Apollo / logs /train_log.jsonl
viknesh100's picture
last 2026-10-25 16:22:51
5ba4d62 verified
Raw History Blame Contribute Delete
20.9 kB
{"step": 50, "loss": 2.8028659224510193, "lr": 5.1000000000000006e-05, "tok_s": 11552.598915382217}
{"step": 100, "loss": 1.9497060179710388, "lr": 0.000101, "tok_s": 11589.358527980765}
{"step": 150, "loss": 1.4341304898262024, "lr": 0.00015099999999999998, "tok_s": 11507.257010373407}
{"step": 200, "loss": 1.3642685413360596, "lr": 0.000201, "tok_s": 11730.637570505623}
{"step": 250, "loss": 1.2710880041122437, "lr": 0.000251, "tok_s": 11572.573544045186}
{"step": 300, "loss": 1.287171095609665, "lr": 0.000301, "tok_s": 10364.39865200342}
{"step": 350, "loss": 1.3047236204147339, "lr": 0.000351, "tok_s": 11662.621572755463}
{"step": 400, "loss": 1.1884667873382568, "lr": 0.00040100000000000004, "tok_s": 11501.386997607895}
{"step": 450, "loss": 1.2781931161880493, "lr": 0.000451, "tok_s": 11503.038991437197}
{"step": 500, "loss": 1.2782181799411774, "lr": 0.0005, "tok_s": 11562.246985499703}
{"step": 500, "val": 1.2303815489162646}
{"step": 550, "loss": 1.1694680154323578, "lr": 0.0004999927000362188, "tok_s": 9753.121227195616}
{"step": 600, "loss": 1.1975727677345276, "lr": 0.0004999708006185593, "tok_s": 11637.334002358119}
{"step": 650, "loss": 1.1599978506565094, "lr": 0.0004999343031680435, "tok_s": 11395.358530310064}
{"step": 700, "loss": 1.163205862045288, "lr": 0.0004998832100529384, "tok_s": 11644.465670051819}
{"step": 750, "loss": 1.1639525294303894, "lr": 0.0004998175245886032, "tok_s": 11166.24466544801}
{"step": 800, "loss": 1.1093396246433258, "lr": 0.0004997372510372735, "tok_s": 10110.679896371572}
{"step": 850, "loss": 1.1807280778884888, "lr": 0.0004996423946077849, "tok_s": 11754.688905823192}
{"step": 900, "loss": 1.1615480482578278, "lr": 0.0004995329614552355, "tok_s": 11799.123037683841}
{"step": 950, "loss": 1.0689589083194733, "lr": 0.0004994089586805856, "tok_s": 11680.25408177374}
{"step": 1000, "loss": 1.0942313075065613, "lr": 0.0004992703943301972, "tok_s": 11554.724351694773}
{"step": 1000, "val": 1.11277735084536}
{"step": 1050, "loss": 1.0733357220888138, "lr": 0.0004991172773953129, "tok_s": 9399.217223882995}
{"step": 1100, "loss": 1.0639665573835373, "lr": 0.000498949617811471, "tok_s": 11486.31056071279}
{"step": 1150, "loss": 1.0982843339443207, "lr": 0.0004987674264578614, "tok_s": 11326.930158767456}
{"step": 1200, "loss": 1.1902237236499786, "lr": 0.0004985707151566204, "tok_s": 11534.502449073025}
{"step": 1250, "loss": 1.1196982860565186, "lr": 0.0004983594966720621, "tok_s": 11888.318458055766}
{"step": 1300, "loss": 1.1175005733966827, "lr": 0.0004981337847098515, "tok_s": 10214.068944815484}
{"step": 1350, "loss": 1.0803119838237762, "lr": 0.0004978935939161141, "tok_s": 11178.970856420934}
{"step": 1400, "loss": 1.1061341166496277, "lr": 0.0004976389398764864, "tok_s": 11487.023716313572}
{"step": 1450, "loss": 1.0312305688858032, "lr": 0.0004973698391151043, "tok_s": 11231.070536687095}
{"step": 1500, "loss": 0.9659281671047211, "lr": 0.0004970863090935304, "tok_s": 11226.159486114655}
{"step": 1500, "val": 1.05957053480797}
{"step": 1550, "loss": 1.011614352464676, "lr": 0.0004967883682096214, "tok_s": 6704.42094367761}
{"step": 1600, "loss": 1.0625123083591461, "lr": 0.0004964760357963345, "tok_s": 11490.557096428607}
{"step": 1650, "loss": 1.0165170282125473, "lr": 0.0004961493321204723, "tok_s": 11740.80025139491}
{"step": 1700, "loss": 1.0327295362949371, "lr": 0.000495808278381368, "tok_s": 11638.61440045709}
{"step": 1750, "loss": 1.0872966647148132, "lr": 0.0004954528967095102, "tok_s": 11625.900581816122}
{"step": 1800, "loss": 1.0192022621631622, "lr": 0.0004950832101651062, "tok_s": 10138.620092399811}
{"step": 1850, "loss": 1.108778938651085, "lr": 0.0004946992427365862, "tok_s": 11919.693803213151}
{"step": 1900, "loss": 1.0043965429067612, "lr": 0.0004943010193390463, "tok_s": 11551.08261486249}
{"step": 1950, "loss": 1.0240698605775833, "lr": 0.0004938885658126319, "tok_s": 11555.541021284836}
{"step": 2000, "loss": 1.0520465672016144, "lr": 0.0004934619089208617, "tok_s": 11835.184937356122}
{"step": 2000, "val": 1.0306326885984347}
{"step": 2050, "loss": 0.9558898210525513, "lr": 0.0004930210763488896, "tok_s": 9431.63391432083}
{"step": 2100, "loss": 1.1127627193927765, "lr": 0.0004925660967017097, "tok_s": 11306.87947014527}
{"step": 2150, "loss": 0.9377566874027252, "lr": 0.0004920969995022991, "tok_s": 11477.956421235065}
{"step": 2200, "loss": 0.9158404171466827, "lr": 0.0004916138151897029, "tok_s": 11438.149299703851}
{"step": 2250, "loss": 0.9491850137710571, "lr": 0.0004911165751170588, "tok_s": 10902.9688445616}
{"step": 2300, "loss": 0.9459744989871979, "lr": 0.0004906053115495624, "tok_s": 11105.443409350219}
{"step": 2350, "loss": 0.9584931284189224, "lr": 0.0004900800576623741, "tok_s": 11372.444075852156}
{"step": 2400, "loss": 1.003243327140808, "lr": 0.0004895408475384656, "tok_s": 11364.128072708927}
{"step": 2450, "loss": 1.0431920439004898, "lr": 0.0004889877161664096, "tok_s": 11223.018779697995}
{"step": 2500, "loss": 1.0404050946235657, "lr": 0.0004884206994381077, "tok_s": 11530.480610719782}
{"step": 2500, "val": 1.0162541255538677}
{"step": 2550, "loss": 0.9785652458667755, "lr": 0.00048783983414646317, "tok_s": 10281.700503737515}
{"step": 2600, "loss": 1.0436426550149918, "lr": 0.00048724515798299217, "tok_s": 11634.371053517274}
{"step": 2650, "loss": 1.1103270947933197, "lr": 0.0004866367095353789, "tok_s": 11056.127020705517}
{"step": 2700, "loss": 0.950615182518959, "lr": 0.00048601452828497105, "tok_s": 11526.497592910251}
{"step": 2750, "loss": 1.0283890217542648, "lr": 0.0004853786546042184, "tok_s": 11666.564765511455}
{"step": 2800, "loss": 0.9967371821403503, "lr": 0.0004847291297540528, "tok_s": 10199.338517363227}
{"step": 2850, "loss": 0.9842794686555862, "lr": 0.000484065995881211, "tok_s": 11835.055291031998}
{"step": 2900, "loss": 0.9477149248123169, "lr": 0.00048338929601549974, "tok_s": 11048.32031848698}
{"step": 2950, "loss": 1.0679392516613007, "lr": 0.0004826990740670035, "tok_s": 12326.74366007212}
{"step": 3000, "loss": 1.0268112570047379, "lr": 0.0004819953748232355, "tok_s": 11524.361935668105}
{"step": 3000, "val": 1.0056617164024308}
{"step": 3050, "loss": 0.8380935788154602, "lr": 0.0004812782439462311, "tok_s": 9236.681905245903}
{"step": 3100, "loss": 0.922642171382904, "lr": 0.00048054772796958517, "tok_s": 11703.74553658057}
{"step": 3150, "loss": 1.0035590380430222, "lr": 0.0004798038742954328, "tok_s": 11861.711256992668}
{"step": 3200, "loss": 0.8704427033662796, "lr": 0.0004790467311913727, "tok_s": 11622.985913125389}
{"step": 3250, "loss": 0.9539512693881989, "lr": 0.000478276347787336, "tok_s": 11735.285151458536}
{"step": 3300, "loss": 0.9530164301395416, "lr": 0.0004774927740723977, "tok_s": 10195.81031675594}
{"step": 3350, "loss": 0.951401486992836, "lr": 0.00047669606089153333, "tok_s": 11692.711896531971}
{"step": 3400, "loss": 1.0514138340950012, "lr": 0.0004758862599423194, "tok_s": 11741.993986408821}
{"step": 3450, "loss": 0.9536926448345184, "lr": 0.0004750634237715791, "tok_s": 11685.213397338779}
{"step": 3500, "loss": 0.9804253131151199, "lr": 0.0004742276057719722, "tok_s": 11621.918138409417}
{"step": 3500, "val": 0.992344190807752}
{"step": 3550, "loss": 1.0051552951335907, "lr": 0.00047337886017853115, "tok_s": 9746.121056909162}
{"step": 3600, "loss": 0.9926250576972961, "lr": 0.00047251724206514103, "tok_s": 11597.446375034846}
{"step": 3650, "loss": 0.9381612986326218, "lr": 0.0004716428073409666, "tok_s": 11176.349479128861}
{"step": 3700, "loss": 1.0210675746202469, "lr": 0.0004707556127468238, "tok_s": 11324.653280241391}
{"step": 3750, "loss": 0.970032349228859, "lr": 0.00046985571585149877, "tok_s": 11326.496636168933}
{"step": 3800, "loss": 0.999545618891716, "lr": 0.00046894317504801107, "tok_s": 10225.938349523994}
{"step": 3850, "loss": 1.0156055688858032, "lr": 0.00046801804954982594, "tok_s": 11700.692179168767}
{"step": 3900, "loss": 1.0276009738445282, "lr": 0.0004670803993870113, "tok_s": 11151.554240169788}
{"step": 3950, "loss": 0.9460368752479553, "lr": 0.00046613028540234226, "tok_s": 11493.898738517186}
{"step": 4000, "loss": 0.9760070890188217, "lr": 0.00046516776924735386, "tok_s": 11698.29862842279}
{"step": 4000, "val": 0.9860499541033672}
{"step": 4050, "loss": 1.0344319343566895, "lr": 0.00046419291337834, "tok_s": 5297.005207523198}
{"step": 4100, "loss": 0.965756818652153, "lr": 0.000463205781052301, "tok_s": 11623.745917981978}
{"step": 4150, "loss": 1.0032114535570145, "lr": 0.00046220643632283897, "tok_s": 11480.679093131625}
{"step": 4200, "loss": 0.9334534406661987, "lr": 0.00046119494403600123, "tok_s": 11406.116165598372}
{"step": 4250, "loss": 1.0164708644151688, "lr": 0.0004601713698260727, "tok_s": 11466.300681720002}
{"step": 4300, "loss": 1.0036650002002716, "lr": 0.00045913578011131707, "tok_s": 10141.077852688666}
{"step": 4350, "loss": 0.9906778186559677, "lr": 0.00045808824208966694, "tok_s": 11638.272867252601}
{"step": 4400, "loss": 1.0169064104557037, "lr": 0.00045702882373436317, "tok_s": 11354.72472732349}
{"step": 4450, "loss": 1.0073717534542084, "lr": 0.00045595759378954477, "tok_s": 11782.418575819584}
{"step": 4500, "loss": 1.0174897760152817, "lr": 0.0004548746217657878, "tok_s": 11560.028122839394}
{"step": 4500, "val": 0.9816185243748854}
{"step": 4550, "loss": 0.9217008501291275, "lr": 0.0004537799779355947, "tok_s": 9538.120034670928}
{"step": 4600, "loss": 0.9363394528627396, "lr": 0.0004526737333288351, "tok_s": 11619.155439024462}
{"step": 4650, "loss": 1.0208152532577515, "lr": 0.0004515559597281362, "tok_s": 11345.028843358494}
{"step": 4700, "loss": 0.9493127763271332, "lr": 0.000450426729664225, "tok_s": 11719.154670895525}
{"step": 4750, "loss": 0.9685873985290527, "lr": 0.00044928611641122226, "tok_s": 11201.26461135152}
{"step": 4800, "loss": 0.9956986904144287, "lr": 0.00044813419398188735, "tok_s": 10132.215659469719}
{"step": 4850, "loss": 0.8821884095668793, "lr": 0.00044697103712281584, "tok_s": 11717.309645108237}
{"step": 4900, "loss": 0.9659938961267471, "lr": 0.00044579672130958957, "tok_s": 11524.500850994255}
{"step": 4950, "loss": 1.0071173012256622, "lr": 0.00044461132274187877, "tok_s": 11282.860116696014}
{"step": 5000, "loss": 0.8721496760845184, "lr": 0.00044341491833849774, "tok_s": 11607.678039241935}
{"step": 5000, "val": 0.97480074131469}
{"step": 5050, "loss": 0.9395202547311783, "lr": 0.0004422075857324137, "tok_s": 9286.639209682688}
{"step": 5100, "loss": 0.9885113686323166, "lr": 0.0004409894032657093, "tok_s": 11746.714756535626}
{"step": 5150, "loss": 0.9291734397411346, "lr": 0.0004397604499844991, "tok_s": 11530.919993018828}
{"step": 5200, "loss": 0.9205205589532852, "lr": 0.00043852080563380025, "tok_s": 11840.745792387617}
{"step": 5250, "loss": 0.98750239610672, "lr": 0.0004372705506523583, "tok_s": 11292.382442400472}
{"step": 5300, "loss": 0.9522096961736679, "lr": 0.00043600976616742725, "tok_s": 10260.04712666266}
{"step": 5350, "loss": 0.981817901134491, "lr": 0.00043473853398950566, "tok_s": 11888.156363283502}
{"step": 5400, "loss": 0.9003369957208633, "lr": 0.00043345693660702764, "tok_s": 10911.079116496805}
{"step": 5450, "loss": 0.9559416323900223, "lr": 0.0004321650571810109, "tok_s": 12087.949784463652}
{"step": 5500, "loss": 0.974891871213913, "lr": 0.0004308629795396599, "tok_s": 11380.297840264166}
{"step": 5500, "val": 0.9696236983085492}
{"step": 5550, "loss": 0.9151506274938583, "lr": 0.00042955078817292694, "tok_s": 9465.688302522582}
{"step": 5600, "loss": 0.9893773794174194, "lr": 0.00042822856822702935, "tok_s": 11796.957781902658}
{"step": 5650, "loss": 0.9009336978197098, "lr": 0.00042689640549892465, "tok_s": 11667.289010607941}
{"step": 5700, "loss": 0.8839318305253983, "lr": 0.0004255543864307431, "tok_s": 11595.156083009204}
{"step": 5750, "loss": 0.9286369830369949, "lr": 0.0004242025981041789, "tok_s": 11174.161847579357}
{"step": 5800, "loss": 0.9847307354211807, "lr": 0.0004228411282348395, "tok_s": 9942.029980207022}
{"step": 5850, "loss": 0.9574754536151886, "lr": 0.0004214700651665534, "tok_s": 11257.411060782706}
{"step": 5900, "loss": 0.995709627866745, "lr": 0.0004200894978656384, "tok_s": 11761.224944949214}
{"step": 5950, "loss": 0.8774397522211075, "lr": 0.0004186995159151283, "tok_s": 11694.495624954956}
{"step": 6000, "loss": 0.9471210688352585, "lr": 0.0004173002095089599, "tok_s": 11272.9472678596}
{"step": 6000, "val": 0.9611533339643262}
{"step": 6050, "loss": 1.0156346261501312, "lr": 0.0004158916694461206, "tok_s": 9739.558154579505}
{"step": 6100, "loss": 0.9734700471162796, "lr": 0.0004144739871247566, "tok_s": 11393.290888783686}
{"step": 6150, "loss": 0.9343434721231461, "lr": 0.000413047254536242, "tok_s": 11501.551279032587}
{"step": 6200, "loss": 1.0079717934131622, "lr": 0.00041161156425921004, "tok_s": 11460.807090200768}
{"step": 6250, "loss": 0.9110617190599442, "lr": 0.0004101670094535453, "tok_s": 11692.005473906802}
{"step": 6300, "loss": 0.9644292294979095, "lr": 0.00040871368385433894, "tok_s": 10152.085817299067}
{"step": 6350, "loss": 0.925446942448616, "lr": 0.0004072516817658065, "tok_s": 11507.7521884764}
{"step": 6400, "loss": 0.9550258219242096, "lr": 0.00040578109805516823, "tok_s": 11480.200716422149}
{"step": 6450, "loss": 1.0059584081172943, "lr": 0.00040430202814649386, "tok_s": 11263.968075311124}
{"step": 6500, "loss": 0.884832039475441, "lr": 0.00040281456801451003, "tok_s": 11605.29633880577}
{"step": 6500, "val": 0.9599877314996045}
{"step": 6550, "loss": 1.0062945485115051, "lr": 0.0004013188141783732, "tok_s": 9309.62340920016}
{"step": 6600, "loss": 0.9999616146087646, "lr": 0.00039981486369540623, "tok_s": 11621.909306073661}
{"step": 6650, "loss": 0.9427875131368637, "lr": 0.0003983028141548008, "tok_s": 11453.583991816397}
{"step": 6700, "loss": 0.9787264764308929, "lr": 0.00039678276367128456, "tok_s": 11800.93383582994}
{"step": 6750, "loss": 0.9591351747512817, "lr": 0.00039525481087875525, "tok_s": 11123.249564176658}
{"step": 6800, "loss": 0.8588589429855347, "lr": 0.0003937190549238799, "tok_s": 10676.450615775106}
{"step": 6850, "loss": 0.9168222546577454, "lr": 0.00039217559545966154, "tok_s": 11401.364827861378}
{"step": 6900, "loss": 0.9095785021781921, "lr": 0.00039062453263897297, "tok_s": 11830.040166112909}
{"step": 6950, "loss": 0.8336162120103836, "lr": 0.0003890659671080579, "tok_s": 11552.610785696475}
{"step": 7000, "loss": 0.897206500172615, "lr": 0.00038750000000000004, "tok_s": 11717.52582057227}
{"step": 7000, "val": 0.9517536415514984}
{"step": 7050, "loss": 0.9109133780002594, "lr": 0.00038592673292816096, "tok_s": 9434.791862260514}
{"step": 7100, "loss": 1.0114559978246689, "lr": 0.00038434626797958637, "tok_s": 10540.335234296823}
{"step": 7150, "loss": 0.9344796240329742, "lr": 0.00038275870770838194, "tok_s": 11583.24355450805}
{"step": 7200, "loss": 1.0006868541240692, "lr": 0.0003811641551290585, "tok_s": 11535.484609849753}
{"step": 7250, "loss": 0.8796019852161407, "lr": 0.00037956271370984796, "tok_s": 11622.747946844444}
{"step": 7300, "loss": 0.9174224585294724, "lr": 0.000377954487365989, "tok_s": 11301.934139064853}
{"step": 7350, "loss": 0.9398274123668671, "lr": 0.0003763395804529843, "tok_s": 11758.831223379582}
{"step": 7400, "loss": 0.8948804289102554, "lr": 0.0003747180977598293, "tok_s": 11620.264897862884}
{"step": 7450, "loss": 0.8398376554250717, "lr": 0.0003730901445022123, "tok_s": 11317.74285077296}
{"step": 7500, "loss": 0.9142066687345505, "lr": 0.0003714558263156872, "tok_s": 11828.59581917065}
{"step": 7500, "val": 0.9503500261869426}
{"step": 7550, "loss": 0.9116263836622238, "lr": 0.0003698152492488191, "tok_s": 9612.287703829546}
{"step": 7600, "loss": 0.9790852218866348, "lr": 0.0003681685197563027, "tok_s": 11928.681148666805}
{"step": 7650, "loss": 1.014655277132988, "lr": 0.0003665157446920551, "tok_s": 11655.7058840645}
{"step": 7700, "loss": 0.9283265322446823, "lr": 0.00036485703130228147, "tok_s": 11249.434982691966}
{"step": 7750, "loss": 1.0162805169820786, "lr": 0.0003631924872185169, "tok_s": 11395.550941614047}
{"step": 7800, "loss": 0.954286515712738, "lr": 0.0003615222204506415, "tok_s": 10705.30918217756}
{"step": 7850, "loss": 0.911504477262497, "lr": 0.0003598463393798721, "tok_s": 11703.895325554678}
{"step": 7900, "loss": 1.0585387200117111, "lr": 0.00035816495275173, "tok_s": 11696.353545427748}
{"step": 7950, "loss": 0.8546959608793259, "lr": 0.0003564781696689838, "tok_s": 11434.262589851927}
{"step": 8000, "loss": 0.9698650538921356, "lr": 0.0003547860995845705, "tok_s": 11603.74468574655}
{"step": 8000, "val": 0.9458130263105567}
{"step": 8050, "loss": 0.9880534559488297, "lr": 0.00035308885229449316, "tok_s": 9655.124173147819}
{"step": 8100, "loss": 0.9275493323802948, "lr": 0.0003513865379306961, "tok_s": 11004.957054099046}
{"step": 8150, "loss": 0.9639717489480972, "lr": 0.0003496792669539189, "tok_s": 11744.564217754145}
{"step": 8200, "loss": 0.9406543374061584, "lr": 0.00034796715014652864, "tok_s": 11435.237235603576}
{"step": 8250, "loss": 0.924078643321991, "lr": 0.00034625029860533137, "tok_s": 12020.552146555481}
{"step": 8300, "loss": 1.0230797976255417, "lr": 0.0003445288237343632, "tok_s": 10896.177029730932}
{"step": 8350, "loss": 0.8909507542848587, "lr": 0.0003428028372376616, "tok_s": 11361.22741895809}
{"step": 8400, "loss": 0.9881814271211624, "lr": 0.000341072451112017, "tok_s": 11646.900736459189}
{"step": 8450, "loss": 0.9249340891838074, "lr": 0.00033933777763970506, "tok_s": 11042.831427447185}
{"step": 8500, "loss": 0.9522179812192917, "lr": 0.00033759892938120187, "tok_s": 11541.118154036021}
{"step": 8500, "val": 0.9413201191527985}
{"step": 8550, "loss": 0.8793904930353165, "lr": 0.0003358560191678789, "tok_s": 9154.740128206668}
{"step": 8600, "loss": 0.9102108329534531, "lr": 0.00033410916009468205, "tok_s": 11829.148722013313}
{"step": 8650, "loss": 0.8403000384569168, "lr": 0.0003323584655127935, "tok_s": 11800.404228018604}
{"step": 8700, "loss": 0.9125953167676926, "lr": 0.0003306040490222757, "tok_s": 11665.622368045373}
{"step": 8750, "loss": 0.9345011115074158, "lr": 0.00032884602446470054, "tok_s": 11502.78527665403}
{"step": 8800, "loss": 0.9377343505620956, "lr": 0.00032708450591576225, "tok_s": 10616.445943003491}
{"step": 8850, "loss": 1.0096127539873123, "lr": 0.00032531960767787505, "tok_s": 11469.318854810545}
{"step": 8900, "loss": 0.9317106604576111, "lr": 0.00032355144427275643, "tok_s": 11138.75241225665}
{"step": 8950, "loss": 0.9293224811553955, "lr": 0.0003217801304339958, "tok_s": 11247.340473217446}
{"step": 9000, "loss": 0.964231863617897, "lr": 0.00032000578109961, "tok_s": 11340.567425741032}
{"step": 9000, "val": 0.9389676964853613}
{"step": 9050, "loss": 0.8604180365800858, "lr": 0.0003182285114045844, "tok_s": 9617.351521222936}
{"step": 9100, "loss": 0.8690464347600937, "lr": 0.0003164484366734026, "tok_s": 10216.780959769232}
{"step": 9150, "loss": 0.8417228758335114, "lr": 0.00031466567241256307, "tok_s": 11541.702645298923}
{"step": 9200, "loss": 0.8443079143762589, "lr": 0.0003128803343030836, "tok_s": 11634.265785426089}
{"step": 9250, "loss": 0.9757714718580246, "lr": 0.0003110925381929961, "tok_s": 11398.204709355263}
{"step": 9300, "loss": 0.9590603411197662, "lr": 0.0003093024000898277, "tok_s": 10411.333719886072}
{"step": 9350, "loss": 0.9241775721311569, "lr": 0.0003075100361530748, "tok_s": 11693.941419259121}
{"step": 9400, "loss": 0.9348391741514206, "lr": 0.00030571556268666465, "tok_s": 11712.477724803488}
{"step": 9450, "loss": 0.8580559343099594, "lr": 0.0003039190961314088, "tok_s": 11813.136524587573}
{"step": 9500, "loss": 0.9944417774677277, "lr": 0.0003021207530574477, "tok_s": 11608.198047003738}
{"step": 9500, "val": 0.9355872968198322}
{"step": 9550, "loss": 0.9577423483133316, "lr": 0.00030032065015668627, "tok_s": 9534.848452471158}
{"step": 9600, "loss": 0.9909506291151047, "lr": 0.0002985189042352221, "tok_s": 12062.44303286884}
{"step": 9650, "loss": 0.8807881623506546, "lr": 5.150541507043142e-05, "tok_s": 12206.208918833974}
{"step": 9700, "loss": 0.8910769075155258, "lr": 5.110634692737243e-05, "tok_s": 10753.538505919938}
{"step": 9750, "loss": 0.8895992785692215, "lr": 5.076848907349929e-05, "tok_s": 11421.998198297353}
{"step": 9800, "loss": 0.8433485478162766, "lr": 5.049193387577573e-05, "tok_s": 10341.461850629155}
{"step": 9850, "loss": 0.8942935466766357, "lr": 5.0276756941631436e-05, "tok_s": 11306.013554883324}
{"step": 9900, "loss": 0.9275110810995102, "lr": 5.012301709829164e-05, "tok_s": 11747.883706671695}
{"step": 9950, "loss": 0.8948111087083817, "lr": 5.003075637669448e-05, "tok_s": 11318.57667123224}
{"step": 10000, "loss": 0.8525521159172058, "lr": 5e-05, "tok_s": 11364.966562504143}
{"step": 10000, "val": 0.923981524555829}