_norm": 0.3519302010536194, "learning_rate": 1.7659941084477488e-05, "loss": 0.1948, "step": 11890 }, { "epoch": 0.6006157573310452, "grad_norm": 0.3734939694404602, "learning_rate": 1.7654275198434022e-05, "loss": 0.1995, "step": 11900 }, { "epoch": 0.6011204764548529, "grad_norm": 0.38880518078804016, "learning_rate": 1.7648603372642242e-05, "loss": 0.2039, "step": 11910 }, { "epoch": 0.6016251955786605, "grad_norm": 0.40201830863952637, "learning_rate": 1.764292561150351e-05, "loss": 0.2041, "step": 11920 }, { "epoch": 0.6021299147024681, "grad_norm": 0.39442816376686096, "learning_rate": 1.7637241919423795e-05, "loss": 0.2085, "step": 11930 }, { "epoch": 0.6026346338262757, "grad_norm": 0.38582512736320496, "learning_rate": 1.763155230081366e-05, "loss": 0.2033, "step": 11940 }, { "epoch": 0.6031393529500833, "grad_norm": 0.3951614797115326, "learning_rate": 1.7625856760088268e-05, "loss": 0.1979, "step": 11950 }, { "epoch": 0.6036440720738909, "grad_norm": 0.41499537229537964, "learning_rate": 1.7620155301667394e-05, "loss": 0.2042, "step": 11960 }, { "epoch": 0.6041487911976985, "grad_norm": 0.397180438041687, "learning_rate": 1.7614447929975383e-05, "loss": 0.1983, "step": 11970 }, { "epoch": 0.604653510321506, "grad_norm": 0.3790379762649536, "learning_rate": 1.760873464944118e-05, "loss": 0.1982, "step": 11980 }, { "epoch": 0.6051582294453137, "grad_norm": 0.4035373330116272, "learning_rate": 1.7603015464498315e-05, "loss": 0.1998, "step": 11990 }, { "epoch": 0.6056629485691213, "grad_norm": 0.3578663766384125, "learning_rate": 1.75972903795849e-05, "loss": 0.201, "step": 12000 }, { "epoch": 0.6061676676929288, "grad_norm": 0.37748315930366516, "learning_rate": 1.759155939914362e-05, "loss": 0.1987, "step": 12010 }, { "epoch": 0.6066723868167365, "grad_norm": 0.37748974561691284, "learning_rate": 1.7585822527621736e-05, "loss": 0.1999, "step": 12020 }, { "epoch": 0.6071771059405441, "grad_norm": 0.4352845251560211, "learning_rate": 1.7580079769471093e-05, "loss": 0.1997, "step": 12030 }, { "epoch": 0.6076818250643516, "grad_norm": 0.3747280240058899, "learning_rate": 1.757433112914809e-05, "loss": 0.1974, "step": 12040 }, { "epoch": 0.6081865441881593, "grad_norm": 0.4629654884338379, "learning_rate": 1.7568576611113696e-05, "loss": 0.1998, "step": 12050 }, { "epoch": 0.6086912633119669, "grad_norm": 0.3980845510959625, "learning_rate": 1.7562816219833433e-05, "loss": 0.1911, "step": 12060 }, { "epoch": 0.6091959824357744, "grad_norm": 0.3969227373600006, "learning_rate": 1.7557049959777395e-05, "loss": 0.1964, "step": 12070 }, { "epoch": 0.6097007015595821, "grad_norm": 0.3948403298854828, "learning_rate": 1.7551277835420223e-05, "loss": 0.1977, "step": 12080 }, { "epoch": 0.6102054206833897, "grad_norm": 0.38488689064979553, "learning_rate": 1.754549985124111e-05, "loss": 0.2015, "step": 12090 }, { "epoch": 0.6107101398071973, "grad_norm": 0.377568781375885, "learning_rate": 1.7539716011723788e-05, "loss": 0.1976, "step": 12100 }, { "epoch": 0.6112148589310049, "grad_norm": 0.4071504473686218, "learning_rate": 1.7533926321356544e-05, "loss": 0.1957, "step": 12110 }, { "epoch": 0.6117195780548125, "grad_norm": 0.38919949531555176, "learning_rate": 1.75281307846322e-05, "loss": 0.1968, "step": 12120 }, { "epoch": 0.6122242971786201, "grad_norm": 0.4229075312614441, "learning_rate": 1.752232940604812e-05, "loss": 0.1987, "step": 12130 }, { "epoch": 0.6127290163024277, "grad_norm": 0.39213117957115173, "learning_rate": 1.7516522190106185e-05, "loss": 0.2044, "step": 12140 }, { "epoch": 0.6132337354262353, "grad_norm": 0.3885519802570343, "learning_rate": 1.7510709141312837e-05, "loss": 0.1998, "step": 12150 }, { "epoch": 0.6137384545500429, "grad_norm": 0.43953508138656616, "learning_rate": 1.7504890264179007e-05, "loss": 0.1958, "step": 12160 }, { "epoch": 0.6142431736738505, "grad_norm": 0.3994976282119751, "learning_rate": 1.749906556322018e-05, "loss": 0.2001, "step": 12170 }, { "epoch": 0.6147478927976581, "grad_norm": 0.409870982170105, "learning_rate": 1.7493235042956337e-05, "loss": 0.2019, "step": 12180 }, { "epoch": 0.6152526119214657, "grad_norm": 0.39965468645095825, "learning_rate": 1.7487398707911993e-05, "loss": 0.2048, "step": 12190 }, { "epoch": 0.6157573310452733, "grad_norm": 0.38115406036376953, "learning_rate": 1.7481556562616165e-05, "loss": 0.1963, "step": 12200 }, { "epoch": 0.6162620501690809, "grad_norm": 0.4095768630504608, "learning_rate": 1.747570861160238e-05, "loss": 0.1969, "step": 12210 }, { "epoch": 0.6167667692928885, "grad_norm": 0.3909987807273865, "learning_rate": 1.7469854859408672e-05, "loss": 0.2034, "step": 12220 }, { "epoch": 0.6172714884166961, "grad_norm": 0.388033002614975, "learning_rate": 1.7463995310577577e-05, "loss": 0.1933, "step": 12230 }, { "epoch": 0.6177762075405037, "grad_norm": 0.3954012393951416, "learning_rate": 1.745812996965613e-05, "loss": 0.1993, "step": 12240 }, { "epoch": 0.6182809266643113, "grad_norm": 0.41114819049835205, "learning_rate": 1.7452258841195858e-05, "loss": 0.1941, "step": 12250 }, { "epoch": 0.6187856457881189, "grad_norm": 0.396997332572937, "learning_rate": 1.7446381929752773e-05, "loss": 0.1995, "step": 12260 }, { "epoch": 0.6192903649119265, "grad_norm": 0.47175946831703186, "learning_rate": 1.7440499239887395e-05, "loss": 0.2005, "step": 12270 }, { "epoch": 0.6197950840357341, "grad_norm": 0.37771347165107727, "learning_rate": 1.7434610776164704e-05, "loss": 0.2018, "step": 12280 }, { "epoch": 0.6202998031595417, "grad_norm": 0.3708938956260681, "learning_rate": 1.7428716543154177e-05, "loss": 0.2018, "step": 12290 }, { "epoch": 0.6208045222833494, "grad_norm": 0.3980335295200348, "learning_rate": 1.7422816545429762e-05, "loss": 0.1987, "step": 12300 }, { "epoch": 0.6213092414071569, "grad_norm": 0.3915196657180786, "learning_rate": 1.741691078756988e-05, "loss": 0.1932, "step": 12310 }, { "epoch": 0.6218139605309645, "grad_norm": 0.3662637174129486, "learning_rate": 1.7410999274157423e-05, "loss": 0.1963, "step": 12320 }, { "epoch": 0.6223186796547722, "grad_norm": 0.3465867042541504, "learning_rate": 1.740508200977975e-05, "loss": 0.1965, "step": 12330 }, { "epoch": 0.6228233987785797, "grad_norm": 0.37208297848701477, "learning_rate": 1.739915899902868e-05, "loss": 0.2007, "step": 12340 }, { "epoch": 0.6233281179023873, "grad_norm": 0.3631781041622162, "learning_rate": 1.7393230246500493e-05, "loss": 0.1922, "step": 12350 }, { "epoch": 0.623832837026195, "grad_norm": 0.3841148018836975, "learning_rate": 1.7387295756795927e-05, "loss": 0.1978, "step": 12360 }, { "epoch": 0.6243375561500025, "grad_norm": 0.3531671464443207, "learning_rate": 1.738135553452017e-05, "loss": 0.1941, "step": 12370 }, { "epoch": 0.6248422752738101, "grad_norm": 0.3941947817802429, "learning_rate": 1.7375409584282857e-05, "loss": 0.2054, "step": 12380 }, { "epoch": 0.6253469943976178, "grad_norm": 0.4228980541229248, "learning_rate": 1.736945791069807e-05, "loss": 0.2039, "step": 12390 }, { "epoch": 0.6258517135214253, "grad_norm": 0.35877537727355957, "learning_rate": 1.736350051838433e-05, "loss": 0.198, "step": 12400 }, { "epoch": 0.6263564326452329, "grad_norm": 0.4509330987930298, "learning_rate": 1.7357537411964603e-05, "loss": 0.2032, "step": 12410 }, { "epoch": 0.6268611517690406, "grad_norm": 0.4022054672241211, "learning_rate": 1.7351568596066274e-05, "loss": 0.1958, "step": 12420 }, { "epoch": 0.6273658708928481, "grad_norm": 0.39182671904563904, "learning_rate": 1.7345594075321174e-05, "loss": 0.1967, "step": 12430 }, { "epoch": 0.6278705900166557, "grad_norm": 0.3739950954914093, "learning_rate": 1.7339613854365557e-05, "loss": 0.2042, "step": 12440 }, { "epoch": 0.6283753091404634, "grad_norm": 0.348954439163208, "learning_rate": 1.7333627937840094e-05, "loss": 0.2029, "step": 12450 }, { "epoch": 0.6288800282642709, "grad_norm": 0.3909941017627716, "learning_rate": 1.7327636330389882e-05, "loss": 0.1998, "step": 12460 }, { "epoch": 0.6293847473880785, "grad_norm": 0.3606491982936859, "learning_rate": 1.732163903666443e-05, "loss": 0.198, "step": 12470 }, { "epoch": 0.6298894665118862, "grad_norm": 0.3633866012096405, "learning_rate": 1.731563606131767e-05, "loss": 0.1991, "step": 12480 }, { "epoch": 0.6303941856356937, "grad_norm": 0.3769007921218872, "learning_rate": 1.730962740900793e-05, "loss": 0.1967, "step": 12490 }, { "epoch": 0.6308989047595014, "grad_norm": 0.4067450165748596, "learning_rate": 1.730361308439794e-05, "loss": 0.198, "step": 12500 }, { "epoch": 0.631403623883309, "grad_norm": 0.3991717994213104, "learning_rate": 1.7297593092154853e-05, "loss": 0.2011, "step": 12510 }, { "epoch": 0.6319083430071165, "grad_norm": 0.42232346534729004, "learning_rate": 1.72915674369502e-05, "loss": 0.1959, "step": 12520 }, { "epoch": 0.6324130621309242, "grad_norm": 0.4012322425842285, "learning_rate": 1.7285536123459922e-05, "loss": 0.1992, "step": 12530 }, { "epoch": 0.6329177812547317, "grad_norm": 0.36620205640792847, "learning_rate": 1.7279499156364332e-05, "loss": 0.202, "step": 12540 }, { "epoch": 0.6334225003785393, "grad_norm": 0.3866264820098877, "learning_rate": 1.7273456540348144e-05, "loss": 0.1953, "step": 12550 }, { "epoch": 0.633927219502347, "grad_norm": 0.37210196256637573, "learning_rate": 1.7267408280100455e-05, "loss": 0.1984, "step": 12560 }, { "epoch": 0.6344319386261545, "grad_norm": 0.3809277415275574, "learning_rate": 1.7261354380314735e-05, "loss": 0.1965, "step": 12570 }, { "epoch": 0.6349366577499621, "grad_norm": 0.3741433024406433, "learning_rate": 1.7255294845688842e-05, "loss": 0.2005, "step": 12580 }, { "epoch": 0.6354413768737698, "grad_norm": 0.4012896716594696, "learning_rate": 1.724922968092499e-05, "loss": 0.1942, "step": 12590 }, { "epoch": 0.6359460959975773, "grad_norm": 0.4193804860115051, "learning_rate": 1.7243158890729777e-05, "loss": 0.1962, "step": 12600 }, { "epoch": 0.6364508151213849, "grad_norm": 0.37034115195274353, "learning_rate": 1.723708247981416e-05, "loss": 0.2028, "step": 12610 }, { "epoch": 0.6369555342451926, "grad_norm": 0.39561498165130615, "learning_rate": 1.7231000452893458e-05, "loss": 0.1969, "step": 12620 }, { "epoch": 0.6374602533690001, "grad_norm": 0.3656936287879944, "learning_rate": 1.722491281468735e-05, "loss": 0.1969, "step": 12630 }, { "epoch": 0.6379649724928077, "grad_norm": 0.3869703412055969, "learning_rate": 1.721881956991986e-05, "loss": 0.1985, "step": 12640 }, { "epoch": 0.6384696916166154, "grad_norm": 0.38972997665405273, "learning_rate": 1.721272072331938e-05, "loss": 0.1981, "step": 12650 }, { "epoch": 0.6389744107404229, "grad_norm": 0.4091373085975647, "learning_rate": 1.7206616279618633e-05, "loss": 0.1994, "step": 12660 }, { "epoch": 0.6394791298642306, "grad_norm": 0.3884584307670593, "learning_rate": 1.7200506243554697e-05, "loss": 0.198, "step": 12670 }, { "epoch": 0.6399838489880382, "grad_norm": 0.374698668718338, "learning_rate": 1.719439061986898e-05, "loss": 0.1956, "step": 12680 }, { "epoch": 0.6404885681118457, "grad_norm": 0.3848966062068939, "learning_rate": 1.718826941330723e-05, "loss": 0.1982, "step": 12690 }, { "epoch": 0.6409932872356534, "grad_norm": 0.37581998109817505, "learning_rate": 1.7182142628619533e-05, "loss": 0.195, "step": 12700 }, { "epoch": 0.641498006359461, "grad_norm": 0.3918176293373108, "learning_rate": 1.7176010270560298e-05, "loss": 0.1961, "step": 12710 }, { "epoch": 0.6420027254832685, "grad_norm": 0.38475972414016724, "learning_rate": 1.7169872343888255e-05, "loss": 0.1951, "step": 12720 }, { "epoch": 0.6425074446070762, "grad_norm": 0.4185774028301239, "learning_rate": 1.7163728853366463e-05, "loss": 0.2014, "step": 12730 }, { "epoch": 0.6430121637308838, "grad_norm": 0.36200910806655884, "learning_rate": 1.7157579803762292e-05, "loss": 0.1942, "step": 12740 }, { "epoch": 0.6435168828546913, "grad_norm": 0.39098918437957764, "learning_rate": 1.715142519984743e-05, "loss": 0.1994, "step": 12750 }, { "epoch": 0.644021601978499, "grad_norm": 0.38908007740974426, "learning_rate": 1.714526504639788e-05, "loss": 0.2071, "step": 12760 }, { "epoch": 0.6445263211023066, "grad_norm": 0.3928014636039734, "learning_rate": 1.713909934819394e-05, "loss": 0.1996, "step": 12770 }, { "epoch": 0.6450310402261141, "grad_norm": 0.40639176964759827, "learning_rate": 1.713292811002022e-05, "loss": 0.2018, "step": 12780 }, { "epoch": 0.6455357593499218, "grad_norm": 0.37025558948516846, "learning_rate": 1.7126751336665624e-05, "loss": 0.1984, "step": 12790 }, { "epoch": 0.6460404784737294, "grad_norm": 0.39998531341552734, "learning_rate": 1.7120569032923353e-05, "loss": 0.1976, "step": 12800 }, { "epoch": 0.6465451975975369, "grad_norm": 0.4011460840702057, "learning_rate": 1.7114381203590896e-05, "loss": 0.1945, "step": 12810 }, { "epoch": 0.6470499167213446, "grad_norm": 0.4153386950492859, "learning_rate": 1.7108187853470043e-05, "loss": 0.1965, "step": 12820 }, { "epoch": 0.6475546358451522, "grad_norm": 0.37832820415496826, "learning_rate": 1.710198898736685e-05, "loss": 0.2068, "step": 12830 }, { "epoch": 0.6480593549689597, "grad_norm": 0.38299107551574707, "learning_rate": 1.709578461009166e-05, "loss": 0.1889, "step": 12840 }, { "epoch": 0.6485640740927674, "grad_norm": 0.39121997356414795, "learning_rate": 1.7089574726459104e-05, "loss": 0.1999, "step": 12850 }, { "epoch": 0.649068793216575, "grad_norm": 0.40152978897094727, "learning_rate": 1.708335934128807e-05, "loss": 0.2025, "step": 12860 }, { "epoch": 0.6495735123403826, "grad_norm": 0.4284897446632385, "learning_rate": 1.7077138459401723e-05, "loss": 0.196, "step": 12870 }, { "epoch": 0.6500782314641902, "grad_norm": 0.37975409626960754, "learning_rate": 1.7070912085627495e-05, "loss": 0.1993, "step": 12880 }, { "epoch": 0.6505829505879978, "grad_norm": 0.39149725437164307, "learning_rate": 1.7064680224797074e-05, "loss": 0.2025, "step": 12890 }, { "epoch": 0.6510876697118054, "grad_norm": 0.40011101961135864, "learning_rate": 1.705844288174641e-05, "loss": 0.1976, "step": 12900 }, { "epoch": 0.651592388835613, "grad_norm": 0.3902651369571686, "learning_rate": 1.7052200061315708e-05, "loss": 0.1978, "step": 12910 }, { "epoch": 0.6520971079594206, "grad_norm": 0.39409568905830383, "learning_rate": 1.704595176834942e-05, "loss": 0.198, "step": 12920 }, { "epoch": 0.6526018270832282, "grad_norm": 0.38591471314430237, "learning_rate": 1.7039698007696246e-05, "loss": 0.1971, "step": 12930 }, { "epoch": 0.6531065462070358, "grad_norm": 0.3889164924621582, "learning_rate": 1.703343878420913e-05, "loss": 0.1971, "step": 12940 }, { "epoch": 0.6536112653308433, "grad_norm": 0.3969559967517853, "learning_rate": 1.7027174102745253e-05, "loss": 0.1991, "step": 12950 }, { "epoch": 0.654115984454651, "grad_norm": 0.4020228981971741, "learning_rate": 1.7020903968166038e-05, "loss": 0.1948, "step": 12960 }, { "epoch": 0.6546207035784586, "grad_norm": 0.4006873369216919, "learning_rate": 1.701462838533713e-05, "loss": 0.1957, "step": 12970 }, { "epoch": 0.6551254227022661, "grad_norm": 0.37443792819976807, "learning_rate": 1.7008347359128407e-05, "loss": 0.1974, "step": 12980 }, { "epoch": 0.6556301418260738, "grad_norm": 0.37341782450675964, "learning_rate": 1.700206089441397e-05, "loss": 0.1944, "step": 12990 }, { "epoch": 0.6561348609498814, "grad_norm": 0.3694671392440796, "learning_rate": 1.699576899607214e-05, "loss": 0.1978, "step": 13000 }, { "epoch": 0.6566395800736889, "grad_norm": 0.38782092928886414, "learning_rate": 1.6989471668985464e-05, "loss": 0.2008, "step": 13010 }, { "epoch": 0.6571442991974966, "grad_norm": 0.3584984540939331, "learning_rate": 1.6983168918040684e-05, "loss": 0.2004, "step": 13020 }, { "epoch": 0.6576490183213042, "grad_norm": 0.38087981939315796, "learning_rate": 1.697686074812876e-05, "loss": 0.193, "step": 13030 }, { "epoch": 0.6581537374451117, "grad_norm": 0.3971461355686188, "learning_rate": 1.6970547164144866e-05, "loss": 0.198, "step": 13040 }, { "epoch": 0.6586584565689194, "grad_norm": 0.3880884349346161, "learning_rate": 1.696422817098836e-05, "loss": 0.2024, "step": 13050 }, { "epoch": 0.659163175692727, "grad_norm": 0.3585631549358368, "learning_rate": 1.6957903773562804e-05, "loss": 0.1957, "step": 13060 }, { "epoch": 0.6596678948165347, "grad_norm": 0.3763216733932495, "learning_rate": 1.6951573976775967e-05, "loss": 0.1932, "step": 13070 }, { "epoch": 0.6601726139403422, "grad_norm": 0.3846004605293274, "learning_rate": 1.6945238785539787e-05, "loss": 0.1972, "step": 13080 }, { "epoch": 0.6606773330641498, "grad_norm": 0.3510109782218933, "learning_rate": 1.69388982047704e-05, "loss": 0.197, "step": 13090 }, { "epoch": 0.6611820521879574, "grad_norm": 0.4155005216598511, "learning_rate": 1.6932552239388123e-05, "loss": 0.1997, "step": 13100 }, { "epoch": 0.661686771311765, "grad_norm": 0.3863025903701782, "learning_rate": 1.6926200894317454e-05, "loss": 0.2014, "step": 13110 }, { "epoch": 0.6621914904355726, "grad_norm": 0.3492284119129181, "learning_rate": 1.6919844174487056e-05, "loss": 0.1951, "step": 13120 }, { "epoch": 0.6626962095593802, "grad_norm": 0.3814416229724884, "learning_rate": 1.6913482084829774e-05, "loss": 0.1941, "step": 13130 }, { "epoch": 0.6632009286831878, "grad_norm": 0.5353518128395081, "learning_rate": 1.690711463028261e-05, "loss": 0.1978, "step": 13140 }, { "epoch": 0.6637056478069954, "grad_norm": 0.367686003446579, "learning_rate": 1.6900741815786743e-05, "loss": 0.1982, "step": 13150 }, { "epoch": 0.664210366930803, "grad_norm": 0.34120479226112366, "learning_rate": 1.6894363646287495e-05, "loss": 0.1992, "step": 13160 }, { "epoch": 0.6647150860546106, "grad_norm": 0.3741379976272583, "learning_rate": 1.688798012673435e-05, "loss": 0.1939, "step": 13170 }, { "epoch": 0.6652198051784182, "grad_norm": 0.3939100503921509, "learning_rate": 1.6881591262080955e-05, "loss": 0.1997, "step": 13180 }, { "epoch": 0.6657245243022258, "grad_norm": 0.47499963641166687, "learning_rate": 1.6875197057285085e-05, "loss": 0.1993, "step": 13190 }, { "epoch": 0.6662292434260334, "grad_norm": 0.3781881034374237, "learning_rate": 1.686879751730867e-05, "loss": 0.1969, "step": 13200 }, { "epoch": 0.666733962549841, "grad_norm": 0.36944580078125, "learning_rate": 1.686239264711778e-05, "loss": 0.1996, "step": 13210 }, { "epoch": 0.6672386816736486, "grad_norm": 0.39957374334335327, "learning_rate": 1.6855982451682623e-05, "loss": 0.194, "step": 13220 }, { "epoch": 0.6677434007974562, "grad_norm": 0.3784330189228058, "learning_rate": 1.684956693597753e-05, "loss": 0.1996, "step": 13230 }, { "epoch": 0.6682481199212638, "grad_norm": 0.3768441081047058, "learning_rate": 1.6843146104980976e-05, "loss": 0.1992, "step": 13240 }, { "epoch": 0.6687528390450714, "grad_norm": 0.37468549609184265, "learning_rate": 1.6836719963675543e-05, "loss": 0.2024, "step": 13250 }, { "epoch": 0.669257558168879, "grad_norm": 0.38508161902427673, "learning_rate": 1.6830288517047947e-05, "loss": 0.1934, "step": 13260 }, { "epoch": 0.6697622772926867, "grad_norm": 0.39833149313926697, "learning_rate": 1.6823851770089016e-05, "loss": 0.2041, "step": 13270 }, { "epoch": 0.6702669964164942, "grad_norm": 0.42643097043037415, "learning_rate": 1.6817409727793687e-05, "loss": 0.1949, "step": 13280 }, { "epoch": 0.6707717155403018, "grad_norm": 0.3868141174316406, "learning_rate": 1.681096239516102e-05, "loss": 0.1992, "step": 13290 }, { "epoch": 0.6712764346641095, "grad_norm": 0.39797836542129517, "learning_rate": 1.680450977719416e-05, "loss": 0.1963, "step": 13300 }, { "epoch": 0.671781153787917, "grad_norm": 0.36084139347076416, "learning_rate": 1.679805187890037e-05, "loss": 0.1962, "step": 13310 }, { "epoch": 0.6722858729117246, "grad_norm": 0.4004514813423157, "learning_rate": 1.679158870529101e-05, "loss": 0.2001, "step": 13320 }, { "epoch": 0.6727905920355323, "grad_norm": 0.3666176199913025, "learning_rate": 1.678512026138152e-05, "loss": 0.1959, "step": 13330 }, { "epoch": 0.6732953111593398, "grad_norm": 0.41817930340766907, "learning_rate": 1.6778646552191446e-05, "loss": 0.194, "step": 13340 }, { "epoch": 0.6738000302831474, "grad_norm": 0.4148036241531372, "learning_rate": 1.6772167582744402e-05, "loss": 0.1996, "step": 13350 }, { "epoch": 0.6743047494069551, "grad_norm": 0.3899047374725342, "learning_rate": 1.6765683358068106e-05, "loss": 0.1965, "step": 13360 }, { "epoch": 0.6748094685307626, "grad_norm": 0.3621644675731659, "learning_rate": 1.6759193883194337e-05, "loss": 0.1967, "step": 13370 }, { "epoch": 0.6753141876545702, "grad_norm": 0.38677746057510376, "learning_rate": 1.675269916315895e-05, "loss": 0.1984, "step": 13380 }, { "epoch": 0.6758189067783779, "grad_norm": 0.36188623309135437, "learning_rate": 1.674619920300188e-05, "loss": 0.2001, "step": 13390 }, { "epoch": 0.6763236259021854, "grad_norm": 0.3755648732185364, "learning_rate": 1.673969400776712e-05, "loss": 0.1929, "step": 13400 }, { "epoch": 0.676828345025993, "grad_norm": 0.3883925676345825, "learning_rate": 1.673318358250273e-05, "loss": 0.1984, "step": 13410 }, { "epoch": 0.6773330641498007, "grad_norm": 0.3662387430667877, "learning_rate": 1.672666793226082e-05, "loss": 0.1983, "step": 13420 }, { "epoch": 0.6778377832736082, "grad_norm": 0.42700374126434326, "learning_rate": 1.6720147062097566e-05, "loss": 0.1955, "step": 13430 }, { "epoch": 0.6783425023974159, "grad_norm": 0.41889095306396484, "learning_rate": 1.6713620977073186e-05, "loss": 0.1915, "step": 13440 }, { "epoch": 0.6788472215212235, "grad_norm": 0.38137534260749817, "learning_rate": 1.6707089682251952e-05, "loss": 0.2025, "step": 13450 }, { "epoch": 0.679351940645031, "grad_norm": 0.37026092410087585, "learning_rate": 1.6700553182702173e-05, "loss": 0.1984, "step": 13460 }, { "epoch": 0.6798566597688387, "grad_norm": 0.4479407072067261, "learning_rate": 1.66940114834962e-05, "loss": 0.1952, "step": 13470 }, { "epoch": 0.6803613788926463, "grad_norm": 0.3865918815135956, "learning_rate": 1.6687464589710413e-05, "loss": 0.1991, "step": 13480 }, { "epoch": 0.6808660980164538, "grad_norm": 0.3804604113101959, "learning_rate": 1.6680912506425232e-05, "loss": 0.2014, "step": 13490 }, { "epoch": 0.6813708171402615, "grad_norm": 0.385052353143692, "learning_rate": 1.6674355238725107e-05, "loss": 0.2004, "step": 13500 }, { "epoch": 0.681875536264069, "grad_norm": 0.3784804344177246, "learning_rate": 1.6667792791698492e-05, "loss": 0.2014, "step": 13510 }, { "epoch": 0.6823802553878766, "grad_norm": 0.3824881911277771, "learning_rate": 1.6661225170437877e-05, "loss": 0.199, "step": 13520 }, { "epoch": 0.6828849745116843, "grad_norm": 0.39223480224609375, "learning_rate": 1.665465238003976e-05, "loss": 0.197, "step": 13530 }, { "epoch": 0.6833896936354918, "grad_norm": 0.37662914395332336, "learning_rate": 1.664807442560466e-05, "loss": 0.1967, "step": 13540 }, { "epoch": 0.6838944127592994, "grad_norm": 0.39476969838142395, "learning_rate": 1.6641491312237092e-05, "loss": 0.201, "step": 13550 }, { "epoch": 0.6843991318831071, "grad_norm": 0.37896186113357544, "learning_rate": 1.6634903045045572e-05, "loss": 0.192, "step": 13560 }, { "epoch": 0.6849038510069146, "grad_norm": 0.4094081521034241, "learning_rate": 1.662830962914263e-05, "loss": 0.1952, "step": 13570 }, { "epoch": 0.6854085701307222, "grad_norm": 0.38278260827064514, "learning_rate": 1.662171106964478e-05, "loss": 0.1995, "step": 13580 }, { "epoch": 0.6859132892545299, "grad_norm": 0.3789641857147217, "learning_rate": 1.6615107371672533e-05, "loss": 0.2012, "step": 13590 }, { "epoch": 0.6864180083783374, "grad_norm": 0.3790159821510315, "learning_rate": 1.6608498540350388e-05, "loss": 0.1964, "step": 13600 }, { "epoch": 0.686922727502145, "grad_norm": 0.3926520347595215, "learning_rate": 1.6601884580806816e-05, "loss": 0.1971, "step": 13610 }, { "epoch": 0.6874274466259527, "grad_norm": 0.38520777225494385, "learning_rate": 1.659526549817428e-05, "loss": 0.197, "step": 13620 }, { "epoch": 0.6879321657497602, "grad_norm": 0.39610493183135986, "learning_rate": 1.6588641297589218e-05, "loss": 0.1987, "step": 13630 }, { "epoch": 0.6884368848735679, "grad_norm": 0.40462470054626465, "learning_rate": 1.6582011984192032e-05, "loss": 0.1959, "step": 13640 }, { "epoch": 0.6889416039973755, "grad_norm": 0.4262600839138031, "learning_rate": 1.6575377563127095e-05, "loss": 0.1915, "step": 13650 }, { "epoch": 0.689446323121183, "grad_norm": 0.383183091878891, "learning_rate": 1.656873803954275e-05, "loss": 0.1993, "step": 13660 }, { "epoch": 0.6899510422449907, "grad_norm": 0.4083116948604584, "learning_rate": 1.656209341859129e-05, "loss": 0.1986, "step": 13670 }, { "epoch": 0.6904557613687983, "grad_norm": 0.3747680187225342, "learning_rate": 1.655544370542897e-05, "loss": 0.1959, "step": 13680 }, { "epoch": 0.6909604804926058, "grad_norm": 0.38988664746284485, "learning_rate": 1.654878890521599e-05, "loss": 0.1932, "step": 13690 }, { "epoch": 0.6914651996164135, "grad_norm": 0.38024818897247314, "learning_rate": 1.6542129023116506e-05, "loss": 0.1969, "step": 13700 }, { "epoch": 0.6919699187402211, "grad_norm": 0.3934050500392914, "learning_rate": 1.653546406429861e-05, "loss": 0.1929, "step": 13710 }, { "epoch": 0.6924746378640286, "grad_norm": 0.35372960567474365, "learning_rate": 1.652879403393434e-05, "loss": 0.1945, "step": 13720 }, { "epoch": 0.6929793569878363, "grad_norm": 0.4251823127269745, "learning_rate": 1.6522118937199664e-05, "loss": 0.1995, "step": 13730 }, { "epoch": 0.6934840761116439, "grad_norm": 0.38878360390663147, "learning_rate": 1.6515438779274484e-05, "loss": 0.1961, "step": 13740 }, { "epoch": 0.6939887952354514, "grad_norm": 0.4020015001296997, "learning_rate": 1.650875356534263e-05, "loss": 0.1963, "step": 13750 }, { "epoch": 0.6944935143592591, "grad_norm": 0.4074333906173706, "learning_rate": 1.6502063300591852e-05, "loss": 0.1962, "step": 13760 }, { "epoch": 0.6949982334830667, "grad_norm": 0.38548344373703003, "learning_rate": 1.6495367990213832e-05, "loss": 0.1968, "step": 13770 }, { "epoch": 0.6955029526068742, "grad_norm": 0.3974095582962036, "learning_rate": 1.6488667639404145e-05, "loss": 0.1984, "step": 13780 }, { "epoch": 0.6960076717306819, "grad_norm": 0.38586390018463135, "learning_rate": 1.6481962253362298e-05, "loss": 0.1918, "step": 13790 }, { "epoch": 0.6965123908544895, "grad_norm": 0.3638611435890198, "learning_rate": 1.6475251837291696e-05, "loss": 0.2009, "step": 13800 }, { "epoch": 0.697017109978297, "grad_norm": 0.4091808795928955, "learning_rate": 1.6468536396399647e-05, "loss": 0.1881, "step": 13810 }, { "epoch": 0.6975218291021047, "grad_norm": 0.43478116393089294, "learning_rate": 1.6461815935897362e-05, "loss": 0.1965, "step": 13820 }, { "epoch": 0.6980265482259123, "grad_norm": 0.3636973202228546, "learning_rate": 1.645509046099995e-05, "loss": 0.194, "step": 13830 }, { "epoch": 0.6985312673497199, "grad_norm": 0.3876038193702698, "learning_rate": 1.6448359976926393e-05, "loss": 0.1897, "step": 13840 }, { "epoch": 0.6990359864735275, "grad_norm": 0.378083199262619, "learning_rate": 1.6441624488899588e-05, "loss": 0.1966, "step": 13850 }, { "epoch": 0.699540705597335, "grad_norm": 0.3922813832759857, "learning_rate": 1.643488400214629e-05, "loss": 0.1982, "step": 13860 }, { "epoch": 0.7000454247211427, "grad_norm": 0.368722528219223, "learning_rate": 1.642813852189715e-05, "loss": 0.191, "step": 13870 }, { "epoch": 0.7005501438449503, "grad_norm": 0.3934316635131836, "learning_rate": 1.642138805338669e-05, "loss": 0.1971, "step": 13880 }, { "epoch": 0.7010548629687579, "grad_norm": 0.37000471353530884, "learning_rate": 1.64146326018533e-05, "loss": 0.1973, "step": 13890 }, { "epoch": 0.7015595820925655, "grad_norm": 0.38313034176826477, "learning_rate": 1.6407872172539225e-05, "loss": 0.2013, "step": 13900 }, { "epoch": 0.7020643012163731, "grad_norm": 0.3806428015232086, "learning_rate": 1.64011067706906e-05, "loss": 0.1911, "step": 13910 }, { "epoch": 0.7025690203401806, "grad_norm": 0.37560582160949707, "learning_rate": 1.63943364015574e-05, "loss": 0.1996, "step": 13920 }, { "epoch": 0.7030737394639883, "grad_norm": 0.40906569361686707, "learning_rate": 1.6387561070393458e-05, "loss": 0.2035, "step": 13930 }, { "epoch": 0.7035784585877959, "grad_norm": 0.3923541009426117, "learning_rate": 1.6380780782456452e-05, "loss": 0.1956, "step": 13940 }, { "epoch": 0.7040831777116034, "grad_norm": 0.4144946038722992, "learning_rate": 1.6373995543007926e-05, "loss": 0.2041, "step": 13950 }, { "epoch": 0.7045878968354111, "grad_norm": 0.3996979892253876, "learning_rate": 1.6367205357313244e-05, "loss": 0.1906, "step": 13960 }, { "epoch": 0.7050926159592187, "grad_norm": 0.3782827854156494, "learning_rate": 1.6360410230641617e-05, "loss": 0.1948, "step": 13970 }, { "epoch": 0.7055973350830262, "grad_norm": 0.41548803448677063, "learning_rate": 1.6353610168266093e-05, "loss": 0.198, "step": 13980 }, { "epoch": 0.7061020542068339, "grad_norm": 0.3644377887248993, "learning_rate": 1.6346805175463547e-05, "loss": 0.1935, "step": 13990 }, { "epoch": 0.7066067733306415, "grad_norm": 0.36729636788368225, "learning_rate": 1.633999525751468e-05, "loss": 0.1973, "step": 14000 }, { "epoch": 0.7071114924544492, "grad_norm": 0.3803146779537201, "learning_rate": 1.633318041970402e-05, "loss": 0.1983, "step": 14010 }, { "epoch": 0.7076162115782567, "grad_norm": 0.3989185392856598, "learning_rate": 1.6326360667319906e-05, "loss": 0.1953, "step": 14020 }, { "epoch": 0.7081209307020643, "grad_norm": 0.381484717130661, "learning_rate": 1.631953600565449e-05, "loss": 0.1985, "step": 14030 }, { "epoch": 0.708625649825872, "grad_norm": 0.383317232131958, "learning_rate": 1.631270644000374e-05, "loss": 0.1979, "step": 14040 }, { "epoch": 0.7091303689496795, "grad_norm": 0.4024946093559265, "learning_rate": 1.630587197566743e-05, "loss": 0.1955, "step": 14050 }, { "epoch": 0.7096350880734871, "grad_norm": 0.3680899143218994, "learning_rate": 1.629903261794912e-05, "loss": 0.1964, "step": 14060 }, { "epoch": 0.7101398071972947, "grad_norm": 0.34081384539604187, "learning_rate": 1.629218837215619e-05, "loss": 0.1945, "step": 14070 }, { "epoch": 0.7106445263211023, "grad_norm": 0.3675892949104309, "learning_rate": 1.62853392435998e-05, "loss": 0.1897, "step": 14080 }, { "epoch": 0.7111492454449099, "grad_norm": 0.3632557690143585, "learning_rate": 1.6278485237594902e-05, "loss": 0.1878, "step": 14090 }, { "epoch": 0.7116539645687175, "grad_norm": 0.36727526783943176, "learning_rate": 1.6271626359460223e-05, "loss": 0.1962, "step": 14100 }, { "epoch": 0.7121586836925251, "grad_norm": 0.3732534646987915, "learning_rate": 1.6264762614518293e-05, "loss": 0.2005, "step": 14110 }, { "epoch": 0.7126634028163327, "grad_norm": 0.36209800839424133, "learning_rate": 1.62578940080954e-05, "loss": 0.1896, "step": 14120 }, { "epoch": 0.7131681219401403, "grad_norm": 0.3621096909046173, "learning_rate": 1.625102054552161e-05, "loss": 0.1897, "step": 14130 }, { "epoch": 0.7136728410639479, "grad_norm": 0.3879000246524811, "learning_rate": 1.624414223213076e-05, "loss": 0.1949, "step": 14140 }, { "epoch": 0.7141775601877555, "grad_norm": 0.36160922050476074, "learning_rate": 1.6237259073260444e-05, "loss": 0.196, "step": 14150 }, { "epoch": 0.7146822793115631, "grad_norm": 0.39675718545913696, "learning_rate": 1.6230371074252027e-05, "loss": 0.1915, "step": 14160 }, { "epoch": 0.7151869984353707, "grad_norm": 0.3618093430995941, "learning_rate": 1.6223478240450615e-05, "loss": 0.1956, "step": 14170 }, { "epoch": 0.7156917175591783, "grad_norm": 0.4066559374332428, "learning_rate": 1.6216580577205085e-05, "loss": 0.1975, "step": 14180 }, { "epoch": 0.7161964366829859, "grad_norm": 0.37876927852630615, "learning_rate": 1.6209678089868042e-05, "loss": 0.1983, "step": 14190 }, { "epoch": 0.7167011558067935, "grad_norm": 0.4123234450817108, "learning_rate": 1.6202770783795854e-05, "loss": 0.1962, "step": 14200 }, { "epoch": 0.7172058749306012, "grad_norm": 0.37156733870506287, "learning_rate": 1.619585866434861e-05, "loss": 0.2018, "step": 14210 }, { "epoch": 0.7177105940544087, "grad_norm": 0.40807315707206726, "learning_rate": 1.6188941736890145e-05, "loss": 0.1979, "step": 14220 }, { "epoch": 0.7182153131782163, "grad_norm": 0.4033885598182678, "learning_rate": 1.618202000678802e-05, "loss": 0.2025, "step": 14230 }, { "epoch": 0.718720032302024, "grad_norm": 0.3750210702419281, "learning_rate": 1.6175093479413534e-05, "loss": 0.1924, "step": 14240 }, { "epoch": 0.7192247514258315, "grad_norm": 0.3724398910999298, "learning_rate": 1.616816216014169e-05, "loss": 0.1968, "step": 14250 }, { "epoch": 0.7197294705496391, "grad_norm": 0.4031723141670227, "learning_rate": 1.616122605435123e-05, "loss": 0.2006, "step": 14260 }, { "epoch": 0.7202341896734468, "grad_norm": 0.3615586757659912, "learning_rate": 1.6154285167424588e-05, "loss": 0.1958, "step": 14270 }, { "epoch": 0.7207389087972543, "grad_norm": 0.34510958194732666, "learning_rate": 1.6147339504747926e-05, "loss": 0.1986, "step": 14280 }, { "epoch": 0.7212436279210619, "grad_norm": 0.4202043116092682, "learning_rate": 1.614038907171111e-05, "loss": 0.1957, "step": 14290 }, { "epoch": 0.7217483470448696, "grad_norm": 0.3755306899547577, "learning_rate": 1.6133433873707696e-05, "loss": 0.2016, "step": 14300 }, { "epoch": 0.7222530661686771, "grad_norm": 0.39483973383903503, "learning_rate": 1.612647391613495e-05, "loss": 0.1978, "step": 14310 }, { "epoch": 0.7227577852924847, "grad_norm": 0.3971537947654724, "learning_rate": 1.611950920439383e-05, "loss": 0.1904, "step": 14320 }, { "epoch": 0.7232625044162924, "grad_norm": 0.38187363743782043, "learning_rate": 1.6112539743888975e-05, "loss": 0.1938, "step": 14330 }, { "epoch": 0.7237672235400999, "grad_norm": 0.38724425435066223, "learning_rate": 1.6105565540028716e-05, "loss": 0.1964, "step": 14340 }, { "epoch": 0.7242719426639075, "grad_norm": 0.3647630214691162, "learning_rate": 1.6098586598225063e-05, "loss": 0.1953, "step": 14350 }, { "epoch": 0.7247766617877152, "grad_norm": 0.4142031967639923, "learning_rate": 1.6091602923893705e-05, "loss": 0.1946, "step": 14360 }, { "epoch": 0.7252813809115227, "grad_norm": 0.41555142402648926, "learning_rate": 1.6084614522454e-05, "loss": 0.1953, "step": 14370 }, { "epoch": 0.7257861000353303, "grad_norm": 0.3853343427181244, "learning_rate": 1.6077621399328974e-05, "loss": 0.1995, "step": 14380 }, { "epoch": 0.726290819159138, "grad_norm": 0.3774697184562683, "learning_rate": 1.607062355994532e-05, "loss": 0.1948, "step": 14390 }, { "epoch": 0.7267955382829455, "grad_norm": 0.3801785707473755, "learning_rate": 1.6063621009733392e-05, "loss": 0.1941, "step": 14400 }, { "epoch": 0.7273002574067532, "grad_norm": 0.4020797610282898, "learning_rate": 1.6056613754127192e-05, "loss": 0.1959, "step": 14410 }, { "epoch": 0.7278049765305608, "grad_norm": 0.4050591289997101, "learning_rate": 1.6049601798564386e-05, "loss": 0.2006, "step": 14420 }, { "epoch": 0.7283096956543683, "grad_norm": 0.34517136216163635, "learning_rate": 1.604258514848627e-05, "loss": 0.1979, "step": 14430 }, { "epoch": 0.728814414778176, "grad_norm": 0.37919241189956665, "learning_rate": 1.60355638093378e-05, "loss": 0.1949, "step": 14440 }, { "epoch": 0.7293191339019836, "grad_norm": 0.39420458674430847, "learning_rate": 1.6028537786567557e-05, "loss": 0.1983, "step": 14450 }, { "epoch": 0.7298238530257911, "grad_norm": 0.4100387692451477, "learning_rate": 1.602150708562777e-05, "loss": 0.196, "step": 14460 }, { "epoch": 0.7303285721495988, "grad_norm": 0.39618200063705444, "learning_rate": 1.6014471711974287e-05, "loss": 0.1975, "step": 14470 }, { "epoch": 0.7308332912734063, "grad_norm": 0.38923344016075134, "learning_rate": 1.600743167106659e-05, "loss": 0.1946, "step": 14480 }, { "epoch": 0.7313380103972139, "grad_norm": 0.4007700979709625, "learning_rate": 1.6000386968367773e-05, "loss": 0.1909, "step": 14490 }, { "epoch": 0.7318427295210216, "grad_norm": 0.3966238796710968, "learning_rate": 1.5993337609344558e-05, "loss": 0.1974, "step": 14500 }, { "epoch": 0.7323474486448291, "grad_norm": 0.43674030900001526, "learning_rate": 1.5986283599467273e-05, "loss": 0.193, "step": 14510 }, { "epoch": 0.7328521677686367, "grad_norm": 0.3917844891548157, "learning_rate": 1.5979224944209863e-05, "loss": 0.1999, "step": 14520 }, { "epoch": 0.7333568868924444, "grad_norm": 0.36116427183151245, "learning_rate": 1.5972161649049868e-05, "loss": 0.196, "step": 14530 }, { "epoch": 0.7338616060162519, "grad_norm": 0.3800908923149109, "learning_rate": 1.5965093719468435e-05, "loss": 0.1948, "step": 14540 }, { "epoch": 0.7343663251400595, "grad_norm": 0.37332937121391296, "learning_rate": 1.5958021160950307e-05, "loss": 0.1956, "step": 14550 }, { "epoch": 0.7348710442638672, "grad_norm": 0.4044203460216522, "learning_rate": 1.5950943978983815e-05, "loss": 0.1924, "step": 14560 }, { "epoch": 0.7353757633876747, "grad_norm": 0.368037611246109, "learning_rate": 1.5943862179060886e-05, "loss": 0.195, "step": 14570 }, { "epoch": 0.7358804825114824, "grad_norm": 0.489517480134964, "learning_rate": 1.5936775766677016e-05, "loss": 0.1923, "step": 14580 }, { "epoch": 0.73638520163529, "grad_norm": 0.39868563413619995, "learning_rate": 1.5929684747331298e-05, "loss": 0.1993, "step": 14590 }, { "epoch": 0.7368899207590975, "grad_norm": 0.3789558708667755, "learning_rate": 1.5922589126526386e-05, "loss": 0.1994, "step": 14600 }, { "epoch": 0.7373946398829052, "grad_norm": 0.48979437351226807, "learning_rate": 1.5915488909768518e-05, "loss": 0.2007, "step": 14610 }, { "epoch": 0.7378993590067128, "grad_norm": 0.39892202615737915, "learning_rate": 1.5908384102567482e-05, "loss": 0.1925, "step": 14620 }, { "epoch": 0.7384040781305203, "grad_norm": 0.3945135772228241, "learning_rate": 1.5901274710436642e-05, "loss": 0.1947, "step": 14630 }, { "epoch": 0.738908797254328, "grad_norm": 0.38129839301109314, "learning_rate": 1.5894160738892913e-05, "loss": 0.1894, "step": 14640 }, { "epoch": 0.7394135163781356, "grad_norm": 0.45286116003990173, "learning_rate": 1.5887042193456762e-05, "loss": 0.1929, "step": 14650 }, { "epoch": 0.7399182355019431, "grad_norm": 0.42050909996032715, "learning_rate": 1.5879919079652216e-05, "loss": 0.1976, "step": 14660 }, { "epoch": 0.7404229546257508, "grad_norm": 0.3809317350387573, "learning_rate": 1.5872791403006835e-05, "loss": 0.1977, "step": 14670 }, { "epoch": 0.7409276737495584, "grad_norm": 0.43207165598869324, "learning_rate": 1.586565916905173e-05, "loss": 0.1971, "step": 14680 }, { "epoch": 0.7414323928733659, "grad_norm": 0.4038008451461792, "learning_rate": 1.5858522383321536e-05, "loss": 0.1913, "step": 14690 }, { "epoch": 0.7419371119971736, "grad_norm": 0.4066081941127777, "learning_rate": 1.5851381051354432e-05, "loss": 0.1959, "step": 14700 }, { "epoch": 0.7424418311209812, "grad_norm": 0.38415852189064026, "learning_rate": 1.584423517869212e-05, "loss": 0.1966, "step": 14710 }, { "epoch": 0.7429465502447887, "grad_norm": 0.3575616478919983, "learning_rate": 1.5837084770879824e-05, "loss": 0.1947, "step": 14720 }, { "epoch": 0.7434512693685964, "grad_norm": 0.3514828085899353, "learning_rate": 1.582992983346629e-05, "loss": 0.1958, "step": 14730 }, { "epoch": 0.743955988492404, "grad_norm": 0.3653939366340637, "learning_rate": 1.582277037200378e-05, "loss": 0.1955, "step": 14740 }, { "epoch": 0.7444607076162115, "grad_norm": 0.38929611444473267, "learning_rate": 1.5815606392048062e-05, "loss": 0.2012, "step": 14750 }, { "epoch": 0.7449654267400192, "grad_norm": 0.4360821545124054, "learning_rate": 1.5808437899158417e-05, "loss": 0.196, "step": 14760 }, { "epoch": 0.7454701458638268, "grad_norm": 0.3972030580043793, "learning_rate": 1.5801264898897617e-05, "loss": 0.1929, "step": 14770 }, { "epoch": 0.7459748649876344, "grad_norm": 0.40038302540779114, "learning_rate": 1.5794087396831947e-05, "loss": 0.1951, "step": 14780 }, { "epoch": 0.746479584111442, "grad_norm": 0.4083855152130127, "learning_rate": 1.5786905398531173e-05, "loss": 0.1966, "step": 14790 }, { "epoch": 0.7469843032352496, "grad_norm": 0.3844779133796692, "learning_rate": 1.5779718909568556e-05, "loss": 0.1962, "step": 14800 }, { "epoch": 0.7474890223590572, "grad_norm": 0.37785300612449646, "learning_rate": 1.5772527935520845e-05, "loss": 0.1949, "step": 14810 }, { "epoch": 0.7479937414828648, "grad_norm": 0.34392184019088745, "learning_rate": 1.5765332481968256e-05, "loss": 0.1913, "step": 14820 }, { "epoch": 0.7484984606066724, "grad_norm": 0.40543657541275024, "learning_rate": 1.5758132554494495e-05, "loss": 0.1979, "step": 14830 }, { "epoch": 0.74900317973048, "grad_norm": 0.41437873244285583, "learning_rate": 1.5750928158686732e-05, "loss": 0.1942, "step": 14840 }, { "epoch": 0.7495078988542876, "grad_norm": 0.3714321255683899, "learning_rate": 1.574371930013561e-05, "loss": 0.1966, "step": 14850 }, { "epoch": 0.7500126179780952, "grad_norm": 0.39029452204704285, "learning_rate": 1.573650598443523e-05, "loss": 0.1935, "step": 14860 }, { "epoch": 0.7505173371019028, "grad_norm": 0.35789355635643005, "learning_rate": 1.5729288217183153e-05, "loss": 0.1947, "step": 14870 }, { "epoch": 0.7510220562257104, "grad_norm": 0.4065491557121277, "learning_rate": 1.57220660039804e-05, "loss": 0.1889, "step": 14880 }, { "epoch": 0.751526775349518, "grad_norm": 0.40808185935020447, "learning_rate": 1.5714839350431436e-05, "loss": 0.2041, "step": 14890 }, { "epoch": 0.7520314944733256, "grad_norm": 0.33667728304862976, "learning_rate": 1.5707608262144168e-05, "loss": 0.1907, "step": 14900 }, { "epoch": 0.7525362135971332, "grad_norm": 0.38044852018356323, "learning_rate": 1.5700372744729954e-05, "loss": 0.1937, "step": 14910 }, { "epoch": 0.7530409327209407, "grad_norm": 0.39795926213264465, "learning_rate": 1.5693132803803585e-05, "loss": 0.2003, "step": 14920 }, { "epoch": 0.7535456518447484, "grad_norm": 0.387748122215271, "learning_rate": 1.5685888444983282e-05, "loss": 0.1921, "step": 14930 }, { "epoch": 0.754050370968556, "grad_norm": 0.4002469480037689, "learning_rate": 1.5678639673890698e-05, "loss": 0.1937, "step": 14940 }, { "epoch": 0.7545550900923635, "grad_norm": 0.41342753171920776, "learning_rate": 1.567138649615091e-05, "loss": 0.1944, "step": 14950 }, { "epoch": 0.7550598092161712, "grad_norm": 0.43009263277053833, "learning_rate": 1.5664128917392415e-05, "loss": 0.1964, "step": 14960 }, { "epoch": 0.7555645283399788, "grad_norm": 0.3781397342681885, "learning_rate": 1.5656866943247114e-05, "loss": 0.1943, "step": 14970 }, { "epoch": 0.7560692474637865, "grad_norm": 0.35669058561325073, "learning_rate": 1.5649600579350333e-05, "loss": 0.1947, "step": 14980 }, { "epoch": 0.756573966587594, "grad_norm": 0.3725408613681793, "learning_rate": 1.5642329831340805e-05, "loss": 0.1913, "step": 14990 }, { "epoch": 0.7570786857114016, "grad_norm": 0.37430813908576965, "learning_rate": 1.5635054704860652e-05, "loss": 0.1995, "step": 15000 }, { "epoch": 0.7575834048352093, "grad_norm": 0.37308815121650696, "learning_rate": 1.5627775205555402e-05, "loss": 0.1955, "step": 15010 }, { "epoch": 0.7580881239590168, "grad_norm": 0.41655227541923523, "learning_rate": 1.5620491339073983e-05, "loss": 0.185, "step": 15020 }, { "epoch": 0.7585928430828244, "grad_norm": 0.36986878514289856, "learning_rate": 1.5613203111068696e-05, "loss": 0.1957, "step": 15030 }, { "epoch": 0.759097562206632, "grad_norm": 0.377472460269928, "learning_rate": 1.560591052719524e-05, "loss": 0.196, "step": 15040 }, { "epoch": 0.7596022813304396, "grad_norm": 0.36597394943237305, "learning_rate": 1.559861359311269e-05, "loss": 0.1951, "step": 15050 }, { "epoch": 0.7601070004542472, "grad_norm": 0.39048123359680176, "learning_rate": 1.5591312314483493e-05, "loss": 0.1924, "step": 15060 }, { "epoch": 0.7606117195780548, "grad_norm": 0.37922659516334534, "learning_rate": 1.5584006696973473e-05, "loss": 0.1944, "step": 15070 }, { "epoch": 0.7611164387018624, "grad_norm": 0.3633812963962555, "learning_rate": 1.5576696746251817e-05, "loss": 0.1935, "step": 15080 }, { "epoch": 0.76162115782567, "grad_norm": 0.3710060119628906, "learning_rate": 1.5569382467991078e-05, "loss": 0.1908, "step": 15090 }, { "epoch": 0.7621258769494776, "grad_norm": 0.44242531061172485, "learning_rate": 1.5562063867867163e-05, "loss": 0.1992, "step": 15100 }, { "epoch": 0.7626305960732852, "grad_norm": 0.41974419355392456, "learning_rate": 1.5554740951559332e-05, "loss": 0.2017, "step": 15110 }, { "epoch": 0.7631353151970928, "grad_norm": 0.4540882110595703, "learning_rate": 1.5547413724750208e-05, "loss": 0.197, "step": 15120 }, { "epoch": 0.7636400343209004, "grad_norm": 0.4192301034927368, "learning_rate": 1.554008219312574e-05, "loss": 0.191, "step": 15130 }, { "epoch": 0.764144753444708, "grad_norm": 0.36627763509750366, "learning_rate": 1.5532746362375227e-05, "loss": 0.1924, "step": 15140 }, { "epoch": 0.7646494725685157, "grad_norm": 0.385993629693985, "learning_rate": 1.5525406238191308e-05, "loss": 0.1955, "step": 15150 }, { "epoch": 0.7651541916923232, "grad_norm": 0.41594693064689636, "learning_rate": 1.551806182626994e-05, "loss": 0.1947, "step": 15160 }, { "epoch": 0.7656589108161308, "grad_norm": 0.40872934460639954, "learning_rate": 1.5510713132310425e-05, "loss": 0.1969, "step": 15170 }, { "epoch": 0.7661636299399385, "grad_norm": 0.3702622950077057, "learning_rate": 1.5503360162015372e-05, "loss": 0.1956, "step": 15180 }, { "epoch": 0.766668349063746, "grad_norm": 0.38083615899086, "learning_rate": 1.5496002921090723e-05, "loss": 0.1943, "step": 15190 }, { "epoch": 0.7671730681875536, "grad_norm": 0.38578858971595764, "learning_rate": 1.5488641415245724e-05, "loss": 0.1942, "step": 15200 }, { "epoch": 0.7676777873113613, "grad_norm": 0.3787841796875, "learning_rate": 1.5481275650192924e-05, "loss": 0.1925, "step": 15210 }, { "epoch": 0.7681825064351688, "grad_norm": 0.3922238349914551, "learning_rate": 1.5473905631648198e-05, "loss": 0.1927, "step": 15220 }, { "epoch": 0.7686872255589764, "grad_norm": 0.424060583114624, "learning_rate": 1.5466531365330707e-05, "loss": 0.1908, "step": 15230 }, { "epoch": 0.7691919446827841, "grad_norm": 0.3820713758468628, "learning_rate": 1.5459152856962906e-05, "loss": 0.1921, "step": 15240 }, { "epoch": 0.7696966638065916, "grad_norm": 0.42253124713897705, "learning_rate": 1.5451770112270553e-05, "loss": 0.1961, "step": 15250 }, { "epoch": 0.7702013829303992, "grad_norm": 0.42598938941955566, "learning_rate": 1.5444383136982688e-05, "loss": 0.1872, "step": 15260 }, { "epoch": 0.7707061020542069, "grad_norm": 0.3898916244506836, "learning_rate": 1.543699193683163e-05, "loss": 0.1997, "step": 15270 }, { "epoch": 0.7712108211780144, "grad_norm": 0.4159732758998871, "learning_rate": 1.542959651755298e-05, "loss": 0.1955, "step": 15280 }, { "epoch": 0.771715540301822, "grad_norm": 0.38325998187065125, "learning_rate": 1.5422196884885615e-05, "loss": 0.1947, "step": 15290 }, { "epoch": 0.7722202594256297, "grad_norm": 0.38540080189704895, "learning_rate": 1.5414793044571678e-05, "loss": 0.1961, "step": 15300 }, { "epoch": 0.7727249785494372, "grad_norm": 0.4207671582698822, "learning_rate": 1.540738500235658e-05, "loss": 0.1957, "step": 15310 }, { "epoch": 0.7732296976732448, "grad_norm": 0.3838849365711212, "learning_rate": 1.5399972763988995e-05, "loss": 0.1926, "step": 15320 }, { "epoch": 0.7737344167970525, "grad_norm": 0.41926413774490356, "learning_rate": 1.539255633522084e-05, "loss": 0.1921, "step": 15330 }, { "epoch": 0.77423913592086, "grad_norm": 0.39209452271461487, "learning_rate": 1.5385135721807303e-05, "loss": 0.1978, "step": 15340 }, { "epoch": 0.7747438550446677, "grad_norm": 0.37545910477638245, "learning_rate": 1.5377710929506808e-05, "loss": 0.1919, "step": 15350 }, { "epoch": 0.7752485741684753, "grad_norm": 0.38263562321662903, "learning_rate": 1.537028196408102e-05, "loss": 0.193, "step": 15360 }, { "epoch": 0.7757532932922828, "grad_norm": 0.39452534914016724, "learning_rate": 1.536284883129485e-05, "loss": 0.1955, "step": 15370 }, { "epoch": 0.7762580124160905, "grad_norm": 0.3650442361831665, "learning_rate": 1.5355411536916437e-05, "loss": 0.1952, "step": 15380 }, { "epoch": 0.776762731539898, "grad_norm": 0.37393754720687866, "learning_rate": 1.534797008671715e-05, "loss": 0.1849, "step": 15390 }, { "epoch": 0.7772674506637056, "grad_norm": 0.39103785157203674, "learning_rate": 1.5340524486471586e-05, "loss": 0.1938, "step": 15400 }, { "epoch": 0.7777721697875133, "grad_norm": 0.42041975259780884, "learning_rate": 1.5333074741957564e-05, "loss": 0.1977, "step": 15410 }, { "epoch": 0.7782768889113209, "grad_norm": 0.3991634249687195, "learning_rate": 1.5325620858956107e-05, "loss": 0.1932, "step": 15420 }, { "epoch": 0.7787816080351284, "grad_norm": 0.40920063853263855, "learning_rate": 1.531816284325146e-05, "loss": 0.1925, "step": 15430 }, { "epoch": 0.7792863271589361, "grad_norm": 0.4144221544265747, "learning_rate": 1.5310700700631084e-05, "loss": 0.1889, "step": 15440 }, { "epoch": 0.7797910462827436, "grad_norm": 0.38696151971817017, "learning_rate": 1.5303234436885624e-05, "loss": 0.1933, "step": 15450 }, { "epoch": 0.7802957654065512, "grad_norm": 0.4012192189693451, "learning_rate": 1.5295764057808926e-05, "loss": 0.1991, "step": 15460 }, { "epoch": 0.7808004845303589, "grad_norm": 0.4123263657093048, "learning_rate": 1.5288289569198043e-05, "loss": 0.1971, "step": 15470 }, { "epoch": 0.7813052036541664, "grad_norm": 0.38358986377716064, "learning_rate": 1.52808109768532e-05, "loss": 0.195, "step": 15480 }, { "epoch": 0.781809922777974, "grad_norm": 0.4033186733722687, "learning_rate": 1.527332828657782e-05, "loss": 0.1939, "step": 15490 }, { "epoch": 0.7823146419017817, "grad_norm": 0.34229013323783875, "learning_rate": 1.52658415041785e-05, "loss": 0.1941, "step": 15500 }, { "epoch": 0.7828193610255892, "grad_norm": 0.4476543366909027, "learning_rate": 1.5258350635465016e-05, "loss": 0.1936, "step": 15510 }, { "epoch": 0.7833240801493968, "grad_norm": 0.3748190104961395, "learning_rate": 1.5250855686250305e-05, "loss": 0.1875, "step": 15520 }, { "epoch": 0.7838287992732045, "grad_norm": 0.40704455971717834, "learning_rate": 1.5243356662350481e-05, "loss": 0.1939, "step": 15530 }, { "epoch": 0.784333518397012, "grad_norm": 0.3799278140068054, "learning_rate": 1.5235853569584823e-05, "loss": 0.1917, "step": 15540 }, { "epoch": 0.7848382375208197, "grad_norm": 0.39825260639190674, "learning_rate": 1.522834641377575e-05, "loss": 0.1945, "step": 15550 }, { "epoch": 0.7853429566446273, "grad_norm": 0.3782920241355896, "learning_rate": 1.5220835200748849e-05, "loss": 0.1951, "step": 15560 }, { "epoch": 0.7858476757684348, "grad_norm": 0.4127970039844513, "learning_rate": 1.5213319936332855e-05, "loss": 0.1957, "step": 15570 }, { "epoch": 0.7863523948922425, "grad_norm": 0.4096668064594269, "learning_rate": 1.5205800626359644e-05, "loss": 0.1967, "step": 15580 }, { "epoch": 0.7868571140160501, "grad_norm": 0.39283886551856995, "learning_rate": 1.519827727666423e-05, "loss": 0.1927, "step": 15590 }, { "epoch": 0.7873618331398576, "grad_norm": 0.40781739354133606, "learning_rate": 1.5190749893084756e-05, "loss": 0.1976, "step": 15600 }, { "epoch": 0.7878665522636653, "grad_norm": 0.4018222689628601, "learning_rate": 1.5183218481462509e-05, "loss": 0.1983, "step": 15610 }, { "epoch": 0.7883712713874729, "grad_norm": 0.3770211637020111, "learning_rate": 1.517568304764189e-05, "loss": 0.1906, "step": 15620 }, { "epoch": 0.7888759905112804, "grad_norm": 0.4039522111415863, "learning_rate": 1.5168143597470431e-05, "loss": 0.1938, "step": 15630 }, { "epoch": 0.7893807096350881, "grad_norm": 0.3727228343486786, "learning_rate": 1.516060013679877e-05, "loss": 0.1856, "step": 15640 }, { "epoch": 0.7898854287588957, "grad_norm": 0.4120556712150574, "learning_rate": 1.515305267148067e-05, "loss": 0.1977, "step": 15650 }, { "epoch": 0.7903901478827032, "grad_norm": 0.38890233635902405, "learning_rate": 1.5145501207372988e-05, "loss": 0.1927, "step": 15660 }, { "epoch": 0.7908948670065109, "grad_norm": 0.4304879903793335, "learning_rate": 1.5137945750335692e-05, "loss": 0.1834, "step": 15670 }, { "epoch": 0.7913995861303185, "grad_norm": 0.3894989490509033, "learning_rate": 1.5130386306231848e-05, "loss": 0.1919, "step": 15680 }, { "epoch": 0.791904305254126, "grad_norm": 0.4087143838405609, "learning_rate": 1.5122822880927615e-05, "loss": 0.1943, "step": 15690 }, { "epoch": 0.7924090243779337, "grad_norm": 0.3838612735271454, "learning_rate": 1.511525548029224e-05, "loss": 0.1939, "step": 15700 }, { "epoch": 0.7929137435017413, "grad_norm": 0.4017123281955719, "learning_rate": 1.510768411019806e-05, "loss": 0.1929, "step": 15710 }, { "epoch": 0.7934184626255489, "grad_norm": 0.40181493759155273, "learning_rate": 1.5100108776520483e-05, "loss": 0.1917, "step": 15720 }, { "epoch": 0.7939231817493565, "grad_norm": 0.40359485149383545, "learning_rate": 1.5092529485138001e-05, "loss": 0.188, "step": 15730 }, { "epoch": 0.7944279008731641, "grad_norm": 0.3589044511318207, "learning_rate": 1.5084946241932177e-05, "loss": 0.194, "step": 15740 }, { "epoch": 0.7949326199969717, "grad_norm": 0.3784099221229553, "learning_rate": 1.5077359052787637e-05, "loss": 0.196, "step": 15750 }, { "epoch": 0.7954373391207793, "grad_norm": 0.3944705128669739, "learning_rate": 1.5069767923592067e-05, "loss": 0.1955, "step": 15760 }, { "epoch": 0.7959420582445869, "grad_norm": 0.38500866293907166, "learning_rate": 1.5062172860236217e-05, "loss": 0.191, "step": 15770 }, { "epoch": 0.7964467773683945, "grad_norm": 0.3527895510196686, "learning_rate": 1.5054573868613886e-05, "loss": 0.1866, "step": 15780 }, { "epoch": 0.7969514964922021, "grad_norm": 0.3712119162082672, "learning_rate": 1.5046970954621922e-05, "loss": 0.1943, "step": 15790 }, { "epoch": 0.7974562156160097, "grad_norm": 0.391443133354187, "learning_rate": 1.5039364124160219e-05, "loss": 0.1966, "step": 15800 }, { "epoch": 0.7979609347398173, "grad_norm": 0.37361204624176025, "learning_rate": 1.5031753383131702e-05, "loss": 0.1911, "step": 15810 }, { "epoch": 0.7984656538636249, "grad_norm": 0.38801950216293335, "learning_rate": 1.5024138737442342e-05, "loss": 0.1914, "step": 15820 }, { "epoch": 0.7989703729874325, "grad_norm": 0.368264377117157, "learning_rate": 1.5016520193001132e-05, "loss": 0.1947, "step": 15830 }, { "epoch": 0.7994750921112401, "grad_norm": 0.39262187480926514, "learning_rate": 1.5008897755720093e-05, "loss": 0.1883, "step": 15840 }, { "epoch": 0.7999798112350477, "grad_norm": 0.39258620142936707, "learning_rate": 1.5001271431514273e-05, "loss": 0.1905, "step": 15850 }, { "epoch": 0.8004845303588553, "grad_norm": 0.38568031787872314, "learning_rate": 1.4993641226301723e-05, "loss": 0.1906, "step": 15860 }, { "epoch": 0.8009892494826629, "grad_norm": 0.371940940618515, "learning_rate": 1.4986007146003512e-05, "loss": 0.1985, "step": 15870 }, { "epoch": 0.8014939686064705, "grad_norm": 0.3820493817329407, "learning_rate": 1.4978369196543723e-05, "loss": 0.1909, "step": 15880 }, { "epoch": 0.801998687730278, "grad_norm": 0.39306890964508057, "learning_rate": 1.4970727383849432e-05, "loss": 0.1925, "step": 15890 }, { "epoch": 0.8025034068540857, "grad_norm": 0.39481768012046814, "learning_rate": 1.4963081713850718e-05, "loss": 0.1924, "step": 15900 }, { "epoch": 0.8030081259778933, "grad_norm": 0.40292060375213623, "learning_rate": 1.4955432192480648e-05, "loss": 0.192, "step": 15910 }, { "epoch": 0.803512845101701, "grad_norm": 0.3812130391597748, "learning_rate": 1.4947778825675285e-05, "loss": 0.1894, "step": 15920 }, { "epoch": 0.8040175642255085, "grad_norm": 0.3960418999195099, "learning_rate": 1.4940121619373673e-05, "loss": 0.1979, "step": 15930 }, { "epoch": 0.8045222833493161, "grad_norm": 0.40701818466186523, "learning_rate": 1.4932460579517834e-05, "loss": 0.1959, "step": 15940 }, { "epoch": 0.8050270024731238, "grad_norm": 0.36681878566741943, "learning_rate": 1.4924795712052761e-05, "loss": 0.189, "step": 15950 }, { "epoch": 0.8055317215969313, "grad_norm": 0.37501126527786255, "learning_rate": 1.491712702292643e-05, "loss": 0.1906, "step": 15960 }, { "epoch": 0.8060364407207389, "grad_norm": 0.39296025037765503, "learning_rate": 1.4909454518089768e-05, "loss": 0.1956, "step": 15970 }, { "epoch": 0.8065411598445466, "grad_norm": 0.414867639541626, "learning_rate": 1.4901778203496672e-05, "loss": 0.1912, "step": 15980 }, { "epoch": 0.8070458789683541, "grad_norm": 0.3814179003238678, "learning_rate": 1.4894098085103994e-05, "loss": 0.1897, "step": 15990 }, { "epoch": 0.8075505980921617, "grad_norm": 0.3593956232070923, "learning_rate": 1.4886414168871534e-05, "loss": 0.1857, "step": 16000 }, { "epoch": 0.8080553172159693, "grad_norm": 0.35973814129829407, "learning_rate": 1.4878726460762045e-05, "loss": 0.198, "step": 16010 }, { "epoch": 0.8085600363397769, "grad_norm": 0.415672242641449, "learning_rate": 1.4871034966741219e-05, "loss": 0.1954, "step": 16020 }, { "epoch": 0.8090647554635845, "grad_norm": 0.4354953169822693, "learning_rate": 1.4863339692777686e-05, "loss": 0.1969, "step": 16030 }, { "epoch": 0.8095694745873921, "grad_norm": 0.433259516954422, "learning_rate": 1.4855640644843006e-05, "loss": 0.1951, "step": 16040 }, { "epoch": 0.8100741937111997, "grad_norm": 0.40496930480003357, "learning_rate": 1.4847937828911674e-05, "loss": 0.1925, "step": 16050 }, { "epoch": 0.8105789128350073, "grad_norm": 0.4062017798423767, "learning_rate": 1.4840231250961106e-05, "loss": 0.1908, "step": 16060 }, { "epoch": 0.8110836319588149, "grad_norm": 0.3842165768146515, "learning_rate": 1.483252091697164e-05, "loss": 0.1947, "step": 16070 }, { "epoch": 0.8115883510826225, "grad_norm": 0.37029555439949036, "learning_rate": 1.4824806832926522e-05, "loss": 0.1927, "step": 16080 }, { "epoch": 0.8120930702064301, "grad_norm": 0.43411532044410706, "learning_rate": 1.4817089004811914e-05, "loss": 0.1964, "step": 16090 }, { "epoch": 0.8125977893302377, "grad_norm": 0.41371169686317444, "learning_rate": 1.4809367438616881e-05, "loss": 0.1915, "step": 16100 }, { "epoch": 0.8131025084540453, "grad_norm": 0.3820192515850067, "learning_rate": 1.480164214033339e-05, "loss": 0.1985, "step": 16110 }, { "epoch": 0.813607227577853, "grad_norm": 0.38863855600357056, "learning_rate": 1.4793913115956305e-05, "loss": 0.191, "step": 16120 }, { "epoch": 0.8141119467016605, "grad_norm": 0.38157379627227783, "learning_rate": 1.4786180371483376e-05, "loss": 0.1857, "step": 16130 }, { "epoch": 0.8146166658254681, "grad_norm": 0.4020270109176636, "learning_rate": 1.4778443912915248e-05, "loss": 0.1908, "step": 16140 }, { "epoch": 0.8151213849492758, "grad_norm": 0.36504533886909485, "learning_rate": 1.477070374625544e-05, "loss": 0.1927, "step": 16150 }, { "epoch": 0.8156261040730833, "grad_norm": 0.39276713132858276, "learning_rate": 1.4762959877510357e-05, "loss": 0.1896, "step": 16160 }, { "epoch": 0.8161308231968909, "grad_norm": 0.3847932815551758, "learning_rate": 1.4755212312689268e-05, "loss": 0.1925, "step": 16170 }, { "epoch": 0.8166355423206986, "grad_norm": 0.3965621888637543, "learning_rate": 1.4747461057804317e-05, "loss": 0.1923, "step": 16180 }, { "epoch": 0.8171402614445061, "grad_norm": 0.39766907691955566, "learning_rate": 1.4739706118870507e-05, "loss": 0.1894, "step": 16190 }, { "epoch": 0.8176449805683137, "grad_norm": 0.36879870295524597, "learning_rate": 1.4731947501905706e-05, "loss": 0.1953, "step": 16200 }, { "epoch": 0.8181496996921214, "grad_norm": 0.399262398481369, "learning_rate": 1.4724185212930626e-05, "loss": 0.1853, "step": 16210 }, { "epoch": 0.8186544188159289, "grad_norm": 0.40935614705085754, "learning_rate": 1.4716419257968836e-05, "loss": 0.1923, "step": 16220 }, { "epoch": 0.8191591379397365, "grad_norm": 0.4023060202598572, "learning_rate": 1.4708649643046754e-05, "loss": 0.191, "step": 16230 }, { "epoch": 0.8196638570635442, "grad_norm": 0.36848917603492737, "learning_rate": 1.4700876374193626e-05, "loss": 0.1915, "step": 16240 }, { "epoch": 0.8201685761873517, "grad_norm": 0.3725740909576416, "learning_rate": 1.4693099457441541e-05, "loss": 0.1956, "step": 16250 }, { "epoch": 0.8206732953111593, "grad_norm": 0.3830386996269226, "learning_rate": 1.468531889882542e-05, "loss": 0.1936, "step": 16260 }, { "epoch": 0.821178014434967, "grad_norm": 0.4144558012485504, "learning_rate": 1.4677534704383005e-05, "loss": 0.1932, "step": 16270 }, { "epoch": 0.8216827335587745, "grad_norm": 0.4025906026363373, "learning_rate": 1.4669746880154863e-05, "loss": 0.1905, "step": 16280 }, { "epoch": 0.8221874526825822, "grad_norm": 0.39150309562683105, "learning_rate": 1.4661955432184378e-05, "loss": 0.1885, "step": 16290 }, { "epoch": 0.8226921718063898, "grad_norm": 0.40166589617729187, "learning_rate": 1.4654160366517744e-05, "loss": 0.1929, "step": 16300 }, { "epoch": 0.8231968909301973, "grad_norm": 0.38435694575309753, "learning_rate": 1.4646361689203966e-05, "loss": 0.191, "step": 16310 }, { "epoch": 0.823701610054005, "grad_norm": 0.4280558228492737, "learning_rate": 1.4638559406294844e-05, "loss": 0.1926, "step": 16320 }, { "epoch": 0.8242063291778126, "grad_norm": 0.3964633345603943, "learning_rate": 1.4630753523844982e-05, "loss": 0.1941, "step": 16330 }, { "epoch": 0.8247110483016201, "grad_norm": 0.3798883557319641, "learning_rate": 1.462294404791178e-05, "loss": 0.1882, "step": 16340 }, { "epoch": 0.8252157674254278, "grad_norm": 0.38364654779434204, "learning_rate": 1.461513098455542e-05, "loss": 0.1892, "step": 16350 }, { "epoch": 0.8257204865492354, "grad_norm": 0.41219595074653625, "learning_rate": 1.460731433983887e-05, "loss": 0.1944, "step": 16360 }, { "epoch": 0.8262252056730429, "grad_norm": 0.3887147605419159, "learning_rate": 1.4599494119827876e-05, "loss": 0.1863, "step": 16370 }, { "epoch": 0.8267299247968506, "grad_norm": 0.39501288533210754, "learning_rate": 1.4591670330590968e-05, "loss": 0.191, "step": 16380 }, { "epoch": 0.8272346439206582, "grad_norm": 0.3871220052242279, "learning_rate": 1.4583842978199429e-05, "loss": 0.1886, "step": 16390 }, { "epoch": 0.8277393630444657, "grad_norm": 0.3810713589191437, "learning_rate": 1.4576012068727318e-05, "loss": 0.1948, "step": 16400 }, { "epoch": 0.8282440821682734, "grad_norm": 0.37908855080604553, "learning_rate": 1.4568177608251457e-05, "loss": 0.1868, "step": 16410 }, { "epoch": 0.828748801292081, "grad_norm": 0.39710408449172974, "learning_rate": 1.4560339602851414e-05, "loss": 0.1932, "step": 16420 }, { "epoch": 0.8292535204158885, "grad_norm": 0.4028872847557068, "learning_rate": 1.4552498058609516e-05, "loss": 0.1889, "step": 16430 }, { "epoch": 0.8297582395396962, "grad_norm": 0.3509352505207062, "learning_rate": 1.4544652981610828e-05, "loss": 0.1937, "step": 16440 }, { "epoch": 0.8302629586635037, "grad_norm": 0.38003891706466675, "learning_rate": 1.4536804377943166e-05, "loss": 0.1935, "step": 16450 }, { "epoch": 0.8307676777873113, "grad_norm": 0.4138204753398895, "learning_rate": 1.4528952253697076e-05, "loss": 0.1893, "step": 16460 }, { "epoch": 0.831272396911119, "grad_norm": 0.37607863545417786, "learning_rate": 1.4521096614965836e-05, "loss": 0.1921, "step": 16470 }, { "epoch": 0.8317771160349265, "grad_norm": 0.4239766299724579, "learning_rate": 1.451323746784546e-05, "loss": 0.1951, "step": 16480 }, { "epoch": 0.8322818351587342, "grad_norm": 0.36984628438949585, "learning_rate": 1.450537481843467e-05, "loss": 0.1907, "step": 16490 }, { "epoch": 0.8327865542825418, "grad_norm": 0.41318270564079285, "learning_rate": 1.4497508672834918e-05, "loss": 0.1945, "step": 16500 }, { "epoch": 0.8332912734063493, "grad_norm": 0.42964252829551697, "learning_rate": 1.4489639037150363e-05, "loss": 0.1939, "step": 16510 }, { "epoch": 0.833795992530157, "grad_norm": 0.3866402804851532, "learning_rate": 1.4481765917487874e-05, "loss": 0.1904, "step": 16520 }, { "epoch": 0.8343007116539646, "grad_norm": 0.38516736030578613, "learning_rate": 1.4473889319957021e-05, "loss": 0.193, "step": 16530 }, { "epoch": 0.8348054307777721, "grad_norm": 0.4148748815059662, "learning_rate": 1.4466009250670081e-05, "loss": 0.1976, "step": 16540 }, { "epoch": 0.8353101499015798, "grad_norm": 0.3660944104194641, "learning_rate": 1.4458125715742015e-05, "loss": 0.1902, "step": 16550 }, { "epoch": 0.8358148690253874, "grad_norm": 0.4343584477901459, "learning_rate": 1.4450238721290481e-05, "loss": 0.1936, "step": 16560 }, { "epoch": 0.8363195881491949, "grad_norm": 0.435059130191803, "learning_rate": 1.4442348273435815e-05, "loss": 0.1868, "step": 16570 }, { "epoch": 0.8368243072730026, "grad_norm": 0.41719505190849304, "learning_rate": 1.443445437830104e-05, "loss": 0.1922, "step": 16580 }, { "epoch": 0.8373290263968102, "grad_norm": 0.4455874264240265, "learning_rate": 1.4426557042011849e-05, "loss": 0.1933, "step": 16590 }, { "epoch": 0.8378337455206177, "grad_norm": 0.38722264766693115, "learning_rate": 1.4418656270696603e-05, "loss": 0.194, "step": 16600 }, { "epoch": 0.8383384646444254, "grad_norm": 0.4294879734516144, "learning_rate": 1.4410752070486336e-05, "loss": 0.1907, "step": 16610 }, { "epoch": 0.838843183768233, "grad_norm": 0.4019503593444824, "learning_rate": 1.4402844447514739e-05, "loss": 0.193, "step": 16620 }, { "epoch": 0.8393479028920405, "grad_norm": 0.3896719813346863, "learning_rate": 1.4394933407918157e-05, "loss": 0.1957, "step": 16630 }, { "epoch": 0.8398526220158482, "grad_norm": 0.37571385502815247, "learning_rate": 1.4387018957835591e-05, "loss": 0.1896, "step": 16640 }, { "epoch": 0.8403573411396558, "grad_norm": 0.45478227734565735, "learning_rate": 1.4379101103408686e-05, "loss": 0.1921, "step": 16650 }, { "epoch": 0.8408620602634633, "grad_norm": 0.3812844455242157, "learning_rate": 1.4371179850781727e-05, "loss": 0.1959, "step": 16660 }, { "epoch": 0.841366779387271, "grad_norm": 0.36685624718666077, "learning_rate": 1.4363255206101638e-05, "loss": 0.1923, "step": 16670 }, { "epoch": 0.8418714985110786, "grad_norm": 0.37472155690193176, "learning_rate": 1.4355327175517976e-05, "loss": 0.188, "step": 16680 }, { "epoch": 0.8423762176348862, "grad_norm": 0.4065108895301819, "learning_rate": 1.4347395765182928e-05, "loss": 0.1881, "step": 16690 }, { "epoch": 0.8428809367586938, "grad_norm": 0.3829512596130371, "learning_rate": 1.4339460981251294e-05, "loss": 0.192, "step": 16700 }, { "epoch": 0.8433856558825014, "grad_norm": 0.3810509741306305, "learning_rate": 1.43315228298805e-05, "loss": 0.1935, "step": 16710 }, { "epoch": 0.843890375006309, "grad_norm": 0.4485250413417816, "learning_rate": 1.4323581317230589e-05, "loss": 0.1916, "step": 16720 }, { "epoch": 0.8443950941301166, "grad_norm": 0.40549904108047485, "learning_rate": 1.4315636449464197e-05, "loss": 0.1864, "step": 16730 }, { "epoch": 0.8448998132539242, "grad_norm": 0.3687335252761841, "learning_rate": 1.4307688232746582e-05, "loss": 0.1904, "step": 16740 }, { "epoch": 0.8454045323777318, "grad_norm": 0.3896748721599579, "learning_rate": 1.4299736673245586e-05, "loss": 0.1869, "step": 16750 }, { "epoch": 0.8459092515015394, "grad_norm": 0.3967144191265106, "learning_rate": 1.4291781777131654e-05, "loss": 0.19, "step": 16760 }, { "epoch": 0.846413970625347, "grad_norm": 0.35696497559547424, "learning_rate": 1.4283823550577818e-05, "loss": 0.1965, "step": 16770 }, { "epoch": 0.8469186897491546, "grad_norm": 0.3806256353855133, "learning_rate": 1.4275861999759694e-05, "loss": 0.19, "step": 16780 }, { "epoch": 0.8474234088729622, "grad_norm": 0.388893723487854, "learning_rate": 1.4267897130855475e-05, "loss": 0.1926, "step": 16790 }, { "epoch": 0.8479281279967698, "grad_norm": 0.38331449031829834, "learning_rate": 1.4259928950045932e-05, "loss": 0.191, "step": 16800 }, { "epoch": 0.8484328471205774, "grad_norm": 0.40327396988868713, "learning_rate": 1.4251957463514405e-05, "loss": 0.1918, "step": 16810 }, { "epoch": 0.848937566244385, "grad_norm": 0.4201100766658783, "learning_rate": 1.4243982677446804e-05, "loss": 0.1892, "step": 16820 }, { "epoch": 0.8494422853681926, "grad_norm": 0.4181337058544159, "learning_rate": 1.423600459803159e-05, "loss": 0.1944, "step": 16830 }, { "epoch": 0.8499470044920002, "grad_norm": 0.39224597811698914, "learning_rate": 1.4228023231459784e-05, "loss": 0.1883, "step": 16840 }, { "epoch": 0.8504517236158078, "grad_norm": 0.3824494481086731, "learning_rate": 1.422003858392496e-05, "loss": 0.1932, "step": 16850 }, { "epoch": 0.8509564427396153, "grad_norm": 0.3966641128063202, "learning_rate": 1.4212050661623243e-05, "loss": 0.1956, "step": 16860 }, { "epoch": 0.851461161863423, "grad_norm": 0.3945818841457367, "learning_rate": 1.4204059470753281e-05, "loss": 0.1936, "step": 16870 }, { "epoch": 0.8519658809872306, "grad_norm": 0.3976287841796875, "learning_rate": 1.419606501751628e-05, "loss": 0.196, "step": 16880 }, { "epoch": 0.8524706001110383, "grad_norm": 0.4014606773853302, "learning_rate": 1.418806730811596e-05, "loss": 0.1843, "step": 16890 }, { "epoch": 0.8529753192348458, "grad_norm": 0.37068551778793335, "learning_rate": 1.4180066348758586e-05, "loss": 0.1892, "step": 16900 }, { "epoch": 0.8534800383586534, "grad_norm": 0.3733011782169342, "learning_rate": 1.4172062145652925e-05, "loss": 0.1903, "step": 16910 }, { "epoch": 0.853984757482461, "grad_norm": 0.3944968581199646, "learning_rate": 1.4164054705010274e-05, "loss": 0.1923, "step": 16920 }, { "epoch": 0.8544894766062686, "grad_norm": 0.379734605550766, "learning_rate": 1.4156044033044437e-05, "loss": 0.1876, "step": 16930 }, { "epoch": 0.8549941957300762, "grad_norm": 0.42211759090423584, "learning_rate": 1.4148030135971734e-05, "loss": 0.1938, "step": 16940 }, { "epoch": 0.8554989148538839, "grad_norm": 0.5016130805015564, "learning_rate": 1.4140013020010975e-05, "loss": 0.1843, "step": 16950 }, { "epoch": 0.8560036339776914, "grad_norm": 0.3654851019382477, "learning_rate": 1.4131992691383478e-05, "loss": 0.1889, "step": 16960 }, { "epoch": 0.856508353101499, "grad_norm": 0.4221227467060089, "learning_rate": 1.4123969156313048e-05, "loss": 0.1904, "step": 16970 }, { "epoch": 0.8570130722253066, "grad_norm": 0.42534932494163513, "learning_rate": 1.4115942421025981e-05, "loss": 0.1917, "step": 16980 }, { "epoch": 0.8575177913491142, "grad_norm": 0.390306681394577, "learning_rate": 1.4107912491751055e-05, "loss": 0.1931, "step": 16990 }, { "epoch": 0.8580225104729218, "grad_norm": 0.3896608352661133, "learning_rate": 1.409987937471953e-05, "loss": 0.191, "step": 17000 }, { "epoch": 0.8585272295967294, "grad_norm": 0.37777718901634216, "learning_rate": 1.4091843076165135e-05, "loss": 0.1895, "step": 17010 }, { "epoch": 0.859031948720537, "grad_norm": 0.3948253095149994, "learning_rate": 1.4083803602324069e-05, "loss": 0.1927, "step": 17020 }, { "epoch": 0.8595366678443446, "grad_norm": 0.4186212420463562, "learning_rate": 1.4075760959434996e-05, "loss": 0.1871, "step": 17030 }, { "epoch": 0.8600413869681522, "grad_norm": 0.3716995418071747, "learning_rate": 1.4067715153739045e-05, "loss": 0.1888, "step": 17040 }, { "epoch": 0.8605461060919598, "grad_norm": 0.36383745074272156, "learning_rate": 1.4059666191479788e-05, "loss": 0.1984, "step": 17050 }, { "epoch": 0.8610508252157675, "grad_norm": 0.3937947452068329, "learning_rate": 1.4051614078903253e-05, "loss": 0.1926, "step": 17060 }, { "epoch": 0.861555544339575, "grad_norm": 0.37095919251441956, "learning_rate": 1.4043558822257912e-05, "loss": 0.1914, "step": 17070 }, { "epoch": 0.8620602634633826, "grad_norm": 0.3826018273830414, "learning_rate": 1.4035500427794674e-05, "loss": 0.1909, "step": 17080 }, { "epoch": 0.8625649825871903, "grad_norm": 0.43617457151412964, "learning_rate": 1.4027438901766893e-05, "loss": 0.1926, "step": 17090 }, { "epoch": 0.8630697017109978, "grad_norm": 0.3956442177295685, "learning_rate": 1.4019374250430335e-05, "loss": 0.1917, "step": 17100 }, { "epoch": 0.8635744208348054, "grad_norm": 0.4241875112056732, "learning_rate": 1.4011306480043211e-05, "loss": 0.191, "step": 17110 }, { "epoch": 0.8640791399586131, "grad_norm": 0.39926716685295105, "learning_rate": 1.4003235596866138e-05, "loss": 0.1872, "step": 17120 }, { "epoch": 0.8645838590824206, "grad_norm": 0.3971102237701416, "learning_rate": 1.3995161607162156e-05, "loss": 0.1894, "step": 17130 }, { "epoch": 0.8650885782062282, "grad_norm": 0.3578397035598755, "learning_rate": 1.3987084517196713e-05, "loss": 0.1931, "step": 17140 }, { "epoch": 0.8655932973300359, "grad_norm": 0.39606139063835144, "learning_rate": 1.3979004333237663e-05, "loss": 0.1928, "step": 17150 }, { "epoch": 0.8660980164538434, "grad_norm": 0.39284926652908325, "learning_rate": 1.3970921061555261e-05, "loss": 0.194, "step": 17160 }, { "epoch": 0.866602735577651, "grad_norm": 0.38631924986839294, "learning_rate": 1.396283470842216e-05, "loss": 0.1901, "step": 17170 }, { "epoch": 0.8671074547014587, "grad_norm": 0.39773911237716675, "learning_rate": 1.39547452801134e-05, "loss": 0.1929, "step": 17180 }, { "epoch": 0.8676121738252662, "grad_norm": 0.40026170015335083, "learning_rate": 1.394665278290641e-05, "loss": 0.1882, "step": 17190 }, { "epoch": 0.8681168929490738, "grad_norm": 0.38955339789390564, "learning_rate": 1.3938557223081002e-05, "loss": 0.1834, "step": 17200 }, { "epoch": 0.8686216120728815, "grad_norm": 0.4223397672176361, "learning_rate": 1.3930458606919364e-05, "loss": 0.1962, "step": 17210 }, { "epoch": 0.869126331196689, "grad_norm": 0.3966808617115021, "learning_rate": 1.3922356940706054e-05, "loss": 0.1933, "step": 17220 }, { "epoch": 0.8696310503204966, "grad_norm": 0.35512545704841614, "learning_rate": 1.3914252230727994e-05, "loss": 0.1848, "step": 17230 }, { "epoch": 0.8701357694443043, "grad_norm": 0.401493638753891, "learning_rate": 1.3906144483274473e-05, "loss": 0.1869, "step": 17240 }, { "epoch": 0.8706404885681118, "grad_norm": 0.4126547873020172, "learning_rate": 1.3898033704637139e-05, "loss": 0.19, "step": 17250 }, { "epoch": 0.8711452076919195, "grad_norm": 0.37719863653182983, "learning_rate": 1.3889919901109985e-05, "loss": 0.1892, "step": 17260 }, { "epoch": 0.8716499268157271, "grad_norm": 0.3759639263153076, "learning_rate": 1.388180307898936e-05, "loss": 0.1862, "step": 17270 }, { "epoch": 0.8721546459395346, "grad_norm": 0.40240710973739624, "learning_rate": 1.3873683244573946e-05, "loss": 0.1878, "step": 17280 }, { "epoch": 0.8726593650633423, "grad_norm": 0.42486846446990967, "learning_rate": 1.3865560404164766e-05, "loss": 0.1874, "step": 17290 }, { "epoch": 0.8731640841871499, "grad_norm": 0.38658639788627625, "learning_rate": 1.3857434564065178e-05, "loss": 0.1887, "step": 17300 }, { "epoch": 0.8736688033109574, "grad_norm": 0.3735341429710388, "learning_rate": 1.384930573058087e-05, "loss": 0.1912, "step": 17310 }, { "epoch": 0.8741735224347651, "grad_norm": 0.39644214510917664, "learning_rate": 1.3841173910019849e-05, "loss": 0.1883, "step": 17320 }, { "epoch": 0.8746782415585727, "grad_norm": 0.39270687103271484, "learning_rate": 1.3833039108692438e-05, "loss": 0.1846, "step": 17330 }, { "epoch": 0.8751829606823802, "grad_norm": 0.3906450569629669, "learning_rate": 1.3824901332911273e-05, "loss": 0.1909, "step": 17340 }, { "epoch": 0.8756876798061879, "grad_norm": 0.4019029438495636, "learning_rate": 1.3816760588991307e-05, "loss": 0.1863, "step": 17350 }, { "epoch": 0.8761923989299955, "grad_norm": 0.3638235032558441, "learning_rate": 1.3808616883249788e-05, "loss": 0.1869, "step": 17360 }, { "epoch": 0.876697118053803, "grad_norm": 0.4051116406917572, "learning_rate": 1.3800470222006259e-05, "loss": 0.1859, "step": 17370 }, { "epoch": 0.8772018371776107, "grad_norm": 0.3601747751235962, "learning_rate": 1.379232061158257e-05, "loss": 0.1835, "step": 17380 }, { "epoch": 0.8777065563014183, "grad_norm": 0.3887779116630554, "learning_rate": 1.3784168058302845e-05, "loss": 0.1884, "step": 17390 }, { "epoch": 0.8782112754252258, "grad_norm": 0.4080141484737396, "learning_rate": 1.3776012568493502e-05, "loss": 0.1934, "step": 17400 }, { "epoch": 0.8787159945490335, "grad_norm": 0.4419008493423462, "learning_rate": 1.376785414848323e-05, "loss": 0.1888, "step": 17410 }, { "epoch": 0.879220713672841, "grad_norm": 0.3907400965690613, "learning_rate": 1.3759692804603001e-05, "loss": 0.1849, "step": 17420 }, { "epoch": 0.8797254327966486, "grad_norm": 0.3940833806991577, "learning_rate": 1.3751528543186048e-05, "loss": 0.1892, "step": 17430 }, { "epoch": 0.8802301519204563, "grad_norm": 0.45420166850090027, "learning_rate": 1.374336137056787e-05, "loss": 0.1887, "step": 17440 }, { "epoch": 0.8807348710442638, "grad_norm": 0.3886755704879761, "learning_rate": 1.3735191293086224e-05, "loss": 0.1927, "step": 17450 }, { "epoch": 0.8812395901680715, "grad_norm": 0.39444541931152344, "learning_rate": 1.3727018317081129e-05, "loss": 0.1893, "step": 17460 }, { "epoch": 0.8817443092918791, "grad_norm": 0.3883327841758728, "learning_rate": 1.371884244889484e-05, "loss": 0.183, "step": 17470 }, { "epoch": 0.8822490284156866, "grad_norm": 0.3823162913322449, "learning_rate": 1.3710663694871867e-05, "loss": 0.187, "step": 17480 }, { "epoch": 0.8827537475394943, "grad_norm": 0.39884987473487854, "learning_rate": 1.3702482061358962e-05, "loss": 0.1862, "step": 17490 }, { "epoch": 0.8832584666633019, "grad_norm": 0.3719819486141205, "learning_rate": 1.3694297554705095e-05, "loss": 0.1882, "step": 17500 }, { "epoch": 0.8837631857871094, "grad_norm": 0.4320856034755707, "learning_rate": 1.3686110181261478e-05, "loss": 0.1944, "step": 17510 }, { "epoch": 0.8842679049109171, "grad_norm": 0.4061492383480072, "learning_rate": 1.367791994738155e-05, "loss": 0.1892, "step": 17520 }, { "epoch": 0.8847726240347247, "grad_norm": 0.38453060388565063, "learning_rate": 1.3669726859420967e-05, "loss": 0.1886, "step": 17530 }, { "epoch": 0.8852773431585322, "grad_norm": 0.3693595826625824, "learning_rate": 1.3661530923737591e-05, "loss": 0.1855, "step": 17540 }, { "epoch": 0.8857820622823399, "grad_norm": 0.4047423303127289, "learning_rate": 1.3653332146691505e-05, "loss": 0.1841, "step": 17550 }, { "epoch": 0.8862867814061475, "grad_norm": 0.3869906961917877, "learning_rate": 1.3645130534644995e-05, "loss": 0.1884, "step": 17560 }, { "epoch": 0.886791500529955, "grad_norm": 0.49165910482406616, "learning_rate": 1.3636926093962541e-05, "loss": 0.1849, "step": 17570 }, { "epoch": 0.8872962196537627, "grad_norm": 0.3990466594696045, "learning_rate": 1.3628718831010826e-05, "loss": 0.1881, "step": 17580 }, { "epoch": 0.8878009387775703, "grad_norm": 0.38278889656066895, "learning_rate": 1.3620508752158714e-05, "loss": 0.1893, "step": 17590 }, { "epoch": 0.8883056579013778, "grad_norm": 0.3712950348854065, "learning_rate": 1.3612295863777264e-05, "loss": 0.1859, "step": 17600 }, { "epoch": 0.8888103770251855, "grad_norm": 0.3666357696056366, "learning_rate": 1.3604080172239704e-05, "loss": 0.1886, "step": 17610 }, { "epoch": 0.8893150961489931, "grad_norm": 0.3947659432888031, "learning_rate": 1.3595861683921454e-05, "loss": 0.1924, "step": 17620 }, { "epoch": 0.8898198152728007, "grad_norm": 0.39866843819618225, "learning_rate": 1.3587640405200084e-05, "loss": 0.1924, "step": 17630 }, { "epoch": 0.8903245343966083, "grad_norm": 0.39450138807296753, "learning_rate": 1.3579416342455342e-05, "loss": 0.1915, "step": 17640 }, { "epoch": 0.8908292535204159, "grad_norm": 0.41644126176834106, "learning_rate": 1.3571189502069138e-05, "loss": 0.1884, "step": 17650 }, { "epoch": 0.8913339726442235, "grad_norm": 0.4018542766571045, "learning_rate": 1.3562959890425529e-05, "loss": 0.1888, "step": 17660 }, { "epoch": 0.8918386917680311, "grad_norm": 0.37818506360054016, "learning_rate": 1.3554727513910728e-05, "loss": 0.1939, "step": 17670 }, { "epoch": 0.8923434108918387, "grad_norm": 0.3896495997905731, "learning_rate": 1.3546492378913092e-05, "loss": 0.1936, "step": 17680 }, { "epoch": 0.8928481300156463, "grad_norm": 0.41057732701301575, "learning_rate": 1.3538254491823118e-05, "loss": 0.1949, "step": 17690 }, { "epoch": 0.8933528491394539, "grad_norm": 0.4044891893863678, "learning_rate": 1.3530013859033442e-05, "loss": 0.1921, "step": 17700 }, { "epoch": 0.8938575682632615, "grad_norm": 0.37531018257141113, "learning_rate": 1.3521770486938826e-05, "loss": 0.1864, "step": 17710 }, { "epoch": 0.8943622873870691, "grad_norm": 0.34309306740760803, "learning_rate": 1.3513524381936159e-05, "loss": 0.1867, "step": 17720 }, { "epoch": 0.8948670065108767, "grad_norm": 0.3826574385166168, "learning_rate": 1.3505275550424455e-05, "loss": 0.186, "step": 17730 }, { "epoch": 0.8953717256346843, "grad_norm": 0.4171966016292572, "learning_rate": 1.3497023998804837e-05, "loss": 0.1866, "step": 17740 }, { "epoch": 0.8958764447584919, "grad_norm": 0.3703576922416687, "learning_rate": 1.3488769733480544e-05, "loss": 0.1866, "step": 17750 }, { "epoch": 0.8963811638822995, "grad_norm": 0.3967248201370239, "learning_rate": 1.3480512760856918e-05, "loss": 0.1891, "step": 17760 }, { "epoch": 0.896885883006107, "grad_norm": 0.4023715853691101, "learning_rate": 1.3472253087341405e-05, "loss": 0.1929, "step": 17770 }, { "epoch": 0.8973906021299147, "grad_norm": 0.4654636085033417, "learning_rate": 1.3463990719343543e-05, "loss": 0.1919, "step": 17780 }, { "epoch": 0.8978953212537223, "grad_norm": 0.3911932408809662, "learning_rate": 1.345572566327496e-05, "loss": 0.1878, "step": 17790 }, { "epoch": 0.8984000403775299, "grad_norm": 0.39471837878227234, "learning_rate": 1.3447457925549383e-05, "loss": 0.1912, "step": 17800 }, { "epoch": 0.8989047595013375, "grad_norm": 0.40654850006103516, "learning_rate": 1.3439187512582599e-05, "loss": 0.1907, "step": 17810 }, { "epoch": 0.8994094786251451, "grad_norm": 0.47032544016838074, "learning_rate": 1.3430914430792484e-05, "loss": 0.1975, "step": 17820 }, { "epoch": 0.8999141977489528, "grad_norm": 0.3912856876850128, "learning_rate": 1.3422638686598983e-05, "loss": 0.1857, "step": 17830 }, { "epoch": 0.9004189168727603, "grad_norm": 0.3901309072971344, "learning_rate": 1.3414360286424114e-05, "loss": 0.1866, "step": 17840 }, { "epoch": 0.9009236359965679, "grad_norm": 0.4043125808238983, "learning_rate": 1.3406079236691939e-05, "loss": 0.1837, "step": 17850 }, { "epoch": 0.9014283551203756, "grad_norm": 0.37775176763534546, "learning_rate": 1.3397795543828587e-05, "loss": 0.1878, "step": 17860 }, { "epoch": 0.9019330742441831, "grad_norm": 0.40250468254089355, "learning_rate": 1.3389509214262245e-05, "loss": 0.1942, "step": 17870 }, { "epoch": 0.9024377933679907, "grad_norm": 0.385993093252182, "learning_rate": 1.3381220254423127e-05, "loss": 0.184, "step": 17880 }, { "epoch": 0.9029425124917984, "grad_norm": 0.3871241807937622, "learning_rate": 1.3372928670743507e-05, "loss": 0.1825, "step": 17890 }, { "epoch": 0.9034472316156059, "grad_norm": 0.3772827386856079, "learning_rate": 1.3364634469657682e-05, "loss": 0.1892, "step": 17900 }, { "epoch": 0.9039519507394135, "grad_norm": 0.4015592932701111, "learning_rate": 1.3356337657601995e-05, "loss": 0.1894, "step": 17910 }, { "epoch": 0.9044566698632212, "grad_norm": 0.40057751536369324, "learning_rate": 1.3348038241014791e-05, "loss": 0.1863, "step": 17920 }, { "epoch": 0.9049613889870287, "grad_norm": 0.35777053236961365, "learning_rate": 1.3339736226336464e-05, "loss": 0.1866, "step": 17930 }, { "epoch": 0.9054661081108363, "grad_norm": 0.36989134550094604, "learning_rate": 1.3331431620009405e-05, "loss": 0.1896, "step": 17940 }, { "epoch": 0.905970827234644, "grad_norm": 0.40947768092155457, "learning_rate": 1.3323124428478018e-05, "loss": 0.1891, "step": 17950 }, { "epoch": 0.9064755463584515, "grad_norm": 0.4183034598827362, "learning_rate": 1.3314814658188722e-05, "loss": 0.1905, "step": 17960 }, { "epoch": 0.9069802654822591, "grad_norm": 0.4044203460216522, "learning_rate": 1.3306502315589933e-05, "loss": 0.1888, "step": 17970 }, { "epoch": 0.9074849846060667, "grad_norm": 0.40425872802734375, "learning_rate": 1.3298187407132061e-05, "loss": 0.1877, "step": 17980 }, { "epoch": 0.9079897037298743, "grad_norm": 0.3932884633541107, "learning_rate": 1.3289869939267506e-05, "loss": 0.1836, "step": 17990 }, { "epoch": 0.9084944228536819, "grad_norm": 0.38710352778434753, "learning_rate": 1.3281549918450658e-05, "loss": 0.1862, "step": 18000 }, { "epoch": 0.9089991419774895, "grad_norm": 0.42150115966796875, "learning_rate": 1.3273227351137887e-05, "loss": 0.1869, "step": 18010 }, { "epoch": 0.9095038611012971, "grad_norm": 0.4699268937110901, "learning_rate": 1.326490224378754e-05, "loss": 0.188, "step": 18020 }, { "epoch": 0.9100085802251048, "grad_norm": 0.385500431060791, "learning_rate": 1.3256574602859934e-05, "loss": 0.187, "step": 18030 }, { "epoch": 0.9105132993489123, "grad_norm": 0.3661568760871887, "learning_rate": 1.3248244434817345e-05, "loss": 0.1838, "step": 18040 }, { "epoch": 0.9110180184727199, "grad_norm": 0.3784615397453308, "learning_rate": 1.3239911746124025e-05, "loss": 0.1854, "step": 18050 }, { "epoch": 0.9115227375965276, "grad_norm": 0.42229214310646057, "learning_rate": 1.3231576543246171e-05, "loss": 0.1901, "step": 18060 }, { "epoch": 0.9120274567203351, "grad_norm": 0.41551342606544495, "learning_rate": 1.3223238832651932e-05, "loss": 0.1874, "step": 18070 }, { "epoch": 0.9125321758441427, "grad_norm": 0.40857526659965515, "learning_rate": 1.321489862081141e-05, "loss": 0.1878, "step": 18080 }, { "epoch": 0.9130368949679504, "grad_norm": 0.4177916646003723, "learning_rate": 1.3206555914196638e-05, "loss": 0.1904, "step": 18090 }, { "epoch": 0.9135416140917579, "grad_norm": 0.40407809615135193, "learning_rate": 1.3198210719281587e-05, "loss": 0.1876, "step": 18100 }, { "epoch": 0.9140463332155655, "grad_norm": 0.4145451784133911, "learning_rate": 1.3189863042542175e-05, "loss": 0.1904, "step": 18110 }, { "epoch": 0.9145510523393732, "grad_norm": 0.43739816546440125, "learning_rate": 1.3181512890456219e-05, "loss": 0.1868, "step": 18120 }, { "epoch": 0.9150557714631807, "grad_norm": 0.4065525233745575, "learning_rate": 1.3173160269503475e-05, "loss": 0.1927, "step": 18130 }, { "epoch": 0.9155604905869883, "grad_norm": 0.3947850465774536, "learning_rate": 1.316480518616561e-05, "loss": 0.1957, "step": 18140 }, { "epoch": 0.916065209710796, "grad_norm": 0.3730889856815338, "learning_rate": 1.3156447646926208e-05, "loss": 0.1864, "step": 18150 }, { "epoch": 0.9165699288346035, "grad_norm": 0.38471749424934387, "learning_rate": 1.3148087658270745e-05, "loss": 0.1869, "step": 18160 }, { "epoch": 0.9170746479584111, "grad_norm": 0.38841649889945984, "learning_rate": 1.313972522668661e-05, "loss": 0.1832, "step": 18170 }, { "epoch": 0.9175793670822188, "grad_norm": 0.4182887375354767, "learning_rate": 1.3131360358663083e-05, "loss": 0.1888, "step": 18180 }, { "epoch": 0.9180840862060263, "grad_norm": 0.4276795983314514, "learning_rate": 1.312299306069133e-05, "loss": 0.1909, "step": 18190 }, { "epoch": 0.918588805329834, "grad_norm": 0.39521312713623047, "learning_rate": 1.3114623339264418e-05, "loss": 0.1857, "step": 18200 }, { "epoch": 0.9190935244536416, "grad_norm": 0.4137890636920929, "learning_rate": 1.3106251200877278e-05, "loss": 0.1875, "step": 18210 }, { "epoch": 0.9195982435774491, "grad_norm": 0.4018981158733368, "learning_rate": 1.3097876652026726e-05, "loss": 0.1891, "step": 18220 }, { "epoch": 0.9201029627012568, "grad_norm": 0.3807357847690582, "learning_rate": 1.3089499699211439e-05, "loss": 0.1908, "step": 18230 }, { "epoch": 0.9206076818250644, "grad_norm": 0.39533624053001404, "learning_rate": 1.3081120348931976e-05, "loss": 0.1851, "step": 18240 }, { "epoch": 0.9211124009488719, "grad_norm": 0.3895586431026459, "learning_rate": 1.3072738607690739e-05, "loss": 0.191, "step": 18250 }, { "epoch": 0.9216171200726796, "grad_norm": 0.38842660188674927, "learning_rate": 1.3064354481991992e-05, "loss": 0.1865, "step": 18260 }, { "epoch": 0.9221218391964872, "grad_norm": 0.36495429277420044, "learning_rate": 1.3055967978341855e-05, "loss": 0.1845, "step": 18270 }, { "epoch": 0.9226265583202947, "grad_norm": 0.37781986594200134, "learning_rate": 1.304757910324829e-05, "loss": 0.1827, "step": 18280 }, { "epoch": 0.9231312774441024, "grad_norm": 0.382387638092041, "learning_rate": 1.3039187863221092e-05, "loss": 0.1901, "step": 18290 }, { "epoch": 0.92363599656791, "grad_norm": 0.4121244251728058, "learning_rate": 1.3030794264771897e-05, "loss": 0.1904, "step": 18300 }, { "epoch": 0.9241407156917175, "grad_norm": 0.38884395360946655, "learning_rate": 1.3022398314414177e-05, "loss": 0.1886, "step": 18310 }, { "epoch": 0.9246454348155252, "grad_norm": 0.40891653299331665, "learning_rate": 1.301400001866322e-05, "loss": 0.1874, "step": 18320 }, { "epoch": 0.9251501539393328, "grad_norm": 0.38639605045318604, "learning_rate": 1.3005599384036138e-05, "loss": 0.1904, "step": 18330 }, { "epoch": 0.9256548730631403, "grad_norm": 0.4162602424621582, "learning_rate": 1.2997196417051854e-05, "loss": 0.1888, "step": 18340 }, { "epoch": 0.926159592186948, "grad_norm": 0.42429137229919434, "learning_rate": 1.2988791124231106e-05, "loss": 0.1886, "step": 18350 }, { "epoch": 0.9266643113107556, "grad_norm": 0.36188003420829773, "learning_rate": 1.2980383512096437e-05, "loss": 0.1834, "step": 18360 }, { "epoch": 0.9271690304345631, "grad_norm": 0.39754724502563477, "learning_rate": 1.2971973587172189e-05, "loss": 0.1851, "step": 18370 }, { "epoch": 0.9276737495583708, "grad_norm": 0.40513288974761963, "learning_rate": 1.296356135598449e-05, "loss": 0.1907, "step": 18380 }, { "epoch": 0.9281784686821783, "grad_norm": 0.39540326595306396, "learning_rate": 1.2955146825061275e-05, "loss": 0.1884, "step": 18390 }, { "epoch": 0.928683187805986, "grad_norm": 0.391646146774292, "learning_rate": 1.2946730000932246e-05, "loss": 0.1911, "step": 18400 }, { "epoch": 0.9291879069297936, "grad_norm": 0.3708418309688568, "learning_rate": 1.2938310890128896e-05, "loss": 0.186, "step": 18410 }, { "epoch": 0.9296926260536011, "grad_norm": 0.3623686730861664, "learning_rate": 1.2929889499184488e-05, "loss": 0.184, "step": 18420 }, { "epoch": 0.9301973451774088, "grad_norm": 0.40290018916130066, "learning_rate": 1.2921465834634054e-05, "loss": 0.1873, "step": 18430 }, { "epoch": 0.9307020643012164, "grad_norm": 0.4136424660682678, "learning_rate": 1.2913039903014395e-05, "loss": 0.1904, "step": 18440 }, { "epoch": 0.9312067834250239, "grad_norm": 0.38041770458221436, "learning_rate": 1.2904611710864063e-05, "loss": 0.1871, "step": 18450 }, { "epoch": 0.9317115025488316, "grad_norm": 0.37278133630752563, "learning_rate": 1.2896181264723375e-05, "loss": 0.1806, "step": 18460 }, { "epoch": 0.9322162216726392, "grad_norm": 0.4447067081928253, "learning_rate": 1.2887748571134386e-05, "loss": 0.19, "step": 18470 }, { "epoch": 0.9327209407964467, "grad_norm": 0.41927793622016907, "learning_rate": 1.2879313636640903e-05, "loss": 0.187, "step": 18480 }, { "epoch": 0.9332256599202544, "grad_norm": 0.4079114496707916, "learning_rate": 1.2870876467788465e-05, "loss": 0.1847, "step": 18490 }, { "epoch": 0.933730379044062, "grad_norm": 0.38684362173080444, "learning_rate": 1.2862437071124354e-05, "loss": 0.1871, "step": 18500 }, { "epoch": 0.9342350981678695, "grad_norm": 0.400623619556427, "learning_rate": 1.2853995453197574e-05, "loss": 0.1897, "step": 18510 }, { "epoch": 0.9347398172916772, "grad_norm": 0.4177345931529999, "learning_rate": 1.2845551620558852e-05, "loss": 0.1835, "step": 18520 }, { "epoch": 0.9352445364154848, "grad_norm": 0.3982730209827423, "learning_rate": 1.2837105579760638e-05, "loss": 0.187, "step": 18530 }, { "epoch": 0.9357492555392923, "grad_norm": 0.4048924446105957, "learning_rate": 1.2828657337357096e-05, "loss": 0.1931, "step": 18540 }, { "epoch": 0.9362539746631, "grad_norm": 0.3783653676509857, "learning_rate": 1.2820206899904093e-05, "loss": 0.1883, "step": 18550 }, { "epoch": 0.9367586937869076, "grad_norm": 0.40518417954444885, "learning_rate": 1.28117542739592e-05, "loss": 0.184, "step": 18560 }, { "epoch": 0.9372634129107151, "grad_norm": 0.3878217339515686, "learning_rate": 1.2803299466081696e-05, "loss": 0.1895, "step": 18570 }, { "epoch": 0.9377681320345228, "grad_norm": 0.40706539154052734, "learning_rate": 1.2794842482832539e-05, "loss": 0.1856, "step": 18580 }, { "epoch": 0.9382728511583304, "grad_norm": 0.40574854612350464, "learning_rate": 1.2786383330774386e-05, "loss": 0.1794, "step": 18590 }, { "epoch": 0.938777570282138, "grad_norm": 0.4051927328109741, "learning_rate": 1.277792201647157e-05, "loss": 0.1883, "step": 18600 }, { "epoch": 0.9392822894059456, "grad_norm": 0.3852958083152771, "learning_rate": 1.2769458546490108e-05, "loss": 0.1893, "step": 18610 }, { "epoch": 0.9397870085297532, "grad_norm": 0.41109198331832886, "learning_rate": 1.2760992927397683e-05, "loss": 0.187, "step": 18620 }, { "epoch": 0.9402917276535608, "grad_norm": 0.4046623408794403, "learning_rate": 1.2752525165763657e-05, "loss": 0.19, "step": 18630 }, { "epoch": 0.9407964467773684, "grad_norm": 0.4416605234146118, "learning_rate": 1.274405526815904e-05, "loss": 0.1905, "step": 18640 }, { "epoch": 0.941301165901176, "grad_norm": 0.4671986401081085, "learning_rate": 1.2735583241156503e-05, "loss": 0.1873, "step": 18650 }, { "epoch": 0.9418058850249836, "grad_norm": 0.39447131752967834, "learning_rate": 1.2727109091330382e-05, "loss": 0.1838, "step": 18660 }, { "epoch": 0.9423106041487912, "grad_norm": 0.3601526618003845, "learning_rate": 1.271863282525665e-05, "loss": 0.1819, "step": 18670 }, { "epoch": 0.9428153232725988, "grad_norm": 0.37990450859069824, "learning_rate": 1.2710154449512918e-05, "loss": 0.1898, "step": 18680 }, { "epoch": 0.9433200423964064, "grad_norm": 0.38716715574264526, "learning_rate": 1.2701673970678443e-05, "loss": 0.1798, "step": 18690 }, { "epoch": 0.943824761520214, "grad_norm": 0.41000890731811523, "learning_rate": 1.2693191395334113e-05, "loss": 0.1886, "step": 18700 }, { "epoch": 0.9443294806440216, "grad_norm": 0.38004541397094727, "learning_rate": 1.2684706730062434e-05, "loss": 0.1785, "step": 18710 }, { "epoch": 0.9448341997678292, "grad_norm": 0.38889482617378235, "learning_rate": 1.2676219981447546e-05, "loss": 0.1817, "step": 18720 }, { "epoch": 0.9453389188916368, "grad_norm": 0.4031127691268921, "learning_rate": 1.2667731156075198e-05, "loss": 0.1903, "step": 18730 }, { "epoch": 0.9458436380154444, "grad_norm": 0.42967334389686584, "learning_rate": 1.2659240260532757e-05, "loss": 0.1858, "step": 18740 }, { "epoch": 0.946348357139252, "grad_norm": 0.4163878858089447, "learning_rate": 1.2650747301409182e-05, "loss": 0.185, "step": 18750 }, { "epoch": 0.9468530762630596, "grad_norm": 0.3954657018184662, "learning_rate": 1.2642252285295053e-05, "loss": 0.1854, "step": 18760 }, { "epoch": 0.9473577953868673, "grad_norm": 0.4097488224506378, "learning_rate": 1.2633755218782533e-05, "loss": 0.1882, "step": 18770 }, { "epoch": 0.9478625145106748, "grad_norm": 0.41508227586746216, "learning_rate": 1.262525610846538e-05, "loss": 0.1877, "step": 18780 }, { "epoch": 0.9483672336344824, "grad_norm": 0.4029572308063507, "learning_rate": 1.2616754960938938e-05, "loss": 0.1818, "step": 18790 }, { "epoch": 0.9488719527582901, "grad_norm": 0.37432044744491577, "learning_rate": 1.2608251782800127e-05, "loss": 0.1889, "step": 18800 }, { "epoch": 0.9493766718820976, "grad_norm": 0.39409905672073364, "learning_rate": 1.2599746580647457e-05, "loss": 0.1856, "step": 18810 }, { "epoch": 0.9498813910059052, "grad_norm": 0.4346454441547394, "learning_rate": 1.2591239361080993e-05, "loss": 0.1863, "step": 18820 }, { "epoch": 0.9503861101297129, "grad_norm": 0.4063919186592102, "learning_rate": 1.258273013070237e-05, "loss": 0.1851, "step": 18830 }, { "epoch": 0.9508908292535204, "grad_norm": 0.38064175844192505, "learning_rate": 1.257421889611479e-05, "loss": 0.1867, "step": 18840 }, { "epoch": 0.951395548377328, "grad_norm": 0.3972936272621155, "learning_rate": 1.2565705663922997e-05, "loss": 0.1833, "step": 18850 }, { "epoch": 0.9519002675011357, "grad_norm": 0.3956112563610077, "learning_rate": 1.2557190440733304e-05, "loss": 0.1839, "step": 18860 }, { "epoch": 0.9524049866249432, "grad_norm": 0.39520660042762756, "learning_rate": 1.2548673233153552e-05, "loss": 0.1897, "step": 18870 }, { "epoch": 0.9529097057487508, "grad_norm": 0.4157237708568573, "learning_rate": 1.2540154047793129e-05, "loss": 0.1861, "step": 18880 }, { "epoch": 0.9534144248725585, "grad_norm": 0.3810465335845947, "learning_rate": 1.2531632891262958e-05, "loss": 0.1879, "step": 18890 }, { "epoch": 0.953919143996366, "grad_norm": 0.4200023114681244, "learning_rate": 1.2523109770175492e-05, "loss": 0.192, "step": 18900 }, { "epoch": 0.9544238631201736, "grad_norm": 0.3746134340763092, "learning_rate": 1.2514584691144704e-05, "loss": 0.189, "step": 18910 }, { "epoch": 0.9549285822439812, "grad_norm": 0.38868263363838196, "learning_rate": 1.250605766078609e-05, "loss": 0.1885, "step": 18920 }, { "epoch": 0.9554333013677888, "grad_norm": 0.4028845429420471, "learning_rate": 1.2497528685716663e-05, "loss": 0.1843, "step": 18930 }, { "epoch": 0.9559380204915964, "grad_norm": 0.3548697233200073, "learning_rate": 1.2488997772554938e-05, "loss": 0.183, "step": 18940 }, { "epoch": 0.956442739615404, "grad_norm": 0.3994232714176178, "learning_rate": 1.2480464927920943e-05, "loss": 0.1835, "step": 18950 }, { "epoch": 0.9569474587392116, "grad_norm": 0.3968152403831482, "learning_rate": 1.2471930158436193e-05, "loss": 0.1869, "step": 18960 }, { "epoch": 0.9574521778630193, "grad_norm": 0.40542981028556824, "learning_rate": 1.2463393470723708e-05, "loss": 0.1847, "step": 18970 }, { "epoch": 0.9579568969868268, "grad_norm": 0.44324395060539246, "learning_rate": 1.2454854871407993e-05, "loss": 0.1865, "step": 18980 }, { "epoch": 0.9584616161106344, "grad_norm": 0.43222367763519287, "learning_rate": 1.2446314367115031e-05, "loss": 0.1855, "step": 18990 }, { "epoch": 0.9589663352344421, "grad_norm": 0.39202016592025757, "learning_rate": 1.2437771964472292e-05, "loss": 0.1883, "step": 19000 }, { "epoch": 0.9594710543582496, "grad_norm": 0.4227850139141083, "learning_rate": 1.242922767010871e-05, "loss": 0.1926, "step": 19010 }, { "epoch": 0.9599757734820572, "grad_norm": 0.3796577751636505, "learning_rate": 1.2420681490654698e-05, "loss": 0.1834, "step": 19020 }, { "epoch": 0.9604804926058649, "grad_norm": 0.3752273619174957, "learning_rate": 1.2412133432742119e-05, "loss": 0.1836, "step": 19030 }, { "epoch": 0.9609852117296724, "grad_norm": 0.3826806843280792, "learning_rate": 1.2403583503004306e-05, "loss": 0.1871, "step": 19040 }, { "epoch": 0.96148993085348, "grad_norm": 0.370390385389328, "learning_rate": 1.2395031708076036e-05, "loss": 0.1844, "step": 19050 }, { "epoch": 0.9619946499772877, "grad_norm": 0.41818445920944214, "learning_rate": 1.2386478054593534e-05, "loss": 0.1845, "step": 19060 }, { "epoch": 0.9624993691010952, "grad_norm": 0.4110012650489807, "learning_rate": 1.2377922549194473e-05, "loss": 0.1906, "step": 19070 }, { "epoch": 0.9630040882249028, "grad_norm": 0.38379669189453125, "learning_rate": 1.2369365198517958e-05, "loss": 0.1801, "step": 19080 }, { "epoch": 0.9635088073487105, "grad_norm": 0.3884803354740143, "learning_rate": 1.236080600920453e-05, "loss": 0.1879, "step": 19090 }, { "epoch": 0.964013526472518, "grad_norm": 0.394203782081604, "learning_rate": 1.235224498789615e-05, "loss": 0.1826, "step": 19100 }, { "epoch": 0.9645182455963256, "grad_norm": 0.41411563754081726, "learning_rate": 1.2343682141236206e-05, "loss": 0.1841, "step": 19110 }, { "epoch": 0.9650229647201333, "grad_norm": 0.42363905906677246, "learning_rate": 1.2335117475869506e-05, "loss": 0.1918, "step": 19120 }, { "epoch": 0.9655276838439408, "grad_norm": 0.40305760502815247, "learning_rate": 1.2326550998442262e-05, "loss": 0.1856, "step": 19130 }, { "epoch": 0.9660324029677484, "grad_norm": 0.4416186213493347, "learning_rate": 1.2317982715602091e-05, "loss": 0.1805, "step": 19140 }, { "epoch": 0.9665371220915561, "grad_norm": 0.389775812625885, "learning_rate": 1.2309412633998019e-05, "loss": 0.1903, "step": 19150 }, { "epoch": 0.9670418412153636, "grad_norm": 0.40692880749702454, "learning_rate": 1.2300840760280463e-05, "loss": 0.1777, "step": 19160 }, { "epoch": 0.9675465603391713, "grad_norm": 0.39865750074386597, "learning_rate": 1.2292267101101233e-05, "loss": 0.1889, "step": 19170 }, { "epoch": 0.9680512794629789, "grad_norm": 0.3984813690185547, "learning_rate": 1.2283691663113522e-05, "loss": 0.1817, "step": 19180 }, { "epoch": 0.9685559985867864, "grad_norm": 0.3841911852359772, "learning_rate": 1.22751144529719e-05, "loss": 0.185, "step": 19190 }, { "epoch": 0.9690607177105941, "grad_norm": 0.39884617924690247, "learning_rate": 1.2266535477332325e-05, "loss": 0.1855, "step": 19200 }, { "epoch": 0.9695654368344017, "grad_norm": 0.44988569617271423, "learning_rate": 1.2257954742852107e-05, "loss": 0.1898, "step": 19210 }, { "epoch": 0.9700701559582092, "grad_norm": 0.4106396734714508, "learning_rate": 1.224937225618994e-05, "loss": 0.1847, "step": 19220 }, { "epoch": 0.9705748750820169, "grad_norm": 0.41007187962532043, "learning_rate": 1.2240788024005861e-05, "loss": 0.1857, "step": 19230 }, { "epoch": 0.9710795942058245, "grad_norm": 0.3749086260795593, "learning_rate": 1.223220205296127e-05, "loss": 0.1847, "step": 19240 }, { "epoch": 0.971584313329632, "grad_norm": 0.39011332392692566, "learning_rate": 1.2223614349718917e-05, "loss": 0.1859, "step": 19250 }, { "epoch": 0.9720890324534397, "grad_norm": 0.3921906650066376, "learning_rate": 1.2215024920942896e-05, "loss": 0.1859, "step": 19260 }, { "epoch": 0.9725937515772473, "grad_norm": 0.37081339955329895, "learning_rate": 1.2206433773298632e-05, "loss": 0.1919, "step": 19270 }, { "epoch": 0.9730984707010548, "grad_norm": 0.3966238796710968, "learning_rate": 1.2197840913452895e-05, "loss": 0.1863, "step": 19280 }, { "epoch": 0.9736031898248625, "grad_norm": 0.3983743488788605, "learning_rate": 1.2189246348073778e-05, "loss": 0.1836, "step": 19290 }, { "epoch": 0.97410790894867, "grad_norm": 0.39500346779823303, "learning_rate": 1.2180650083830697e-05, "loss": 0.1872, "step": 19300 }, { "epoch": 0.9746126280724776, "grad_norm": 0.405495285987854, "learning_rate": 1.2172052127394389e-05, "loss": 0.1822, "step": 19310 }, { "epoch": 0.9751173471962853, "grad_norm": 0.4609345495700836, "learning_rate": 1.21634524854369e-05, "loss": 0.1843, "step": 19320 }, { "epoch": 0.9756220663200929, "grad_norm": 0.4241788387298584, "learning_rate": 1.215485116463159e-05, "loss": 0.1875, "step": 19330 }, { "epoch": 0.9761267854439005, "grad_norm": 0.39858144521713257, "learning_rate": 1.2146248171653116e-05, "loss": 0.1813, "step": 19340 }, { "epoch": 0.9766315045677081, "grad_norm": 0.40153568983078003, "learning_rate": 1.2137643513177442e-05, "loss": 0.1874, "step": 19350 }, { "epoch": 0.9771362236915156, "grad_norm": 0.40968558192253113, "learning_rate": 1.2129037195881807e-05, "loss": 0.184, "step": 19360 }, { "epoch": 0.9776409428153233, "grad_norm": 0.3997901976108551, "learning_rate": 1.2120429226444754e-05, "loss": 0.1885, "step": 19370 }, { "epoch": 0.9781456619391309, "grad_norm": 0.3866599500179291, "learning_rate": 1.2111819611546099e-05, "loss": 0.186, "step": 19380 }, { "epoch": 0.9786503810629384, "grad_norm": 0.38477715849876404, "learning_rate": 1.2103208357866943e-05, "loss": 0.1816, "step": 19390 }, { "epoch": 0.9791551001867461, "grad_norm": 0.4093908965587616, "learning_rate": 1.2094595472089648e-05, "loss": 0.1877, "step": 19400 }, { "epoch": 0.9796598193105537, "grad_norm": 0.43984702229499817, "learning_rate": 1.2085980960897848e-05, "loss": 0.1874, "step": 19410 }, { "epoch": 0.9801645384343612, "grad_norm": 0.37637844681739807, "learning_rate": 1.2077364830976442e-05, "loss": 0.1827, "step": 19420 }, { "epoch": 0.9806692575581689, "grad_norm": 0.40419793128967285, "learning_rate": 1.2068747089011579e-05, "loss": 0.1849, "step": 19430 }, { "epoch": 0.9811739766819765, "grad_norm": 0.39993032813072205, "learning_rate": 1.2060127741690664e-05, "loss": 0.1787, "step": 19440 }, { "epoch": 0.981678695805784, "grad_norm": 0.44488808512687683, "learning_rate": 1.2051506795702338e-05, "loss": 0.1816, "step": 19450 }, { "epoch": 0.9821834149295917, "grad_norm": 0.40668126940727234, "learning_rate": 1.2042884257736497e-05, "loss": 0.1855, "step": 19460 }, { "epoch": 0.9826881340533993, "grad_norm": 0.4074295163154602, "learning_rate": 1.2034260134484268e-05, "loss": 0.1841, "step": 19470 }, { "epoch": 0.9831928531772068, "grad_norm": 0.39995354413986206, "learning_rate": 1.2025634432637995e-05, "loss": 0.1893, "step": 19480 }, { "epoch": 0.9836975723010145, "grad_norm": 0.43158194422721863, "learning_rate": 1.2017007158891264e-05, "loss": 0.1846, "step": 19490 }, { "epoch": 0.9842022914248221, "grad_norm": 0.41605162620544434, "learning_rate": 1.2008378319938874e-05, "loss": 0.1887, "step": 19500 }, { "epoch": 0.9847070105486296, "grad_norm": 0.4008845090866089, "learning_rate": 1.1999747922476835e-05, "loss": 0.1875, "step": 19510 }, { "epoch": 0.9852117296724373, "grad_norm": 0.4134013056755066, "learning_rate": 1.1991115973202371e-05, "loss": 0.1885, "step": 19520 }, { "epoch": 0.9857164487962449, "grad_norm": 0.3742181360721588, "learning_rate": 1.1982482478813915e-05, "loss": 0.1819, "step": 19530 }, { "epoch": 0.9862211679200525, "grad_norm": 0.40392449498176575, "learning_rate": 1.197384744601109e-05, "loss": 0.1838, "step": 19540 }, { "epoch": 0.9867258870438601, "grad_norm": 0.4069797396659851, "learning_rate": 1.196521088149471e-05, "loss": 0.1831, "step": 19550 }, { "epoch": 0.9872306061676677, "grad_norm": 0.3964247405529022, "learning_rate": 1.1956572791966792e-05, "loss": 0.1863, "step": 19560 }, { "epoch": 0.9877353252914753, "grad_norm": 0.4302219748497009, "learning_rate": 1.1947933184130524e-05, "loss": 0.1895, "step": 19570 }, { "epoch": 0.9882400444152829, "grad_norm": 0.39273980259895325, "learning_rate": 1.193929206469028e-05, "loss": 0.1819, "step": 19580 }, { "epoch": 0.9887447635390905, "grad_norm": 0.40586337447166443, "learning_rate": 1.1930649440351599e-05, "loss": 0.1853, "step": 19590 }, { "epoch": 0.9892494826628981, "grad_norm": 0.4366891384124756, "learning_rate": 1.1922005317821194e-05, "loss": 0.1849, "step": 19600 }, { "epoch": 0.9897542017867057, "grad_norm": 0.39312854409217834, "learning_rate": 1.1913359703806941e-05, "loss": 0.1854, "step": 19610 }, { "epoch": 0.9902589209105133, "grad_norm": 0.3899368643760681, "learning_rate": 1.190471260501787e-05, "loss": 0.1809, "step": 19620 }, { "epoch": 0.9907636400343209, "grad_norm": 0.4024716019630432, "learning_rate": 1.189606402816416e-05, "loss": 0.18, "step": 19630 }, { "epoch": 0.9912683591581285, "grad_norm": 0.4122626781463623, "learning_rate": 1.1887413979957148e-05, "loss": 0.1798, "step": 19640 }, { "epoch": 0.9917730782819361, "grad_norm": 0.41943690180778503, "learning_rate": 1.1878762467109302e-05, "loss": 0.1869, "step": 19650 }, { "epoch": 0.9922777974057437, "grad_norm": 0.39539793133735657, "learning_rate": 1.1870109496334232e-05, "loss": 0.1841, "step": 19660 }, { "epoch": 0.9927825165295513, "grad_norm": 0.4011574685573578, "learning_rate": 1.1861455074346677e-05, "loss": 0.1819, "step": 19670 }, { "epoch": 0.9932872356533589, "grad_norm": 0.4197707772254944, "learning_rate": 1.1852799207862507e-05, "loss": 0.1845, "step": 19680 }, { "epoch": 0.9937919547771665, "grad_norm": 0.3969573974609375, "learning_rate": 1.1844141903598705e-05, "loss": 0.1813, "step": 19690 }, { "epoch": 0.9942966739009741, "grad_norm": 0.39650118350982666, "learning_rate": 1.1835483168273377e-05, "loss": 0.1868, "step": 19700 }, { "epoch": 0.9948013930247817, "grad_norm": 0.40741580724716187, "learning_rate": 1.1826823008605732e-05, "loss": 0.1869, "step": 19710 }, { "epoch": 0.9953061121485893, "grad_norm": 0.39383557438850403, "learning_rate": 1.1818161431316093e-05, "loss": 0.1902, "step": 19720 }, { "epoch": 0.9958108312723969, "grad_norm": 0.40619343519210815, "learning_rate": 1.1809498443125875e-05, "loss": 0.185, "step": 19730 }, { "epoch": 0.9963155503962046, "grad_norm": 0.42451363801956177, "learning_rate": 1.18008340507576e-05, "loss": 0.1881, "step": 19740 }, { "epoch": 0.9968202695200121, "grad_norm": 0.3952495753765106, "learning_rate": 1.179216826093486e-05, "loss": 0.1852, "step": 19750 }, { "epoch": 0.9973249886438197, "grad_norm": 0.41204485297203064, "learning_rate": 1.1783501080382349e-05, "loss": 0.1913, "step": 19760 }, { "epoch": 0.9978297077676274, "grad_norm": 0.39689990878105164, "learning_rate": 1.1774832515825832e-05, "loss": 0.1797, "step": 19770 }, { "epoch": 0.9983344268914349, "grad_norm": 0.3918308615684509, "learning_rate": 1.1766162573992153e-05, "loss": 0.1813, "step": 19780 }, { "epoch": 0.9988391460152425, "grad_norm": 0.39842039346694946, "learning_rate": 1.175749126160922e-05, "loss": 0.1885, "step": 19790 }, { "epoch": 0.9993438651390502, "grad_norm": 0.39777183532714844, "learning_rate": 1.1748818585406004e-05, "loss": 0.1843, "step": 19800 }, { "epoch": 0.9998485842628577, "grad_norm": 0.36155563592910767, "learning_rate": 1.1740144552112536e-05, "loss": 0.1838, "step": 19810 }, { "epoch": 1.0003533033866654, "grad_norm": 0.34840667247772217, "learning_rate": 1.1731469168459906e-05, "loss": 0.1781, "step": 19820 }, { "epoch": 1.0008580225104728, "grad_norm": 0.4441397190093994, "learning_rate": 1.1722792441180242e-05, "loss": 0.1729, "step": 19830 }, { "epoch": 1.0013627416342805, "grad_norm": 0.43244704604148865, "learning_rate": 1.1714114377006725e-05, "loss": 0.176, "step": 19840 }, { "epoch": 1.0018674607580882, "grad_norm": 0.44057613611221313, "learning_rate": 1.170543498267356e-05, "loss": 0.1709, "step": 19850 }, { "epoch": 1.0023721798818956, "grad_norm": 0.4264165461063385, "learning_rate": 1.1696754264915995e-05, "loss": 0.1764, "step": 19860 }, { "epoch": 1.0028768990057033, "grad_norm": 0.420516699552536, "learning_rate": 1.1688072230470302e-05, "loss": 0.1733, "step": 19870 }, { "epoch": 1.003381618129511, "grad_norm": 0.4225519895553589, "learning_rate": 1.1679388886073777e-05, "loss": 0.169, "step": 19880 }, { "epoch": 1.0038863372533184, "grad_norm": 0.500748336315155, "learning_rate": 1.1670704238464729e-05, "loss": 0.172, "step": 19890 }, { "epoch": 1.0043910563771261, "grad_norm": 0.4070868194103241, "learning_rate": 1.1662018294382476e-05, "loss": 0.1745, "step": 19900 }, { "epoch": 1.0048957755009338, "grad_norm": 0.4627508819103241, "learning_rate": 1.1653331060567347e-05, "loss": 0.1695, "step": 19910 }, { "epoch": 1.0054004946247412, "grad_norm": 0.4450300335884094, "learning_rate": 1.1644642543760673e-05, "loss": 0.1721, "step": 19920 }, { "epoch": 1.005905213748549, "grad_norm": 0.4622417092323303, "learning_rate": 1.163595275070478e-05, "loss": 0.1705, "step": 19930 }, { "epoch": 1.0064099328723566, "grad_norm": 0.4213803708553314, "learning_rate": 1.1627261688142973e-05, "loss": 0.1717, "step": 19940 }, { "epoch": 1.006914651996164, "grad_norm": 0.45333626866340637, "learning_rate": 1.1618569362819559e-05, "loss": 0.1751, "step": 19950 }, { "epoch": 1.0074193711199717, "grad_norm": 0.4487689137458801, "learning_rate": 1.1609875781479816e-05, "loss": 0.1705, "step": 19960 }, { "epoch": 1.0079240902437794, "grad_norm": 0.4083845913410187, "learning_rate": 1.1601180950869997e-05, "loss": 0.1693, "step": 19970 }, { "epoch": 1.0084288093675868, "grad_norm": 0.4832732677459717, "learning_rate": 1.1592484877737325e-05, "loss": 0.1737, "step": 19980 }, { "epoch": 1.0089335284913945, "grad_norm": 0.45176923274993896, "learning_rate": 1.1583787568829989e-05, "loss": 0.1749, "step": 19990 }, { "epoch": 1.0094382476152022, "grad_norm": 0.43392476439476013, "learning_rate": 1.1575089030897138e-05, "loss": 0.1647, "step": 20000 } ], "logging_steps": 10, "max_steps": 39626, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 1000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 2.6832279303782138e+20, "train_batch_size": 2, "trial_name": null, "trial_params": null }