Slayer1B-1.02-checkpoints / run /metrics.jsonl
Maggio33's picture
Run finished: all 25 checkpoint sums; run record
90d8986 verified
Raw History Blame Contribute Delete
29.7 kB
{"step": 2260, "loss": 2.6378720313310624, "lr": 0.0006, "tok_s": 54163.695954675175}
{"step": 2270, "loss": 2.6460640758275984, "lr": 0.0006, "tok_s": 113488.50294930224}
{"step": 2280, "loss": 2.653155395388603, "lr": 0.0006, "tok_s": 113230.54847007773}
{"step": 2290, "loss": 2.6472118228673933, "lr": 0.0006, "tok_s": 113190.92124895199}
{"step": 2300, "loss": 2.643577426671982, "lr": 0.0006, "tok_s": 113098.68795347646}
{"step": 2310, "loss": 2.6365307360887527, "lr": 0.0006, "tok_s": 113221.80939415}
{"step": 2320, "loss": 2.6296934127807616, "lr": 0.0006, "tok_s": 113236.62872436077}
{"step": 2330, "loss": 2.6421230286359787, "lr": 0.0006, "tok_s": 113292.30348617081}
{"step": 2340, "loss": 2.635071650147438, "lr": 0.0006, "tok_s": 113237.98882457404}
{"step": 2350, "loss": 2.6248689711093904, "lr": 0.0006, "tok_s": 113262.57305575028}
{"step": 2360, "loss": 2.6174856185913087, "lr": 0.0006, "tok_s": 113301.48777098813}
{"step": 2370, "loss": 2.619669410586357, "lr": 0.0006, "tok_s": 113344.54925072301}
{"step": 2380, "loss": 2.625941291451454, "lr": 0.0006, "tok_s": 113443.01682762847}
{"step": 2390, "loss": 2.617666631937027, "lr": 0.0006, "tok_s": 113352.53425671047}
{"step": 2400, "loss": 2.6314773172140122, "lr": 0.0006, "tok_s": 113379.56437417993}
{"step": 2410, "loss": 2.636362352967262, "lr": 0.0006, "tok_s": 103710.16530619493}
{"step": 2420, "loss": 2.6255384594202043, "lr": 0.0006, "tok_s": 113315.05678284209}
{"step": 2430, "loss": 2.6180602222681046, "lr": 0.0006, "tok_s": 113253.22563764181}
{"step": 2440, "loss": 2.6159376561641694, "lr": 0.0006, "tok_s": 113251.32507680678}
{"step": 2450, "loss": 2.6271055400371552, "lr": 0.0006, "tok_s": 113259.65541302253}
{"step": 2460, "loss": 2.6269268840551376, "lr": 0.0006, "tok_s": 113265.98148917091}
{"step": 2470, "loss": 2.6160128891468046, "lr": 0.0006, "tok_s": 113418.96638907543}
{"step": 2480, "loss": 2.625563257932663, "lr": 0.0006, "tok_s": 113387.51280404892}
{"step": 2490, "loss": 2.633164280653, "lr": 0.0006, "tok_s": 113373.57075807398}
{"step": 2500, "loss": 2.623558396100998, "lr": 0.0006, "tok_s": 113429.57220360303}
{"step": 2510, "loss": 2.6179771780967713, "lr": 0.0006, "tok_s": 113347.27817685794}
{"step": 2520, "loss": 2.616503244638443, "lr": 0.0006, "tok_s": 113324.7297746929}
{"step": 2530, "loss": 2.601152727007866, "lr": 0.0006, "tok_s": 113268.21421905964}
{"step": 2540, "loss": 2.6064374834299087, "lr": 0.0006, "tok_s": 113219.90434975743}
{"step": 2550, "loss": 2.6060184240341187, "lr": 0.0006, "tok_s": 113163.21258235228}
{"step": 2560, "loss": 2.593849849700928, "lr": 0.0006, "tok_s": 104294.77181017162}
{"step": 2570, "loss": 2.606165447831154, "lr": 0.0006, "tok_s": 113333.0539747935}
{"step": 2580, "loss": 2.6027530133724213, "lr": 0.0006, "tok_s": 113214.97677297554}
{"step": 2590, "loss": 2.609057742357254, "lr": 0.0006, "tok_s": 113178.10569858113}
{"step": 2600, "loss": 2.607905259728432, "lr": 0.0006, "tok_s": 113193.803013775}
{"step": 2610, "loss": 2.6177456051111223, "lr": 0.0006, "tok_s": 113198.54665063276}
{"step": 2620, "loss": 2.5998134881258013, "lr": 0.0006, "tok_s": 113183.25551335078}
{"step": 2630, "loss": 2.5993745803833006, "lr": 0.0006, "tok_s": 112992.14466014972}
{"step": 2640, "loss": 2.600064641237259, "lr": 0.0006, "tok_s": 113120.96347341369}
{"step": 2650, "loss": 2.6212158262729646, "lr": 0.0006, "tok_s": 113194.0293777815}
{"step": 2660, "loss": 2.5813804030418397, "lr": 0.0006, "tok_s": 113227.98432384146}
{"step": 2670, "loss": 2.600023439526558, "lr": 0.0006, "tok_s": 113302.24580075931}
{"step": 2680, "loss": 2.5943311184644697, "lr": 0.0006, "tok_s": 113405.55699928511}
{"step": 2690, "loss": 2.591424310207367, "lr": 0.0006, "tok_s": 113344.4256897398}
{"step": 2700, "loss": 2.5958881229162216, "lr": 0.0006, "tok_s": 113295.10898888392}
{"step": 2710, "loss": 2.6001838117837908, "lr": 0.0006, "tok_s": 104284.22304904599}
{"step": 2720, "loss": 2.589606782793999, "lr": 0.0006, "tok_s": 113130.26055238869}
{"step": 2730, "loss": 2.6118201702833175, "lr": 0.0006, "tok_s": 113009.35701680859}
{"step": 2740, "loss": 2.594229730963707, "lr": 0.0006, "tok_s": 113003.76048035844}
{"step": 2750, "loss": 2.5820365637540816, "lr": 0.0006, "tok_s": 113043.09519126004}
{"step": 2760, "loss": 2.567574167251587, "lr": 0.0006, "tok_s": 113155.0504344196}
{"step": 2770, "loss": 2.5999461323022843, "lr": 0.0006, "tok_s": 113241.45642617445}
{"step": 2780, "loss": 2.5972472369670867, "lr": 0.0006, "tok_s": 113110.34838112668}
{"step": 2790, "loss": 2.5851343244314196, "lr": 0.0006, "tok_s": 113233.36111874181}
{"step": 2800, "loss": 2.580645111203194, "lr": 0.0006, "tok_s": 113205.495593116}
{"step": 2810, "loss": 2.5820507168769837, "lr": 0.0006, "tok_s": 113123.08021331835}
{"step": 2820, "loss": 2.5823105007410048, "lr": 0.0006, "tok_s": 113254.04484948712}
{"step": 2830, "loss": 2.567517247796059, "lr": 0.0006, "tok_s": 113403.5185677449}
{"step": 2840, "loss": 2.5863809108734133, "lr": 0.0006, "tok_s": 113376.50654829404}
{"step": 2850, "loss": 2.5571762710809707, "lr": 0.0006, "tok_s": 113451.00517840579}
{"step": 2860, "loss": 2.5816752552986144, "lr": 0.0006, "tok_s": 103743.43397999853}
{"step": 2870, "loss": 2.574698638916016, "lr": 0.0006, "tok_s": 113432.99566922922}
{"step": 2880, "loss": 2.5715499103069304, "lr": 0.0006, "tok_s": 113227.13167474863}
{"step": 2890, "loss": 2.5775507360696794, "lr": 0.0006, "tok_s": 113314.582650445}
{"step": 2900, "loss": 2.586867955327034, "lr": 0.0006, "tok_s": 113436.30523527799}
{"step": 2910, "loss": 2.5714492172002794, "lr": 0.0006, "tok_s": 113417.56157529159}
{"step": 2920, "loss": 2.577394333481789, "lr": 0.0006, "tok_s": 113436.34239292378}
{"step": 2930, "loss": 2.581504136323929, "lr": 0.0006, "tok_s": 113426.76120777498}
{"step": 2940, "loss": 2.560689753293991, "lr": 0.0006, "tok_s": 113484.40730938577}
{"step": 2950, "loss": 2.5817849963903425, "lr": 0.0006, "tok_s": 113379.94960997697}
{"step": 2960, "loss": 2.565641948580742, "lr": 0.0006, "tok_s": 113391.62717973923}
{"step": 2970, "loss": 2.5828717201948166, "lr": 0.0006, "tok_s": 113329.24113202913}
{"step": 2980, "loss": 2.587402009963989, "lr": 0.0006, "tok_s": 113351.73436162286}
{"step": 2990, "loss": 2.558534586429596, "lr": 0.0006, "tok_s": 113330.74655515088}
{"step": 3000, "loss": 2.5749335050582887, "lr": 0.0006, "tok_s": 113326.92890336885}
{"step": 3010, "loss": 2.560028624534607, "lr": 0.0006, "tok_s": 104128.74146122867}
{"step": 3020, "loss": 2.5549273073673247, "lr": 0.0006, "tok_s": 113341.85287827457}
{"step": 3030, "loss": 2.553494539856911, "lr": 0.0006, "tok_s": 113235.82171785664}
{"step": 3040, "loss": 2.5648223042488096, "lr": 0.0006, "tok_s": 113213.60498534725}
{"step": 3050, "loss": 2.5729682445526123, "lr": 0.0006, "tok_s": 113293.5467272772}
{"step": 3060, "loss": 2.5515669375658034, "lr": 0.0006, "tok_s": 113304.05904211561}
{"step": 3070, "loss": 2.573497411608696, "lr": 0.0006, "tok_s": 113346.19734047222}
{"step": 3080, "loss": 2.578151398897171, "lr": 0.0006, "tok_s": 113365.84198349853}
{"step": 3090, "loss": 2.56215680539608, "lr": 0.0006, "tok_s": 113344.7730048676}
{"step": 3100, "loss": 2.5570638865232467, "lr": 0.0006, "tok_s": 113372.36988979351}
{"step": 3110, "loss": 2.53885004222393, "lr": 0.0006, "tok_s": 113364.12786788846}
{"step": 3120, "loss": 2.5614664763212205, "lr": 0.0006, "tok_s": 113393.6450109741}
{"step": 3130, "loss": 2.5638656586408617, "lr": 0.0006, "tok_s": 113414.79679983859}
{"step": 3140, "loss": 2.5503393709659576, "lr": 0.0006, "tok_s": 113357.90594108404}
{"step": 3150, "loss": 2.546285945177078, "lr": 0.0006, "tok_s": 113405.36868034542}
{"step": 3160, "loss": 2.568587252497673, "lr": 0.0006, "tok_s": 104167.36785518505}
{"step": 3170, "loss": 2.549229696393013, "lr": 0.0006, "tok_s": 113505.52208471627}
{"step": 3180, "loss": 2.5449759900569915, "lr": 0.0006, "tok_s": 113474.63735939334}
{"step": 3190, "loss": 2.5458628952503206, "lr": 0.0006, "tok_s": 113521.77479624831}
{"step": 3200, "loss": 2.528648945689201, "lr": 0.0006, "tok_s": 113402.09688480721}
{"step": 3210, "loss": 2.5579574763774873, "lr": 0.0006, "tok_s": 113391.29507183156}
{"step": 3220, "loss": 2.549374204874039, "lr": 0.0006, "tok_s": 113360.76407398761}
{"step": 3230, "loss": 2.575362265110016, "lr": 0.0006, "tok_s": 113407.32851458364}
{"step": 3240, "loss": 2.536187893152237, "lr": 0.0006, "tok_s": 113385.01988438464}
{"step": 3250, "loss": 2.5610834300518035, "lr": 0.0006, "tok_s": 113385.82141859595}
{"step": 3260, "loss": 2.555594432353973, "lr": 0.0006, "tok_s": 113390.16077428088}
{"step": 3270, "loss": 2.5300355553627014, "lr": 0.0006, "tok_s": 113441.69364067784}
{"step": 3280, "loss": 2.574072352051735, "lr": 0.0006, "tok_s": 113383.69629616944}
{"step": 3290, "loss": 2.5494110912084578, "lr": 0.0006, "tok_s": 113407.9016809377}
{"step": 3300, "loss": 2.5483794897794723, "lr": 0.0006, "tok_s": 113464.05677941408}
{"step": 3310, "loss": 2.552239054441452, "lr": 0.0006, "tok_s": 103994.69404498156}
{"step": 3310, "loss": 2.552243909239769, "lr": 0.0006, "tok_s": 69366.90559591736}
{"step": 3320, "loss": 2.5475963354110718, "lr": 0.0006, "tok_s": 113742.04494866873}
{"step": 3330, "loss": 2.5545255839824677, "lr": 0.0006, "tok_s": 113417.49810649194}
{"step": 3340, "loss": 2.560713341832161, "lr": 0.0006, "tok_s": 113416.22435827281}
{"step": 3350, "loss": 2.546109199523926, "lr": 0.0006, "tok_s": 113434.06382577884}
{"step": 3360, "loss": 2.5294811576604843, "lr": 0.0006, "tok_s": 113332.75462698432}
{"step": 3370, "loss": 2.5508994191884993, "lr": 0.0006, "tok_s": 113382.60541144497}
{"step": 3380, "loss": 2.538939541578293, "lr": 0.0006, "tok_s": 113390.60425853376}
{"step": 3390, "loss": 2.5574604868888855, "lr": 0.0006, "tok_s": 113446.98657369113}
{"step": 3400, "loss": 2.531900441646576, "lr": 0.0006, "tok_s": 113366.82734583625}
{"step": 3410, "loss": 2.5479785233736036, "lr": 0.0006, "tok_s": 113477.76489550142}
{"step": 3420, "loss": 2.5433236747980117, "lr": 0.0006, "tok_s": 113481.02319735294}
{"step": 3430, "loss": 2.53036005795002, "lr": 0.0006, "tok_s": 113440.0860773651}
{"step": 3440, "loss": 2.544103464484215, "lr": 0.0006, "tok_s": 113378.62701698006}
{"step": 3450, "loss": 2.542275521159172, "lr": 0.0006, "tok_s": 113375.89190486596}
{"step": 3460, "loss": 2.5296660274267198, "lr": 0.0006, "tok_s": 103034.78923974141}
{"step": 3470, "loss": 2.540792864561081, "lr": 0.0006, "tok_s": 113495.61435710841}
{"step": 3480, "loss": 2.5270156413316727, "lr": 0.0006, "tok_s": 113438.44110797667}
{"step": 3490, "loss": 2.517756628990173, "lr": 0.0006, "tok_s": 113415.87835996659}
{"step": 3500, "loss": 2.5449524402618406, "lr": 0.0006, "tok_s": 113433.28559962595}
{"step": 3510, "loss": 2.531450942158699, "lr": 0.0006, "tok_s": 113432.6791172494}
{"step": 3520, "loss": 2.5568427979946136, "lr": 0.0006, "tok_s": 113367.92114146875}
{"step": 3530, "loss": 2.524763083457947, "lr": 0.0006, "tok_s": 113400.97055826851}
{"step": 3540, "loss": 2.5320355355739594, "lr": 0.0006, "tok_s": 113415.4311683264}
{"step": 3550, "loss": 2.518521711230278, "lr": 0.0006, "tok_s": 113453.50158583127}
{"step": 3560, "loss": 2.5318174034357073, "lr": 0.0006, "tok_s": 113512.17770964756}
{"step": 3570, "loss": 2.5361551493406296, "lr": 0.0006, "tok_s": 113549.31928455493}
{"step": 3580, "loss": 2.520270451903343, "lr": 0.0006, "tok_s": 113541.35460281018}
{"step": 3590, "loss": 2.519323045015335, "lr": 0.0006, "tok_s": 113589.64821487517}
{"step": 3600, "loss": 2.529676714539528, "lr": 0.0006, "tok_s": 113468.27331770094}
{"step": 3610, "loss": 2.52926487326622, "lr": 0.0006, "tok_s": 103847.44875487789}
{"step": 3620, "loss": 2.5098627656698227, "lr": 0.0006, "tok_s": 113306.6295542172}
{"step": 3630, "loss": 2.528286191821098, "lr": 0.0006, "tok_s": 113298.97528276322}
{"step": 3640, "loss": 2.5159570276737213, "lr": 0.0006, "tok_s": 113425.02214025022}
{"step": 3650, "loss": 2.5353025048971176, "lr": 0.0006, "tok_s": 113360.45026253427}
{"step": 3660, "loss": 2.536824107170105, "lr": 0.0006, "tok_s": 113458.45580196235}
{"step": 3670, "loss": 2.528869104385376, "lr": 0.0006, "tok_s": 113415.31885914215}
{"step": 3680, "loss": 2.523462137579918, "lr": 0.0006, "tok_s": 113398.37237319368}
{"step": 3690, "loss": 2.508430853486061, "lr": 0.0006, "tok_s": 113492.0605918775}
{"step": 3700, "loss": 2.5221195220947266, "lr": 0.0006, "tok_s": 113470.05586831846}
{"step": 3710, "loss": 2.5199011743068693, "lr": 0.0006, "tok_s": 113454.65471146544}
{"step": 3720, "loss": 2.5169616669416426, "lr": 0.0006, "tok_s": 113444.35350602554}
{"step": 3730, "loss": 2.518206512928009, "lr": 0.0006, "tok_s": 113426.25279193783}
{"step": 3740, "loss": 2.519015923142433, "lr": 0.0006, "tok_s": 113474.36361303383}
{"step": 3750, "loss": 2.522451010346413, "lr": 0.0006, "tok_s": 113413.6643717516}
{"step": 3760, "loss": 2.522769567370415, "lr": 0.0006, "tok_s": 103658.02352919859}
{"step": 3770, "loss": 2.5047480016946793, "lr": 0.0006, "tok_s": 113351.88014151526}
{"step": 3780, "loss": 2.529524013400078, "lr": 0.0006, "tok_s": 113185.32681414363}
{"step": 3790, "loss": 2.5280852377414704, "lr": 0.0006, "tok_s": 113212.1944714416}
{"step": 3800, "loss": 2.5217163443565367, "lr": 0.0006, "tok_s": 113284.55689940552}
{"step": 3810, "loss": 2.5047918766736985, "lr": 0.0006, "tok_s": 113372.72614375515}
{"step": 3820, "loss": 2.499832785129547, "lr": 0.0006, "tok_s": 113377.15831726926}
{"step": 3830, "loss": 2.517762616276741, "lr": 0.0006, "tok_s": 113412.51675850774}
{"step": 3840, "loss": 2.5171126186847688, "lr": 0.0006, "tok_s": 113319.29495531281}
{"step": 3850, "loss": 2.517152005434036, "lr": 0.0006, "tok_s": 113274.12580668811}
{"step": 3860, "loss": 2.516161471605301, "lr": 0.0006, "tok_s": 113267.2909538657}
{"step": 3870, "loss": 2.5158184498548506, "lr": 0.0006, "tok_s": 113344.42802658804}
{"step": 3880, "loss": 2.4964658975601197, "lr": 0.0006, "tok_s": 113398.47646204621}
{"step": 3890, "loss": 2.4944855988025667, "lr": 0.0006, "tok_s": 113395.27026223778}
{"step": 3900, "loss": 2.5360247820615767, "lr": 0.0006, "tok_s": 113331.24097344765}
{"step": 3910, "loss": 2.510073643922806, "lr": 0.0006, "tok_s": 103924.60997926955}
{"step": 3920, "loss": 2.5018421798944472, "lr": 0.0006, "tok_s": 113529.16936606}
{"step": 3930, "loss": 2.5048530459403993, "lr": 0.0006, "tok_s": 113535.62113410038}
{"step": 3940, "loss": 2.507371097803116, "lr": 0.0006, "tok_s": 113477.8647382411}
{"step": 3950, "loss": 2.5109413385391237, "lr": 0.0006, "tok_s": 113382.3858924311}
{"step": 3960, "loss": 2.509239321947098, "lr": 0.0006, "tok_s": 113400.36383660419}
{"step": 3970, "loss": 2.517616701126099, "lr": 0.0006, "tok_s": 113380.72768904656}
{"step": 3980, "loss": 2.4976404905319214, "lr": 0.0006, "tok_s": 113399.85507259867}
{"step": 3990, "loss": 2.513507655262947, "lr": 0.0006, "tok_s": 113426.28877288576}
{"step": 4000, "loss": 2.511553782224655, "lr": 0.0006, "tok_s": 113425.41265791935}
{"step": 4010, "loss": 2.500321289896965, "lr": 0.0006, "tok_s": 113398.16302652958}
{"step": 4020, "loss": 2.4992417335510253, "lr": 0.0006, "tok_s": 113342.5200220743}
{"step": 4030, "loss": 2.5163413524627685, "lr": 0.0006, "tok_s": 113397.28412983529}
{"step": 4040, "loss": 2.5013698637485504, "lr": 0.0006, "tok_s": 113433.28940296087}
{"step": 4050, "loss": 2.497578480839729, "lr": 0.0006, "tok_s": 113376.27506981557}
{"step": 4060, "loss": 2.493202328681946, "lr": 0.0006, "tok_s": 103368.31787661929}
{"step": 4070, "loss": 2.5038338005542755, "lr": 0.0006, "tok_s": 113304.53600545507}
{"step": 4080, "loss": 2.4876507937908174, "lr": 0.0006, "tok_s": 113205.21760738062}
{"step": 4090, "loss": 2.5058240830898284, "lr": 0.0006, "tok_s": 113272.48243776122}
{"step": 4100, "loss": 2.502291461825371, "lr": 0.0006, "tok_s": 113365.43726519967}
{"step": 4110, "loss": 2.485821622610092, "lr": 0.0006, "tok_s": 113409.3869690764}
{"step": 4120, "loss": 2.5061758875846865, "lr": 0.0006, "tok_s": 113426.30018148378}
{"step": 4130, "loss": 2.4939279556274414, "lr": 0.0006, "tok_s": 113464.52777262102}
{"step": 4140, "loss": 2.4891185432672502, "lr": 0.0006, "tok_s": 113440.08958855676}
{"step": 4150, "loss": 2.5098605930805205, "lr": 0.0006, "tok_s": 113423.3972060889}
{"step": 4160, "loss": 2.50315383374691, "lr": 0.0006, "tok_s": 113441.34456089842}
{"step": 4170, "loss": 2.5015115469694136, "lr": 0.0006, "tok_s": 113452.66017011652}
{"step": 4180, "loss": 2.4884935170412064, "lr": 0.0006, "tok_s": 113357.99184074918}
{"step": 4190, "loss": 2.474381321668625, "lr": 0.0006, "tok_s": 113462.62918747231}
{"step": 4200, "loss": 2.4929632246494293, "lr": 0.0006, "tok_s": 113399.39309544492}
{"step": 4210, "loss": 2.4864968329668047, "lr": 0.0006, "tok_s": 103676.49588276418}
{"step": 4220, "loss": 2.5061026334762575, "lr": 0.0006, "tok_s": 113468.84885674443}
{"step": 4230, "loss": 2.496199369430542, "lr": 0.0006, "tok_s": 113397.39464903001}
{"step": 4240, "loss": 2.481010702252388, "lr": 0.0006, "tok_s": 113409.09803815269}
{"step": 4250, "loss": 2.480253142118454, "lr": 0.0006, "tok_s": 113467.58947015084}
{"step": 4260, "loss": 2.4770757406949997, "lr": 0.0006, "tok_s": 113386.98661581842}
{"step": 4270, "loss": 2.4968675822019577, "lr": 0.0006, "tok_s": 113420.59880125185}
{"step": 4280, "loss": 2.4802572041749955, "lr": 0.0006, "tok_s": 113523.74363749768}
{"step": 4290, "loss": 2.4952429115772246, "lr": 0.0006, "tok_s": 113518.03245730147}
{"step": 4300, "loss": 2.4723120987415315, "lr": 0.0006, "tok_s": 113462.10610710706}
{"step": 4310, "loss": 2.4940085232257845, "lr": 0.0006, "tok_s": 113483.46031160506}
{"step": 4320, "loss": 2.4724506765604017, "lr": 0.0006, "tok_s": 113486.44337885121}
{"step": 4330, "loss": 2.4983938962221144, "lr": 0.0006, "tok_s": 113468.24111579062}
{"step": 4340, "loss": 2.483950546383858, "lr": 0.0006, "tok_s": 113540.67690893252}
{"step": 4350, "loss": 2.479211297631264, "lr": 0.0006, "tok_s": 113479.90994269725}
{"step": 4360, "loss": 2.4763258039951324, "lr": 0.0006, "tok_s": 103523.96635694042}
{"step": 4370, "loss": 2.475200706720352, "lr": 0.0006, "tok_s": 113575.40711514717}
{"step": 4380, "loss": 2.4888437926769256, "lr": 0.0006, "tok_s": 113537.8829727179}
{"step": 4390, "loss": 2.489239552617073, "lr": 0.0006, "tok_s": 113517.02219700716}
{"step": 4400, "loss": 2.469476267695427, "lr": 0.0006, "tok_s": 113477.06922193407}
{"step": 4410, "loss": 2.513887012004852, "lr": 0.0006, "tok_s": 113637.84081435436}
{"step": 4420, "loss": 2.4855977207422257, "lr": 0.0006, "tok_s": 113706.76033922531}
{"step": 4430, "loss": 2.4761888533830643, "lr": 0.0006, "tok_s": 113673.92411350721}
{"step": 4440, "loss": 2.487928441166878, "lr": 0.0006, "tok_s": 113638.9574634579}
{"step": 4450, "loss": 2.471976470947266, "lr": 0.0006, "tok_s": 113623.01345428736}
{"step": 4460, "loss": 2.460330379009247, "lr": 0.0006, "tok_s": 113673.74988632422}
{"step": 4470, "loss": 2.4890677452087404, "lr": 0.0006, "tok_s": 113640.001020217}
{"step": 4480, "loss": 2.471729075908661, "lr": 0.0006, "tok_s": 113601.73992175955}
{"step": 4490, "loss": 2.467163008451462, "lr": 0.0006, "tok_s": 113598.26635856497}
{"step": 4500, "loss": 2.472475653886795, "lr": 0.0006, "tok_s": 113553.6518136188}
{"step": 4510, "loss": 2.482602682709694, "lr": 0.0006, "tok_s": 103577.38274520745}
{"step": 4520, "loss": 2.4781239122152328, "lr": 0.0006, "tok_s": 113483.84478962694}
{"step": 4530, "loss": 2.4872170954942705, "lr": 0.0006, "tok_s": 113480.27565703327}
{"step": 4540, "loss": 2.499987980723381, "lr": 0.0006, "tok_s": 113492.42521305675}
{"step": 4550, "loss": 2.4715964794158936, "lr": 0.0006, "tok_s": 113540.70065153111}
{"step": 4560, "loss": 2.4682059705257418, "lr": 0.0006, "tok_s": 113576.85045190042}
{"step": 4570, "loss": 2.4744611471891402, "lr": 0.0006, "tok_s": 113596.04847136037}
{"step": 4580, "loss": 2.4727610617876055, "lr": 0.0006, "tok_s": 103452.9722652336}
{"step": 4590, "loss": 2.4994258373975753, "lr": 0.0006, "tok_s": 113739.7793806262}
{"step": 4600, "loss": 2.4827966541051865, "lr": 0.0006, "tok_s": 113582.3102981254}
{"step": 4610, "loss": 2.4645325779914855, "lr": 0.0006, "tok_s": 113496.51733126781}
{"step": 4620, "loss": 2.454718691110611, "lr": 0.0006, "tok_s": 113495.82494240193}
{"step": 4630, "loss": 2.464149960875511, "lr": 0.0006, "tok_s": 113574.61902946117}
{"step": 4640, "loss": 2.466769376397133, "lr": 0.0006, "tok_s": 113599.77835063064}
{"step": 4650, "loss": 2.462449124455452, "lr": 0.0006, "tok_s": 113639.68243093535}
{"step": 4660, "loss": 2.4818092405796053, "lr": 0.0006, "tok_s": 103917.20408724205}
{"step": 4670, "loss": 2.4701306104660032, "lr": 0.0006, "tok_s": 113585.13135590253}
{"step": 4680, "loss": 2.4618037313222887, "lr": 0.0006, "tok_s": 113590.0345862501}
{"step": 4690, "loss": 2.4735905438661576, "lr": 0.0006, "tok_s": 113529.03514518448}
{"step": 4700, "loss": 2.474966636300087, "lr": 0.0006, "tok_s": 113608.64953441896}
{"step": 4710, "loss": 2.484015592932701, "lr": 0.0006, "tok_s": 113560.8833997222}
{"step": 4720, "loss": 2.4699823588132857, "lr": 0.0006, "tok_s": 113551.30198097652}
{"step": 4730, "loss": 2.469978502392769, "lr": 0.0006, "tok_s": 113481.28467774508}
{"step": 4740, "loss": 2.452965420484543, "lr": 0.0006, "tok_s": 113568.94730551858}
{"step": 4750, "loss": 2.4710094064474104, "lr": 0.0006, "tok_s": 113572.81882116079}
{"step": 4760, "loss": 2.4663816720247267, "lr": 0.0006, "tok_s": 113603.73061158962}
{"step": 4770, "loss": 2.467884439229965, "lr": 0.0006, "tok_s": 113602.24668420492}
{"step": 4780, "loss": 2.4541150510311125, "lr": 0.0006, "tok_s": 113678.82090906404}
{"step": 4790, "loss": 2.4816306978464127, "lr": 0.0006, "tok_s": 113650.97156467}
{"step": 4800, "loss": 2.475759890675545, "lr": 0.0006, "tok_s": 113559.93189977408}
{"step": 4810, "loss": 2.4679528146982195, "lr": 0.0006, "tok_s": 103725.7722012927}
{"step": 4820, "loss": 2.471183884143829, "lr": 0.0006, "tok_s": 113625.16575758668}
{"step": 4830, "loss": 2.4593372106552125, "lr": 0.0006, "tok_s": 113556.25184159672}
{"step": 4840, "loss": 2.465355834364891, "lr": 0.0006, "tok_s": 113478.35985541999}
{"step": 4850, "loss": 2.4657993465662003, "lr": 0.0006, "tok_s": 113490.3101499708}
{"step": 4860, "loss": 2.4544647514820097, "lr": 0.0006, "tok_s": 113481.36666512625}
{"step": 4870, "loss": 2.4667342752218246, "lr": 0.0006, "tok_s": 113477.50489529116}
{"step": 4880, "loss": 2.4509788781404493, "lr": 0.0006, "tok_s": 113546.0485584636}
{"step": 4890, "loss": 2.4516087144613268, "lr": 0.0006, "tok_s": 113630.5671297953}
{"step": 4900, "loss": 2.4707871943712236, "lr": 0.0006, "tok_s": 113538.1159908874}
{"step": 4910, "loss": 2.4487895727157594, "lr": 0.0006, "tok_s": 113455.46952300113}
{"step": 4920, "loss": 2.4655384361743926, "lr": 0.0006, "tok_s": 113426.5839345317}
{"step": 4930, "loss": 2.4648147106170653, "lr": 0.0006, "tok_s": 113460.91594893657}
{"step": 4940, "loss": 2.456055524945259, "lr": 0.0006, "tok_s": 113459.65322602692}
{"step": 4950, "loss": 2.4695463329553604, "lr": 0.0006, "tok_s": 113572.9197110907}
{"step": 4960, "loss": 2.4648830592632294, "lr": 0.0006, "tok_s": 103875.62571215193}
{"step": 4970, "loss": 2.4608558863401413, "lr": 0.0006, "tok_s": 113532.17212826577}
{"step": 4980, "loss": 2.4565968781709673, "lr": 0.0006, "tok_s": 113478.1247401003}
{"step": 4990, "loss": 2.442355880141258, "lr": 0.0006, "tok_s": 113538.64182408252}
{"step": 5000, "loss": 2.4349629461765288, "lr": 0.0006, "tok_s": 113491.19663939967}
{"step": 5010, "loss": 2.471127787232399, "lr": 0.0006, "tok_s": 113660.79540275631}
{"step": 5020, "loss": 2.464408999681473, "lr": 0.0006, "tok_s": 113670.53221487158}
{"step": 5030, "loss": 2.458827015757561, "lr": 0.0006, "tok_s": 113622.36061681264}
{"step": 5040, "loss": 2.4523632645606996, "lr": 0.0006, "tok_s": 113572.54812028691}
{"step": 5050, "loss": 2.4439399152994157, "lr": 0.0006, "tok_s": 113548.52804295871}
{"step": 5060, "loss": 2.4671801000833513, "lr": 0.0006, "tok_s": 113564.79805877413}
{"step": 5070, "loss": 2.473263296484947, "lr": 0.0006, "tok_s": 113576.61258184741}
{"step": 5080, "loss": 2.4474672853946684, "lr": 0.0006, "tok_s": 113594.28455146388}
{"step": 5090, "loss": 2.45911126434803, "lr": 0.0006, "tok_s": 113671.4370931073}
{"step": 5100, "loss": 2.465122324228287, "lr": 0.0006, "tok_s": 113745.21283593963}
{"step": 5110, "loss": 2.453180584311485, "lr": 0.0006, "tok_s": 103673.52675492538}
{"step": 5120, "loss": 2.466964456439018, "lr": 0.0006, "tok_s": 113644.65938124248}
{"step": 5130, "loss": 2.4614065438508987, "lr": 0.0006, "tok_s": 113651.93751334744}
{"step": 5140, "loss": 2.4419899851083757, "lr": 0.0006, "tok_s": 113699.15743698699}
{"step": 5150, "loss": 2.437181091308594, "lr": 0.0006, "tok_s": 113721.97772208464}
{"step": 5160, "loss": 2.4452788919210433, "lr": 0.0006, "tok_s": 113717.9387221414}
{"step": 5170, "loss": 2.435718649625778, "lr": 0.0006, "tok_s": 113762.03333386843}
{"step": 5180, "loss": 2.459063759446144, "lr": 0.0006, "tok_s": 113792.51384831581}
{"step": 5190, "loss": 2.459544023871422, "lr": 0.0006, "tok_s": 113706.93496159046}
{"step": 5200, "loss": 2.450521168112755, "lr": 0.0006, "tok_s": 113752.91604776992}
{"step": 5210, "loss": 2.439773029088974, "lr": 0.0006, "tok_s": 113727.55887123825}
{"step": 5220, "loss": 2.4541631042957306, "lr": 0.0006, "tok_s": 113741.3878010993}
{"step": 5230, "loss": 2.441424238681793, "lr": 0.0006, "tok_s": 113674.33985169171}
{"step": 5240, "loss": 2.451197901368141, "lr": 0.0006, "tok_s": 113698.67685156131}
{"step": 5250, "loss": 2.4385138243436812, "lr": 0.0006, "tok_s": 113675.85210662337}
{"step": 5260, "loss": 2.433074262738228, "lr": 0.0006, "tok_s": 103747.07302664852}
{"step": 5270, "loss": 2.444551035761833, "lr": 0.0006, "tok_s": 113601.81592116642}
{"step": 5280, "loss": 2.450376832485199, "lr": 0.0006, "tok_s": 113474.69386549082}
{"step": 5290, "loss": 2.4448972046375275, "lr": 0.0006, "tok_s": 113529.2681270379}
{"step": 5300, "loss": 2.438400202989578, "lr": 0.0006, "tok_s": 113653.27236455353}
{"step": 5310, "loss": 2.4586148828268053, "lr": 0.0006, "tok_s": 113652.11989710835}
{"step": 5320, "loss": 2.4554229259490965, "lr": 0.0006, "tok_s": 113624.571899254}
{"step": 5330, "loss": 2.448426017165184, "lr": 0.0006, "tok_s": 113641.33236102376}
{"step": 5340, "loss": 2.427547889947891, "lr": 0.0006, "tok_s": 113641.9974558415}
{"step": 5350, "loss": 2.4413449883461, "lr": 0.0006, "tok_s": 113608.46846402404}
{"step": 5360, "loss": 2.4409123778343202, "lr": 0.0006, "tok_s": 113613.67043256783}
{"step": 5370, "loss": 2.433877891302109, "lr": 0.0006, "tok_s": 113685.8468698236}
{"step": 5380, "loss": 2.4381643027067184, "lr": 0.0006, "tok_s": 113680.65092511136}
{"step": 5390, "loss": 2.4466341555118563, "lr": 0.0006, "tok_s": 113681.15604107229}
{"step": 5400, "loss": 2.436362287402153, "lr": 0.0006, "tok_s": 113703.5046416651}
{"step": 5410, "loss": 2.4301235884428025, "lr": 0.0006, "tok_s": 103637.31166233298}
{"step": 5420, "loss": 2.447957953810692, "lr": 0.0006, "tok_s": 113723.52417985954}
{"step": 5430, "loss": 2.449167564511299, "lr": 0.0006, "tok_s": 113731.8106047239}
{"step": 5440, "loss": 2.439679542183876, "lr": 0.0006, "tok_s": 113647.26857089653}
{"step": 5450, "loss": 2.4379460632801058, "lr": 0.0006, "tok_s": 113588.3125108504}
{"step": 5460, "loss": 2.448152431845665, "lr": 0.0006, "tok_s": 113606.0600185472}
{"step": 5470, "loss": 2.44596126973629, "lr": 0.0006, "tok_s": 113589.65877624456}
{"step": 5480, "loss": 2.447248247265816, "lr": 0.0006, "tok_s": 113612.5428342656}
{"step": 5490, "loss": 2.437393549084663, "lr": 0.0006, "tok_s": 113740.14618355881}
{"step": 5500, "loss": 2.438390865921974, "lr": 0.0006, "tok_s": 113749.0657824142}
{"step": 5510, "loss": 2.4427515268325806, "lr": 0.0006, "tok_s": 113729.91306358097}
{"step": 5520, "loss": 2.4300746649503706, "lr": 0.0006, "tok_s": 113717.00752282796}
{"step": 5530, "loss": 2.441298487782478, "lr": 0.0006, "tok_s": 113765.59931823723}
{"step": 5540, "loss": 2.441736474633217, "lr": 0.0006, "tok_s": 113675.88413266317}
{"step": 5550, "loss": 2.443009552359581, "lr": 0.0006, "tok_s": 113649.54690110344}
{"step": 5560, "loss": 2.4515492498874663, "lr": 0.0006, "tok_s": 103950.41041870663}
{"step": 5570, "loss": 2.43553469479084, "lr": 0.0006, "tok_s": 113729.22047095528}
{"step": 5580, "loss": 2.449972856044769, "lr": 0.0006, "tok_s": 113738.76281645863}
{"step": 5590, "loss": 2.4493987262248993, "lr": 0.0006, "tok_s": 113699.00135650419}
{"step": 5600, "loss": 2.443732500076294, "lr": 0.0006, "tok_s": 113682.2091884946}
{"step": 5610, "loss": 2.4473921239376066, "lr": 0.0006, "tok_s": 113640.14607436192}
{"step": 5620, "loss": 2.452719032764435, "lr": 0.0006, "tok_s": 113734.10673769937}
{"step": 5630, "loss": 2.437294617295265, "lr": 0.0006, "tok_s": 113688.78004665032}
{"step": 5640, "loss": 2.445009562373161, "lr": 0.0006, "tok_s": 113696.18316343095}
{"step": 5650, "loss": 2.449304112792015, "lr": 0.0006, "tok_s": 113643.11477393162}
{"step": 5660, "loss": 2.461463364958763, "lr": 0.0006, "tok_s": 113659.35140033766}
{"step": 5670, "loss": 2.4395452797412873, "lr": 0.0006, "tok_s": 113718.34419702215}
{"step": 5680, "loss": 2.437824636697769, "lr": 0.0006, "tok_s": 113697.41735490512}
{"step": 5690, "loss": 2.4195524990558623, "lr": 0.0006, "tok_s": 113736.64120909988}
{"step": 5700, "loss": 2.4312000945210457, "lr": 0.0006, "tok_s": 113698.2503537696}
{"step": 5710, "loss": 2.439151257276535, "lr": 0.0006, "tok_s": 103762.42468412804}
{"step": 5720, "loss": 2.418699198961258, "lr": 0.0006, "tok_s": 113655.06866266046}