{ "name": "normal-model-ablation", "attention_type": "standard", "params": 1498496, "params_excluding_indexers": 1498496, "val_loss": 3.4248253107070923, "val_ppl": 30.71727840314173, "steps": 40690, "train_tokens": 1999994880, "seed": 1337, "log": [ { "step": 50, "loss": 7.648939208984375, "indexer_kl": 0.0, "lr": 0.001, "tokens_per_s": 2363149.0623330018 }, { "step": 100, "loss": 6.532793579101562, "indexer_kl": 0.0, "lr": 0.002, "tokens_per_s": 2363988.825870876 }, { "step": 150, "loss": 5.866292114257813, "indexer_kl": 0.0, "lr": 0.001999993527593341, "tokens_per_s": 2364134.4022017717 }, { "step": 200, "loss": 5.428878173828125, "indexer_kl": 0.0, "lr": 0.001999973579415524, "tokens_per_s": 2364310.093602896 }, { "step": 250, "loss": 5.125506591796875, "indexer_kl": 0.0, "lr": 0.0019999401530695817, "tokens_per_s": 2364501.540194997 }, { "step": 300, "loss": 4.932823791503906, "indexer_kl": 0.0, "lr": 0.0019998932490561125, "tokens_per_s": 2364898.813939611 }, { "step": 350, "loss": 4.802083129882813, "indexer_kl": 0.0, "lr": 0.00199983286807756, "tokens_per_s": 2364946.2249820535 }, { "step": 400, "loss": 4.702893676757813, "indexer_kl": 0.0, "lr": 0.0019997590110381997, "tokens_per_s": 2364936.7490808354 }, { "step": 450, "loss": 4.638193359375, "indexer_kl": 0.0, "lr": 0.0019996716790441284, "tokens_per_s": 2365077.030751819 }, { "step": 500, "loss": 4.567515869140625, "indexer_kl": 0.0, "lr": 0.0019995708734032464, "tokens_per_s": 2365186.9887292064 }, { "step": 550, "loss": 4.511327209472657, "indexer_kl": 0.0, "lr": 0.001999456595625237, "tokens_per_s": 2365294.823211181 }, { "step": 600, "loss": 4.4699462890625, "indexer_kl": 0.0, "lr": 0.001999328847421545, "tokens_per_s": 2365321.278435137 }, { "step": 650, "loss": 4.422857666015625, "indexer_kl": 0.0, "lr": 0.001999187630705351, "tokens_per_s": 2365351.2629185687 }, { "step": 700, "loss": 4.3891299438476565, "indexer_kl": 0.0, "lr": 0.0019990329475915417, "tokens_per_s": 2365414.378649714 }, { "step": 750, "loss": 4.359731140136719, "indexer_kl": 0.0, "lr": 0.0019988648003966803, "tokens_per_s": 2365481.4582522465 }, { "step": 800, "loss": 4.3241729736328125, "indexer_kl": 0.0, "lr": 0.0019986831916389692, "tokens_per_s": 2365593.0862674806 }, { "step": 850, "loss": 4.301809387207031, "indexer_kl": 0.0, "lr": 0.0019984881240382147, "tokens_per_s": 2365628.0370933237 }, { "step": 900, "loss": 4.25659423828125, "indexer_kl": 0.0, "lr": 0.001998279600515784, "tokens_per_s": 2365700.2772627347 }, { "step": 950, "loss": 4.203756713867188, "indexer_kl": 0.0, "lr": 0.0019980576241945642, "tokens_per_s": 2365757.744108179 }, { "step": 1000, "loss": 4.183764953613281, "indexer_kl": 0.0, "lr": 0.001997822198398912, "tokens_per_s": 2365765.8114079665 }, { "step": 1050, "loss": 4.1194775390625, "indexer_kl": 0.0, "lr": 0.001997573326654608, "tokens_per_s": 2365811.713585091 }, { "step": 1100, "loss": 4.085085144042969, "indexer_kl": 0.0, "lr": 0.001997311012688801, "tokens_per_s": 2365878.1760932603 }, { "step": 1150, "loss": 4.049246215820313, "indexer_kl": 0.0, "lr": 0.001997035260429951, "tokens_per_s": 2365908.7120877816 }, { "step": 1200, "loss": 4.034196472167968, "indexer_kl": 0.0, "lr": 0.0019967460740077754, "tokens_per_s": 2365901.542522324 }, { "step": 1250, "loss": 4.01317138671875, "indexer_kl": 0.0, "lr": 0.0019964434577531827, "tokens_per_s": 2365885.193871997 }, { "step": 1300, "loss": 3.997111511230469, "indexer_kl": 0.0, "lr": 0.001996127416198208, "tokens_per_s": 2365852.580510005 }, { "step": 1350, "loss": 3.969423828125, "indexer_kl": 0.0, "lr": 0.001995797954075948, "tokens_per_s": 2365862.9077159036 }, { "step": 1400, "loss": 3.96874755859375, "indexer_kl": 0.0, "lr": 0.0019954550763204874, "tokens_per_s": 2365863.653996134 }, { "step": 1450, "loss": 3.9396133422851562, "indexer_kl": 0.0, "lr": 0.0019950987880668256, "tokens_per_s": 2365855.1738323844 }, { "step": 1500, "loss": 3.942455139160156, "indexer_kl": 0.0, "lr": 0.0019947290946508004, "tokens_per_s": 2365844.200154269 }, { "step": 1550, "loss": 3.9267047119140623, "indexer_kl": 0.0, "lr": 0.0019943460016090078, "tokens_per_s": 2365845.9681223766 }, { "step": 1600, "loss": 3.907215270996094, "indexer_kl": 0.0, "lr": 0.001993949514678718, "tokens_per_s": 2365859.300222584 }, { "step": 1650, "loss": 3.886343994140625, "indexer_kl": 0.0, "lr": 0.001993539639797793, "tokens_per_s": 2365850.367353153 }, { "step": 1700, "loss": 3.8931393432617187, "indexer_kl": 0.0, "lr": 0.001993116383104593, "tokens_per_s": 2365874.716178031 }, { "step": 1750, "loss": 3.8917095947265623, "indexer_kl": 0.0, "lr": 0.0019926797509378868, "tokens_per_s": 2365898.4963976922 }, { "step": 1800, "loss": 3.8888079833984377, "indexer_kl": 0.0, "lr": 0.0019922297498367577, "tokens_per_s": 2365907.9231186537 }, { "step": 1850, "loss": 3.8674688720703125, "indexer_kl": 0.0, "lr": 0.0019917663865405034, "tokens_per_s": 2365910.3386303657 }, { "step": 1900, "loss": 3.868305358886719, "indexer_kl": 0.0, "lr": 0.001991289667988538, "tokens_per_s": 2365725.8240885152 }, { "step": 1950, "loss": 3.861421813964844, "indexer_kl": 0.0, "lr": 0.001990799601320285, "tokens_per_s": 2365721.28488152 }, { "step": 2000, "loss": 3.8439151000976564, "indexer_kl": 0.0, "lr": 0.0019902961938750713, "tokens_per_s": 2365723.270809914 }, { "step": 2050, "loss": 3.844996032714844, "indexer_kl": 0.0, "lr": 0.001989779453192019, "tokens_per_s": 2365724.312340054 }, { "step": 2100, "loss": 3.8411569213867187, "indexer_kl": 0.0, "lr": 0.001989249387009931, "tokens_per_s": 2365728.807581166 }, { "step": 2150, "loss": 3.8154672241210936, "indexer_kl": 0.0, "lr": 0.001988706003267174, "tokens_per_s": 2365619.9002684793 }, { "step": 2200, "loss": 3.8307904052734374, "indexer_kl": 0.0, "lr": 0.0019881493101015623, "tokens_per_s": 2365656.226260755 }, { "step": 2250, "loss": 3.8134255981445313, "indexer_kl": 0.0, "lr": 0.001987579315850234, "tokens_per_s": 2365603.2284849808 }, { "step": 2300, "loss": 3.809312744140625, "indexer_kl": 0.0, "lr": 0.001986996029049527, "tokens_per_s": 2365610.2005907726 }, { "step": 2350, "loss": 3.7917156982421876, "indexer_kl": 0.0, "lr": 0.00198639945843485, "tokens_per_s": 2365646.816639603 }, { "step": 2400, "loss": 3.8041644287109375, "indexer_kl": 0.0, "lr": 0.001985789612940554, "tokens_per_s": 2365661.831258642 }, { "step": 2450, "loss": 3.8070977783203124, "indexer_kl": 0.0, "lr": 0.001985166501699796, "tokens_per_s": 2365668.4771750565 }, { "step": 2500, "loss": 3.783924255371094, "indexer_kl": 0.0, "lr": 0.0019845301340444023, "tokens_per_s": 2365674.412092384 }, { "step": 2550, "loss": 3.7888543701171873, "indexer_kl": 0.0, "lr": 0.0019838805195047313, "tokens_per_s": 2365688.8650238784 }, { "step": 2600, "loss": 3.7852914428710935, "indexer_kl": 0.0, "lr": 0.001983217667809529, "tokens_per_s": 2365706.9595662183 }, { "step": 2650, "loss": 3.7806036376953127, "indexer_kl": 0.0, "lr": 0.0019825415888857826, "tokens_per_s": 2365719.034300667 }, { "step": 2700, "loss": 3.777296447753906, "indexer_kl": 0.0, "lr": 0.001981852292858573, "tokens_per_s": 2365740.6562754093 }, { "step": 2750, "loss": 3.7734365844726563, "indexer_kl": 0.0, "lr": 0.0019811497900509237, "tokens_per_s": 2365730.4155096156 }, { "step": 2800, "loss": 3.7739547729492187, "indexer_kl": 0.0, "lr": 0.001980434090983644, "tokens_per_s": 2365728.3648194945 }, { "step": 2850, "loss": 3.7633148193359376, "indexer_kl": 0.0, "lr": 0.001979705206375173, "tokens_per_s": 2365741.207696818 }, { "step": 2900, "loss": 3.762046203613281, "indexer_kl": 0.0, "lr": 0.0019789631471414204, "tokens_per_s": 2365743.478877632 }, { "step": 2950, "loss": 3.7482318115234374, "indexer_kl": 0.0, "lr": 0.001978207924395599, "tokens_per_s": 2365739.6453517764 }, { "step": 3000, "loss": 3.7447048950195314, "indexer_kl": 0.0, "lr": 0.001977439549448063, "tokens_per_s": 2365759.096751134 }, { "step": 3050, "loss": 3.7526791381835936, "indexer_kl": 0.0, "lr": 0.001976658033806136, "tokens_per_s": 2365765.689463216 }, { "step": 3100, "loss": 3.7484735107421874, "indexer_kl": 0.0, "lr": 0.001975863389173937, "tokens_per_s": 2365785.6701074634 }, { "step": 3150, "loss": 3.745319519042969, "indexer_kl": 0.0, "lr": 0.0019750556274522094, "tokens_per_s": 2365795.941217237 }, { "step": 3200, "loss": 3.7427322387695314, "indexer_kl": 0.0, "lr": 0.0019742347607381396, "tokens_per_s": 2365804.00796527 }, { "step": 3250, "loss": 3.734724426269531, "indexer_kl": 0.0, "lr": 0.0019734008013251774, "tokens_per_s": 2365806.8728579464 }, { "step": 3300, "loss": 3.7363052368164062, "indexer_kl": 0.0, "lr": 0.0019725537617028503, "tokens_per_s": 2365813.8549764343 }, { "step": 3350, "loss": 3.7382769775390625, "indexer_kl": 0.0, "lr": 0.001971693654556578, "tokens_per_s": 2365824.1946284124 }, { "step": 3400, "loss": 3.73150634765625, "indexer_kl": 0.0, "lr": 0.0019708204927674816, "tokens_per_s": 2365820.519661802 }, { "step": 3450, "loss": 3.725441589355469, "indexer_kl": 0.0, "lr": 0.001969934289412191, "tokens_per_s": 2365696.240661284 }, { "step": 3500, "loss": 3.7239511108398435, "indexer_kl": 0.0, "lr": 0.001969035057762649, "tokens_per_s": 2365702.945406527 }, { "step": 3550, "loss": 3.7278607177734373, "indexer_kl": 0.0, "lr": 0.0019681228112859122, "tokens_per_s": 2365709.1630875976 }, { "step": 3600, "loss": 3.730074462890625, "indexer_kl": 0.0, "lr": 0.00196719756364395, "tokens_per_s": 2365595.5631893845 }, { "step": 3650, "loss": 3.7295181274414064, "indexer_kl": 0.0, "lr": 0.00196625932869344, "tokens_per_s": 2365604.73188933 }, { "step": 3700, "loss": 3.714951477050781, "indexer_kl": 0.0, "lr": 0.001965308120485559, "tokens_per_s": 2365615.406263004 }, { "step": 3750, "loss": 3.718502197265625, "indexer_kl": 0.0, "lr": 0.001964343953265774, "tokens_per_s": 2365628.7349893274 }, { "step": 3800, "loss": 3.7099569702148436, "indexer_kl": 0.0, "lr": 0.0019633668414736293, "tokens_per_s": 2365626.2974535734 }, { "step": 3850, "loss": 3.7241705322265624, "indexer_kl": 0.0, "lr": 0.001962376799742529, "tokens_per_s": 2365627.6741906614 }, { "step": 3900, "loss": 3.715791015625, "indexer_kl": 0.0, "lr": 0.001961373842899518, "tokens_per_s": 2365634.7370036696 }, { "step": 3950, "loss": 3.70549560546875, "indexer_kl": 0.0, "lr": 0.0019603579859650603, "tokens_per_s": 2365642.6381470906 }, { "step": 4000, "loss": 3.7019998168945314, "indexer_kl": 0.0, "lr": 0.001959329244152815, "tokens_per_s": 2365655.5402133064 }, { "step": 4050, "loss": 3.7154296875, "indexer_kl": 0.0, "lr": 0.0019582876328694057, "tokens_per_s": 2365663.478865041 }, { "step": 4100, "loss": 3.716644592285156, "indexer_kl": 0.0, "lr": 0.0019572331677141933, "tokens_per_s": 2365667.19837918 }, { "step": 4150, "loss": 3.704065856933594, "indexer_kl": 0.0, "lr": 0.0019561658644790397, "tokens_per_s": 2365674.739939881 }, { "step": 4200, "loss": 3.699429626464844, "indexer_kl": 0.0, "lr": 0.0019550857391480727, "tokens_per_s": 2365672.6395769287 }, { "step": 4250, "loss": 3.6998077392578126, "indexer_kl": 0.0, "lr": 0.001953992807897445, "tokens_per_s": 2365685.362595788 }, { "step": 4300, "loss": 3.7020452880859374, "indexer_kl": 0.0, "lr": 0.0019528870870950947, "tokens_per_s": 2365690.176177968 }, { "step": 4350, "loss": 3.682428894042969, "indexer_kl": 0.0, "lr": 0.0019517685933004977, "tokens_per_s": 2365706.1185155995 }, { "step": 4400, "loss": 3.70173095703125, "indexer_kl": 0.0, "lr": 0.00195063734326442, "tokens_per_s": 2365722.210831372 }, { "step": 4450, "loss": 3.6870770263671875, "indexer_kl": 0.0, "lr": 0.0019494933539286688, "tokens_per_s": 2365720.9639009563 }, { "step": 4500, "loss": 3.6904336547851564, "indexer_kl": 0.0, "lr": 0.0019483366424258364, "tokens_per_s": 2365724.6010287995 }, { "step": 4550, "loss": 3.687826843261719, "indexer_kl": 0.0, "lr": 0.0019471672260790447, "tokens_per_s": 2365729.1904296842 }, { "step": 4600, "loss": 3.679774169921875, "indexer_kl": 0.0, "lr": 0.0019459851224016855, "tokens_per_s": 2365731.8859807616 }, { "step": 4650, "loss": 3.6956427001953127, "indexer_kl": 0.0, "lr": 0.0019447903490971592, "tokens_per_s": 2365737.8571781293 }, { "step": 4700, "loss": 3.687264099121094, "indexer_kl": 0.0, "lr": 0.0019435829240586077, "tokens_per_s": 2365748.6746102404 }, { "step": 4750, "loss": 3.6860531616210936, "indexer_kl": 0.0, "lr": 0.0019423628653686487, "tokens_per_s": 2365755.966623381 }, { "step": 4800, "loss": 3.680949401855469, "indexer_kl": 0.0, "lr": 0.0019411301912991025, "tokens_per_s": 2365753.7519748863 }, { "step": 4850, "loss": 3.682414855957031, "indexer_kl": 0.0, "lr": 0.001939884920310721, "tokens_per_s": 2365742.3919056314 }, { "step": 4900, "loss": 3.677304992675781, "indexer_kl": 0.0, "lr": 0.0019386270710529088, "tokens_per_s": 2365662.377639233 }, { "step": 4950, "loss": 3.682525939941406, "indexer_kl": 0.0, "lr": 0.0019373566623634452, "tokens_per_s": 2365661.082347401 }, { "step": 5000, "loss": 3.6768450927734375, "indexer_kl": 0.0, "lr": 0.0019360737132682027, "tokens_per_s": 2365656.620614829 }, { "step": 5050, "loss": 3.6778695678710935, "indexer_kl": 0.0, "lr": 0.0019347782429808595, "tokens_per_s": 2365653.548092881 }, { "step": 5100, "loss": 3.6749481201171874, "indexer_kl": 0.0, "lr": 0.0019334702709026146, "tokens_per_s": 2365647.0814135415 }, { "step": 5150, "loss": 3.66169677734375, "indexer_kl": 0.0, "lr": 0.0019321498166218964, "tokens_per_s": 2365654.3500175234 }, { "step": 5200, "loss": 3.6875457763671875, "indexer_kl": 0.0, "lr": 0.001930816899914068, "tokens_per_s": 2365642.0958327623 }, { "step": 5250, "loss": 3.677765197753906, "indexer_kl": 0.0, "lr": 0.0019294715407411332, "tokens_per_s": 2365642.9808442355 }, { "step": 5300, "loss": 3.6712857055664063, "indexer_kl": 0.0, "lr": 0.0019281137592514353, "tokens_per_s": 2365567.239906478 }, { "step": 5350, "loss": 3.6632171630859376, "indexer_kl": 0.0, "lr": 0.0019267435757793572, "tokens_per_s": 2365570.30967417 }, { "step": 5400, "loss": 3.6715707397460937, "indexer_kl": 0.0, "lr": 0.0019253610108450163, "tokens_per_s": 2365549.6925933226 }, { "step": 5450, "loss": 3.665740966796875, "indexer_kl": 0.0, "lr": 0.001923966085153956, "tokens_per_s": 2365555.277509411 }, { "step": 5500, "loss": 3.6599325561523437, "indexer_kl": 0.0, "lr": 0.001922558819596838, "tokens_per_s": 2365564.3191890744 }, { "step": 5550, "loss": 3.6636090087890625, "indexer_kl": 0.0, "lr": 0.001921139235249127, "tokens_per_s": 2365559.606605402 }, { "step": 5600, "loss": 3.6606784057617188, "indexer_kl": 0.0, "lr": 0.0019197073533707765, "tokens_per_s": 2365556.9994123806 }, { "step": 5650, "loss": 3.6625640869140623, "indexer_kl": 0.0, "lr": 0.0019182631954059103, "tokens_per_s": 2365551.440585623 }, { "step": 5700, "loss": 3.6650271606445313, "indexer_kl": 0.0, "lr": 0.0019168067829825012, "tokens_per_s": 2365543.0935560986 }, { "step": 5750, "loss": 3.653719787597656, "indexer_kl": 0.0, "lr": 0.0019153381379120463, "tokens_per_s": 2365467.3336076057 }, { "step": 5800, "loss": 3.6499945068359376, "indexer_kl": 0.0, "lr": 0.0019138572821892417, "tokens_per_s": 2365446.7113829986 }, { "step": 5850, "loss": 3.653059997558594, "indexer_kl": 0.0, "lr": 0.001912364237991652, "tokens_per_s": 2365361.5710576777 }, { "step": 5900, "loss": 3.6531854248046876, "indexer_kl": 0.0, "lr": 0.0019108590276793792, "tokens_per_s": 2365362.7345012086 }, { "step": 5950, "loss": 3.659659729003906, "indexer_kl": 0.0, "lr": 0.0019093416737947266, "tokens_per_s": 2365311.4852002426 }, { "step": 6000, "loss": 3.673414611816406, "indexer_kl": 0.0, "lr": 0.0019078121990618623, "tokens_per_s": 2365303.5257385755 }, { "step": 6050, "loss": 3.6563531494140626, "indexer_kl": 0.0, "lr": 0.001906270626386478, "tokens_per_s": 2365307.9210410696 }, { "step": 6100, "loss": 3.6574200439453124, "indexer_kl": 0.0, "lr": 0.0019047169788554473, "tokens_per_s": 2365299.849923774 }, { "step": 6150, "loss": 3.648107604980469, "indexer_kl": 0.0, "lr": 0.0019031512797364773, "tokens_per_s": 2365233.3785801805 }, { "step": 6200, "loss": 3.641368408203125, "indexer_kl": 0.0, "lr": 0.0019015735524777642, "tokens_per_s": 2365233.050855107 }, { "step": 6250, "loss": 3.648925476074219, "indexer_kl": 0.0, "lr": 0.0018999838207076382, "tokens_per_s": 2365233.653170734 }, { "step": 6300, "loss": 3.6356442260742186, "indexer_kl": 0.0, "lr": 0.0018983821082342112, "tokens_per_s": 2365228.9264036003 }, { "step": 6350, "loss": 3.639400634765625, "indexer_kl": 0.0, "lr": 0.0018967684390450209, "tokens_per_s": 2365225.4791812995 }, { "step": 6400, "loss": 3.6440493774414064, "indexer_kl": 0.0, "lr": 0.001895142837306671, "tokens_per_s": 2365225.8466909877 }, { "step": 6450, "loss": 3.642680358886719, "indexer_kl": 0.0, "lr": 0.0018935053273644688, "tokens_per_s": 2365229.6835864075 }, { "step": 6500, "loss": 3.64785400390625, "indexer_kl": 0.0, "lr": 0.0018918559337420615, "tokens_per_s": 2365221.375539062 }, { "step": 6550, "loss": 3.6406289672851564, "indexer_kl": 0.0, "lr": 0.0018901946811410678, "tokens_per_s": 2365180.590685803 }, { "step": 6600, "loss": 3.6532958984375, "indexer_kl": 0.0, "lr": 0.001888521594440709, "tokens_per_s": 2365167.662187262 }, { "step": 6650, "loss": 3.6528497314453126, "indexer_kl": 0.0, "lr": 0.0018868366986974363, "tokens_per_s": 2365107.584993063 }, { "step": 6700, "loss": 3.6515374755859376, "indexer_kl": 0.0, "lr": 0.0018851400191445553, "tokens_per_s": 2365099.307042194 }, { "step": 6750, "loss": 3.641993103027344, "indexer_kl": 0.0, "lr": 0.0018834315811918471, "tokens_per_s": 2365103.930398825 }, { "step": 6800, "loss": 3.6519775390625, "indexer_kl": 0.0, "lr": 0.00188171141042519, "tokens_per_s": 2365095.026993393 }, { "step": 6850, "loss": 3.63876708984375, "indexer_kl": 0.0, "lr": 0.0018799795326061742, "tokens_per_s": 2365067.2608990665 }, { "step": 6900, "loss": 3.6280551147460938, "indexer_kl": 0.0, "lr": 0.001878235973671717, "tokens_per_s": 2365050.475299618 }, { "step": 6950, "loss": 3.6306121826171873, "indexer_kl": 0.0, "lr": 0.0018764807597336747, "tokens_per_s": 2365041.981139623 }, { "step": 7000, "loss": 3.623145751953125, "indexer_kl": 0.0, "lr": 0.0018747139170784504, "tokens_per_s": 2365038.914539301 }, { "step": 7050, "loss": 3.645218505859375, "indexer_kl": 0.0, "lr": 0.0018729354721666014, "tokens_per_s": 2365040.8790395563 }, { "step": 7100, "loss": 3.6277902221679685, "indexer_kl": 0.0, "lr": 0.0018711454516324422, "tokens_per_s": 2365033.8662700774 }, { "step": 7150, "loss": 3.62594482421875, "indexer_kl": 0.0, "lr": 0.0018693438822836468, "tokens_per_s": 2364975.782660542 }, { "step": 7200, "loss": 3.622897033691406, "indexer_kl": 0.0, "lr": 0.0018675307911008448, "tokens_per_s": 2364976.5920859785 }, { "step": 7250, "loss": 3.616207275390625, "indexer_kl": 0.0, "lr": 0.00186570620523722, "tokens_per_s": 2364982.0492656985 }, { "step": 7300, "loss": 3.634427490234375, "indexer_kl": 0.0, "lr": 0.0018638701520181024, "tokens_per_s": 2364977.42694824 }, { "step": 7350, "loss": 3.621290588378906, "indexer_kl": 0.0, "lr": 0.0018620226589405597, "tokens_per_s": 2364975.108078643 }, { "step": 7400, "loss": 3.619018249511719, "indexer_kl": 0.0, "lr": 0.0018601637536729838, "tokens_per_s": 2364976.5344445417 }, { "step": 7450, "loss": 3.6386614990234376, "indexer_kl": 0.0, "lr": 0.0018582934640546786, "tokens_per_s": 2364940.6118204915 }, { "step": 7500, "loss": 3.6343368530273437, "indexer_kl": 0.0, "lr": 0.0018564118180954417, "tokens_per_s": 2364943.9383568126 }, { "step": 7550, "loss": 3.626528015136719, "indexer_kl": 0.0, "lr": 0.0018545188439751455, "tokens_per_s": 2364939.455721778 }, { "step": 7600, "loss": 3.630843200683594, "indexer_kl": 0.0, "lr": 0.0018526145700433153, "tokens_per_s": 2364876.487960935 }, { "step": 7650, "loss": 3.6246981811523438, "indexer_kl": 0.0, "lr": 0.0018506990248187037, "tokens_per_s": 2364883.501569451 }, { "step": 7700, "loss": 3.6175244140625, "indexer_kl": 0.0, "lr": 0.0018487722369888646, "tokens_per_s": 2364885.0302139176 }, { "step": 7750, "loss": 3.6196307373046874, "indexer_kl": 0.0, "lr": 0.0018468342354097237, "tokens_per_s": 2364887.312724784 }, { "step": 7800, "loss": 3.6219744873046875, "indexer_kl": 0.0, "lr": 0.0018448850491051445, "tokens_per_s": 2364881.691875571 }, { "step": 7850, "loss": 3.62067626953125, "indexer_kl": 0.0, "lr": 0.0018429247072664966, "tokens_per_s": 2364881.9518356295 }, { "step": 7900, "loss": 3.6147811889648436, "indexer_kl": 0.0, "lr": 0.0018409532392522161, "tokens_per_s": 2364880.9585569776 }, { "step": 7950, "loss": 3.627166442871094, "indexer_kl": 0.0, "lr": 0.0018389706745873665, "tokens_per_s": 2364885.314656563 }, { "step": 8000, "loss": 3.626260070800781, "indexer_kl": 0.0, "lr": 0.001836977042963197, "tokens_per_s": 2364885.031667207 }, { "step": 8050, "loss": 3.6284640502929686, "indexer_kl": 0.0, "lr": 0.001834972374236698, "tokens_per_s": 2364876.2666989216 }, { "step": 8100, "loss": 3.641448974609375, "indexer_kl": 0.0, "lr": 0.0018329566984301537, "tokens_per_s": 2364874.8641672824 }, { "step": 8150, "loss": 3.6088037109375, "indexer_kl": 0.0, "lr": 0.0018309300457306909, "tokens_per_s": 2364877.8659037896 }, { "step": 8200, "loss": 3.619315185546875, "indexer_kl": 0.0, "lr": 0.0018288924464898294, "tokens_per_s": 2364879.3059205334 }, { "step": 8250, "loss": 3.608692932128906, "indexer_kl": 0.0, "lr": 0.0018268439312230265, "tokens_per_s": 2364875.967123093 }, { "step": 8300, "loss": 3.6183990478515624, "indexer_kl": 0.0, "lr": 0.0018247845306092196, "tokens_per_s": 2364843.0375410705 }, { "step": 8350, "loss": 3.6180816650390626, "indexer_kl": 0.0, "lr": 0.0018227142754903673, "tokens_per_s": 2364840.8656519637 }, { "step": 8400, "loss": 3.603656005859375, "indexer_kl": 0.0, "lr": 0.001820633196870987, "tokens_per_s": 2364842.549704516 }, { "step": 8450, "loss": 3.6040631103515626, "indexer_kl": 0.0, "lr": 0.0018185413259176907, "tokens_per_s": 2364788.448812087 }, { "step": 8500, "loss": 3.618874816894531, "indexer_kl": 0.0, "lr": 0.001816438693958719, "tokens_per_s": 2364785.5354625946 }, { "step": 8550, "loss": 3.6168673706054686, "indexer_kl": 0.0, "lr": 0.0018143253324834703, "tokens_per_s": 2364788.1987387124 }, { "step": 8600, "loss": 3.609369201660156, "indexer_kl": 0.0, "lr": 0.001812201273142031, "tokens_per_s": 2364787.954447432 }, { "step": 8650, "loss": 3.6126895141601563, "indexer_kl": 0.0, "lr": 0.0018100665477447, "tokens_per_s": 2364796.1173172467 }, { "step": 8700, "loss": 3.6114541625976564, "indexer_kl": 0.0, "lr": 0.0018079211882615137, "tokens_per_s": 2364799.497019427 }, { "step": 8750, "loss": 3.615689392089844, "indexer_kl": 0.0, "lr": 0.0018057652268217662, "tokens_per_s": 2364801.4833473475 }, { "step": 8800, "loss": 3.6078955078125, "indexer_kl": 0.0, "lr": 0.0018035986957135285, "tokens_per_s": 2364801.5451914654 }, { "step": 8850, "loss": 3.615896911621094, "indexer_kl": 0.0, "lr": 0.0018014216273831642, "tokens_per_s": 2364801.330477557 }, { "step": 8900, "loss": 3.616408386230469, "indexer_kl": 0.0, "lr": 0.0017992340544348456, "tokens_per_s": 2364747.51629173 }, { "step": 8950, "loss": 3.5964016723632812, "indexer_kl": 0.0, "lr": 0.001797036009630063, "tokens_per_s": 2364738.544006515 }, { "step": 9000, "loss": 3.620291442871094, "indexer_kl": 0.0, "lr": 0.0017948275258871352, "tokens_per_s": 2364700.1151752463 }, { "step": 9050, "loss": 3.613389587402344, "indexer_kl": 0.0, "lr": 0.0017926086362807171, "tokens_per_s": 2364703.3907696293 }, { "step": 9100, "loss": 3.607340087890625, "indexer_kl": 0.0, "lr": 0.0017903793740413037, "tokens_per_s": 2364704.4127704375 }, { "step": 9150, "loss": 3.60697998046875, "indexer_kl": 0.0, "lr": 0.001788139772554731, "tokens_per_s": 2364709.2713567335 }, { "step": 9200, "loss": 3.604131164550781, "indexer_kl": 0.0, "lr": 0.001785889865361679, "tokens_per_s": 2364712.5234107664 }, { "step": 9250, "loss": 3.5959896850585937, "indexer_kl": 0.0, "lr": 0.0017836296861571672, "tokens_per_s": 2364712.9252684885 }, { "step": 9300, "loss": 3.5956317138671876, "indexer_kl": 0.0, "lr": 0.0017813592687900511, "tokens_per_s": 2364718.972221969 }, { "step": 9350, "loss": 3.6035455322265624, "indexer_kl": 0.0, "lr": 0.0017790786472625141, "tokens_per_s": 2364722.7990874248 }, { "step": 9400, "loss": 3.610584411621094, "indexer_kl": 0.0, "lr": 0.0017767878557295594, "tokens_per_s": 2364732.001497261 }, { "step": 9450, "loss": 3.604847717285156, "indexer_kl": 0.0, "lr": 0.0017744869284984975, "tokens_per_s": 2364738.4658819544 }, { "step": 9500, "loss": 3.593907775878906, "indexer_kl": 0.0, "lr": 0.0017721759000284341, "tokens_per_s": 2364731.933761791 }, { "step": 9550, "loss": 3.595683898925781, "indexer_kl": 0.0, "lr": 0.001769854804929752, "tokens_per_s": 2364726.5948169352 }, { "step": 9600, "loss": 3.5920730590820313, "indexer_kl": 0.0, "lr": 0.0017675236779635935, "tokens_per_s": 2364732.404277861 }, { "step": 9650, "loss": 3.6064910888671875, "indexer_kl": 0.0, "lr": 0.0017651825540413405, "tokens_per_s": 2364695.9690775853 }, { "step": 9700, "loss": 3.59421875, "indexer_kl": 0.0, "lr": 0.0017628314682240909, "tokens_per_s": 2364701.7728992705 }, { "step": 9750, "loss": 3.5996664428710936, "indexer_kl": 0.0, "lr": 0.0017604704557221342, "tokens_per_s": 2364706.977524667 }, { "step": 9800, "loss": 3.602231750488281, "indexer_kl": 0.0, "lr": 0.001758099551894423, "tokens_per_s": 2364712.214864954 }, { "step": 9850, "loss": 3.6064202880859373, "indexer_kl": 0.0, "lr": 0.0017557187922480444, "tokens_per_s": 2364670.4103628304 }, { "step": 9900, "loss": 3.590587158203125, "indexer_kl": 0.0, "lr": 0.0017533282124376885, "tokens_per_s": 2364673.447817483 }, { "step": 9950, "loss": 3.593367004394531, "indexer_kl": 0.0, "lr": 0.0017509278482651137, "tokens_per_s": 2364673.7560565863 }, { "step": 10000, "loss": 3.5957794189453125, "indexer_kl": 0.0, "lr": 0.00174851773567861, "tokens_per_s": 2364678.08902054 }, { "step": 10050, "loss": 3.5963470458984377, "indexer_kl": 0.0, "lr": 0.0017460979107724634, "tokens_per_s": 2364676.638449722 }, { "step": 10100, "loss": 3.5905441284179687, "indexer_kl": 0.0, "lr": 0.0017436684097864106, "tokens_per_s": 2364635.8338883487 }, { "step": 10150, "loss": 3.5904031372070313, "indexer_kl": 0.0, "lr": 0.0017412292691051019, "tokens_per_s": 2364634.835614576 }, { "step": 10200, "loss": 3.5910330200195313, "indexer_kl": 0.0, "lr": 0.0017387805252575515, "tokens_per_s": 2364634.9346806556 }, { "step": 10250, "loss": 3.5820733642578126, "indexer_kl": 0.0, "lr": 0.0017363222149165928, "tokens_per_s": 2364635.7392843124 }, { "step": 10300, "loss": 3.5871868896484376, "indexer_kl": 0.0, "lr": 0.0017338543748983291, "tokens_per_s": 2364637.2128197337 }, { "step": 10350, "loss": 3.5957821655273436, "indexer_kl": 0.0, "lr": 0.0017313770421615818, "tokens_per_s": 2364636.6176309437 }, { "step": 10400, "loss": 3.5816354370117187, "indexer_kl": 0.0, "lr": 0.0017288902538073365, "tokens_per_s": 2364633.6862561074 }, { "step": 10450, "loss": 3.5896295166015624, "indexer_kl": 0.0, "lr": 0.0017263940470781888, "tokens_per_s": 2364596.305752937 }, { "step": 10500, "loss": 3.5917376708984374, "indexer_kl": 0.0, "lr": 0.0017238884593577845, "tokens_per_s": 2364594.1367804054 }, { "step": 10550, "loss": 3.582034912109375, "indexer_kl": 0.0, "lr": 0.001721373528170261, "tokens_per_s": 2364595.302064731 }, { "step": 10600, "loss": 3.5925473022460936, "indexer_kl": 0.0, "lr": 0.0017188492911796862, "tokens_per_s": 2364597.3314079526 }, { "step": 10650, "loss": 3.594691162109375, "indexer_kl": 0.0, "lr": 0.0017163157861894926, "tokens_per_s": 2364574.474201118 }, { "step": 10700, "loss": 3.585426025390625, "indexer_kl": 0.0, "lr": 0.0017137730511419117, "tokens_per_s": 2364575.646574995 }, { "step": 10750, "loss": 3.5925192260742187, "indexer_kl": 0.0, "lr": 0.0017112211241174066, "tokens_per_s": 2364556.3072662908 }, { "step": 10800, "loss": 3.588118896484375, "indexer_kl": 0.0, "lr": 0.0017086600433341011, "tokens_per_s": 2364558.2057752106 }, { "step": 10850, "loss": 3.5715011596679687, "indexer_kl": 0.0, "lr": 0.0017060898471472064, "tokens_per_s": 2364561.5315569006 }, { "step": 10900, "loss": 3.5959091186523438, "indexer_kl": 0.0, "lr": 0.001703510574048449, "tokens_per_s": 2364527.3759424533 }, { "step": 10950, "loss": 3.5825439453125, "indexer_kl": 0.0, "lr": 0.0017009222626654923, "tokens_per_s": 2364529.764392938 }, { "step": 11000, "loss": 3.5883978271484374, "indexer_kl": 0.0, "lr": 0.0016983249517613585, "tokens_per_s": 2364535.723304881 }, { "step": 11050, "loss": 3.5922412109375, "indexer_kl": 0.0, "lr": 0.0016957186802338483, "tokens_per_s": 2364535.21520825 }, { "step": 11100, "loss": 3.5863275146484375, "indexer_kl": 0.0, "lr": 0.0016931034871149587, "tokens_per_s": 2364539.7716639037 }, { "step": 11150, "loss": 3.590816650390625, "indexer_kl": 0.0, "lr": 0.0016904794115702975, "tokens_per_s": 2364543.2754312498 }, { "step": 11200, "loss": 3.575264587402344, "indexer_kl": 0.0, "lr": 0.001687846492898498, "tokens_per_s": 2364520.1049385443 }, { "step": 11250, "loss": 3.5897125244140624, "indexer_kl": 0.0, "lr": 0.0016852047705306296, "tokens_per_s": 2364519.0967425047 }, { "step": 11300, "loss": 3.5808901977539063, "indexer_kl": 0.0, "lr": 0.0016825542840296064, "tokens_per_s": 2364519.535052073 }, { "step": 11350, "loss": 3.588467712402344, "indexer_kl": 0.0, "lr": 0.0016798950730895974, "tokens_per_s": 2364519.1260418473 }, { "step": 11400, "loss": 3.572989807128906, "indexer_kl": 0.0, "lr": 0.0016772271775354298, "tokens_per_s": 2364523.05739595 }, { "step": 11450, "loss": 3.58401123046875, "indexer_kl": 0.0, "lr": 0.0016745506373219924, "tokens_per_s": 2364492.2628333867 }, { "step": 11500, "loss": 3.5739675903320314, "indexer_kl": 0.0, "lr": 0.0016718654925336385, "tokens_per_s": 2364455.9547486575 }, { "step": 11550, "loss": 3.5822259521484376, "indexer_kl": 0.0, "lr": 0.0016691717833835858, "tokens_per_s": 2364461.6978353625 }, { "step": 11600, "loss": 3.5779901123046876, "indexer_kl": 0.0, "lr": 0.0016664695502133125, "tokens_per_s": 2364463.6275863596 }, { "step": 11650, "loss": 3.5769583129882814, "indexer_kl": 0.0, "lr": 0.0016637588334919543, "tokens_per_s": 2364464.1999847554 }, { "step": 11700, "loss": 3.5774386596679686, "indexer_kl": 0.0, "lr": 0.0016610396738156983, "tokens_per_s": 2364430.4365166263 }, { "step": 11750, "loss": 3.5856033325195313, "indexer_kl": 0.0, "lr": 0.0016583121119071748, "tokens_per_s": 2364432.670778018 }, { "step": 11800, "loss": 3.578681640625, "indexer_kl": 0.0, "lr": 0.0016555761886148472, "tokens_per_s": 2364433.2199775204 }, { "step": 11850, "loss": 3.5592086791992186, "indexer_kl": 0.0, "lr": 0.0016528319449124005, "tokens_per_s": 2364432.5059148963 }, { "step": 11900, "loss": 3.55782470703125, "indexer_kl": 0.0, "lr": 0.0016500794218981282, "tokens_per_s": 2364430.3394244346 }, { "step": 11950, "loss": 3.5758621215820314, "indexer_kl": 0.0, "lr": 0.0016473186607943162, "tokens_per_s": 2364428.2591451653 }, { "step": 12000, "loss": 3.5809661865234377, "indexer_kl": 0.0, "lr": 0.0016445497029466244, "tokens_per_s": 2364432.559807022 }, { "step": 12050, "loss": 3.5732562255859377, "indexer_kl": 0.0, "lr": 0.0016417725898234701, "tokens_per_s": 2364409.797328372 }, { "step": 12100, "loss": 3.5762158203125, "indexer_kl": 0.0, "lr": 0.001638987363015405, "tokens_per_s": 2364411.848270312 }, { "step": 12150, "loss": 3.5660626220703127, "indexer_kl": 0.0, "lr": 0.0016361940642344926, "tokens_per_s": 2364415.7950529377 }, { "step": 12200, "loss": 3.571099853515625, "indexer_kl": 0.0, "lr": 0.001633392735313683, "tokens_per_s": 2364423.868247423 }, { "step": 12250, "loss": 3.5705807495117186, "indexer_kl": 0.0, "lr": 0.0016305834182061892, "tokens_per_s": 2364429.568932023 }, { "step": 12300, "loss": 3.56845947265625, "indexer_kl": 0.0, "lr": 0.0016277661549848551, "tokens_per_s": 2364440.1022981284 }, { "step": 12350, "loss": 3.5802548217773436, "indexer_kl": 0.0, "lr": 0.0016249409878415272, "tokens_per_s": 2364447.076718962 }, { "step": 12400, "loss": 3.577550048828125, "indexer_kl": 0.0, "lr": 0.001622107959086423, "tokens_per_s": 2364451.8976514465 }, { "step": 12450, "loss": 3.572491455078125, "indexer_kl": 0.0, "lr": 0.0016192671111474966, "tokens_per_s": 2364424.676425467 }, { "step": 12500, "loss": 3.576234130859375, "indexer_kl": 0.0, "lr": 0.001616418486569804, "tokens_per_s": 2364427.463499286 }, { "step": 12550, "loss": 3.574979553222656, "indexer_kl": 0.0, "lr": 0.0016135621280148657, "tokens_per_s": 2364434.063741631 }, { "step": 12600, "loss": 3.56525390625, "indexer_kl": 0.0, "lr": 0.0016106980782600265, "tokens_per_s": 2364405.9249353437 }, { "step": 12650, "loss": 3.5671127319335936, "indexer_kl": 0.0, "lr": 0.0016078263801978172, "tokens_per_s": 2364382.9587971363 }, { "step": 12700, "loss": 3.5707806396484374, "indexer_kl": 0.0, "lr": 0.0016049470768353107, "tokens_per_s": 2364391.30013632 }, { "step": 12750, "loss": 3.5693258666992187, "indexer_kl": 0.0, "lr": 0.0016020602112934781, "tokens_per_s": 2364399.6781987003 }, { "step": 12800, "loss": 3.5557077026367185, "indexer_kl": 0.0, "lr": 0.0015991658268065432, "tokens_per_s": 2364407.480301528 }, { "step": 12850, "loss": 3.5649639892578127, "indexer_kl": 0.0, "lr": 0.0015962639667213353, "tokens_per_s": 2364412.077402423 }, { "step": 12900, "loss": 3.5791412353515626, "indexer_kl": 0.0, "lr": 0.0015933546744966384, "tokens_per_s": 2364417.1097591957 }, { "step": 12950, "loss": 3.5680227661132813, "indexer_kl": 0.0, "lr": 0.0015904379937025427, "tokens_per_s": 2364421.2782368273 }, { "step": 13000, "loss": 3.5711679077148437, "indexer_kl": 0.0, "lr": 0.0015875139680197907, "tokens_per_s": 2364425.2561305296 }, { "step": 13050, "loss": 3.5824591064453126, "indexer_kl": 0.0, "lr": 0.0015845826412391234, "tokens_per_s": 2364427.813388818 }, { "step": 13100, "loss": 3.5715289306640625, "indexer_kl": 0.0, "lr": 0.0015816440572606236, "tokens_per_s": 2364433.4582793736 }, { "step": 13150, "loss": 3.5651315307617186, "indexer_kl": 0.0, "lr": 0.0015786982600930605, "tokens_per_s": 2364437.9961783206 }, { "step": 13200, "loss": 3.561279602050781, "indexer_kl": 0.0, "lr": 0.0015757452938532281, "tokens_per_s": 2364443.752893853 }, { "step": 13250, "loss": 3.5546798706054688, "indexer_kl": 0.0, "lr": 0.0015727852027652867, "tokens_per_s": 2364448.9422484897 }, { "step": 13300, "loss": 3.5681298828125, "indexer_kl": 0.0, "lr": 0.001569818031160099, "tokens_per_s": 2364455.191608724 }, { "step": 13350, "loss": 3.5541864013671876, "indexer_kl": 0.0, "lr": 0.0015668438234745668, "tokens_per_s": 2364460.423210999 }, { "step": 13400, "loss": 3.568317565917969, "indexer_kl": 0.0, "lr": 0.0015638626242509659, "tokens_per_s": 2364464.444034929 }, { "step": 13450, "loss": 3.568704833984375, "indexer_kl": 0.0, "lr": 0.0015608744781362785, "tokens_per_s": 2364479.030401394 }, { "step": 13500, "loss": 3.5567755126953124, "indexer_kl": 0.0, "lr": 0.0015578794298815246, "tokens_per_s": 2364481.560487746 }, { "step": 13550, "loss": 3.5615283203125, "indexer_kl": 0.0, "lr": 0.0015548775243410921, "tokens_per_s": 2364485.0806097663 }, { "step": 13600, "loss": 3.544371337890625, "indexer_kl": 0.0, "lr": 0.0015518688064720646, "tokens_per_s": 2364469.432204897 }, { "step": 13650, "loss": 3.560160827636719, "indexer_kl": 0.0, "lr": 0.0015488533213335485, "tokens_per_s": 2364470.992164751 }, { "step": 13700, "loss": 3.552525939941406, "indexer_kl": 0.0, "lr": 0.0015458311140859981, "tokens_per_s": 2364490.2313127085 }, { "step": 13750, "loss": 3.5629592895507813, "indexer_kl": 0.0, "lr": 0.0015428022299905394, "tokens_per_s": 2364502.4869046756 }, { "step": 13800, "loss": 3.5404953002929687, "indexer_kl": 0.0, "lr": 0.0015397667144082918, "tokens_per_s": 2364521.893583951 }, { "step": 13850, "loss": 3.551219787597656, "indexer_kl": 0.0, "lr": 0.0015367246127996888, "tokens_per_s": 2364538.983012529 }, { "step": 13900, "loss": 3.570863952636719, "indexer_kl": 0.0, "lr": 0.0015336759707237984, "tokens_per_s": 2364554.2795850597 }, { "step": 13950, "loss": 3.5488177490234376, "indexer_kl": 0.0, "lr": 0.0015306208338376384, "tokens_per_s": 2364565.8058795147 }, { "step": 14000, "loss": 3.5605899047851564, "indexer_kl": 0.0, "lr": 0.0015275592478954955, "tokens_per_s": 2364577.9880337077 }, { "step": 14050, "loss": 3.545021667480469, "indexer_kl": 0.0, "lr": 0.0015244912587482377, "tokens_per_s": 2364589.5218769177 }, { "step": 14100, "loss": 3.5545281982421875, "indexer_kl": 0.0, "lr": 0.0015214169123426292, "tokens_per_s": 2364602.366656633 }, { "step": 14150, "loss": 3.549293212890625, "indexer_kl": 0.0, "lr": 0.0015183362547206405, "tokens_per_s": 2364609.642766092 }, { "step": 14200, "loss": 3.547585754394531, "indexer_kl": 0.0, "lr": 0.001515249332018762, "tokens_per_s": 2364628.2302917093 }, { "step": 14250, "loss": 3.55408935546875, "indexer_kl": 0.0, "lr": 0.0015121561904673092, "tokens_per_s": 2364638.7583765243 }, { "step": 14300, "loss": 3.5476739501953123, "indexer_kl": 0.0, "lr": 0.001509056876389733, "tokens_per_s": 2364647.6045392696 }, { "step": 14350, "loss": 3.55639404296875, "indexer_kl": 0.0, "lr": 0.001505951436201925, "tokens_per_s": 2364651.947412489 }, { "step": 14400, "loss": 3.55270751953125, "indexer_kl": 0.0, "lr": 0.0015028399164115232, "tokens_per_s": 2364654.6101718904 }, { "step": 14450, "loss": 3.553960876464844, "indexer_kl": 0.0, "lr": 0.0014997223636172138, "tokens_per_s": 2364638.398179981 }, { "step": 14500, "loss": 3.5518014526367185, "indexer_kl": 0.0, "lr": 0.001496598824508035, "tokens_per_s": 2364642.7278394364 }, { "step": 14550, "loss": 3.5458859252929686, "indexer_kl": 0.0, "lr": 0.0014934693458626771, "tokens_per_s": 2364650.165037217 }, { "step": 14600, "loss": 3.55221435546875, "indexer_kl": 0.0, "lr": 0.0014903339745487819, "tokens_per_s": 2364655.1400107215 }, { "step": 14650, "loss": 3.5402435302734374, "indexer_kl": 0.0, "lr": 0.0014871927575222403, "tokens_per_s": 2364660.27173962 }, { "step": 14700, "loss": 3.5534176635742187, "indexer_kl": 0.0, "lr": 0.0014840457418264913, "tokens_per_s": 2364665.123181983 }, { "step": 14750, "loss": 3.5538287353515625, "indexer_kl": 0.0, "lr": 0.0014808929745918139, "tokens_per_s": 2364671.626147072 }, { "step": 14800, "loss": 3.5455078125, "indexer_kl": 0.0, "lr": 0.0014777345030346238, "tokens_per_s": 2364677.4822645457 }, { "step": 14850, "loss": 3.559847412109375, "indexer_kl": 0.0, "lr": 0.001474570374456767, "tokens_per_s": 2364681.430472998 }, { "step": 14900, "loss": 3.542239074707031, "indexer_kl": 0.0, "lr": 0.0014714006362448076, "tokens_per_s": 2364683.9050042424 }, { "step": 14950, "loss": 3.5535177612304687, "indexer_kl": 0.0, "lr": 0.0014682253358693229, "tokens_per_s": 2364688.962857593 }, { "step": 15000, "loss": 3.5480502319335936, "indexer_kl": 0.0, "lr": 0.001465044520884189, "tokens_per_s": 2364692.164302681 }, { "step": 15050, "loss": 3.5443096923828126, "indexer_kl": 0.0, "lr": 0.0014618582389258703, "tokens_per_s": 2364694.8020099634 }, { "step": 15100, "loss": 3.5397885131835936, "indexer_kl": 0.0, "lr": 0.0014586665377127048, "tokens_per_s": 2364699.6622133255 }, { "step": 15150, "loss": 3.5456619262695312, "indexer_kl": 0.0, "lr": 0.0014554694650441916, "tokens_per_s": 2364702.3293950935 }, { "step": 15200, "loss": 3.5523635864257814, "indexer_kl": 0.0, "lr": 0.0014522670688002718, "tokens_per_s": 2364706.279914898 }, { "step": 15250, "loss": 3.5431146240234375, "indexer_kl": 0.0, "lr": 0.0014490593969406153, "tokens_per_s": 2364714.814753194 }, { "step": 15300, "loss": 3.540928955078125, "indexer_kl": 0.0, "lr": 0.001445846497503899, "tokens_per_s": 2364719.891805239 }, { "step": 15350, "loss": 3.5598834228515623, "indexer_kl": 0.0, "lr": 0.0014426284186070902, "tokens_per_s": 2364722.977900558 }, { "step": 15400, "loss": 3.545151672363281, "indexer_kl": 0.0, "lr": 0.0014394052084447237, "tokens_per_s": 2364724.957226373 }, { "step": 15450, "loss": 3.553248291015625, "indexer_kl": 0.0, "lr": 0.0014361769152881822, "tokens_per_s": 2364730.9915405395 }, { "step": 15500, "loss": 3.544927673339844, "indexer_kl": 0.0, "lr": 0.0014329435874849705, "tokens_per_s": 2364731.7685276284 }, { "step": 15550, "loss": 3.54208740234375, "indexer_kl": 0.0, "lr": 0.0014297052734579957, "tokens_per_s": 2364737.0426833895 }, { "step": 15600, "loss": 3.5472427368164063, "indexer_kl": 0.0, "lr": 0.0014264620217048366, "tokens_per_s": 2364742.7890357035 }, { "step": 15650, "loss": 3.5483197021484374, "indexer_kl": 0.0, "lr": 0.0014232138807970228, "tokens_per_s": 2364747.675417071 }, { "step": 15700, "loss": 3.539051818847656, "indexer_kl": 0.0, "lr": 0.0014199608993793029, "tokens_per_s": 2364752.8382272706 }, { "step": 15750, "loss": 3.535797424316406, "indexer_kl": 0.0, "lr": 0.0014167031261689196, "tokens_per_s": 2364755.7397135133 }, { "step": 15800, "loss": 3.5343276977539064, "indexer_kl": 0.0, "lr": 0.0014134406099548767, "tokens_per_s": 2364761.737091763 }, { "step": 15850, "loss": 3.5437777709960936, "indexer_kl": 0.0, "lr": 0.001410173399597211, "tokens_per_s": 2364766.6664111284 }, { "step": 15900, "loss": 3.5442266845703125, "indexer_kl": 0.0, "lr": 0.0014069015440262595, "tokens_per_s": 2364769.12687096 }, { "step": 15950, "loss": 3.5477496337890626, "indexer_kl": 0.0, "lr": 0.001403625092241927, "tokens_per_s": 2364772.9120278717 }, { "step": 16000, "loss": 3.5419326782226563, "indexer_kl": 0.0, "lr": 0.0014003440933129515, "tokens_per_s": 2364776.7905186624 }, { "step": 16050, "loss": 3.5443405151367187, "indexer_kl": 0.0, "lr": 0.0013970585963761699, "tokens_per_s": 2364784.5286522578 }, { "step": 16100, "loss": 3.5306256103515623, "indexer_kl": 0.0, "lr": 0.0013937686506357828, "tokens_per_s": 2364789.7690163646 }, { "step": 16150, "loss": 3.5452001953125, "indexer_kl": 0.0, "lr": 0.0013904743053626159, "tokens_per_s": 2364794.646068541 }, { "step": 16200, "loss": 3.523923034667969, "indexer_kl": 0.0, "lr": 0.0013871756098933839, "tokens_per_s": 2364797.7097460437 }, { "step": 16250, "loss": 3.5314926147460937, "indexer_kl": 0.0, "lr": 0.0013838726136299504, "tokens_per_s": 2364800.5509233107 }, { "step": 16300, "loss": 3.5491314697265626, "indexer_kl": 0.0, "lr": 0.001380565366038589, "tokens_per_s": 2364806.742990235 }, { "step": 16350, "loss": 3.534290466308594, "indexer_kl": 0.0, "lr": 0.0013772539166492408, "tokens_per_s": 2364811.4770215373 }, { "step": 16400, "loss": 3.5383270263671873, "indexer_kl": 0.0, "lr": 0.0013739383150547753, "tokens_per_s": 2364813.421591741 }, { "step": 16450, "loss": 3.533769226074219, "indexer_kl": 0.0, "lr": 0.0013706186109102448, "tokens_per_s": 2364818.6985732364 }, { "step": 16500, "loss": 3.5260491943359376, "indexer_kl": 0.0, "lr": 0.0013672948539321435, "tokens_per_s": 2364825.8013639 }, { "step": 16550, "loss": 3.534014892578125, "indexer_kl": 0.0, "lr": 0.0013639670938976603, "tokens_per_s": 2364830.800950062 }, { "step": 16600, "loss": 3.525398864746094, "indexer_kl": 0.0, "lr": 0.0013606353806439352, "tokens_per_s": 2364835.3602667865 }, { "step": 16650, "loss": 3.5152182006835937, "indexer_kl": 0.0, "lr": 0.0013572997640673126, "tokens_per_s": 2364841.0701671243 }, { "step": 16700, "loss": 3.53513916015625, "indexer_kl": 0.0, "lr": 0.0013539602941225932, "tokens_per_s": 2364845.222233505 }, { "step": 16750, "loss": 3.539285888671875, "indexer_kl": 0.0, "lr": 0.0013506170208222867, "tokens_per_s": 2364849.576261172 }, { "step": 16800, "loss": 3.529910888671875, "indexer_kl": 0.0, "lr": 0.0013472699942358624, "tokens_per_s": 2364856.2844932037 }, { "step": 16850, "loss": 3.5255462646484377, "indexer_kl": 0.0, "lr": 0.0013439192644890002, "tokens_per_s": 2364863.580830079 }, { "step": 16900, "loss": 3.52579833984375, "indexer_kl": 0.0, "lr": 0.001340564881762838, "tokens_per_s": 2364868.8949673716 }, { "step": 16950, "loss": 3.527019348144531, "indexer_kl": 0.0, "lr": 0.001337206896293222, "tokens_per_s": 2364872.4108681316 }, { "step": 17000, "loss": 3.520314025878906, "indexer_kl": 0.0, "lr": 0.0013338453583699545, "tokens_per_s": 2364880.2561384174 }, { "step": 17050, "loss": 3.524703369140625, "indexer_kl": 0.0, "lr": 0.0013304803183360387, "tokens_per_s": 2364886.4261683915 }, { "step": 17100, "loss": 3.5166552734375, "indexer_kl": 0.0, "lr": 0.001327111826586927, "tokens_per_s": 2364892.0794548304 }, { "step": 17150, "loss": 3.522206115722656, "indexer_kl": 0.0, "lr": 0.0013237399335697638, "tokens_per_s": 2364896.21763158 }, { "step": 17200, "loss": 3.5350634765625, "indexer_kl": 0.0, "lr": 0.001320364689782634, "tokens_per_s": 2364876.187711476 }, { "step": 17250, "loss": 3.517574462890625, "indexer_kl": 0.0, "lr": 0.0013169861457738023, "tokens_per_s": 2364877.0044874386 }, { "step": 17300, "loss": 3.5157424926757814, "indexer_kl": 0.0, "lr": 0.0013136043521409587, "tokens_per_s": 2364881.3572889385 }, { "step": 17350, "loss": 3.522073059082031, "indexer_kl": 0.0, "lr": 0.0013102193595304601, "tokens_per_s": 2364885.004861621 }, { "step": 17400, "loss": 3.525579528808594, "indexer_kl": 0.0, "lr": 0.001306831218636572, "tokens_per_s": 2364887.674201846 }, { "step": 17450, "loss": 3.5211441040039064, "indexer_kl": 0.0, "lr": 0.0013034399802007092, "tokens_per_s": 2364890.743335755 }, { "step": 17500, "loss": 3.5405035400390625, "indexer_kl": 0.0, "lr": 0.0013000456950106759, "tokens_per_s": 2364893.6569730043 }, { "step": 17550, "loss": 3.5232278442382814, "indexer_kl": 0.0, "lr": 0.0012966484138999042, "tokens_per_s": 2364875.9984877133 }, { "step": 17600, "loss": 3.5264984130859376, "indexer_kl": 0.0, "lr": 0.0012932481877466948, "tokens_per_s": 2364882.018605157 }, { "step": 17650, "loss": 3.520211486816406, "indexer_kl": 0.0, "lr": 0.0012898450674734534, "tokens_per_s": 2364892.7954997197 }, { "step": 17700, "loss": 3.5328128051757814, "indexer_kl": 0.0, "lr": 0.0012864391040459287, "tokens_per_s": 2364894.965392848 }, { "step": 17750, "loss": 3.535531005859375, "indexer_kl": 0.0, "lr": 0.0012830303484724485, "tokens_per_s": 2364875.9310452314 }, { "step": 17800, "loss": 3.511838073730469, "indexer_kl": 0.0, "lr": 0.0012796188518031573, "tokens_per_s": 2364878.4317528186 }, { "step": 17850, "loss": 3.5089761352539064, "indexer_kl": 0.0, "lr": 0.0012762046651292496, "tokens_per_s": 2364884.3425136353 }, { "step": 17900, "loss": 3.5251666259765626, "indexer_kl": 0.0, "lr": 0.0012727878395822065, "tokens_per_s": 2364864.279042975 }, { "step": 17950, "loss": 3.5317181396484374, "indexer_kl": 0.0, "lr": 0.0012693684263330297, "tokens_per_s": 2364838.3461269913 }, { "step": 18000, "loss": 3.530771484375, "indexer_kl": 0.0, "lr": 0.0012659464765914742, "tokens_per_s": 2364838.2739646314 }, { "step": 18050, "loss": 3.5215744018554687, "indexer_kl": 0.0, "lr": 0.0012625220416052816, "tokens_per_s": 2364843.215823321 }, { "step": 18100, "loss": 3.5273776245117188, "indexer_kl": 0.0, "lr": 0.001259095172659414, "tokens_per_s": 2364848.9891788065 }, { "step": 18150, "loss": 3.5221051025390624, "indexer_kl": 0.0, "lr": 0.0012556659210752848, "tokens_per_s": 2364860.3669840097 }, { "step": 18200, "loss": 3.5287545776367186, "indexer_kl": 0.0, "lr": 0.001252234338209989, "tokens_per_s": 2364862.3248299723 }, { "step": 18250, "loss": 3.519761047363281, "indexer_kl": 0.0, "lr": 0.0012488004754555367, "tokens_per_s": 2364866.5893192687 }, { "step": 18300, "loss": 3.5211480712890624, "indexer_kl": 0.0, "lr": 0.0012453643842380818, "tokens_per_s": 2364873.3327986277 }, { "step": 18350, "loss": 3.517532958984375, "indexer_kl": 0.0, "lr": 0.001241926116017151, "tokens_per_s": 2364878.760783681 }, { "step": 18400, "loss": 3.5208819580078123, "indexer_kl": 0.0, "lr": 0.001238485722284875, "tokens_per_s": 2364861.9926373805 }, { "step": 18450, "loss": 3.5243911743164062, "indexer_kl": 0.0, "lr": 0.0012350432545652173, "tokens_per_s": 2364869.567102641 }, { "step": 18500, "loss": 3.524724426269531, "indexer_kl": 0.0, "lr": 0.0012315987644132005, "tokens_per_s": 2364874.8937843316 }, { "step": 18550, "loss": 3.524533996582031, "indexer_kl": 0.0, "lr": 0.001228152303414136, "tokens_per_s": 2364880.8337788237 }, { "step": 18600, "loss": 3.5142147827148436, "indexer_kl": 0.0, "lr": 0.001224703923182851, "tokens_per_s": 2364871.7617013757 }, { "step": 18650, "loss": 3.538498840332031, "indexer_kl": 0.0, "lr": 0.0012212536753629158, "tokens_per_s": 2364878.177148174 }, { "step": 18700, "loss": 3.5136566162109375, "indexer_kl": 0.0, "lr": 0.0012178016116258694, "tokens_per_s": 2364882.0152504235 }, { "step": 18750, "loss": 3.5139193725585938, "indexer_kl": 0.0, "lr": 0.0012143477836704466, "tokens_per_s": 2364888.717880903 }, { "step": 18800, "loss": 3.5139068603515624, "indexer_kl": 0.0, "lr": 0.0012108922432218037, "tokens_per_s": 2364894.0400259187 }, { "step": 18850, "loss": 3.508048095703125, "indexer_kl": 0.0, "lr": 0.0012074350420307434, "tokens_per_s": 2364878.480534247 }, { "step": 18900, "loss": 3.5128903198242187, "indexer_kl": 0.0, "lr": 0.0012039762318729395, "tokens_per_s": 2364873.771399023 }, { "step": 18950, "loss": 3.5089511108398437, "indexer_kl": 0.0, "lr": 0.0012005158645481632, "tokens_per_s": 2364878.406503608 }, { "step": 19000, "loss": 3.528037414550781, "indexer_kl": 0.0, "lr": 0.0011970539918795045, "tokens_per_s": 2364880.7256286745 }, { "step": 19050, "loss": 3.512792053222656, "indexer_kl": 0.0, "lr": 0.0011935906657125992, "tokens_per_s": 2364885.580200913 }, { "step": 19100, "loss": 3.501037292480469, "indexer_kl": 0.0, "lr": 0.00119012593791485, "tokens_per_s": 2364892.075418113 }, { "step": 19150, "loss": 3.5131405639648436, "indexer_kl": 0.0, "lr": 0.0011866598603746514, "tokens_per_s": 2364894.9923606804 }, { "step": 19200, "loss": 3.5143804931640625, "indexer_kl": 0.0, "lr": 0.0011831924850006109, "tokens_per_s": 2364900.506639355 }, { "step": 19250, "loss": 3.515915832519531, "indexer_kl": 0.0, "lr": 0.0011797238637207739, "tokens_per_s": 2364903.186433562 }, { "step": 19300, "loss": 3.5028890991210937, "indexer_kl": 0.0, "lr": 0.001176254048481843, "tokens_per_s": 2364910.4164202646 }, { "step": 19350, "loss": 3.5074734497070312, "indexer_kl": 0.0, "lr": 0.001172783091248404, "tokens_per_s": 2364913.232031024 }, { "step": 19400, "loss": 3.5280422973632812, "indexer_kl": 0.0, "lr": 0.0011693110440021428, "tokens_per_s": 2364915.4486076813 }, { "step": 19450, "loss": 3.505807189941406, "indexer_kl": 0.0, "lr": 0.0011658379587410723, "tokens_per_s": 2364920.377835977 }, { "step": 19500, "loss": 3.5260272216796875, "indexer_kl": 0.0, "lr": 0.0011623638874787483, "tokens_per_s": 2364926.286275528 }, { "step": 19550, "loss": 3.5001876831054686, "indexer_kl": 0.0, "lr": 0.0011588888822434951, "tokens_per_s": 2364931.083519488 }, { "step": 19600, "loss": 3.515910949707031, "indexer_kl": 0.0, "lr": 0.0011554129950776231, "tokens_per_s": 2364937.0383673767 }, { "step": 19650, "loss": 3.515985412597656, "indexer_kl": 0.0, "lr": 0.0011519362780366515, "tokens_per_s": 2364941.28133283 }, { "step": 19700, "loss": 3.4967575073242188, "indexer_kl": 0.0, "lr": 0.001148458783188527, "tokens_per_s": 2364946.099072952 }, { "step": 19750, "loss": 3.5081820678710938, "indexer_kl": 0.0, "lr": 0.001144980562612846, "tokens_per_s": 2364952.433675114 }, { "step": 19800, "loss": 3.4970703125, "indexer_kl": 0.0, "lr": 0.0011415016684000728, "tokens_per_s": 2364968.1166770984 }, { "step": 19850, "loss": 3.4941351318359377, "indexer_kl": 0.0, "lr": 0.0011380221526507595, "tokens_per_s": 2364983.030660471 }, { "step": 19900, "loss": 3.5108740234375, "indexer_kl": 0.0, "lr": 0.0011345420674747685, "tokens_per_s": 2364995.4635757534 }, { "step": 19950, "loss": 3.5072314453125, "indexer_kl": 0.0, "lr": 0.0011310614649904873, "tokens_per_s": 2365002.017832295 }, { "step": 20000, "loss": 3.51745361328125, "indexer_kl": 0.0, "lr": 0.0011275803973240539, "tokens_per_s": 2365012.4462108077 }, { "step": 20050, "loss": 3.504329833984375, "indexer_kl": 0.0, "lr": 0.0011240989166085697, "tokens_per_s": 2365016.182638834 }, { "step": 20100, "loss": 3.5151690673828124, "indexer_kl": 0.0, "lr": 0.0011206170749833249, "tokens_per_s": 2365020.7009266205 }, { "step": 20150, "loss": 3.4942831420898437, "indexer_kl": 0.0, "lr": 0.001117134924593012, "tokens_per_s": 2365029.626689752 }, { "step": 20200, "loss": 3.507962646484375, "indexer_kl": 0.0, "lr": 0.0011136525175869502, "tokens_per_s": 2365032.304347115 }, { "step": 20250, "loss": 3.51506591796875, "indexer_kl": 0.0, "lr": 0.0011101699061183, "tokens_per_s": 2365031.6272615152 }, { "step": 20300, "loss": 3.5123248291015625, "indexer_kl": 0.0, "lr": 0.001106687142343285, "tokens_per_s": 2365041.1432089433 }, { "step": 20350, "loss": 3.496890869140625, "indexer_kl": 0.0, "lr": 0.001103204278420409, "tokens_per_s": 2365053.1443374334 }, { "step": 20400, "loss": 3.499667053222656, "indexer_kl": 0.0, "lr": 0.0010997213665096762, "tokens_per_s": 2365062.1966494224 }, { "step": 20450, "loss": 3.5097500610351564, "indexer_kl": 0.0, "lr": 0.0010962384587718088, "tokens_per_s": 2365071.488692376 }, { "step": 20500, "loss": 3.513338928222656, "indexer_kl": 0.0, "lr": 0.0010927556073674681, "tokens_per_s": 2365081.528281334 }, { "step": 20550, "loss": 3.4938507080078125, "indexer_kl": 0.0, "lr": 0.00108927286445647, "tokens_per_s": 2365098.0389152593 }, { "step": 20600, "loss": 3.492110595703125, "indexer_kl": 0.0, "lr": 0.001085790282197006, "tokens_per_s": 2365082.559409871 }, { "step": 20650, "loss": 3.4954425048828126, "indexer_kl": 0.0, "lr": 0.001082307912744862, "tokens_per_s": 2365087.6102032447 }, { "step": 20700, "loss": 3.502156982421875, "indexer_kl": 0.0, "lr": 0.0010788258082526365, "tokens_per_s": 2365097.360624905 }, { "step": 20750, "loss": 3.498072204589844, "indexer_kl": 0.0, "lr": 0.001075344020868961, "tokens_per_s": 2365102.8156782715 }, { "step": 20800, "loss": 3.4985757446289063, "indexer_kl": 0.0, "lr": 0.0010718626027377163, "tokens_per_s": 2365104.9833335066 }, { "step": 20850, "loss": 3.499417724609375, "indexer_kl": 0.0, "lr": 0.0010683816059972543, "tokens_per_s": 2365107.0221733153 }, { "step": 20900, "loss": 3.5071295166015624, "indexer_kl": 0.0, "lr": 0.0010649010827796152, "tokens_per_s": 2365112.2981638694 }, { "step": 20950, "loss": 3.510190124511719, "indexer_kl": 0.0, "lr": 0.0010614210852097493, "tokens_per_s": 2365117.6746237013 }, { "step": 21000, "loss": 3.494609680175781, "indexer_kl": 0.0, "lr": 0.0010579416654047321, "tokens_per_s": 2365120.380634972 }, { "step": 21050, "loss": 3.5057772827148437, "indexer_kl": 0.0, "lr": 0.0010544628754729892, "tokens_per_s": 2365123.228477729 }, { "step": 21100, "loss": 3.4850814819335936, "indexer_kl": 0.0, "lr": 0.001050984767513511, "tokens_per_s": 2365127.418225456 }, { "step": 21150, "loss": 3.4918231201171874, "indexer_kl": 0.0, "lr": 0.0010475073936150757, "tokens_per_s": 2365130.3912156676 }, { "step": 21200, "loss": 3.4890936279296874, "indexer_kl": 0.0, "lr": 0.0010440308058554677, "tokens_per_s": 2365135.1113264393 }, { "step": 21250, "loss": 3.4873672485351563, "indexer_kl": 0.0, "lr": 0.0010405550563006977, "tokens_per_s": 2365144.800618524 }, { "step": 21300, "loss": 3.489290771484375, "indexer_kl": 0.0, "lr": 0.0010370801970042238, "tokens_per_s": 2365127.8646931723 }, { "step": 21350, "loss": 3.49572265625, "indexer_kl": 0.0, "lr": 0.0010336062800061715, "tokens_per_s": 2365131.6374158803 }, { "step": 21400, "loss": 3.4981134033203123, "indexer_kl": 0.0, "lr": 0.0010301333573325543, "tokens_per_s": 2365135.4990275768 }, { "step": 21450, "loss": 3.4998342895507815, "indexer_kl": 0.0, "lr": 0.0010266614809944933, "tokens_per_s": 2365141.128807853 }, { "step": 21500, "loss": 3.5064056396484373, "indexer_kl": 0.0, "lr": 0.001023190702987441, "tokens_per_s": 2365145.4287326112 }, { "step": 21550, "loss": 3.492300720214844, "indexer_kl": 0.0, "lr": 0.0010197210752904006, "tokens_per_s": 2365149.0967849847 }, { "step": 21600, "loss": 3.5137738037109374, "indexer_kl": 0.0, "lr": 0.0010162526498651478, "tokens_per_s": 2365152.605914789 }, { "step": 21650, "loss": 3.4962158203125, "indexer_kl": 0.0, "lr": 0.0010127854786554534, "tokens_per_s": 2365157.377229596 }, { "step": 21700, "loss": 3.498583984375, "indexer_kl": 0.0, "lr": 0.001009319613586304, "tokens_per_s": 2365161.3925709836 }, { "step": 21750, "loss": 3.4964617919921874, "indexer_kl": 0.0, "lr": 0.0010058551065631259, "tokens_per_s": 2365164.3714531697 }, { "step": 21800, "loss": 3.5001953125, "indexer_kl": 0.0, "lr": 0.001002392009471007, "tokens_per_s": 2365149.9146819296 }, { "step": 21850, "loss": 3.4949246215820313, "indexer_kl": 0.0, "lr": 0.0009989303741739196, "tokens_per_s": 2365147.552603776 }, { "step": 21900, "loss": 3.490021057128906, "indexer_kl": 0.0, "lr": 0.0009954702525139434, "tokens_per_s": 2365149.3507257006 }, { "step": 21950, "loss": 3.483595886230469, "indexer_kl": 0.0, "lr": 0.0009920116963104905, "tokens_per_s": 2365141.1399939028 }, { "step": 22000, "loss": 3.50059326171875, "indexer_kl": 0.0, "lr": 0.0009885547573595288, "tokens_per_s": 2365143.0345424507 }, { "step": 22050, "loss": 3.4934783935546876, "indexer_kl": 0.0, "lr": 0.0009850994874328045, "tokens_per_s": 2365146.277819875 }, { "step": 22100, "loss": 3.48314453125, "indexer_kl": 0.0, "lr": 0.0009816459382770686, "tokens_per_s": 2365148.940419964 }, { "step": 22150, "loss": 3.4878802490234375, "indexer_kl": 0.0, "lr": 0.000978194161613302, "tokens_per_s": 2365152.5869468143 }, { "step": 22200, "loss": 3.4946859741210936, "indexer_kl": 0.0, "lr": 0.0009747442091359414, "tokens_per_s": 2365155.510589731 }, { "step": 22250, "loss": 3.4716452026367186, "indexer_kl": 0.0, "lr": 0.0009712961325121013, "tokens_per_s": 2365157.9796332642 }, { "step": 22300, "loss": 3.488453063964844, "indexer_kl": 0.0, "lr": 0.0009678499833808058, "tokens_per_s": 2365161.9439956285 }, { "step": 22350, "loss": 3.499755859375, "indexer_kl": 0.0, "lr": 0.0009644058133522111, "tokens_per_s": 2365153.1417279434 }, { "step": 22400, "loss": 3.48358642578125, "indexer_kl": 0.0, "lr": 0.000960963674006835, "tokens_per_s": 2365144.7894656383 }, { "step": 22450, "loss": 3.49045166015625, "indexer_kl": 0.0, "lr": 0.0009575236168947821, "tokens_per_s": 2365148.0846652514 }, { "step": 22500, "loss": 3.4919366455078125, "indexer_kl": 0.0, "lr": 0.0009540856935349742, "tokens_per_s": 2365152.677317971 }, { "step": 22550, "loss": 3.4869140625, "indexer_kl": 0.0, "lr": 0.0009506499554143771, "tokens_per_s": 2365140.1160172853 }, { "step": 22600, "loss": 3.48158447265625, "indexer_kl": 0.0, "lr": 0.0009472164539872306, "tokens_per_s": 2365145.5019593644 }, { "step": 22650, "loss": 3.492267761230469, "indexer_kl": 0.0, "lr": 0.0009437852406742765, "tokens_per_s": 2365149.032441779 }, { "step": 22700, "loss": 3.4897137451171876, "indexer_kl": 0.0, "lr": 0.0009403563668619898, "tokens_per_s": 2365152.408722476 }, { "step": 22750, "loss": 3.4833782958984374, "indexer_kl": 0.0, "lr": 0.0009369298839018095, "tokens_per_s": 2365157.3672195836 }, { "step": 22800, "loss": 3.4793621826171877, "indexer_kl": 0.0, "lr": 0.0009335058431093672, "tokens_per_s": 2365143.5052113114 }, { "step": 22850, "loss": 3.482807922363281, "indexer_kl": 0.0, "lr": 0.0009300842957637219, "tokens_per_s": 2365150.1001891615 }, { "step": 22900, "loss": 3.4970632934570314, "indexer_kl": 0.0, "lr": 0.0009266652931065886, "tokens_per_s": 2365141.7651429456 }, { "step": 22950, "loss": 3.4861151123046876, "indexer_kl": 0.0, "lr": 0.000923248886341574, "tokens_per_s": 2365128.26673146 }, { "step": 23000, "loss": 3.4910540771484375, "indexer_kl": 0.0, "lr": 0.0009198351266334068, "tokens_per_s": 2365130.112772416 }, { "step": 23050, "loss": 3.494971923828125, "indexer_kl": 0.0, "lr": 0.000916424065107175, "tokens_per_s": 2365132.2450996027 }, { "step": 23100, "loss": 3.482679443359375, "indexer_kl": 0.0, "lr": 0.0009130157528475551, "tokens_per_s": 2365135.551045869 }, { "step": 23150, "loss": 3.4744677734375, "indexer_kl": 0.0, "lr": 0.0009096102408980536, "tokens_per_s": 2365140.688764926 }, { "step": 23200, "loss": 3.4877804565429686, "indexer_kl": 0.0, "lr": 0.0009062075802602356, "tokens_per_s": 2365143.9424045538 }, { "step": 23250, "loss": 3.4820846557617187, "indexer_kl": 0.0, "lr": 0.000902807821892968, "tokens_per_s": 2365146.369787122 }, { "step": 23300, "loss": 3.4879183959960938, "indexer_kl": 0.0, "lr": 0.0008994110167116493, "tokens_per_s": 2365151.2905520666 }, { "step": 23350, "loss": 3.473363037109375, "indexer_kl": 0.0, "lr": 0.0008960172155874529, "tokens_per_s": 2365154.7562719556 }, { "step": 23400, "loss": 3.4754608154296873, "indexer_kl": 0.0, "lr": 0.0008926264693465616, "tokens_per_s": 2365157.3688098737 }, { "step": 23450, "loss": 3.4725552368164063, "indexer_kl": 0.0, "lr": 0.0008892388287694093, "tokens_per_s": 2365163.031946918 }, { "step": 23500, "loss": 3.47448486328125, "indexer_kl": 0.0, "lr": 0.0008858543445899165, "tokens_per_s": 2365167.443606251 }, { "step": 23550, "loss": 3.477320556640625, "indexer_kl": 0.0, "lr": 0.0008824730674947352, "tokens_per_s": 2365172.0301208515 }, { "step": 23600, "loss": 3.481239929199219, "indexer_kl": 0.0, "lr": 0.0008790950481224862, "tokens_per_s": 2365176.0050831535 }, { "step": 23650, "loss": 3.4881295776367187, "indexer_kl": 0.0, "lr": 0.0008757203370630027, "tokens_per_s": 2365179.826716569 }, { "step": 23700, "loss": 3.467179260253906, "indexer_kl": 0.0, "lr": 0.0008723489848565711, "tokens_per_s": 2365184.512691456 }, { "step": 23750, "loss": 3.47642822265625, "indexer_kl": 0.0, "lr": 0.0008689810419931765, "tokens_per_s": 2365188.737938442 }, { "step": 23800, "loss": 3.484112548828125, "indexer_kl": 0.0, "lr": 0.0008656165589117438, "tokens_per_s": 2365191.8543415726 }, { "step": 23850, "loss": 3.4794451904296877, "indexer_kl": 0.0, "lr": 0.0008622555859993841, "tokens_per_s": 2365197.1034725895 }, { "step": 23900, "loss": 3.4725830078125, "indexer_kl": 0.0, "lr": 0.0008588981735906391, "tokens_per_s": 2365200.025864046 }, { "step": 23950, "loss": 3.476612854003906, "indexer_kl": 0.0, "lr": 0.0008555443719667287, "tokens_per_s": 2365203.382463012 }, { "step": 24000, "loss": 3.465234680175781, "indexer_kl": 0.0, "lr": 0.0008521942313547959, "tokens_per_s": 2365190.6350007704 }, { "step": 24050, "loss": 3.4822317504882814, "indexer_kl": 0.0, "lr": 0.0008488478019271566, "tokens_per_s": 2365194.6097968807 }, { "step": 24100, "loss": 3.479034423828125, "indexer_kl": 0.0, "lr": 0.0008455051338005468, "tokens_per_s": 2365198.01189677 }, { "step": 24150, "loss": 3.479100646972656, "indexer_kl": 0.0, "lr": 0.0008421662770353726, "tokens_per_s": 2365202.2100466276 }, { "step": 24200, "loss": 3.466640625, "indexer_kl": 0.0, "lr": 0.0008388312816349609, "tokens_per_s": 2365207.303601703 }, { "step": 24250, "loss": 3.4698468017578126, "indexer_kl": 0.0, "lr": 0.0008355001975448098, "tokens_per_s": 2365211.1810901063 }, { "step": 24300, "loss": 3.4776907348632813, "indexer_kl": 0.0, "lr": 0.0008321730746518408, "tokens_per_s": 2365214.3949524914 }, { "step": 24350, "loss": 3.486700134277344, "indexer_kl": 0.0, "lr": 0.0008288499627836516, "tokens_per_s": 2365218.434770441 }, { "step": 24400, "loss": 3.4796820068359375, "indexer_kl": 0.0, "lr": 0.0008255309117077709, "tokens_per_s": 2365219.6232457757 }, { "step": 24450, "loss": 3.4615213012695314, "indexer_kl": 0.0, "lr": 0.0008222159711309114, "tokens_per_s": 2365206.9105389877 }, { "step": 24500, "loss": 3.4822769165039062, "indexer_kl": 0.0, "lr": 0.0008189051906982268, "tokens_per_s": 2365208.869711499 }, { "step": 24550, "loss": 3.475203552246094, "indexer_kl": 0.0, "lr": 0.0008155986199925671, "tokens_per_s": 2365213.4018265144 }, { "step": 24600, "loss": 3.478824462890625, "indexer_kl": 0.0, "lr": 0.0008122963085337372, "tokens_per_s": 2365217.5228399565 }, { "step": 24650, "loss": 3.481581726074219, "indexer_kl": 0.0, "lr": 0.0008089983057777541, "tokens_per_s": 2365219.503623977 }, { "step": 24700, "loss": 3.4629388427734376, "indexer_kl": 0.0, "lr": 0.0008057046611161083, "tokens_per_s": 2365221.800483434 }, { "step": 24750, "loss": 3.4691983032226563, "indexer_kl": 0.0, "lr": 0.0008024154238750207, "tokens_per_s": 2365223.719677372 }, { "step": 24800, "loss": 3.489212951660156, "indexer_kl": 0.0, "lr": 0.0007991306433147074, "tokens_per_s": 2365225.856538691 }, { "step": 24850, "loss": 3.4727203369140627, "indexer_kl": 0.0, "lr": 0.0007958503686286401, "tokens_per_s": 2365229.41749611 }, { "step": 24900, "loss": 3.4637997436523436, "indexer_kl": 0.0, "lr": 0.0007925746489428092, "tokens_per_s": 2365232.218739163 }, { "step": 24950, "loss": 3.4632748413085936, "indexer_kl": 0.0, "lr": 0.0007893035333149887, "tokens_per_s": 2365234.591115606 }, { "step": 25000, "loss": 3.4773428344726565, "indexer_kl": 0.0, "lr": 0.0007860370707340018, "tokens_per_s": 2365235.852280143 }, { "step": 25050, "loss": 3.4731619262695315, "indexer_kl": 0.0, "lr": 0.0007827753101189872, "tokens_per_s": 2365239.757032862 }, { "step": 25100, "loss": 3.4758746337890627, "indexer_kl": 0.0, "lr": 0.0007795183003186648, "tokens_per_s": 2365242.872154514 }, { "step": 25150, "loss": 3.4547137451171874, "indexer_kl": 0.0, "lr": 0.0007762660901106062, "tokens_per_s": 2365246.76039611 }, { "step": 25200, "loss": 3.4731298828125, "indexer_kl": 0.0, "lr": 0.0007730187282005037, "tokens_per_s": 2365248.4461532314 }, { "step": 25250, "loss": 3.4768878173828126, "indexer_kl": 0.0, "lr": 0.0007697762632214402, "tokens_per_s": 2365251.0849537286 }, { "step": 25300, "loss": 3.4557916259765626, "indexer_kl": 0.0, "lr": 0.0007665387437331616, "tokens_per_s": 2365236.4544062093 }, { "step": 25350, "loss": 3.4727288818359376, "indexer_kl": 0.0, "lr": 0.0007633062182213488, "tokens_per_s": 2365224.443332569 }, { "step": 25400, "loss": 3.4774163818359374, "indexer_kl": 0.0, "lr": 0.0007600787350968919, "tokens_per_s": 2365225.876604572 }, { "step": 25450, "loss": 3.467467956542969, "indexer_kl": 0.0, "lr": 0.0007568563426951658, "tokens_per_s": 2365228.7351478273 }, { "step": 25500, "loss": 3.475078430175781, "indexer_kl": 0.0, "lr": 0.0007536390892753062, "tokens_per_s": 2365231.0770130996 }, { "step": 25550, "loss": 3.4518896484375, "indexer_kl": 0.0, "lr": 0.0007504270230194852, "tokens_per_s": 2365234.623671811 }, { "step": 25600, "loss": 3.46828125, "indexer_kl": 0.0, "lr": 0.0007472201920321915, "tokens_per_s": 2365236.603577883 }, { "step": 25650, "loss": 3.478263244628906, "indexer_kl": 0.0, "lr": 0.0007440186443395101, "tokens_per_s": 2365238.662519482 }, { "step": 25700, "loss": 3.4622412109375, "indexer_kl": 0.0, "lr": 0.0007408224278884019, "tokens_per_s": 2365240.122157951 }, { "step": 25750, "loss": 3.461891784667969, "indexer_kl": 0.0, "lr": 0.000737631590545986, "tokens_per_s": 2365243.183229396 }, { "step": 25800, "loss": 3.483406982421875, "indexer_kl": 0.0, "lr": 0.0007344461800988234, "tokens_per_s": 2365231.638851225 }, { "step": 25850, "loss": 3.4675137329101564, "indexer_kl": 0.0, "lr": 0.0007312662442522002, "tokens_per_s": 2365233.2946512997 }, { "step": 25900, "loss": 3.4667648315429687, "indexer_kl": 0.0, "lr": 0.0007280918306294153, "tokens_per_s": 2365236.327059724 }, { "step": 25950, "loss": 3.4637802124023436, "indexer_kl": 0.0, "lr": 0.0007249229867710643, "tokens_per_s": 2365223.8274475755 }, { "step": 26000, "loss": 3.457705383300781, "indexer_kl": 0.0, "lr": 0.0007217597601343297, "tokens_per_s": 2365227.4268360236 }, { "step": 26050, "loss": 3.471446533203125, "indexer_kl": 0.0, "lr": 0.000718602198092269, "tokens_per_s": 2365228.94674958 }, { "step": 26100, "loss": 3.4567535400390623, "indexer_kl": 0.0, "lr": 0.0007154503479331064, "tokens_per_s": 2365230.0480834157 }, { "step": 26150, "loss": 3.461361999511719, "indexer_kl": 0.0, "lr": 0.0007123042568595242, "tokens_per_s": 2365234.14936976 }, { "step": 26200, "loss": 3.4673977661132813, "indexer_kl": 0.0, "lr": 0.0007091639719879534, "tokens_per_s": 2365236.3644859795 }, { "step": 26250, "loss": 3.45150390625, "indexer_kl": 0.0, "lr": 0.0007060295403478727, "tokens_per_s": 2365240.7131193383 }, { "step": 26300, "loss": 3.457644348144531, "indexer_kl": 0.0, "lr": 0.0007029010088811005, "tokens_per_s": 2365242.313031177 }, { "step": 26350, "loss": 3.455341796875, "indexer_kl": 0.0, "lr": 0.0006997784244410948, "tokens_per_s": 2365245.1086983676 }, { "step": 26400, "loss": 3.4632437133789065, "indexer_kl": 0.0, "lr": 0.0006966618337922463, "tokens_per_s": 2365247.2914367886 }, { "step": 26450, "loss": 3.4476272583007814, "indexer_kl": 0.0, "lr": 0.0006935512836091851, "tokens_per_s": 2365249.5038871286 }, { "step": 26500, "loss": 3.454140319824219, "indexer_kl": 0.0, "lr": 0.0006904468204760769, "tokens_per_s": 2365253.865601436 }, { "step": 26550, "loss": 3.454395446777344, "indexer_kl": 0.0, "lr": 0.0006873484908859264, "tokens_per_s": 2365258.8262051116 }, { "step": 26600, "loss": 3.451828918457031, "indexer_kl": 0.0, "lr": 0.000684256341239881, "tokens_per_s": 2365262.400121207 }, { "step": 26650, "loss": 3.4538909912109377, "indexer_kl": 0.0, "lr": 0.000681170417846537, "tokens_per_s": 2365255.5010455353 }, { "step": 26700, "loss": 3.4567965698242187, "indexer_kl": 0.0, "lr": 0.0006780907669212453, "tokens_per_s": 2365259.211098993 }, { "step": 26750, "loss": 3.4562948608398436, "indexer_kl": 0.0, "lr": 0.0006750174345854181, "tokens_per_s": 2365247.951238871 }, { "step": 26800, "loss": 3.458800964355469, "indexer_kl": 0.0, "lr": 0.0006719504668658394, "tokens_per_s": 2365250.067749467 }, { "step": 26850, "loss": 3.459291687011719, "indexer_kl": 0.0, "lr": 0.0006688899096939767, "tokens_per_s": 2365239.5097178 }, { "step": 26900, "loss": 3.461752624511719, "indexer_kl": 0.0, "lr": 0.0006658358089052914, "tokens_per_s": 2365242.560098736 }, { "step": 26950, "loss": 3.4553628540039063, "indexer_kl": 0.0, "lr": 0.0006627882102385522, "tokens_per_s": 2365244.5328467973 }, { "step": 27000, "loss": 3.453165283203125, "indexer_kl": 0.0, "lr": 0.0006597471593351514, "tokens_per_s": 2365247.4098729575 }, { "step": 27050, "loss": 3.4544491577148437, "indexer_kl": 0.0, "lr": 0.000656712701738421, "tokens_per_s": 2365251.095881621 }, { "step": 27100, "loss": 3.454961853027344, "indexer_kl": 0.0, "lr": 0.0006536848828929505, "tokens_per_s": 2365252.911800632 }, { "step": 27150, "loss": 3.4570046997070314, "indexer_kl": 0.0, "lr": 0.000650663748143906, "tokens_per_s": 2365256.1873084637 }, { "step": 27200, "loss": 3.45305419921875, "indexer_kl": 0.0, "lr": 0.0006476493427363508, "tokens_per_s": 2365258.649653059 }, { "step": 27250, "loss": 3.4566030883789063, "indexer_kl": 0.0, "lr": 0.0006446417118145694, "tokens_per_s": 2365262.6156520634 }, { "step": 27300, "loss": 3.445639953613281, "indexer_kl": 0.0, "lr": 0.0006416409004213899, "tokens_per_s": 2365263.384279411 }, { "step": 27350, "loss": 3.4549441528320313, "indexer_kl": 0.0, "lr": 0.0006386469534975099, "tokens_per_s": 2365266.1503813923 }, { "step": 27400, "loss": 3.449703369140625, "indexer_kl": 0.0, "lr": 0.0006356599158808229, "tokens_per_s": 2365268.4666582914 }, { "step": 27450, "loss": 3.435882873535156, "indexer_kl": 0.0, "lr": 0.0006326798323057483, "tokens_per_s": 2365270.653892986 }, { "step": 27500, "loss": 3.4410018920898438, "indexer_kl": 0.0, "lr": 0.0006297067474025606, "tokens_per_s": 2365275.313993377 }, { "step": 27550, "loss": 3.4477825927734376, "indexer_kl": 0.0, "lr": 0.0006267407056967196, "tokens_per_s": 2365277.07800456 }, { "step": 27600, "loss": 3.435632629394531, "indexer_kl": 0.0, "lr": 0.0006237817516082063, "tokens_per_s": 2365280.3547162055 }, { "step": 27650, "loss": 3.439797668457031, "indexer_kl": 0.0, "lr": 0.0006208299294508554, "tokens_per_s": 2365283.635289479 }, { "step": 27700, "loss": 3.4449847412109373, "indexer_kl": 0.0, "lr": 0.000617885283431693, "tokens_per_s": 2365287.1342547503 }, { "step": 27750, "loss": 3.442242431640625, "indexer_kl": 0.0, "lr": 0.0006149478576502734, "tokens_per_s": 2365275.7435630686 }, { "step": 27800, "loss": 3.434183349609375, "indexer_kl": 0.0, "lr": 0.0006120176960980203, "tokens_per_s": 2365278.147890627 }, { "step": 27850, "loss": 3.4394717407226563, "indexer_kl": 0.0, "lr": 0.0006090948426575662, "tokens_per_s": 2365281.8522150978 }, { "step": 27900, "loss": 3.4407919311523436, "indexer_kl": 0.0, "lr": 0.0006061793411020957, "tokens_per_s": 2365284.468483177 }, { "step": 27950, "loss": 3.4380401611328124, "indexer_kl": 0.0, "lr": 0.0006032712350946912, "tokens_per_s": 2365274.3398675546 }, { "step": 28000, "loss": 3.4359490966796873, "indexer_kl": 0.0, "lr": 0.0006003705681876778, "tokens_per_s": 2365278.807450492 }, { "step": 28050, "loss": 3.4584530639648436, "indexer_kl": 0.0, "lr": 0.0005974773838219707, "tokens_per_s": 2365280.2822568975 }, { "step": 28100, "loss": 3.4535870361328125, "indexer_kl": 0.0, "lr": 0.0005945917253264253, "tokens_per_s": 2365284.5949464077 }, { "step": 28150, "loss": 3.4370379638671875, "indexer_kl": 0.0, "lr": 0.0005917136359171888, "tokens_per_s": 2365287.332537631 }, { "step": 28200, "loss": 3.434856262207031, "indexer_kl": 0.0, "lr": 0.0005888431586970522, "tokens_per_s": 2365290.7022936638 }, { "step": 28250, "loss": 3.4362640380859375, "indexer_kl": 0.0, "lr": 0.0005859803366548047, "tokens_per_s": 2365295.5202712067 }, { "step": 28300, "loss": 3.435060729980469, "indexer_kl": 0.0, "lr": 0.0005831252126645896, "tokens_per_s": 2365283.9726290028 }, { "step": 28350, "loss": 3.4427362060546876, "indexer_kl": 0.0, "lr": 0.0005802778294852639, "tokens_per_s": 2365287.0988236405 }, { "step": 28400, "loss": 3.4515997314453126, "indexer_kl": 0.0, "lr": 0.0005774382297597568, "tokens_per_s": 2365290.964118875 }, { "step": 28450, "loss": 3.4294314575195313, "indexer_kl": 0.0, "lr": 0.0005746064560144302, "tokens_per_s": 2365294.799624686 }, { "step": 28500, "loss": 3.4461099243164064, "indexer_kl": 0.0, "lr": 0.0005717825506584426, "tokens_per_s": 2365297.4114454454 }, { "step": 28550, "loss": 3.449992980957031, "indexer_kl": 0.0, "lr": 0.0005689665559831152, "tokens_per_s": 2365300.685197197 }, { "step": 28600, "loss": 3.4374554443359373, "indexer_kl": 0.0, "lr": 0.0005661585141612969, "tokens_per_s": 2365302.7908391403 }, { "step": 28650, "loss": 3.433175354003906, "indexer_kl": 0.0, "lr": 0.0005633584672467328, "tokens_per_s": 2365306.595070594 }, { "step": 28700, "loss": 3.427209777832031, "indexer_kl": 0.0, "lr": 0.0005605664571734348, "tokens_per_s": 2365310.4645412983 }, { "step": 28750, "loss": 3.430868835449219, "indexer_kl": 0.0, "lr": 0.0005577825257550546, "tokens_per_s": 2365314.0874154265 }, { "step": 28800, "loss": 3.436483154296875, "indexer_kl": 0.0, "lr": 0.0005550067146842555, "tokens_per_s": 2365316.835524559 }, { "step": 28850, "loss": 3.4284188842773435, "indexer_kl": 0.0, "lr": 0.0005522390655320895, "tokens_per_s": 2365319.755661954 }, { "step": 28900, "loss": 3.433955078125, "indexer_kl": 0.0, "lr": 0.0005494796197473733, "tokens_per_s": 2365322.926754039 }, { "step": 28950, "loss": 3.427716064453125, "indexer_kl": 0.0, "lr": 0.0005467284186560699, "tokens_per_s": 2365325.788802636 }, { "step": 29000, "loss": 3.4444024658203123, "indexer_kl": 0.0, "lr": 0.0005439855034606678, "tokens_per_s": 2365326.8058830486 }, { "step": 29050, "loss": 3.43893310546875, "indexer_kl": 0.0, "lr": 0.0005412509152395637, "tokens_per_s": 2365330.933124212 }, { "step": 29100, "loss": 3.4416094970703126, "indexer_kl": 0.0, "lr": 0.0005385246949464484, "tokens_per_s": 2365332.8984414954 }, { "step": 29150, "loss": 3.435738220214844, "indexer_kl": 0.0, "lr": 0.0005358068834096933, "tokens_per_s": 2365335.6921194037 }, { "step": 29200, "loss": 3.4339947509765625, "indexer_kl": 0.0, "lr": 0.0005330975213317392, "tokens_per_s": 2365339.6993274484 }, { "step": 29250, "loss": 3.4332470703125, "indexer_kl": 0.0, "lr": 0.0005303966492884853, "tokens_per_s": 2365341.8529927954 }, { "step": 29300, "loss": 3.4290481567382813, "indexer_kl": 0.0, "lr": 0.0005277043077286825, "tokens_per_s": 2365344.1197218504 }, { "step": 29350, "loss": 3.4365884399414064, "indexer_kl": 0.0, "lr": 0.0005250205369733283, "tokens_per_s": 2365345.978356059 }, { "step": 29400, "loss": 3.42076904296875, "indexer_kl": 0.0, "lr": 0.0005223453772150625, "tokens_per_s": 2365348.8054492376 }, { "step": 29450, "loss": 3.438873596191406, "indexer_kl": 0.0, "lr": 0.000519678868517564, "tokens_per_s": 2365350.8424218576 }, { "step": 29500, "loss": 3.434095458984375, "indexer_kl": 0.0, "lr": 0.0005170210508149522, "tokens_per_s": 2365351.0399348345 }, { "step": 29550, "loss": 3.418112487792969, "indexer_kl": 0.0, "lr": 0.000514371963911189, "tokens_per_s": 2365352.3967214003 }, { "step": 29600, "loss": 3.426996765136719, "indexer_kl": 0.0, "lr": 0.0005117316474794824, "tokens_per_s": 2365354.3448799383 }, { "step": 29650, "loss": 3.423758239746094, "indexer_kl": 0.0, "lr": 0.0005091001410616916, "tokens_per_s": 2365356.134530006 }, { "step": 29700, "loss": 3.43627197265625, "indexer_kl": 0.0, "lr": 0.0005064774840677351, "tokens_per_s": 2365359.6561459806 }, { "step": 29750, "loss": 3.4352191162109373, "indexer_kl": 0.0, "lr": 0.0005038637157750021, "tokens_per_s": 2365362.716202364 }, { "step": 29800, "loss": 3.4254525756835936, "indexer_kl": 0.0, "lr": 0.0005012588753277619, "tokens_per_s": 2365365.7678193958 }, { "step": 29850, "loss": 3.4219461059570313, "indexer_kl": 0.0, "lr": 0.0004986630017365794, "tokens_per_s": 2365369.1438012444 }, { "step": 29900, "loss": 3.430557861328125, "indexer_kl": 0.0, "lr": 0.0004960761338777296, "tokens_per_s": 2365371.8822113373 }, { "step": 29950, "loss": 3.4279446411132812, "indexer_kl": 0.0, "lr": 0.0004934983104926167, "tokens_per_s": 2365374.612390621 }, { "step": 30000, "loss": 3.4206924438476562, "indexer_kl": 0.0, "lr": 0.0004909295701871927, "tokens_per_s": 2365377.057558681 }, { "step": 30050, "loss": 3.435638427734375, "indexer_kl": 0.0, "lr": 0.0004883699514313802, "tokens_per_s": 2365380.1565981065 }, { "step": 30100, "loss": 3.4259246826171874, "indexer_kl": 0.0, "lr": 0.00048581949255849504, "tokens_per_s": 2365383.4563346803 }, { "step": 30150, "loss": 3.4144888305664063, "indexer_kl": 0.0, "lr": 0.00048327823176467415, "tokens_per_s": 2365385.666754282 }, { "step": 30200, "loss": 3.4328179931640626, "indexer_kl": 0.0, "lr": 0.00048074620710830115, "tokens_per_s": 2365385.963796792 }, { "step": 30250, "loss": 3.4339981079101562, "indexer_kl": 0.0, "lr": 0.00047822345650943865, "tokens_per_s": 2365388.143031404 }, { "step": 30300, "loss": 3.410023193359375, "indexer_kl": 0.0, "lr": 0.00047571001774925813, "tokens_per_s": 2365376.930729186 }, { "step": 30350, "loss": 3.4362933349609377, "indexer_kl": 0.0, "lr": 0.0004732059284694767, "tokens_per_s": 2365380.1683508633 }, { "step": 30400, "loss": 3.424769287109375, "indexer_kl": 0.0, "lr": 0.0004707112261717904, "tokens_per_s": 2365382.646316782 }, { "step": 30450, "loss": 3.423951416015625, "indexer_kl": 0.0, "lr": 0.0004682259482173155, "tokens_per_s": 2365386.5270509073 }, { "step": 30500, "loss": 3.41597412109375, "indexer_kl": 0.0, "lr": 0.0004657501318260265, "tokens_per_s": 2365375.479027562 }, { "step": 30550, "loss": 3.42817138671875, "indexer_kl": 0.0, "lr": 0.0004632838140762009, "tokens_per_s": 2365379.533772811 }, { "step": 30600, "loss": 3.4227261352539062, "indexer_kl": 0.0, "lr": 0.00046082703190386136, "tokens_per_s": 2365382.367307293 }, { "step": 30650, "loss": 3.432532958984375, "indexer_kl": 0.0, "lr": 0.0004583798221022258, "tokens_per_s": 2365372.645494427 }, { "step": 30700, "loss": 3.422876892089844, "indexer_kl": 0.0, "lr": 0.0004559422213211527, "tokens_per_s": 2365374.9143465045 }, { "step": 30750, "loss": 3.429842224121094, "indexer_kl": 0.0, "lr": 0.00045351426606659575, "tokens_per_s": 2365377.198771639 }, { "step": 30800, "loss": 3.426011047363281, "indexer_kl": 0.0, "lr": 0.0004510959927000542, "tokens_per_s": 2365380.8257067315 }, { "step": 30850, "loss": 3.4385476684570313, "indexer_kl": 0.0, "lr": 0.0004486874374380303, "tokens_per_s": 2365383.80221564 }, { "step": 30900, "loss": 3.4263156127929686, "indexer_kl": 0.0, "lr": 0.0004462886363514864, "tokens_per_s": 2365386.7664643764 }, { "step": 30950, "loss": 3.425262145996094, "indexer_kl": 0.0, "lr": 0.00044389962536530385, "tokens_per_s": 2365389.9903473225 }, { "step": 31000, "loss": 3.4152154541015625, "indexer_kl": 0.0, "lr": 0.0004415204402577458, "tokens_per_s": 2365393.2222243734 }, { "step": 31050, "loss": 3.4245263671875, "indexer_kl": 0.0, "lr": 0.0004391511166599216, "tokens_per_s": 2365397.6586566092 }, { "step": 31100, "loss": 3.4314215087890627, "indexer_kl": 0.0, "lr": 0.00043679169005525324, "tokens_per_s": 2365400.935029378 }, { "step": 31150, "loss": 3.424627380371094, "indexer_kl": 0.0, "lr": 0.00043444219577894194, "tokens_per_s": 2365403.282577406 }, { "step": 31200, "loss": 3.4311758422851564, "indexer_kl": 0.0, "lr": 0.0004321026690174421, "tokens_per_s": 2365407.0518071144 }, { "step": 31250, "loss": 3.4163107299804687, "indexer_kl": 0.0, "lr": 0.0004297731448079325, "tokens_per_s": 2365410.1437283605 }, { "step": 31300, "loss": 3.435802001953125, "indexer_kl": 0.0, "lr": 0.00042745365803779196, "tokens_per_s": 2365413.694879874 }, { "step": 31350, "loss": 3.435652770996094, "indexer_kl": 0.0, "lr": 0.0004251442434440755, "tokens_per_s": 2365415.800219311 }, { "step": 31400, "loss": 3.420720520019531, "indexer_kl": 0.0, "lr": 0.0004228449356129971, "tokens_per_s": 2365417.6257259157 }, { "step": 31450, "loss": 3.404501647949219, "indexer_kl": 0.0, "lr": 0.00042055576897940915, "tokens_per_s": 2365419.8915852746 }, { "step": 31500, "loss": 3.4316314697265624, "indexer_kl": 0.0, "lr": 0.00041827677782628844, "tokens_per_s": 2365424.1448613205 }, { "step": 31550, "loss": 3.420281982421875, "indexer_kl": 0.0, "lr": 0.0004160079962842201, "tokens_per_s": 2365426.9910851084 }, { "step": 31600, "loss": 3.4292361450195314, "indexer_kl": 0.0, "lr": 0.00041374945833089, "tokens_per_s": 2365429.9932134454 }, { "step": 31650, "loss": 3.418418273925781, "indexer_kl": 0.0, "lr": 0.00041150119779057395, "tokens_per_s": 2365433.3383065485 }, { "step": 31700, "loss": 3.419227294921875, "indexer_kl": 0.0, "lr": 0.0004092632483336306, "tokens_per_s": 2365436.788440287 }, { "step": 31750, "loss": 3.4287643432617188, "indexer_kl": 0.0, "lr": 0.0004070356434759982, "tokens_per_s": 2365440.869694058 }, { "step": 31800, "loss": 3.4237051391601563, "indexer_kl": 0.0, "lr": 0.0004048184165786928, "tokens_per_s": 2365442.4083917057 }, { "step": 31850, "loss": 3.415086364746094, "indexer_kl": 0.0, "lr": 0.0004026116008473081, "tokens_per_s": 2365443.3593915086 }, { "step": 31900, "loss": 3.4280099487304687, "indexer_kl": 0.0, "lr": 0.0004004152293315178, "tokens_per_s": 2365446.2761917897 }, { "step": 31950, "loss": 3.413166809082031, "indexer_kl": 0.0, "lr": 0.00039822933492458156, "tokens_per_s": 2365447.7643827884 }, { "step": 32000, "loss": 3.428000183105469, "indexer_kl": 0.0, "lr": 0.00039605395036285183, "tokens_per_s": 2365450.3445924153 }, { "step": 32050, "loss": 3.4238455200195315, "indexer_kl": 0.0, "lr": 0.00039388910822528417, "tokens_per_s": 2365453.7966203475 }, { "step": 32100, "loss": 3.4179556274414065, "indexer_kl": 0.0, "lr": 0.000391734840932948, "tokens_per_s": 2365455.4690770484 }, { "step": 32150, "loss": 3.4269732666015624, "indexer_kl": 0.0, "lr": 0.0003895911807485424, "tokens_per_s": 2365456.6914379355 }, { "step": 32200, "loss": 3.4116946411132814, "indexer_kl": 0.0, "lr": 0.00038745815977591237, "tokens_per_s": 2365447.4598378465 }, { "step": 32250, "loss": 3.40714599609375, "indexer_kl": 0.0, "lr": 0.00038533580995956876, "tokens_per_s": 2365449.354825701 }, { "step": 32300, "loss": 3.4080770874023436, "indexer_kl": 0.0, "lr": 0.000383224163084208, "tokens_per_s": 2365438.4885577243 }, { "step": 32350, "loss": 3.4089889526367188, "indexer_kl": 0.0, "lr": 0.0003811232507742387, "tokens_per_s": 2365432.010216321 }, { "step": 32400, "loss": 3.400970458984375, "indexer_kl": 0.0, "lr": 0.00037903310449330537, "tokens_per_s": 2365434.525887477 }, { "step": 32450, "loss": 3.415177917480469, "indexer_kl": 0.0, "lr": 0.0003769537555438197, "tokens_per_s": 2365435.659629381 }, { "step": 32500, "loss": 3.424596862792969, "indexer_kl": 0.0, "lr": 0.0003748852350664894, "tokens_per_s": 2365438.6947474713 }, { "step": 32550, "loss": 3.4213604736328125, "indexer_kl": 0.0, "lr": 0.0003728275740398542, "tokens_per_s": 2365440.7941749534 }, { "step": 32600, "loss": 3.425797119140625, "indexer_kl": 0.0, "lr": 0.0003707808032798197, "tokens_per_s": 2365442.8372136545 }, { "step": 32650, "loss": 3.418845520019531, "indexer_kl": 0.0, "lr": 0.00036874495343919777, "tokens_per_s": 2365432.2022077455 }, { "step": 32700, "loss": 3.4159307861328125, "indexer_kl": 0.0, "lr": 0.00036672005500724557, "tokens_per_s": 2365434.0031243567 }, { "step": 32750, "loss": 3.410948486328125, "indexer_kl": 0.0, "lr": 0.00036470613830921116, "tokens_per_s": 2365437.1410783916 }, { "step": 32800, "loss": 3.407222900390625, "indexer_kl": 0.0, "lr": 0.0003627032335058771, "tokens_per_s": 2365439.9012524253 }, { "step": 32850, "loss": 3.4310650634765625, "indexer_kl": 0.0, "lr": 0.0003607113705931107, "tokens_per_s": 2365441.819388896 }, { "step": 32900, "loss": 3.423568115234375, "indexer_kl": 0.0, "lr": 0.00035873057940141295, "tokens_per_s": 2365435.1984340656 }, { "step": 32950, "loss": 3.413141784667969, "indexer_kl": 0.0, "lr": 0.0003567608895954738, "tokens_per_s": 2365437.37569435 }, { "step": 33000, "loss": 3.411988525390625, "indexer_kl": 0.0, "lr": 0.00035480233067372596, "tokens_per_s": 2365440.989758715 }, { "step": 33050, "loss": 3.4133740234375, "indexer_kl": 0.0, "lr": 0.00035285493196790426, "tokens_per_s": 2365444.539520434 }, { "step": 33100, "loss": 3.4060800170898435, "indexer_kl": 0.0, "lr": 0.00035091872264260616, "tokens_per_s": 2365445.794135327 }, { "step": 33150, "loss": 3.403880310058594, "indexer_kl": 0.0, "lr": 0.0003489937316948552, "tokens_per_s": 2365448.219029327 }, { "step": 33200, "loss": 3.4084408569335936, "indexer_kl": 0.0, "lr": 0.000347079987953666, "tokens_per_s": 2365451.2513857204 }, { "step": 33250, "loss": 3.401578063964844, "indexer_kl": 0.0, "lr": 0.00034517752007961295, "tokens_per_s": 2365452.876352152 }, { "step": 33300, "loss": 3.420890197753906, "indexer_kl": 0.0, "lr": 0.00034328635656440137, "tokens_per_s": 2365455.03274357 }, { "step": 33350, "loss": 3.415999450683594, "indexer_kl": 0.0, "lr": 0.0003414065257304405, "tokens_per_s": 2365457.123263433 }, { "step": 33400, "loss": 3.3944686889648437, "indexer_kl": 0.0, "lr": 0.0003395380557304187, "tokens_per_s": 2365459.1165153664 }, { "step": 33450, "loss": 3.419419860839844, "indexer_kl": 0.0, "lr": 0.0003376809745468829, "tokens_per_s": 2365460.673770418 }, { "step": 33500, "loss": 3.423117980957031, "indexer_kl": 0.0, "lr": 0.00033583530999181877, "tokens_per_s": 2365462.660640158 }, { "step": 33550, "loss": 3.4171597290039064, "indexer_kl": 0.0, "lr": 0.00033400108970623485, "tokens_per_s": 2365451.392144709 }, { "step": 33600, "loss": 3.4003811645507813, "indexer_kl": 0.0, "lr": 0.0003321783411597479, "tokens_per_s": 2365453.4741368103 }, { "step": 33650, "loss": 3.4024484252929685, "indexer_kl": 0.0, "lr": 0.00033036709165017175, "tokens_per_s": 2365456.911440542 }, { "step": 33700, "loss": 3.40421630859375, "indexer_kl": 0.0, "lr": 0.0003285673683031087, "tokens_per_s": 2365458.433029148 }, { "step": 33750, "loss": 3.4096102905273438, "indexer_kl": 0.0, "lr": 0.00032677919807154357, "tokens_per_s": 2365452.5315218735 }, { "step": 33800, "loss": 3.40908447265625, "indexer_kl": 0.0, "lr": 0.00032500260773543876, "tokens_per_s": 2365454.3778851232 }, { "step": 33850, "loss": 3.4068060302734375, "indexer_kl": 0.0, "lr": 0.0003232376239013345, "tokens_per_s": 2365455.5188190504 }, { "step": 33900, "loss": 3.402943115234375, "indexer_kl": 0.0, "lr": 0.00032148427300195007, "tokens_per_s": 2365458.956586588 }, { "step": 33950, "loss": 3.4091455078125, "indexer_kl": 0.0, "lr": 0.0003197425812957879, "tokens_per_s": 2365460.9947951115 }, { "step": 34000, "loss": 3.4201202392578125, "indexer_kl": 0.0, "lr": 0.00031801257486673977, "tokens_per_s": 2365464.295471426 }, { "step": 34050, "loss": 3.4105599975585936, "indexer_kl": 0.0, "lr": 0.0003162942796236965, "tokens_per_s": 2365466.9153006827 }, { "step": 34100, "loss": 3.4105734252929687, "indexer_kl": 0.0, "lr": 0.0003145877213001608, "tokens_per_s": 2365469.5051666694 }, { "step": 34150, "loss": 3.40491943359375, "indexer_kl": 0.0, "lr": 0.00031289292545386073, "tokens_per_s": 2365472.786856152 }, { "step": 34200, "loss": 3.402999267578125, "indexer_kl": 0.0, "lr": 0.0003112099174663672, "tokens_per_s": 2365474.8082224196 }, { "step": 34250, "loss": 3.4022955322265624, "indexer_kl": 0.0, "lr": 0.0003095387225427141, "tokens_per_s": 2365476.952068372 }, { "step": 34300, "loss": 3.4010797119140626, "indexer_kl": 0.0, "lr": 0.00030787936571102087, "tokens_per_s": 2365478.4803644866 }, { "step": 34350, "loss": 3.4092593383789063, "indexer_kl": 0.0, "lr": 0.00030623187182211755, "tokens_per_s": 2365480.1946400604 }, { "step": 34400, "loss": 3.4045318603515624, "indexer_kl": 0.0, "lr": 0.00030459626554917235, "tokens_per_s": 2365481.746133773 }, { "step": 34450, "loss": 3.3933139038085938, "indexer_kl": 0.0, "lr": 0.0003029725713873223, "tokens_per_s": 2365484.3921921086 }, { "step": 34500, "loss": 3.41294921875, "indexer_kl": 0.0, "lr": 0.0003013608136533069, "tokens_per_s": 2365485.6255030665 }, { "step": 34550, "loss": 3.389093322753906, "indexer_kl": 0.0, "lr": 0.00029976101648510344, "tokens_per_s": 2365475.964762409 }, { "step": 34600, "loss": 3.4111798095703123, "indexer_kl": 0.0, "lr": 0.00029817320384156553, "tokens_per_s": 2365470.117705516 }, { "step": 34650, "loss": 3.3937008666992186, "indexer_kl": 0.0, "lr": 0.00029659739950206376, "tokens_per_s": 2365472.9602879602 }, { "step": 34700, "loss": 3.422117919921875, "indexer_kl": 0.0, "lr": 0.0002950336270661312, "tokens_per_s": 2365475.2729716985 }, { "step": 34750, "loss": 3.4079129028320314, "indexer_kl": 0.0, "lr": 0.0002934819099531086, "tokens_per_s": 2365478.1351162135 }, { "step": 34800, "loss": 3.3957650756835935, "indexer_kl": 0.0, "lr": 0.00029194227140179357, "tokens_per_s": 2365480.365874925 }, { "step": 34850, "loss": 3.416562194824219, "indexer_kl": 0.0, "lr": 0.00029041473447009316, "tokens_per_s": 2365481.9555008076 }, { "step": 34900, "loss": 3.4040069580078125, "indexer_kl": 0.0, "lr": 0.00028889932203467883, "tokens_per_s": 2365485.220411991 }, { "step": 34950, "loss": 3.3954092407226564, "indexer_kl": 0.0, "lr": 0.00028739605679064276, "tokens_per_s": 2365487.6194088687 }, { "step": 35000, "loss": 3.395699768066406, "indexer_kl": 0.0, "lr": 0.000285904961251159, "tokens_per_s": 2365482.4335465394 }, { "step": 35050, "loss": 3.3941940307617187, "indexer_kl": 0.0, "lr": 0.0002844260577471455, "tokens_per_s": 2365484.64769077 }, { "step": 35100, "loss": 3.397530517578125, "indexer_kl": 0.0, "lr": 0.00028295936842693084, "tokens_per_s": 2365487.0643147617 }, { "step": 35150, "loss": 3.413763122558594, "indexer_kl": 0.0, "lr": 0.00028150491525592055, "tokens_per_s": 2365478.872928481 }, { "step": 35200, "loss": 3.4019461059570313, "indexer_kl": 0.0, "lr": 0.00028006272001627054, "tokens_per_s": 2365481.610873249 }, { "step": 35250, "loss": 3.3891259765625, "indexer_kl": 0.0, "lr": 0.0002786328043065589, "tokens_per_s": 2365483.4825287503 }, { "step": 35300, "loss": 3.3927096557617187, "indexer_kl": 0.0, "lr": 0.0002772151895414639, "tokens_per_s": 2365478.5941977925 }, { "step": 35350, "loss": 3.4093283081054686, "indexer_kl": 0.0, "lr": 0.0002758098969514419, "tokens_per_s": 2365481.845326304 }, { "step": 35400, "loss": 3.4001889038085937, "indexer_kl": 0.0, "lr": 0.00027441694758241074, "tokens_per_s": 2365484.602713602 }, { "step": 35450, "loss": 3.3965966796875, "indexer_kl": 0.0, "lr": 0.00027303636229543356, "tokens_per_s": 2365488.107249136 }, { "step": 35500, "loss": 3.4024072265625, "indexer_kl": 0.0, "lr": 0.00027166816176640694, "tokens_per_s": 2365490.350333845 }, { "step": 35550, "loss": 3.4047982788085935, "indexer_kl": 0.0, "lr": 0.00027031236648575096, "tokens_per_s": 2365493.053604671 }, { "step": 35600, "loss": 3.4009494018554687, "indexer_kl": 0.0, "lr": 0.00026896899675810267, "tokens_per_s": 2365490.883545334 }, { "step": 35650, "loss": 3.3886007690429687, "indexer_kl": 0.0, "lr": 0.00026763807270201157, "tokens_per_s": 2365492.6039623437 }, { "step": 35700, "loss": 3.38521240234375, "indexer_kl": 0.0, "lr": 0.00026631961424963845, "tokens_per_s": 2365494.8266707147 }, { "step": 35750, "loss": 3.3945877075195314, "indexer_kl": 0.0, "lr": 0.0002650136411464571, "tokens_per_s": 2365496.8693044977 }, { "step": 35800, "loss": 3.4033251953125, "indexer_kl": 0.0, "lr": 0.00026372017295095835, "tokens_per_s": 2365498.24284552 }, { "step": 35850, "loss": 3.385032043457031, "indexer_kl": 0.0, "lr": 0.00026243922903435756, "tokens_per_s": 2365500.287893678 }, { "step": 35900, "loss": 3.3964608764648436, "indexer_kl": 0.0, "lr": 0.00026117082858030384, "tokens_per_s": 2365503.0530582275 }, { "step": 35950, "loss": 3.408526611328125, "indexer_kl": 0.0, "lr": 0.000259914990584593, "tokens_per_s": 2365505.541001871 }, { "step": 36000, "loss": 3.3957373046875, "indexer_kl": 0.0, "lr": 0.00025867173385488363, "tokens_per_s": 2365496.253619459 }, { "step": 36050, "loss": 3.4028173828125, "indexer_kl": 0.0, "lr": 0.0002574410770104151, "tokens_per_s": 2365497.4370389916 }, { "step": 36100, "loss": 3.400078125, "indexer_kl": 0.0, "lr": 0.0002562230384817278, "tokens_per_s": 2365499.5946001983 }, { "step": 36150, "loss": 3.380582580566406, "indexer_kl": 0.0, "lr": 0.0002550176365103885, "tokens_per_s": 2365500.65900682 }, { "step": 36200, "loss": 3.391004943847656, "indexer_kl": 0.0, "lr": 0.00025382488914871677, "tokens_per_s": 2365491.8458440984 }, { "step": 36250, "loss": 3.401690673828125, "indexer_kl": 0.0, "lr": 0.0002526448142595143, "tokens_per_s": 2365493.7296357276 }, { "step": 36300, "loss": 3.4001690673828127, "indexer_kl": 0.0, "lr": 0.00025147742951579685, "tokens_per_s": 2365496.1675324007 }, { "step": 36350, "loss": 3.413360900878906, "indexer_kl": 0.0, "lr": 0.0002503227524005311, "tokens_per_s": 2365497.9282006253 }, { "step": 36400, "loss": 3.3906890869140627, "indexer_kl": 0.0, "lr": 0.00024918080020637176, "tokens_per_s": 2365497.505205605 }, { "step": 36450, "loss": 3.3942532348632812, "indexer_kl": 0.0, "lr": 0.000248051590035403, "tokens_per_s": 2365498.9151863637 }, { "step": 36500, "loss": 3.388255920410156, "indexer_kl": 0.0, "lr": 0.00024693513879888113, "tokens_per_s": 2365500.032037026 }, { "step": 36550, "loss": 3.3897052001953125, "indexer_kl": 0.0, "lr": 0.00024583146321698366, "tokens_per_s": 2365502.273850531 }, { "step": 36600, "loss": 3.3923068237304688, "indexer_kl": 0.0, "lr": 0.00024474057981855685, "tokens_per_s": 2365504.0386318993 }, { "step": 36650, "loss": 3.399059143066406, "indexer_kl": 0.0, "lr": 0.000243662504940869, "tokens_per_s": 2365505.180955713 }, { "step": 36700, "loss": 3.4055990600585937, "indexer_kl": 0.0, "lr": 0.0002425972547293656, "tokens_per_s": 2365506.50801959 }, { "step": 36750, "loss": 3.4066098022460936, "indexer_kl": 0.0, "lr": 0.00024154484513742774, "tokens_per_s": 2365506.9887683922 }, { "step": 36800, "loss": 3.4038540649414064, "indexer_kl": 0.0, "lr": 0.00024050529192613316, "tokens_per_s": 2365508.420406555 }, { "step": 36850, "loss": 3.3942425537109373, "indexer_kl": 0.0, "lr": 0.00023947861066401979, "tokens_per_s": 2365511.9613675526 }, { "step": 36900, "loss": 3.3904931640625, "indexer_kl": 0.0, "lr": 0.00023846481672685306, "tokens_per_s": 2365513.925979512 }, { "step": 36950, "loss": 3.392222900390625, "indexer_kl": 0.0, "lr": 0.00023746392529739563, "tokens_per_s": 2365517.6019810024 }, { "step": 37000, "loss": 3.393274230957031, "indexer_kl": 0.0, "lr": 0.00023647595136517968, "tokens_per_s": 2365519.23969585 }, { "step": 37050, "loss": 3.3674554443359375, "indexer_kl": 0.0, "lr": 0.00023550090972628256, "tokens_per_s": 2365520.201202772 }, { "step": 37100, "loss": 3.3888958740234374, "indexer_kl": 0.0, "lr": 0.00023453881498310537, "tokens_per_s": 2365520.993312113 }, { "step": 37150, "loss": 3.393912658691406, "indexer_kl": 0.0, "lr": 0.00023358968154415404, "tokens_per_s": 2365521.90530402 }, { "step": 37200, "loss": 3.376514587402344, "indexer_kl": 0.0, "lr": 0.0002326535236238238, "tokens_per_s": 2365523.6940648193 }, { "step": 37250, "loss": 3.389199523925781, "indexer_kl": 0.0, "lr": 0.0002317303552421859, "tokens_per_s": 2365525.4874989158 }, { "step": 37300, "loss": 3.394179382324219, "indexer_kl": 0.0, "lr": 0.00023082019022477833, "tokens_per_s": 2365526.7863927875 }, { "step": 37350, "loss": 3.391060485839844, "indexer_kl": 0.0, "lr": 0.00022992304220239757, "tokens_per_s": 2365528.1646560393 }, { "step": 37400, "loss": 3.387282409667969, "indexer_kl": 0.0, "lr": 0.00022903892461089627, "tokens_per_s": 2365529.500771211 }, { "step": 37450, "loss": 3.4006314086914062, "indexer_kl": 0.0, "lr": 0.00022816785069097983, "tokens_per_s": 2365531.652318265 }, { "step": 37500, "loss": 3.388810119628906, "indexer_kl": 0.0, "lr": 0.00022730983348801027, "tokens_per_s": 2365533.377596897 }, { "step": 37550, "loss": 3.38219482421875, "indexer_kl": 0.0, "lr": 0.00022646488585180912, "tokens_per_s": 2365535.2529731747 }, { "step": 37600, "loss": 3.3943826293945314, "indexer_kl": 0.0, "lr": 0.00022563302043646612, "tokens_per_s": 2365537.651065892 }, { "step": 37650, "loss": 3.3854296875, "indexer_kl": 0.0, "lr": 0.00022481424970014884, "tokens_per_s": 2365540.062980123 }, { "step": 37700, "loss": 3.4042843627929686, "indexer_kl": 0.0, "lr": 0.0002240085859049173, "tokens_per_s": 2365541.0199073413 }, { "step": 37750, "loss": 3.394325866699219, "indexer_kl": 0.0, "lr": 0.00022321604111653882, "tokens_per_s": 2365541.9160594987 }, { "step": 37800, "loss": 3.3938919067382813, "indexer_kl": 0.0, "lr": 0.00022243662720430852, "tokens_per_s": 2365544.277584115 }, { "step": 37850, "loss": 3.3826358032226564, "indexer_kl": 0.0, "lr": 0.00022167035584087086, "tokens_per_s": 2365545.3779027606 }, { "step": 37900, "loss": 3.377445068359375, "indexer_kl": 0.0, "lr": 0.00022091723850204548, "tokens_per_s": 2365546.6894572824 }, { "step": 37950, "loss": 3.3974896240234376, "indexer_kl": 0.0, "lr": 0.0002201772864666545, "tokens_per_s": 2365548.5497212 }, { "step": 38000, "loss": 3.3902740478515625, "indexer_kl": 0.0, "lr": 0.00021945051081635435, "tokens_per_s": 2365549.8443684373 }, { "step": 38050, "loss": 3.3910205078125, "indexer_kl": 0.0, "lr": 0.00021873692243546948, "tokens_per_s": 2365552.0494294623 }, { "step": 38100, "loss": 3.387166748046875, "indexer_kl": 0.0, "lr": 0.00021803653201082947, "tokens_per_s": 2365553.1537087928 }, { "step": 38150, "loss": 3.3823110961914065, "indexer_kl": 0.0, "lr": 0.00021734935003160855, "tokens_per_s": 2365555.350081687 }, { "step": 38200, "loss": 3.3826580810546876, "indexer_kl": 0.0, "lr": 0.00021667538678916924, "tokens_per_s": 2365556.8805961614 }, { "step": 38250, "loss": 3.3956207275390624, "indexer_kl": 0.0, "lr": 0.0002160146523769076, "tokens_per_s": 2365558.1857052734 }, { "step": 38300, "loss": 3.3935015869140623, "indexer_kl": 0.0, "lr": 0.00021536715669010276, "tokens_per_s": 2365559.1989637446 }, { "step": 38350, "loss": 3.396727294921875, "indexer_kl": 0.0, "lr": 0.00021473290942576771, "tokens_per_s": 2365549.131377122 }, { "step": 38400, "loss": 3.3915399169921874, "indexer_kl": 0.0, "lr": 0.0002141119200825049, "tokens_per_s": 2365548.8757805726 }, { "step": 38450, "loss": 3.3951040649414064, "indexer_kl": 0.0, "lr": 0.00021350419796036386, "tokens_per_s": 2365549.078296483 }, { "step": 38500, "loss": 3.39059326171875, "indexer_kl": 0.0, "lr": 0.00021290975216070178, "tokens_per_s": 2365549.362773895 }, { "step": 38550, "loss": 3.3762356567382814, "indexer_kl": 0.0, "lr": 0.000212328591586047, "tokens_per_s": 2365549.3754322724 }, { "step": 38600, "loss": 3.378728332519531, "indexer_kl": 0.0, "lr": 0.00021176072493996599, "tokens_per_s": 2365549.9899927382 }, { "step": 38650, "loss": 3.3529678344726563, "indexer_kl": 0.0, "lr": 0.00021120616072693317, "tokens_per_s": 2365552.3495495366 }, { "step": 38700, "loss": 3.38170654296875, "indexer_kl": 0.0, "lr": 0.0002106649072522032, "tokens_per_s": 2365553.140338392 }, { "step": 38750, "loss": 3.3904241943359374, "indexer_kl": 0.0, "lr": 0.00021013697262168635, "tokens_per_s": 2365544.5532606714 }, { "step": 38800, "loss": 3.3856167602539062, "indexer_kl": 0.0, "lr": 0.00020962236474182793, "tokens_per_s": 2365545.1869549896 }, { "step": 38850, "loss": 3.384383544921875, "indexer_kl": 0.0, "lr": 0.0002091210913194892, "tokens_per_s": 2365547.1422957005 }, { "step": 38900, "loss": 3.385108642578125, "indexer_kl": 0.0, "lr": 0.00020863315986183208, "tokens_per_s": 2365547.937801769 }, { "step": 38950, "loss": 3.3881201171875, "indexer_kl": 0.0, "lr": 0.00020815857767620695, "tokens_per_s": 2365549.3661198043 }, { "step": 39000, "loss": 3.3837844848632814, "indexer_kl": 0.0, "lr": 0.00020769735187004307, "tokens_per_s": 2365551.853544254 }, { "step": 39050, "loss": 3.382044677734375, "indexer_kl": 0.0, "lr": 0.00020724948935074187, "tokens_per_s": 2365554.623763328 }, { "step": 39100, "loss": 3.40516845703125, "indexer_kl": 0.0, "lr": 0.00020681499682557417, "tokens_per_s": 2365555.693733731 }, { "step": 39150, "loss": 3.395960693359375, "indexer_kl": 0.0, "lr": 0.0002063938808015789, "tokens_per_s": 2365557.4750921633 }, { "step": 39200, "loss": 3.380354309082031, "indexer_kl": 0.0, "lr": 0.0002059861475854664, "tokens_per_s": 2365558.216023141 }, { "step": 39250, "loss": 3.386961669921875, "indexer_kl": 0.0, "lr": 0.00020559180328352347, "tokens_per_s": 2365559.6825830545 }, { "step": 39300, "loss": 3.385447692871094, "indexer_kl": 0.0, "lr": 0.00020521085380152226, "tokens_per_s": 2365561.2952898946 }, { "step": 39350, "loss": 3.3808663940429686, "indexer_kl": 0.0, "lr": 0.0002048433048446314, "tokens_per_s": 2365562.4562204685 }, { "step": 39400, "loss": 3.3834735107421876, "indexer_kl": 0.0, "lr": 0.00020448916191733108, "tokens_per_s": 2365563.2070510504 }, { "step": 39450, "loss": 3.37839111328125, "indexer_kl": 0.0, "lr": 0.0002041484303233302, "tokens_per_s": 2365563.808047683 }, { "step": 39500, "loss": 3.37897216796875, "indexer_kl": 0.0, "lr": 0.00020382111516548712, "tokens_per_s": 2365566.805788429 }, { "step": 39550, "loss": 3.3824636840820315, "indexer_kl": 0.0, "lr": 0.00020350722134573315, "tokens_per_s": 2365567.1570761222 }, { "step": 39600, "loss": 3.3890386962890626, "indexer_kl": 0.0, "lr": 0.00020320675356499935, "tokens_per_s": 2365568.0236191605 }, { "step": 39650, "loss": 3.384942932128906, "indexer_kl": 0.0, "lr": 0.00020291971632314585, "tokens_per_s": 2365568.205447041 }, { "step": 39700, "loss": 3.3884347534179686, "indexer_kl": 0.0, "lr": 0.00020264611391889467, "tokens_per_s": 2365569.0083201993 }, { "step": 39750, "loss": 3.386165771484375, "indexer_kl": 0.0, "lr": 0.00020238595044976525, "tokens_per_s": 2365569.447939852 }, { "step": 39800, "loss": 3.386243896484375, "indexer_kl": 0.0, "lr": 0.00020213922981201298, "tokens_per_s": 2365569.7630122425 }, { "step": 39850, "loss": 3.3865347290039063, "indexer_kl": 0.0, "lr": 0.00020190595570057098, "tokens_per_s": 2365570.8885429734 }, { "step": 39900, "loss": 3.3962271118164065, "indexer_kl": 0.0, "lr": 0.00020168613160899488, "tokens_per_s": 2365572.0275810123 }, { "step": 39950, "loss": 3.387021484375, "indexer_kl": 0.0, "lr": 0.00020147976082941028, "tokens_per_s": 2365573.0584548744 }, { "step": 40000, "loss": 3.3888458251953124, "indexer_kl": 0.0, "lr": 0.00020128684645246355, "tokens_per_s": 2365573.735917783 }, { "step": 40050, "loss": 3.3792205810546876, "indexer_kl": 0.0, "lr": 0.00020110739136727546, "tokens_per_s": 2365574.6190810925 }, { "step": 40100, "loss": 3.3882159423828124, "indexer_kl": 0.0, "lr": 0.00020094139826139803, "tokens_per_s": 2365576.422665454 }, { "step": 40150, "loss": 3.3859133911132813, "indexer_kl": 0.0, "lr": 0.00020078886962077437, "tokens_per_s": 2365576.8770693885 }, { "step": 40200, "loss": 3.398948059082031, "indexer_kl": 0.0, "lr": 0.00020064980772970098, "tokens_per_s": 2365578.8239370845 }, { "step": 40250, "loss": 3.375940856933594, "indexer_kl": 0.0, "lr": 0.0002005242146707941, "tokens_per_s": 2365580.50700682 }, { "step": 40300, "loss": 3.3951080322265623, "indexer_kl": 0.0, "lr": 0.0002004120923249583, "tokens_per_s": 2365581.48877839 }, { "step": 40350, "loss": 3.374814147949219, "indexer_kl": 0.0, "lr": 0.00020031344237135814, "tokens_per_s": 2365582.001925761 }, { "step": 40400, "loss": 3.382310791015625, "indexer_kl": 0.0, "lr": 0.00020022826628739336, "tokens_per_s": 2365583.054669233 }, { "step": 40450, "loss": 3.394410400390625, "indexer_kl": 0.0, "lr": 0.0002001565653486765, "tokens_per_s": 2365583.5464946576 }, { "step": 40500, "loss": 3.3925991821289063, "indexer_kl": 0.0, "lr": 0.00020009834062901385, "tokens_per_s": 2365585.3085234594 }, { "step": 40550, "loss": 3.3853573608398437, "indexer_kl": 0.0, "lr": 0.00020005359300038936, "tokens_per_s": 2365587.840036578 }, { "step": 40600, "loss": 3.371038818359375, "indexer_kl": 0.0, "lr": 0.00020002232313295166, "tokens_per_s": 2365587.852807129 }, { "step": 40650, "loss": 3.3825149536132812, "indexer_kl": 0.0, "lr": 0.00020000453149500406, "tokens_per_s": 2365589.551626396 }, { "step": 40690, "loss": 3.393650436401367, "indexer_kl": 0.0, "lr": 0.00020000000269571616, "tokens_per_s": 2365583.2751520397 } ] }